124 14 122 26 31 195 78 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __SOCK_DIAG_H__ #define __SOCK_DIAG_H__ #include <linux/netlink.h> #include <linux/user_namespace.h> #include <net/net_namespace.h> #include <net/sock.h> #include <uapi/linux/sock_diag.h> struct sk_buff; struct nlmsghdr; struct sock; struct sock_diag_handler { __u8 family; int (*dump)(struct sk_buff *skb, struct nlmsghdr *nlh); int (*get_info)(struct sk_buff *skb, struct sock *sk); int (*destroy)(struct sk_buff *skb, struct nlmsghdr *nlh); }; int sock_diag_register(const struct sock_diag_handler *h); void sock_diag_unregister(const struct sock_diag_handler *h); void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)); void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)); u64 __sock_gen_cookie(struct sock *sk); static inline u64 sock_gen_cookie(struct sock *sk) { u64 cookie; preempt_disable(); cookie = __sock_gen_cookie(sk); preempt_enable(); return cookie; } int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie); void sock_diag_save_cookie(struct sock *sk, __u32 *cookie); int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attr); int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, struct sk_buff *skb, int attrtype); static inline enum sknetlink_groups sock_diag_destroy_group(const struct sock *sk) { switch (sk->sk_family) { case AF_INET: if (sk->sk_type == SOCK_RAW) return SKNLGRP_NONE; switch (sk->sk_protocol) { case IPPROTO_TCP: return SKNLGRP_INET_TCP_DESTROY; case IPPROTO_UDP: return SKNLGRP_INET_UDP_DESTROY; default: return SKNLGRP_NONE; } case AF_INET6: if (sk->sk_type == SOCK_RAW) return SKNLGRP_NONE; switch (sk->sk_protocol) { case IPPROTO_TCP: return SKNLGRP_INET6_TCP_DESTROY; case IPPROTO_UDP: return SKNLGRP_INET6_UDP_DESTROY; default: return SKNLGRP_NONE; } default: return SKNLGRP_NONE; } } static inline bool sock_diag_has_destroy_listeners(const struct sock *sk) { const struct net *n = sock_net(sk); const enum sknetlink_groups group = sock_diag_destroy_group(sk); return group != SKNLGRP_NONE && n->diag_nlsk && netlink_has_listeners(n->diag_nlsk, group); } void sock_diag_broadcast_destroy(struct sock *sk); int sock_diag_destroy(struct sock *sk, int err); #endif
628 188 1515 689 5 628 621 596 596 350 1101 646 1344 1209 949 949 948 948 677 645 1209 318 318 318 931 930 727 186 633 515 724 929 927 188 187 18 18 18 50 50 24 24 5 5 2 8 2 54 942 945 7 55 18 40 55 54 27 4 27 3 27 3 27 27 27 27 27 27 98 97 98 98 48 88 98 100 595 516 100 8 18 2889 14 14 14 14 2890 2892 2884 1248 1251 10 370 239 14 2 8 1145 581 10 438 482 15 109 109 91 87 5 92 82 55 10 21 74 1 75 9 57 39 75 54 18 3 1 2 18 73 92 18 105 76 40 21 18 1 75 76 33 33 188 188 187 49 18 18 50 50 50 49 41 50 50 9 43 50 50 169 169 169 169 154 169 169 28 164 168 168 54 50 169 1 4 4 11 11 11 11 /* * mm/rmap.c - physical to virtual reverse mappings * * Copyright 2001, Rik van Riel <riel@conectiva.com.br> * Released under the General Public License (GPL). * * Simple, low overhead reverse mapping scheme. * Please try to keep this thing as modular as possible. * * Provides methods for unmapping each kind of mapped page: * the anon methods track anonymous pages, and * the file methods track pages belonging to an inode. * * Original design by Rik van Riel <riel@conectiva.com.br> 2001 * File methods by Dave McCracken <dmccr@us.ibm.com> 2003, 2004 * Anonymous methods by Andrea Arcangeli <andrea@suse.de> 2004 * Contributions by Hugh Dickins 2003, 2004 */ /* * Lock ordering in mm: * * inode->i_mutex (while writing or truncating, not reading or faulting) * mm->mmap_lock * page->flags PG_locked (lock_page) * (see huegtlbfs below) * hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share) * mapping->i_mmap_rwsem * hugetlb_fault_mutex (hugetlbfs specific page fault mutex) * anon_vma->rwsem * mm->page_table_lock or pte_lock * swap_lock (in swap_duplicate, swap_info_get) * mmlist_lock (in mmput, drain_mmlist and others) * mapping->private_lock (in __set_page_dirty_buffers) * lock_page_memcg move_lock (in __set_page_dirty_buffers) * i_pages lock (widely used) * lruvec->lru_lock (in lock_page_lruvec_irq) * inode->i_lock (in set_page_dirty's __mark_inode_dirty) * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) * sb_lock (within inode_lock in fs/fs-writeback.c) * i_pages lock (widely used, in set_page_dirty, * in arch-dependent flush_dcache_mmap_lock, * within bdi.wb->list_lock in __sync_single_inode) * * anon_vma->rwsem,mapping->i_mutex (memory_failure, collect_procs_anon) * ->tasklist_lock * pte map lock * * * hugetlbfs PageHuge() pages take locks in this order: * mapping->i_mmap_rwsem * hugetlb_fault_mutex (hugetlbfs specific page fault mutex) * page->flags PG_locked (lock_page) */ #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/rcupdate.h> #include <linux/export.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> #include <linux/migrate.h> #include <linux/hugetlb.h> #include <linux/huge_mm.h> #include <linux/backing-dev.h> #include <linux/page_idle.h> #include <linux/memremap.h> #include <linux/userfaultfd_k.h> #include <asm/tlbflush.h> #include <trace/events/tlb.h> #include "internal.h" static struct kmem_cache *anon_vma_cachep; static struct kmem_cache *anon_vma_chain_cachep; static inline struct anon_vma *anon_vma_alloc(void) { struct anon_vma *anon_vma; anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); if (anon_vma) { atomic_set(&anon_vma->refcount, 1); anon_vma->degree = 1; /* Reference for first vma */ anon_vma->parent = anon_vma; /* * Initialise the anon_vma root to point to itself. If called * from fork, the root will be reset to the parents anon_vma. */ anon_vma->root = anon_vma; } return anon_vma; } static inline void anon_vma_free(struct anon_vma *anon_vma) { VM_BUG_ON(atomic_read(&anon_vma->refcount)); /* * Synchronize against page_lock_anon_vma_read() such that * we can safely hold the lock without the anon_vma getting * freed. * * Relies on the full mb implied by the atomic_dec_and_test() from * put_anon_vma() against the acquire barrier implied by * down_read_trylock() from page_lock_anon_vma_read(). This orders: * * page_lock_anon_vma_read() VS put_anon_vma() * down_read_trylock() atomic_dec_and_test() * LOCK MB * atomic_read() rwsem_is_locked() * * LOCK should suffice since the actual taking of the lock must * happen _before_ what follows. */ might_sleep(); if (rwsem_is_locked(&anon_vma->root->rwsem)) { anon_vma_lock_write(anon_vma); anon_vma_unlock_write(anon_vma); } kmem_cache_free(anon_vma_cachep, anon_vma); } static inline struct anon_vma_chain *anon_vma_chain_alloc(gfp_t gfp) { return kmem_cache_alloc(anon_vma_chain_cachep, gfp); } static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain) { kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain); } static void anon_vma_chain_link(struct vm_area_struct *vma, struct anon_vma_chain *avc, struct anon_vma *anon_vma) { avc->vma = vma; avc->anon_vma = anon_vma; list_add(&avc->same_vma, &vma->anon_vma_chain); anon_vma_interval_tree_insert(avc, &anon_vma->rb_root); } /** * __anon_vma_prepare - attach an anon_vma to a memory region * @vma: the memory region in question * * This makes sure the memory mapping described by 'vma' has * an 'anon_vma' attached to it, so that we can associate the * anonymous pages mapped into it with that anon_vma. * * The common case will be that we already have one, which * is handled inline by anon_vma_prepare(). But if * not we either need to find an adjacent mapping that we * can re-use the anon_vma from (very common when the only * reason for splitting a vma has been mprotect()), or we * allocate a new one. * * Anon-vma allocations are very subtle, because we may have * optimistically looked up an anon_vma in page_lock_anon_vma_read() * and that may actually touch the rwsem even in the newly * allocated vma (it depends on RCU to make sure that the * anon_vma isn't actually destroyed). * * As a result, we need to do proper anon_vma locking even * for the new allocation. At the same time, we do not want * to do any locking for the common case of already having * an anon_vma. * * This must be called with the mmap_lock held for reading. */ int __anon_vma_prepare(struct vm_area_struct *vma) { struct mm_struct *mm = vma->vm_mm; struct anon_vma *anon_vma, *allocated; struct anon_vma_chain *avc; might_sleep(); avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_enomem; anon_vma = find_mergeable_anon_vma(vma); allocated = NULL; if (!anon_vma) { anon_vma = anon_vma_alloc(); if (unlikely(!anon_vma)) goto out_enomem_free_avc; allocated = anon_vma; } anon_vma_lock_write(anon_vma); /* page_table_lock to protect against threads */ spin_lock(&mm->page_table_lock); if (likely(!vma->anon_vma)) { vma->anon_vma = anon_vma; anon_vma_chain_link(vma, avc, anon_vma); /* vma reference or self-parent link for new root */ anon_vma->degree++; allocated = NULL; avc = NULL; } spin_unlock(&mm->page_table_lock); anon_vma_unlock_write(anon_vma); if (unlikely(allocated)) put_anon_vma(allocated); if (unlikely(avc)) anon_vma_chain_free(avc); return 0; out_enomem_free_avc: anon_vma_chain_free(avc); out_enomem: return -ENOMEM; } /* * This is a useful helper function for locking the anon_vma root as * we traverse the vma->anon_vma_chain, looping over anon_vma's that * have the same vma. * * Such anon_vma's should have the same root, so you'd expect to see * just a single mutex_lock for the whole traversal. */ static inline struct anon_vma *lock_anon_vma_root(struct anon_vma *root, struct anon_vma *anon_vma) { struct anon_vma *new_root = anon_vma->root; if (new_root != root) { if (WARN_ON_ONCE(root)) up_write(&root->rwsem); root = new_root; down_write(&root->rwsem); } return root; } static inline void unlock_anon_vma_root(struct anon_vma *root) { if (root) up_write(&root->rwsem); } /* * Attach the anon_vmas from src to dst. * Returns 0 on success, -ENOMEM on failure. * * anon_vma_clone() is called by __vma_adjust(), __split_vma(), copy_vma() and * anon_vma_fork(). The first three want an exact copy of src, while the last * one, anon_vma_fork(), may try to reuse an existing anon_vma to prevent * endless growth of anon_vma. Since dst->anon_vma is set to NULL before call, * we can identify this case by checking (!dst->anon_vma && src->anon_vma). * * If (!dst->anon_vma && src->anon_vma) is true, this function tries to find * and reuse existing anon_vma which has no vmas and only one child anon_vma. * This prevents degradation of anon_vma hierarchy to endless linear chain in * case of constantly forking task. On the other hand, an anon_vma with more * than one child isn't reused even if there was no alive vma, thus rmap * walker has a good chance of avoiding scanning the whole hierarchy when it * searches where page is mapped. */ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) { struct anon_vma_chain *avc, *pavc; struct anon_vma *root = NULL; list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) { struct anon_vma *anon_vma; avc = anon_vma_chain_alloc(GFP_NOWAIT | __GFP_NOWARN); if (unlikely(!avc)) { unlock_anon_vma_root(root); root = NULL; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto enomem_failure; } anon_vma = pavc->anon_vma; root = lock_anon_vma_root(root, anon_vma); anon_vma_chain_link(dst, avc, anon_vma); /* * Reuse existing anon_vma if its degree lower than two, * that means it has no vma and only one anon_vma child. * * Do not chose parent anon_vma, otherwise first child * will always reuse it. Root anon_vma is never reused: * it has self-parent reference and at least one child. */ if (!dst->anon_vma && src->anon_vma && anon_vma != src->anon_vma && anon_vma->degree < 2) dst->anon_vma = anon_vma; } if (dst->anon_vma) dst->anon_vma->degree++; unlock_anon_vma_root(root); return 0; enomem_failure: /* * dst->anon_vma is dropped here otherwise its degree can be incorrectly * decremented in unlink_anon_vmas(). * We can safely do this because callers of anon_vma_clone() don't care * about dst->anon_vma if anon_vma_clone() failed. */ dst->anon_vma = NULL; unlink_anon_vmas(dst); return -ENOMEM; } /* * Attach vma to its own anon_vma, as well as to the anon_vmas that * the corresponding VMA in the parent process is attached to. * Returns 0 on success, non-zero on failure. */ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) { struct anon_vma_chain *avc; struct anon_vma *anon_vma; int error; /* Don't bother if the parent process has no anon_vma here. */ if (!pvma->anon_vma) return 0; /* Drop inherited anon_vma, we'll reuse existing or allocate new. */ vma->anon_vma = NULL; /* * First, attach the new VMA to the parent VMA's anon_vmas, * so rmap can find non-COWed pages in child processes. */ error = anon_vma_clone(vma, pvma); if (error) return error; /* An existing anon_vma has been reused, all done then. */ if (vma->anon_vma) return 0; /* Then add our own anon_vma. */ anon_vma = anon_vma_alloc(); if (!anon_vma) goto out_error; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_error_free_anon_vma; /* * The root anon_vma's rwsem is the lock actually used when we * lock any of the anon_vmas in this anon_vma tree. */ anon_vma->root = pvma->anon_vma->root; anon_vma->parent = pvma->anon_vma; /* * With refcounts, an anon_vma can stay around longer than the * process it belongs to. The root anon_vma needs to be pinned until * this anon_vma is freed, because the lock lives in the root. */ get_anon_vma(anon_vma->root); /* Mark this anon_vma as the one where our new (COWed) pages go. */ vma->anon_vma = anon_vma; anon_vma_lock_write(anon_vma); anon_vma_chain_link(vma, avc, anon_vma); anon_vma->parent->degree++; anon_vma_unlock_write(anon_vma); return 0; out_error_free_anon_vma: put_anon_vma(anon_vma); out_error: unlink_anon_vmas(vma); return -ENOMEM; } void unlink_anon_vmas(struct vm_area_struct *vma) { struct anon_vma_chain *avc, *next; struct anon_vma *root = NULL; /* * Unlink each anon_vma chained to the VMA. This list is ordered * from newest to oldest, ensuring the root anon_vma gets freed last. */ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; root = lock_anon_vma_root(root, anon_vma); anon_vma_interval_tree_remove(avc, &anon_vma->rb_root); /* * Leave empty anon_vmas on the list - we'll need * to free them outside the lock. */ if (RB_EMPTY_ROOT(&anon_vma->rb_root.rb_root)) { anon_vma->parent->degree--; continue; } list_del(&avc->same_vma); anon_vma_chain_free(avc); } if (vma->anon_vma) { vma->anon_vma->degree--; /* * vma would still be needed after unlink, and anon_vma will be prepared * when handle fault. */ vma->anon_vma = NULL; } unlock_anon_vma_root(root); /* * Iterate the list once more, it now only contains empty and unlinked * anon_vmas, destroy them. Could not do before due to __put_anon_vma() * needing to write-acquire the anon_vma->root->rwsem. */ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; VM_WARN_ON(anon_vma->degree); put_anon_vma(anon_vma); list_del(&avc->same_vma); anon_vma_chain_free(avc); } } static void anon_vma_ctor(void *data) { struct anon_vma *anon_vma = data; init_rwsem(&anon_vma->rwsem); atomic_set(&anon_vma->refcount, 0); anon_vma->rb_root = RB_ROOT_CACHED; } void __init anon_vma_init(void) { anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma), 0, SLAB_TYPESAFE_BY_RCU|SLAB_PANIC|SLAB_ACCOUNT, anon_vma_ctor); anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain, SLAB_PANIC|SLAB_ACCOUNT); } /* * Getting a lock on a stable anon_vma from a page off the LRU is tricky! * * Since there is no serialization what so ever against page_remove_rmap() * the best this function can do is return a refcount increased anon_vma * that might have been relevant to this page. * * The page might have been remapped to a different anon_vma or the anon_vma * returned may already be freed (and even reused). * * In case it was remapped to a different anon_vma, the new anon_vma will be a * child of the old anon_vma, and the anon_vma lifetime rules will therefore * ensure that any anon_vma obtained from the page will still be valid for as * long as we observe page_mapped() [ hence all those page_mapped() tests ]. * * All users of this function must be very careful when walking the anon_vma * chain and verify that the page in question is indeed mapped in it * [ something equivalent to page_mapped_in_vma() ]. * * Since anon_vma's slab is SLAB_TYPESAFE_BY_RCU and we know from * page_remove_rmap() that the anon_vma pointer from page->mapping is valid * if there is a mapcount, we can dereference the anon_vma after observing * those. */ struct anon_vma *page_get_anon_vma(struct page *page) { struct anon_vma *anon_vma = NULL; unsigned long anon_mapping; rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(page->mapping); if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) goto out; if (!page_mapped(page)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON); if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; goto out; } /* * If this page is still mapped, then its anon_vma cannot have been * freed. But if it has been unmapped, we have no security against the * anon_vma structure being freed and reused (for another anon_vma: * SLAB_TYPESAFE_BY_RCU guarantees that - so the atomic_inc_not_zero() * above cannot corrupt). */ if (!page_mapped(page)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; } out: rcu_read_unlock(); return anon_vma; } /* * Similar to page_get_anon_vma() except it locks the anon_vma. * * Its a little more complex as it tries to keep the fast path to a single * atomic op -- the trylock. If we fail the trylock, we fall back to getting a * reference like with page_get_anon_vma() and then block on the mutex. */ struct anon_vma *page_lock_anon_vma_read(struct page *page) { struct anon_vma *anon_vma = NULL; struct anon_vma *root_anon_vma; unsigned long anon_mapping; rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(page->mapping); if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) goto out; if (!page_mapped(page)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON); root_anon_vma = READ_ONCE(anon_vma->root); if (down_read_trylock(&root_anon_vma->rwsem)) { /* * If the page is still mapped, then this anon_vma is still * its anon_vma, and holding the mutex ensures that it will * not go away, see anon_vma_free(). */ if (!page_mapped(page)) { up_read(&root_anon_vma->rwsem); anon_vma = NULL; } goto out; } /* trylock failed, we got to sleep */ if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; goto out; } if (!page_mapped(page)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; } /* we pinned the anon_vma, its safe to sleep */ rcu_read_unlock(); anon_vma_lock_read(anon_vma); if (atomic_dec_and_test(&anon_vma->refcount)) { /* * Oops, we held the last refcount, release the lock * and bail -- can't simply use put_anon_vma() because * we'll deadlock on the anon_vma_lock_write() recursion. */ anon_vma_unlock_read(anon_vma); __put_anon_vma(anon_vma); anon_vma = NULL; } return anon_vma; out: rcu_read_unlock(); return anon_vma; } void page_unlock_anon_vma_read(struct anon_vma *anon_vma) { anon_vma_unlock_read(anon_vma); } #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* * Flush TLB entries for recently unmapped pages from remote CPUs. It is * important if a PTE was dirty when it was unmapped that it's flushed * before any IO is initiated on the page to prevent lost writes. Similarly, * it must be flushed before freeing to prevent data leakage. */ void try_to_unmap_flush(void) { struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc; if (!tlb_ubc->flush_required) return; arch_tlbbatch_flush(&tlb_ubc->arch); tlb_ubc->flush_required = false; tlb_ubc->writable = false; } /* Flush iff there are potentially writable TLB entries that can race with IO */ void try_to_unmap_flush_dirty(void) { struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc; if (tlb_ubc->writable) try_to_unmap_flush(); } static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) { struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc; arch_tlbbatch_add_mm(&tlb_ubc->arch, mm); tlb_ubc->flush_required = true; /* * Ensure compiler does not re-order the setting of tlb_flush_batched * before the PTE is cleared. */ barrier(); mm->tlb_flush_batched = true; /* * If the PTE was dirty then it's best to assume it's writable. The * caller must use try_to_unmap_flush_dirty() or try_to_unmap_flush() * before the page is queued for IO. */ if (writable) tlb_ubc->writable = true; } /* * Returns true if the TLB flush should be deferred to the end of a batch of * unmap operations to reduce IPIs. */ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { bool should_defer = false; if (!(flags & TTU_BATCH_FLUSH)) return false; /* If remote CPUs need to be flushed then defer batch the flush */ if (cpumask_any_but(mm_cpumask(mm), get_cpu()) < nr_cpu_ids) should_defer = true; put_cpu(); return should_defer; } /* * Reclaim unmaps pages under the PTL but do not flush the TLB prior to * releasing the PTL if TLB flushes are batched. It's possible for a parallel * operation such as mprotect or munmap to race between reclaim unmapping * the page and flushing the page. If this race occurs, it potentially allows * access to data via a stale TLB entry. Tracking all mm's that have TLB * batching in flight would be expensive during reclaim so instead track * whether TLB batching occurred in the past and if so then do a flush here * if required. This will cost one additional flush per reclaim cycle paid * by the first operation at risk such as mprotect and mumap. * * This must be called under the PTL so that an access to tlb_flush_batched * that is potentially a "reclaim vs mprotect/munmap/etc" race will synchronise * via the PTL. */ void flush_tlb_batched_pending(struct mm_struct *mm) { if (data_race(mm->tlb_flush_batched)) { flush_tlb_mm(mm); /* * Do not allow the compiler to re-order the clearing of * tlb_flush_batched before the tlb is flushed. */ barrier(); mm->tlb_flush_batched = false; } } #else static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) { } static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { return false; } #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ /* * At what user virtual address is page expected in vma? * Caller should check the page is actually part of the vma. */ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) { unsigned long address; if (PageAnon(page)) { struct anon_vma *page__anon_vma = page_anon_vma(page); /* * Note: swapoff's unuse_vma() is more efficient with this * check, and needs it to match anon_vma when KSM is active. */ if (!vma->anon_vma || !page__anon_vma || vma->anon_vma->root != page__anon_vma->root) return -EFAULT; } else if (page->mapping) { if (!vma->vm_file || vma->vm_file->f_mapping != page->mapping) return -EFAULT; } else return -EFAULT; address = __vma_address(page, vma); if (unlikely(address < vma->vm_start || address >= vma->vm_end)) return -EFAULT; return address; } pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd = NULL; pmd_t pmde; pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) goto out; p4d = p4d_offset(pgd, address); if (!p4d_present(*p4d)) goto out; pud = pud_offset(p4d, address); if (!pud_present(*pud)) goto out; pmd = pmd_offset(pud, address); /* * Some THP functions use the sequence pmdp_huge_clear_flush(), set_pmd_at() * without holding anon_vma lock for write. So when looking for a * genuine pmde (in which to find pte), test present and !THP together. */ pmde = *pmd; barrier(); if (!pmd_present(pmde) || pmd_trans_huge(pmde)) pmd = NULL; out: return pmd; } struct page_referenced_arg { int mapcount; int referenced; unsigned long vm_flags; struct mem_cgroup *memcg; }; /* * arg: page_referenced_arg will be passed */ static bool page_referenced_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { struct page_referenced_arg *pra = arg; struct page_vma_mapped_walk pvmw = { .page = page, .vma = vma, .address = address, }; int referenced = 0; while (page_vma_mapped_walk(&pvmw)) { address = pvmw.address; if (vma->vm_flags & VM_LOCKED) { page_vma_mapped_walk_done(&pvmw); pra->vm_flags |= VM_LOCKED; return false; /* To break the loop */ } if (pvmw.pte) { if (ptep_clear_flush_young_notify(vma, address, pvmw.pte)) { /* * Don't treat a reference through * a sequentially read mapping as such. * If the page has been used in another mapping, * we will catch it; if this other mapping is * already gone, the unmap path will have set * PG_referenced or activated the page. */ if (likely(!(vma->vm_flags & VM_SEQ_READ))) referenced++; } } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { if (pmdp_clear_flush_young_notify(vma, address, pvmw.pmd)) referenced++; } else { /* unexpected pmd-mapped page? */ WARN_ON_ONCE(1); } pra->mapcount--; } if (referenced) clear_page_idle(page); if (test_and_clear_page_young(page)) referenced++; if (referenced) { pra->referenced++; pra->vm_flags |= vma->vm_flags; } if (!pra->mapcount) return false; /* To break the loop */ return true; } static bool invalid_page_referenced_vma(struct vm_area_struct *vma, void *arg) { struct page_referenced_arg *pra = arg; struct mem_cgroup *memcg = pra->memcg; if (!mm_match_cgroup(vma->vm_mm, memcg)) return true; return false; } /** * page_referenced - test if the page was referenced * @page: the page to test * @is_locked: caller holds lock on the page * @memcg: target memory cgroup * @vm_flags: collect encountered vma->vm_flags who actually referenced the page * * Quick test_and_clear_referenced for all mappings to a page, * returns the number of ptes which referenced the page. */ int page_referenced(struct page *page, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags) { int we_locked = 0; struct page_referenced_arg pra = { .mapcount = total_mapcount(page), .memcg = memcg, }; struct rmap_walk_control rwc = { .rmap_one = page_referenced_one, .arg = (void *)&pra, .anon_lock = page_lock_anon_vma_read, }; *vm_flags = 0; if (!pra.mapcount) return 0; if (!page_rmapping(page)) return 0; if (!is_locked && (!PageAnon(page) || PageKsm(page))) { we_locked = trylock_page(page); if (!we_locked) return 1; } /* * If we are reclaiming on behalf of a cgroup, skip * counting on behalf of references from different * cgroups */ if (memcg) { rwc.invalid_vma = invalid_page_referenced_vma; } rmap_walk(page, &rwc); *vm_flags = pra.vm_flags; if (we_locked) unlock_page(page); return pra.referenced; } static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { struct page_vma_mapped_walk pvmw = { .page = page, .vma = vma, .address = address, .flags = PVMW_SYNC, }; struct mmu_notifier_range range; int *cleaned = arg; /* * We have to assume the worse case ie pmd for invalidation. Note that * the page can not be free from this function. */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, vma, vma->vm_mm, address, min(vma->vm_end, address + page_size(page))); mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { int ret = 0; address = pvmw.address; if (pvmw.pte) { pte_t entry; pte_t *pte = pvmw.pte; if (!pte_dirty(*pte) && !pte_write(*pte)) continue; flush_cache_page(vma, address, pte_pfn(*pte)); entry = ptep_clear_flush(vma, address, pte); entry = pte_wrprotect(entry); entry = pte_mkclean(entry); set_pte_at(vma->vm_mm, address, pte, entry); ret = 1; } else { #ifdef CONFIG_TRANSPARENT_HUGEPAGE pmd_t *pmd = pvmw.pmd; pmd_t entry; if (!pmd_dirty(*pmd) && !pmd_write(*pmd)) continue; flush_cache_page(vma, address, page_to_pfn(page)); entry = pmdp_invalidate(vma, address, pmd); entry = pmd_wrprotect(entry); entry = pmd_mkclean(entry); set_pmd_at(vma->vm_mm, address, pmd, entry); ret = 1; #else /* unexpected pmd-mapped page? */ WARN_ON_ONCE(1); #endif } /* * No need to call mmu_notifier_invalidate_range() as we are * downgrading page table protection not changing it to point * to a new page. * * See Documentation/vm/mmu_notifier.rst */ if (ret) (*cleaned)++; } mmu_notifier_invalidate_range_end(&range); return true; } static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg) { if (vma->vm_flags & VM_SHARED) return false; return true; } int page_mkclean(struct page *page) { int cleaned = 0; struct address_space *mapping; struct rmap_walk_control rwc = { .arg = (void *)&cleaned, .rmap_one = page_mkclean_one, .invalid_vma = invalid_mkclean_vma, }; BUG_ON(!PageLocked(page)); if (!page_mapped(page)) return 0; mapping = page_mapping(page); if (!mapping) return 0; rmap_walk(page, &rwc); return cleaned; } EXPORT_SYMBOL_GPL(page_mkclean); /** * page_move_anon_rmap - move a page to our anon_vma * @page: the page to move to our anon_vma * @vma: the vma the page belongs to * * When a page belongs exclusively to one process after a COW event, * that page can be moved into the anon_vma that belongs to just that * process, so the rmap code will not search the parent or sibling * processes. */ void page_move_anon_rmap(struct page *page, struct vm_area_struct *vma) { struct anon_vma *anon_vma = vma->anon_vma; page = compound_head(page); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_VMA(!anon_vma, vma); anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; /* * Ensure that anon_vma and the PAGE_MAPPING_ANON bit are written * simultaneously, so a concurrent reader (eg page_referenced()'s * PageAnon()) will not see one without the other. */ WRITE_ONCE(page->mapping, (struct address_space *) anon_vma); } /** * __page_set_anon_rmap - set up new anonymous rmap * @page: Page or Hugepage to add to rmap * @vma: VM area to add page to. * @address: User virtual address of the mapping * @exclusive: the page is exclusively owned by the current process */ static void __page_set_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address, int exclusive) { struct anon_vma *anon_vma = vma->anon_vma; BUG_ON(!anon_vma); if (PageAnon(page)) return; /* * If the page isn't exclusively mapped into this vma, * we must use the _oldest_ possible anon_vma for the * page mapping! */ if (!exclusive) anon_vma = anon_vma->root; /* * page_idle does a lockless/optimistic rmap scan on page->mapping. * Make sure the compiler doesn't split the stores of anon_vma and * the PAGE_MAPPING_ANON type identifier, otherwise the rmap code * could mistake the mapping for a struct address_space and crash. */ anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; WRITE_ONCE(page->mapping, (struct address_space *) anon_vma); page->index = linear_page_index(vma, address); } /** * __page_check_anon_rmap - sanity check anonymous rmap addition * @page: the page to add the mapping to * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped */ static void __page_check_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address) { /* * The page's anon-rmap details (mapping and index) are guaranteed to * be set up correctly at this point. * * We have exclusion against page_add_anon_rmap because the caller * always holds the page locked. * * We have exclusion against page_add_new_anon_rmap because those pages * are initially only visible via the pagetables, and the pte is locked * over the call to page_add_new_anon_rmap. */ VM_BUG_ON_PAGE(page_anon_vma(page)->root != vma->anon_vma->root, page); VM_BUG_ON_PAGE(page_to_pgoff(page) != linear_page_index(vma, address), page); } /** * page_add_anon_rmap - add pte mapping to an anonymous page * @page: the page to add the mapping to * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped * @compound: charge the page as compound or small page * * The caller needs to hold the pte lock, and the page must be locked in * the anon_vma case: to serialize mapping,index checking after setting, * and to ensure that PageAnon is not being upgraded racily to PageKsm * (but PageKsm is never downgraded to PageAnon). */ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address, bool compound) { do_page_add_anon_rmap(page, vma, address, compound ? RMAP_COMPOUND : 0); } /* * Special version of the above for do_swap_page, which often runs * into pages that are exclusively owned by the current process. * Everybody else should continue to use page_add_anon_rmap above. */ void do_page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address, int flags) { bool compound = flags & RMAP_COMPOUND; bool first; if (unlikely(PageKsm(page))) lock_page_memcg(page); else VM_BUG_ON_PAGE(!PageLocked(page), page); if (compound) { atomic_t *mapcount; VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(!PageTransHuge(page), page); mapcount = compound_mapcount_ptr(page); first = atomic_inc_and_test(mapcount); } else { first = atomic_inc_and_test(&page->_mapcount); } if (first) { int nr = compound ? thp_nr_pages(page) : 1; /* * We use the irq-unsafe __{inc|mod}_zone_page_stat because * these counters are not modified in interrupt context, and * pte lock(a spinlock) is held, which implies preemption * disabled. */ if (compound) __mod_lruvec_page_state(page, NR_ANON_THPS, nr); __mod_lruvec_page_state(page, NR_ANON_MAPPED, nr); } if (unlikely(PageKsm(page))) { unlock_page_memcg(page); return; } /* address might be in next vma when migration races vma_adjust */ if (first) __page_set_anon_rmap(page, vma, address, flags & RMAP_EXCLUSIVE); else __page_check_anon_rmap(page, vma, address); } /** * page_add_new_anon_rmap - add pte mapping to a new anonymous page * @page: the page to add the mapping to * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped * @compound: charge the page as compound or small page * * Same as page_add_anon_rmap but must only be called on *new* pages. * This means the inc-and-test can be bypassed. * Page does not have to be locked. */ void page_add_new_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address, bool compound) { int nr = compound ? thp_nr_pages(page) : 1; VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma); __SetPageSwapBacked(page); if (compound) { VM_BUG_ON_PAGE(!PageTransHuge(page), page); /* increment count (starts at -1) */ atomic_set(compound_mapcount_ptr(page), 0); if (hpage_pincount_available(page)) atomic_set(compound_pincount_ptr(page), 0); __mod_lruvec_page_state(page, NR_ANON_THPS, nr); } else { /* Anon THP always mapped first with PMD */ VM_BUG_ON_PAGE(PageTransCompound(page), page); /* increment count (starts at -1) */ atomic_set(&page->_mapcount, 0); } __mod_lruvec_page_state(page, NR_ANON_MAPPED, nr); __page_set_anon_rmap(page, vma, address, 1); } /** * page_add_file_rmap - add pte mapping to a file page * @page: the page to add the mapping to * @compound: charge the page as compound or small page * * The caller needs to hold the pte lock. */ void page_add_file_rmap(struct page *page, bool compound) { int i, nr = 1; VM_BUG_ON_PAGE(compound && !PageTransHuge(page), page); lock_page_memcg(page); if (compound && PageTransHuge(page)) { int nr_pages = thp_nr_pages(page); for (i = 0, nr = 0; i < nr_pages; i++) { if (atomic_inc_and_test(&page[i]._mapcount)) nr++; } if (!atomic_inc_and_test(compound_mapcount_ptr(page))) goto out; if (PageSwapBacked(page)) __mod_lruvec_page_state(page, NR_SHMEM_PMDMAPPED, nr_pages); else __mod_lruvec_page_state(page, NR_FILE_PMDMAPPED, nr_pages); } else { if (PageTransCompound(page) && page_mapping(page)) { VM_WARN_ON_ONCE(!PageLocked(page)); SetPageDoubleMap(compound_head(page)); if (PageMlocked(page)) clear_page_mlock(compound_head(page)); } if (!atomic_inc_and_test(&page->_mapcount)) goto out; } __mod_lruvec_page_state(page, NR_FILE_MAPPED, nr); out: unlock_page_memcg(page); } static void page_remove_file_rmap(struct page *page, bool compound) { int i, nr = 1; VM_BUG_ON_PAGE(compound && !PageHead(page), page); /* Hugepages are not counted in NR_FILE_MAPPED for now. */ if (unlikely(PageHuge(page))) { /* hugetlb pages are always mapped with pmds */ atomic_dec(compound_mapcount_ptr(page)); return; } /* page still mapped by someone else? */ if (compound && PageTransHuge(page)) { int nr_pages = thp_nr_pages(page); for (i = 0, nr = 0; i < nr_pages; i++) { if (atomic_add_negative(-1, &page[i]._mapcount)) nr++; } if (!atomic_add_negative(-1, compound_mapcount_ptr(page))) return; if (PageSwapBacked(page)) __mod_lruvec_page_state(page, NR_SHMEM_PMDMAPPED, -nr_pages); else __mod_lruvec_page_state(page, NR_FILE_PMDMAPPED, -nr_pages); } else { if (!atomic_add_negative(-1, &page->_mapcount)) return; } /* * We use the irq-unsafe __{inc|mod}_lruvec_page_state because * these counters are not modified in interrupt context, and * pte lock(a spinlock) is held, which implies preemption disabled. */ __mod_lruvec_page_state(page, NR_FILE_MAPPED, -nr); if (unlikely(PageMlocked(page))) clear_page_mlock(page); } static void page_remove_anon_compound_rmap(struct page *page) { int i, nr; if (!atomic_add_negative(-1, compound_mapcount_ptr(page))) return; /* Hugepages are not counted in NR_ANON_PAGES for now. */ if (unlikely(PageHuge(page))) return; if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return; __mod_lruvec_page_state(page, NR_ANON_THPS, -thp_nr_pages(page)); if (TestClearPageDoubleMap(page)) { /* * Subpages can be mapped with PTEs too. Check how many of * them are still mapped. */ for (i = 0, nr = 0; i < thp_nr_pages(page); i++) { if (atomic_add_negative(-1, &page[i]._mapcount)) nr++; } /* * Queue the page for deferred split if at least one small * page of the compound page is unmapped, but at least one * small page is still mapped. */ if (nr && nr < thp_nr_pages(page)) deferred_split_huge_page(page); } else { nr = thp_nr_pages(page); } if (unlikely(PageMlocked(page))) clear_page_mlock(page); if (nr) __mod_lruvec_page_state(page, NR_ANON_MAPPED, -nr); } /** * page_remove_rmap - take down pte mapping from a page * @page: page to remove mapping from * @compound: uncharge the page as compound or small page * * The caller needs to hold the pte lock. */ void page_remove_rmap(struct page *page, bool compound) { lock_page_memcg(page); if (!PageAnon(page)) { page_remove_file_rmap(page, compound); goto out; } if (compound) { page_remove_anon_compound_rmap(page); goto out; } /* page still mapped by someone else? */ if (!atomic_add_negative(-1, &page->_mapcount)) goto out; /* * We use the irq-unsafe __{inc|mod}_zone_page_stat because * these counters are not modified in interrupt context, and * pte lock(a spinlock) is held, which implies preemption disabled. */ __dec_lruvec_page_state(page, NR_ANON_MAPPED); if (unlikely(PageMlocked(page))) clear_page_mlock(page); if (PageTransCompound(page)) deferred_split_huge_page(compound_head(page)); /* * It would be tidy to reset the PageAnon mapping here, * but that might overwrite a racing page_add_anon_rmap * which increments mapcount after us but sets mapping * before us: so leave the reset to free_unref_page, * and remember that it's only reliable while mapped. * Leaving it set also helps swapoff to reinstate ptes * faster for those pages still in swapcache. */ out: unlock_page_memcg(page); } /* * @arg: enum ttu_flags will be passed to this argument */ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; struct page_vma_mapped_walk pvmw = { .page = page, .vma = vma, .address = address, }; pte_t pteval; struct page *subpage; bool ret = true; struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; /* munlock has nothing to gain from examining un-locked vmas */ if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED)) return true; if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) && is_zone_device_page(page) && !is_device_private_page(page)) return true; if (flags & TTU_SPLIT_HUGE_PMD) { split_huge_pmd_address(vma, address, flags & TTU_SPLIT_FREEZE, page); } /* * For THP, we have to assume the worse case ie pmd for invalidation. * For hugetlb, it could be much worse if we need to do pud * invalidation in the case of pmd sharing. * * Note that the page can not be free in this function as call of * try_to_unmap() must hold a reference on the page. */ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, address, min(vma->vm_end, address + page_size(page))); if (PageHuge(page)) { /* * If sharing is possible, start and end will be adjusted * accordingly. */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); } mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION /* PMD-mapped THP migration entry */ if (!pvmw.pte && (flags & TTU_MIGRATION)) { VM_BUG_ON_PAGE(PageHuge(page) || !PageTransCompound(page), page); set_pmd_migration_entry(&pvmw, page); continue; } #endif /* * If the page is mlock()d, we cannot swap it out. * If it's recently referenced (perhaps page_referenced * skipped over this mm) then we should reactivate it. */ if (!(flags & TTU_IGNORE_MLOCK)) { if (vma->vm_flags & VM_LOCKED) { /* PTE-mapped THP are never mlocked */ if (!PageTransCompound(page)) { /* * Holding pte lock, we do *not* need * mmap_lock here */ mlock_vma_page(page); } ret = false; page_vma_mapped_walk_done(&pvmw); break; } if (flags & TTU_MUNLOCK) continue; } /* Unexpected PMD-mapped THP? */ VM_BUG_ON_PAGE(!pvmw.pte, page); subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); address = pvmw.address; if (PageHuge(page) && !PageAnon(page)) { /* * To call huge_pmd_unshare, i_mmap_rwsem must be * held in write mode. Caller needs to explicitly * do this outside rmap routines. */ VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (huge_pmd_unshare(mm, vma, &address, pvmw.pte)) { /* * huge_pmd_unshare unmapped an entire PMD * page. There is no way of knowing exactly * which PMDs may be cached for this mm, so * we must flush them all. start/end were * already adjusted above to cover this range. */ flush_cache_range(vma, range.start, range.end); flush_tlb_range(vma, range.start, range.end); mmu_notifier_invalidate_range(mm, range.start, range.end); /* * The ref count of the PMD page was dropped * which is part of the way map counting * is done for shared PMDs. Return 'true' * here. When there is no other sharing, * huge_pmd_unshare returns false and we will * unmap the actual page and drop map count * to zero. */ page_vma_mapped_walk_done(&pvmw); break; } } if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) && is_zone_device_page(page)) { swp_entry_t entry; pte_t swp_pte; pteval = ptep_get_and_clear(mm, pvmw.address, pvmw.pte); /* * Store the pfn of the page in a special migration * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ entry = make_migration_entry(page, 0); swp_pte = swp_entry_to_pte(entry); /* * pteval maps a zone device page and is therefore * a swap pte. */ if (pte_swp_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_swp_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte); /* * No need to invalidate here it will synchronize on * against the special swap migration pte. * * The assignment to subpage above was computed from a * swap PTE which results in an invalid pointer. * Since only PAGE_SIZE pages can currently be * migrated, just set it to page. This will need to be * changed when hugepage migrations to device private * memory are supported. */ subpage = page; goto discard; } /* Nuke the page table entry. */ flush_cache_page(vma, address, pte_pfn(*pvmw.pte)); if (should_defer_flush(mm, flags)) { /* * We clear the PTE but do not flush so potentially * a remote CPU could still be writing to the page. * If the entry was previously clean then the * architecture must guarantee that a clear->dirty * transition on a cached TLB entry is written through * and traps if the PTE is unmapped. */ pteval = ptep_get_and_clear(mm, address, pvmw.pte); set_tlb_ubc_flush_pending(mm, pte_dirty(pteval)); } else { pteval = ptep_clear_flush(vma, address, pvmw.pte); } /* Move the dirty bit to the page. Now the pte is gone. */ if (pte_dirty(pteval)) set_page_dirty(page); /* Update high watermark before we lower rss */ update_hiwater_rss(mm); if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) { pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (PageHuge(page)) { hugetlb_count_sub(compound_nr(page), mm); set_huge_swap_pte_at(mm, address, pvmw.pte, pteval, vma_mmu_pagesize(vma)); } else { dec_mm_counter(mm, mm_counter(page)); set_pte_at(mm, address, pvmw.pte, pteval); } } else if (pte_unused(pteval) && !userfaultfd_armed(vma)) { /* * The guest indicated that the page content is of no * interest anymore. Simply discard the pte, vmscan * will take care of the rest. * A future reference will then fault in a new zero * page. When userfaultfd is active, we must not drop * this page though, as its main user (postcopy * migration) will not expect userfaults on already * copied pages. */ dec_mm_counter(mm, mm_counter(page)); /* We have to invalidate as we cleared the pte */ mmu_notifier_invalidate_range(mm, address, address + PAGE_SIZE); } else if (IS_ENABLED(CONFIG_MIGRATION) && (flags & (TTU_MIGRATION|TTU_SPLIT_FREEZE))) { swp_entry_t entry; pte_t swp_pte; if (arch_unmap_one(mm, vma, address, pteval) < 0) { set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } /* * Store the pfn of the page in a special migration * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ entry = make_migration_entry(subpage, pte_write(pteval)); swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); set_pte_at(mm, address, pvmw.pte, swp_pte); /* * No need to invalidate here it will synchronize on * against the special swap migration pte. */ } else if (PageAnon(page)) { swp_entry_t entry = { .val = page_private(subpage) }; pte_t swp_pte; /* * Store the swap location in the pte. * See handle_pte_fault() ... */ if (unlikely(PageSwapBacked(page) != PageSwapCache(page))) { WARN_ON_ONCE(1); ret = false; /* We have to invalidate as we cleared the pte */ mmu_notifier_invalidate_range(mm, address, address + PAGE_SIZE); page_vma_mapped_walk_done(&pvmw); break; } /* MADV_FREE page check */ if (!PageSwapBacked(page)) { if (!PageDirty(page)) { /* Invalidate as we cleared the pte */ mmu_notifier_invalidate_range(mm, address, address + PAGE_SIZE); dec_mm_counter(mm, MM_ANONPAGES); goto discard; } /* * If the page was redirtied, it cannot be * discarded. Remap the page to page table. */ set_pte_at(mm, address, pvmw.pte, pteval); SetPageSwapBacked(page); ret = false; page_vma_mapped_walk_done(&pvmw); break; } if (swap_duplicate(entry) < 0) { set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } if (arch_unmap_one(mm, vma, address, pteval) < 0) { set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } if (list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); if (list_empty(&mm->mmlist)) list_add(&mm->mmlist, &init_mm.mmlist); spin_unlock(&mmlist_lock); } dec_mm_counter(mm, MM_ANONPAGES); inc_mm_counter(mm, MM_SWAPENTS); swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); set_pte_at(mm, address, pvmw.pte, swp_pte); /* Invalidate as we cleared the pte */ mmu_notifier_invalidate_range(mm, address, address + PAGE_SIZE); } else { /* * This is a locked file-backed page, thus it cannot * be removed from the page cache and replaced by a new * page before mmu_notifier_invalidate_range_end, so no * concurrent thread might update its page table to * point at new page while a device still is using this * page. * * See Documentation/vm/mmu_notifier.rst */ dec_mm_counter(mm, mm_counter_file(page)); } discard: /* * No need to call mmu_notifier_invalidate_range() it has be * done above for all cases requiring it to happen under page * table lock before mmu_notifier_invalidate_range_end() * * See Documentation/vm/mmu_notifier.rst */ page_remove_rmap(subpage, PageHuge(page)); put_page(page); } mmu_notifier_invalidate_range_end(&range); return ret; } static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg) { return vma_is_temporary_stack(vma); } static int page_not_mapped(struct page *page) { return !page_mapped(page); } /** * try_to_unmap - try to remove all page table mappings to a page * @page: the page to get unmapped * @flags: action and flags * * Tries to remove all the page table entries which are mapping this * page, used in the pageout path. Caller must hold the page lock. * * If unmap is successful, return true. Otherwise, false. */ bool try_to_unmap(struct page *page, enum ttu_flags flags) { struct rmap_walk_control rwc = { .rmap_one = try_to_unmap_one, .arg = (void *)flags, .done = page_not_mapped, .anon_lock = page_lock_anon_vma_read, }; /* * During exec, a temporary VMA is setup and later moved. * The VMA is moved under the anon_vma lock but not the * page tables leading to a race where migration cannot * find the migration ptes. Rather than increasing the * locking requirements of exec(), migration skips * temporary VMAs until after exec() completes. */ if ((flags & (TTU_MIGRATION|TTU_SPLIT_FREEZE)) && !PageKsm(page) && PageAnon(page)) rwc.invalid_vma = invalid_migration_vma; if (flags & TTU_RMAP_LOCKED) rmap_walk_locked(page, &rwc); else rmap_walk(page, &rwc); return !page_mapcount(page) ? true : false; } /** * try_to_munlock - try to munlock a page * @page: the page to be munlocked * * Called from munlock code. Checks all of the VMAs mapping the page * to make sure nobody else has this page mlocked. The page will be * returned with PG_mlocked cleared if no other vmas have it mlocked. */ void try_to_munlock(struct page *page) { struct rmap_walk_control rwc = { .rmap_one = try_to_unmap_one, .arg = (void *)TTU_MUNLOCK, .done = page_not_mapped, .anon_lock = page_lock_anon_vma_read, }; VM_BUG_ON_PAGE(!PageLocked(page) || PageLRU(page), page); VM_BUG_ON_PAGE(PageCompound(page) && PageDoubleMap(page), page); rmap_walk(page, &rwc); } void __put_anon_vma(struct anon_vma *anon_vma) { struct anon_vma *root = anon_vma->root; anon_vma_free(anon_vma); if (root != anon_vma && atomic_dec_and_test(&root->refcount)) anon_vma_free(root); } static struct anon_vma *rmap_walk_anon_lock(struct page *page, struct rmap_walk_control *rwc) { struct anon_vma *anon_vma; if (rwc->anon_lock) return rwc->anon_lock(page); /* * Note: remove_migration_ptes() cannot use page_lock_anon_vma_read() * because that depends on page_mapped(); but not all its usages * are holding mmap_lock. Users without mmap_lock are required to * take a reference count to prevent the anon_vma disappearing */ anon_vma = page_anon_vma(page); if (!anon_vma) return NULL; anon_vma_lock_read(anon_vma); return anon_vma; } /* * rmap_walk_anon - do something to anonymous page using the object-based * rmap method * @page: the page to be handled * @rwc: control variable according to each walk type * * Find all the mappings of a page using the mapping pointer and the vma chains * contained in the anon_vma struct it points to. * * When called from try_to_munlock(), the mmap_lock of the mm containing the vma * where the page was found will be held for write. So, we won't recheck * vm_flags for that VMA. That should be OK, because that vma shouldn't be * LOCKED. */ static void rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, bool locked) { struct anon_vma *anon_vma; pgoff_t pgoff_start, pgoff_end; struct anon_vma_chain *avc; if (locked) { anon_vma = page_anon_vma(page); /* anon_vma disappear under us? */ VM_BUG_ON_PAGE(!anon_vma, page); } else { anon_vma = rmap_walk_anon_lock(page, rwc); } if (!anon_vma) return; pgoff_start = page_to_pgoff(page); pgoff_end = pgoff_start + thp_nr_pages(page) - 1; anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff_start, pgoff_end) { struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(page, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; if (!rwc->rmap_one(page, vma, address, rwc->arg)) break; if (rwc->done && rwc->done(page)) break; } if (!locked) anon_vma_unlock_read(anon_vma); } /* * rmap_walk_file - do something to file page using the object-based rmap method * @page: the page to be handled * @rwc: control variable according to each walk type * * Find all the mappings of a page using the mapping pointer and the vma chains * contained in the address_space struct it points to. * * When called from try_to_munlock(), the mmap_lock of the mm containing the vma * where the page was found will be held for write. So, we won't recheck * vm_flags for that VMA. That should be OK, because that vma shouldn't be * LOCKED. */ static void rmap_walk_file(struct page *page, struct rmap_walk_control *rwc, bool locked) { struct address_space *mapping = page_mapping(page); pgoff_t pgoff_start, pgoff_end; struct vm_area_struct *vma; /* * The page lock not only makes sure that page->mapping cannot * suddenly be NULLified by truncation, it makes sure that the * structure at mapping cannot be freed and reused yet, * so we can safely take mapping->i_mmap_rwsem. */ VM_BUG_ON_PAGE(!PageLocked(page), page); if (!mapping) return; pgoff_start = page_to_pgoff(page); pgoff_end = pgoff_start + thp_nr_pages(page) - 1; if (!locked) i_mmap_lock_read(mapping); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff_start, pgoff_end) { unsigned long address = vma_address(page, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; if (!rwc->rmap_one(page, vma, address, rwc->arg)) goto done; if (rwc->done && rwc->done(page)) goto done; } done: if (!locked) i_mmap_unlock_read(mapping); } void rmap_walk(struct page *page, struct rmap_walk_control *rwc) { if (unlikely(PageKsm(page))) rmap_walk_ksm(page, rwc); else if (PageAnon(page)) rmap_walk_anon(page, rwc, false); else rmap_walk_file(page, rwc, false); } /* Like rmap_walk, but caller holds relevant rmap lock */ void rmap_walk_locked(struct page *page, struct rmap_walk_control *rwc) { /* no ksm support for now */ VM_BUG_ON_PAGE(PageKsm(page), page); if (PageAnon(page)) rmap_walk_anon(page, rwc, true); else rmap_walk_file(page, rwc, true); } #ifdef CONFIG_HUGETLB_PAGE /* * The following two functions are for anonymous (private mapped) hugepages. * Unlike common anonymous pages, anonymous hugepages have no accounting code * and no lru code, because we handle hugepages differently from common pages. */ void hugepage_add_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address) { struct anon_vma *anon_vma = vma->anon_vma; int first; BUG_ON(!PageLocked(page)); BUG_ON(!anon_vma); /* address might be in next vma when migration races vma_adjust */ first = atomic_inc_and_test(compound_mapcount_ptr(page)); if (first) __page_set_anon_rmap(page, vma, address, 0); } void hugepage_add_new_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address) { BUG_ON(address < vma->vm_start || address >= vma->vm_end); atomic_set(compound_mapcount_ptr(page), 0); if (hpage_pincount_available(page)) atomic_set(compound_pincount_ptr(page), 0); __page_set_anon_rmap(page, vma, address, 1); } #endif /* CONFIG_HUGETLB_PAGE */
567 127 39 122 427 69 435 655 728 799 185 26 772 39 186 186 4 148 16 166 169 96 18 12 8 73 47 18 47 70 11 65 6 15 // SPDX-License-Identifier: GPL-2.0 /* * Convert integer string representation to an integer. * If an integer doesn't fit into specified type, -E is returned. * * Integer starts with optional sign. * kstrtou*() functions do not accept sign "-". * * Radix 0 means autodetection: leading "0x" implies radix 16, * leading "0" implies radix 8, otherwise radix is 10. * Autodetection hints work after optional sign, but not before. * * If -E is returned, result is not touched. */ #include <linux/ctype.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/math64.h> #include <linux/export.h> #include <linux/types.h> #include <linux/uaccess.h> #include "kstrtox.h" const char *_parse_integer_fixup_radix(const char *s, unsigned int *base) { if (*base == 0) { if (s[0] == '0') { if (_tolower(s[1]) == 'x' && isxdigit(s[2])) *base = 16; else *base = 8; } else *base = 10; } if (*base == 16 && s[0] == '0' && _tolower(s[1]) == 'x') s += 2; return s; } /* * Convert non-negative integer string representation in explicitly given radix * to an integer. * Return number of characters consumed maybe or-ed with overflow bit. * If overflow occurs, result integer (incorrect) is still returned. * * Don't you dare use this function. */ unsigned int _parse_integer(const char *s, unsigned int base, unsigned long long *p) { unsigned long long res; unsigned int rv; res = 0; rv = 0; while (1) { unsigned int c = *s; unsigned int lc = c | 0x20; /* don't tolower() this line */ unsigned int val; if ('0' <= c && c <= '9') val = c - '0'; else if ('a' <= lc && lc <= 'f') val = lc - 'a' + 10; else break; if (val >= base) break; /* * Check for overflow only if we are within range of * it in the max base we support (16) */ if (unlikely(res & (~0ull << 60))) { if (res > div_u64(ULLONG_MAX - val, base)) rv |= KSTRTOX_OVERFLOW; } res = res * base + val; rv++; s++; } *p = res; return rv; } static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res) { unsigned long long _res; unsigned int rv; s = _parse_integer_fixup_radix(s, &base); rv = _parse_integer(s, base, &_res); if (rv & KSTRTOX_OVERFLOW) return -ERANGE; if (rv == 0) return -EINVAL; s += rv; if (*s == '\n') s++; if (*s) return -EINVAL; *res = _res; return 0; } /** * kstrtoull - convert a string to an unsigned long long * @s: The start of the string. The string must be null-terminated, and may also * include a single newline before its terminating null. The first character * may also be a plus sign, but not a minus sign. * @base: The number base to use. The maximum supported base is 16. If base is * given as 0, then the base of the string is automatically detected with the * conventional semantics - If it begins with 0x the number will be parsed as a * hexadecimal (case insensitive), if it otherwise begins with 0, it will be * parsed as an octal number. Otherwise it will be parsed as a decimal. * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtoull(). Return code must be checked. */ int kstrtoull(const char *s, unsigned int base, unsigned long long *res) { if (s[0] == '+') s++; return _kstrtoull(s, base, res); } EXPORT_SYMBOL(kstrtoull); /** * kstrtoll - convert a string to a long long * @s: The start of the string. The string must be null-terminated, and may also * include a single newline before its terminating null. The first character * may also be a plus sign or a minus sign. * @base: The number base to use. The maximum supported base is 16. If base is * given as 0, then the base of the string is automatically detected with the * conventional semantics - If it begins with 0x the number will be parsed as a * hexadecimal (case insensitive), if it otherwise begins with 0, it will be * parsed as an octal number. Otherwise it will be parsed as a decimal. * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtoll(). Return code must be checked. */ int kstrtoll(const char *s, unsigned int base, long long *res) { unsigned long long tmp; int rv; if (s[0] == '-') { rv = _kstrtoull(s + 1, base, &tmp); if (rv < 0) return rv; if ((long long)-tmp > 0) return -ERANGE; *res = -tmp; } else { rv = kstrtoull(s, base, &tmp); if (rv < 0) return rv; if ((long long)tmp < 0) return -ERANGE; *res = tmp; } return 0; } EXPORT_SYMBOL(kstrtoll); /* Internal, do not use. */ int _kstrtoul(const char *s, unsigned int base, unsigned long *res) { unsigned long long tmp; int rv; rv = kstrtoull(s, base, &tmp); if (rv < 0) return rv; if (tmp != (unsigned long)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(_kstrtoul); /* Internal, do not use. */ int _kstrtol(const char *s, unsigned int base, long *res) { long long tmp; int rv; rv = kstrtoll(s, base, &tmp); if (rv < 0) return rv; if (tmp != (long)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(_kstrtol); /** * kstrtouint - convert a string to an unsigned int * @s: The start of the string. The string must be null-terminated, and may also * include a single newline before its terminating null. The first character * may also be a plus sign, but not a minus sign. * @base: The number base to use. The maximum supported base is 16. If base is * given as 0, then the base of the string is automatically detected with the * conventional semantics - If it begins with 0x the number will be parsed as a * hexadecimal (case insensitive), if it otherwise begins with 0, it will be * parsed as an octal number. Otherwise it will be parsed as a decimal. * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtoul(). Return code must be checked. */ int kstrtouint(const char *s, unsigned int base, unsigned int *res) { unsigned long long tmp; int rv; rv = kstrtoull(s, base, &tmp); if (rv < 0) return rv; if (tmp != (unsigned int)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtouint); /** * kstrtoint - convert a string to an int * @s: The start of the string. The string must be null-terminated, and may also * include a single newline before its terminating null. The first character * may also be a plus sign or a minus sign. * @base: The number base to use. The maximum supported base is 16. If base is * given as 0, then the base of the string is automatically detected with the * conventional semantics - If it begins with 0x the number will be parsed as a * hexadecimal (case insensitive), if it otherwise begins with 0, it will be * parsed as an octal number. Otherwise it will be parsed as a decimal. * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtol(). Return code must be checked. */ int kstrtoint(const char *s, unsigned int base, int *res) { long long tmp; int rv; rv = kstrtoll(s, base, &tmp); if (rv < 0) return rv; if (tmp != (int)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtoint); int kstrtou16(const char *s, unsigned int base, u16 *res) { unsigned long long tmp; int rv; rv = kstrtoull(s, base, &tmp); if (rv < 0) return rv; if (tmp != (u16)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtou16); int kstrtos16(const char *s, unsigned int base, s16 *res) { long long tmp; int rv; rv = kstrtoll(s, base, &tmp); if (rv < 0) return rv; if (tmp != (s16)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtos16); int kstrtou8(const char *s, unsigned int base, u8 *res) { unsigned long long tmp; int rv; rv = kstrtoull(s, base, &tmp); if (rv < 0) return rv; if (tmp != (u8)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtou8); int kstrtos8(const char *s, unsigned int base, s8 *res) { long long tmp; int rv; rv = kstrtoll(s, base, &tmp); if (rv < 0) return rv; if (tmp != (s8)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtos8); /** * kstrtobool - convert common user inputs into boolean values * @s: input string * @res: result * * This routine returns 0 iff the first character is one of 'Yy1Nn0', or * [oO][NnFf] for "on" and "off". Otherwise it will return -EINVAL. Value * pointed to by res is updated upon finding a match. */ int kstrtobool(const char *s, bool *res) { if (!s) return -EINVAL; switch (s[0]) { case 'y': case 'Y': case '1': *res = true; return 0; case 'n': case 'N': case '0': *res = false; return 0; case 'o': case 'O': switch (s[1]) { case 'n': case 'N': *res = true; return 0; case 'f': case 'F': *res = false; return 0; default: break; } break; default: break; } return -EINVAL; } EXPORT_SYMBOL(kstrtobool); /* * Since "base" would be a nonsense argument, this open-codes the * _from_user helper instead of using the helper macro below. */ int kstrtobool_from_user(const char __user *s, size_t count, bool *res) { /* Longest string needed to differentiate, newline, terminator */ char buf[4]; count = min(count, sizeof(buf) - 1); if (copy_from_user(buf, s, count)) return -EFAULT; buf[count] = '\0'; return kstrtobool(buf, res); } EXPORT_SYMBOL(kstrtobool_from_user); #define kstrto_from_user(f, g, type) \ int f(const char __user *s, size_t count, unsigned int base, type *res) \ { \ /* sign, base 2 representation, newline, terminator */ \ char buf[1 + sizeof(type) * 8 + 1 + 1]; \ \ count = min(count, sizeof(buf) - 1); \ if (copy_from_user(buf, s, count)) \ return -EFAULT; \ buf[count] = '\0'; \ return g(buf, base, res); \ } \ EXPORT_SYMBOL(f) kstrto_from_user(kstrtoull_from_user, kstrtoull, unsigned long long); kstrto_from_user(kstrtoll_from_user, kstrtoll, long long); kstrto_from_user(kstrtoul_from_user, kstrtoul, unsigned long); kstrto_from_user(kstrtol_from_user, kstrtol, long); kstrto_from_user(kstrtouint_from_user, kstrtouint, unsigned int); kstrto_from_user(kstrtoint_from_user, kstrtoint, int); kstrto_from_user(kstrtou16_from_user, kstrtou16, u16); kstrto_from_user(kstrtos16_from_user, kstrtos16, s16); kstrto_from_user(kstrtou8_from_user, kstrtou8, u8); kstrto_from_user(kstrtos8_from_user, kstrtos8, s8);
17 17 1 10 10 10 10 10 // SPDX-License-Identifier: GPL-2.0-only /* * scsi.c Copyright (C) 1992 Drew Eckhardt * Copyright (C) 1993, 1994, 1995, 1999 Eric Youngdale * Copyright (C) 2002, 2003 Christoph Hellwig * * generic mid-level SCSI driver * Initial versions: Drew Eckhardt * Subsequent revisions: Eric Youngdale * * <drew@colorado.edu> * * Bug correction thanks go to : * Rik Faith <faith@cs.unc.edu> * Tommy Thorn <tthorn> * Thomas Wuensche <tw@fgb1.fgb.mw.tu-muenchen.de> * * Modified by Eric Youngdale eric@andante.org or ericy@gnu.ai.mit.edu to * add scatter-gather, multiple outstanding request, and other * enhancements. * * Native multichannel, wide scsi, /proc/scsi and hot plugging * support added by Michael Neuffer <mike@i-connect.net> * * Added request_module("scsi_hostadapter") for kerneld: * (Put an "alias scsi_hostadapter your_hostadapter" in /etc/modprobe.conf) * Bjorn Ekwall <bj0rn@blox.se> * (changed to kmod) * * Major improvements to the timeout, abort, and reset processing, * as well as performance modifications for large queue depths by * Leonard N. Zubkoff <lnz@dandelion.com> * * Converted cli() code to spinlocks, Ingo Molnar * * Jiffies wrap fixes (host->resetting), 3 Dec 1998 Andrea Arcangeli * * out_of_space hacks, D. Gilbert (dpg) 990608 */ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/kernel.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/delay.h> #include <linux/init.h> #include <linux/completion.h> #include <linux/unistd.h> #include <linux/spinlock.h> #include <linux/kmod.h> #include <linux/interrupt.h> #include <linux/notifier.h> #include <linux/cpu.h> #include <linux/mutex.h> #include <linux/async.h> #include <asm/unaligned.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> #include <scsi/scsi_dbg.h> #include <scsi/scsi_device.h> #include <scsi/scsi_driver.h> #include <scsi/scsi_eh.h> #include <scsi/scsi_host.h> #include <scsi/scsi_tcq.h> #include "scsi_priv.h" #include "scsi_logging.h" #define CREATE_TRACE_POINTS #include <trace/events/scsi.h> /* * Definitions and constants. */ /* * Note - the initial logging level can be set here to log events at boot time. * After the system is up, you may enable logging via the /proc interface. */ unsigned int scsi_logging_level; #if defined(CONFIG_SCSI_LOGGING) EXPORT_SYMBOL(scsi_logging_level); #endif /* * Domain for asynchronous system resume operations. It is marked 'exclusive' * to avoid being included in the async_synchronize_full() that is invoked by * dpm_resume(). */ ASYNC_DOMAIN_EXCLUSIVE(scsi_sd_pm_domain); EXPORT_SYMBOL(scsi_sd_pm_domain); #ifdef CONFIG_SCSI_LOGGING void scsi_log_send(struct scsi_cmnd *cmd) { unsigned int level; /* * If ML QUEUE log level is greater than or equal to: * * 1: nothing (match completion) * * 2: log opcode + command of all commands + cmd address * * 3: same as 2 * * 4: same as 3 */ if (unlikely(scsi_logging_level)) { level = SCSI_LOG_LEVEL(SCSI_LOG_MLQUEUE_SHIFT, SCSI_LOG_MLQUEUE_BITS); if (level > 1) { scmd_printk(KERN_INFO, cmd, "Send: scmd 0x%p\n", cmd); scsi_print_command(cmd); } } } void scsi_log_completion(struct scsi_cmnd *cmd, int disposition) { unsigned int level; /* * If ML COMPLETE log level is greater than or equal to: * * 1: log disposition, result, opcode + command, and conditionally * sense data for failures or non SUCCESS dispositions. * * 2: same as 1 but for all command completions. * * 3: same as 2 * * 4: same as 3 plus dump extra junk */ if (unlikely(scsi_logging_level)) { level = SCSI_LOG_LEVEL(SCSI_LOG_MLCOMPLETE_SHIFT, SCSI_LOG_MLCOMPLETE_BITS); if (((level > 0) && (cmd->result || disposition != SUCCESS)) || (level > 1)) { scsi_print_result(cmd, "Done", disposition); scsi_print_command(cmd); if (status_byte(cmd->result) == CHECK_CONDITION) scsi_print_sense(cmd); if (level > 3) scmd_printk(KERN_INFO, cmd, "scsi host busy %d failed %d\n", scsi_host_busy(cmd->device->host), cmd->device->host->host_failed); } } } #endif /** * scsi_finish_command - cleanup and pass command back to upper layer * @cmd: the command * * Description: Pass command off to upper layer for finishing of I/O * request, waking processes that are waiting on results, * etc. */ void scsi_finish_command(struct scsi_cmnd *cmd) { struct scsi_device *sdev = cmd->device; struct scsi_target *starget = scsi_target(sdev); struct Scsi_Host *shost = sdev->host; struct scsi_driver *drv; unsigned int good_bytes; scsi_device_unbusy(sdev, cmd); /* * Clear the flags that say that the device/target/host is no longer * capable of accepting new commands. */ if (atomic_read(&shost->host_blocked)) atomic_set(&shost->host_blocked, 0); if (atomic_read(&starget->target_blocked)) atomic_set(&starget->target_blocked, 0); if (atomic_read(&sdev->device_blocked)) atomic_set(&sdev->device_blocked, 0); /* * If we have valid sense information, then some kind of recovery * must have taken place. Make a note of this. */ if (SCSI_SENSE_VALID(cmd)) cmd->result |= (DRIVER_SENSE << 24); SCSI_LOG_MLCOMPLETE(4, sdev_printk(KERN_INFO, sdev, "Notifying upper driver of completion " "(result %x)\n", cmd->result)); good_bytes = scsi_bufflen(cmd); if (!blk_rq_is_passthrough(cmd->request)) { int old_good_bytes = good_bytes; drv = scsi_cmd_to_driver(cmd); if (drv->done) good_bytes = drv->done(cmd); /* * USB may not give sense identifying bad sector and * simply return a residue instead, so subtract off the * residue if drv->done() error processing indicates no * change to the completion length. */ if (good_bytes == old_good_bytes) good_bytes -= scsi_get_resid(cmd); } scsi_io_completion(cmd, good_bytes); } /* * 1024 is big enough for saturating the fast scsi LUN now */ int scsi_device_max_queue_depth(struct scsi_device *sdev) { return max_t(int, sdev->host->can_queue, 1024); } /** * scsi_change_queue_depth - change a device's queue depth * @sdev: SCSI Device in question * @depth: number of commands allowed to be queued to the driver * * Sets the device queue depth and returns the new value. */ int scsi_change_queue_depth(struct scsi_device *sdev, int depth) { depth = min_t(int, depth, scsi_device_max_queue_depth(sdev)); if (depth > 0) { sdev->queue_depth = depth; wmb(); } if (sdev->request_queue) blk_set_queue_depth(sdev->request_queue, depth); sbitmap_resize(&sdev->budget_map, sdev->queue_depth); return sdev->queue_depth; } EXPORT_SYMBOL(scsi_change_queue_depth); /** * scsi_track_queue_full - track QUEUE_FULL events to adjust queue depth * @sdev: SCSI Device in question * @depth: Current number of outstanding SCSI commands on this device, * not counting the one returned as QUEUE_FULL. * * Description: This function will track successive QUEUE_FULL events on a * specific SCSI device to determine if and when there is a * need to adjust the queue depth on the device. * * Returns: 0 - No change needed, >0 - Adjust queue depth to this new depth, * -1 - Drop back to untagged operation using host->cmd_per_lun * as the untagged command depth * * Lock Status: None held on entry * * Notes: Low level drivers may call this at any time and we will do * "The Right Thing." We are interrupt context safe. */ int scsi_track_queue_full(struct scsi_device *sdev, int depth) { /* * Don't let QUEUE_FULLs on the same * jiffies count, they could all be from * same event. */ if ((jiffies >> 4) == (sdev->last_queue_full_time >> 4)) return 0; sdev->last_queue_full_time = jiffies; if (sdev->last_queue_full_depth != depth) { sdev->last_queue_full_count = 1; sdev->last_queue_full_depth = depth; } else { sdev->last_queue_full_count++; } if (sdev->last_queue_full_count <= 10) return 0; return scsi_change_queue_depth(sdev, depth); } EXPORT_SYMBOL(scsi_track_queue_full); /** * scsi_vpd_inquiry - Request a device provide us with a VPD page * @sdev: The device to ask * @buffer: Where to put the result * @page: Which Vital Product Data to return * @len: The length of the buffer * * This is an internal helper function. You probably want to use * scsi_get_vpd_page instead. * * Returns size of the vpd page on success or a negative error number. */ static int scsi_vpd_inquiry(struct scsi_device *sdev, unsigned char *buffer, u8 page, unsigned len) { int result; unsigned char cmd[16]; if (len < 4) return -EINVAL; cmd[0] = INQUIRY; cmd[1] = 1; /* EVPD */ cmd[2] = page; cmd[3] = len >> 8; cmd[4] = len & 0xff; cmd[5] = 0; /* Control byte */ /* * I'm not convinced we need to try quite this hard to get VPD, but * all the existing users tried this hard. */ result = scsi_execute_req(sdev, cmd, DMA_FROM_DEVICE, buffer, len, NULL, 30 * HZ, 3, NULL); if (result) return -EIO; /* Sanity check that we got the page back that we asked for */ if (buffer[1] != page) return -EIO; return get_unaligned_be16(&buffer[2]) + 4; } /** * scsi_get_vpd_page - Get Vital Product Data from a SCSI device * @sdev: The device to ask * @page: Which Vital Product Data to return * @buf: where to store the VPD * @buf_len: number of bytes in the VPD buffer area * * SCSI devices may optionally supply Vital Product Data. Each 'page' * of VPD is defined in the appropriate SCSI document (eg SPC, SBC). * If the device supports this VPD page, this routine returns a pointer * to a buffer containing the data from that page. The caller is * responsible for calling kfree() on this pointer when it is no longer * needed. If we cannot retrieve the VPD page this routine returns %NULL. */ int scsi_get_vpd_page(struct scsi_device *sdev, u8 page, unsigned char *buf, int buf_len) { int i, result; if (sdev->skip_vpd_pages) goto fail; /* Ask for all the pages supported by this device */ result = scsi_vpd_inquiry(sdev, buf, 0, buf_len); if (result < 4) goto fail; /* If the user actually wanted this page, we can skip the rest */ if (page == 0) return 0; for (i = 4; i < min(result, buf_len); i++) if (buf[i] == page) goto found; if (i < result && i >= buf_len) /* ran off the end of the buffer, give us benefit of doubt */ goto found; /* The device claims it doesn't support the requested page */ goto fail; found: result = scsi_vpd_inquiry(sdev, buf, page, buf_len); if (result < 0) goto fail; return 0; fail: return -EINVAL; } EXPORT_SYMBOL_GPL(scsi_get_vpd_page); /** * scsi_get_vpd_buf - Get Vital Product Data from a SCSI device * @sdev: The device to ask * @page: Which Vital Product Data to return * * Returns %NULL upon failure. */ static struct scsi_vpd *scsi_get_vpd_buf(struct scsi_device *sdev, u8 page) { struct scsi_vpd *vpd_buf; int vpd_len = SCSI_VPD_PG_LEN, result; retry_pg: vpd_buf = kmalloc(sizeof(*vpd_buf) + vpd_len, GFP_KERNEL); if (!vpd_buf) return NULL; result = scsi_vpd_inquiry(sdev, vpd_buf->data, page, vpd_len); if (result < 0) { kfree(vpd_buf); return NULL; } if (result > vpd_len) { vpd_len = result; kfree(vpd_buf); goto retry_pg; } vpd_buf->len = result; return vpd_buf; } static void scsi_update_vpd_page(struct scsi_device *sdev, u8 page, struct scsi_vpd __rcu **sdev_vpd_buf) { struct scsi_vpd *vpd_buf; vpd_buf = scsi_get_vpd_buf(sdev, page); if (!vpd_buf) return; mutex_lock(&sdev->inquiry_mutex); vpd_buf = rcu_replace_pointer(*sdev_vpd_buf, vpd_buf, lockdep_is_held(&sdev->inquiry_mutex)); mutex_unlock(&sdev->inquiry_mutex); if (vpd_buf) kfree_rcu(vpd_buf, rcu); } /** * scsi_attach_vpd - Attach Vital Product Data to a SCSI device structure * @sdev: The device to ask * * Attach the 'Device Identification' VPD page (0x83) and the * 'Unit Serial Number' VPD page (0x80) to a SCSI device * structure. This information can be used to identify the device * uniquely. */ void scsi_attach_vpd(struct scsi_device *sdev) { int i; struct scsi_vpd *vpd_buf; if (!scsi_device_supports_vpd(sdev)) return; /* Ask for all the pages supported by this device */ vpd_buf = scsi_get_vpd_buf(sdev, 0); if (!vpd_buf) return; for (i = 4; i < vpd_buf->len; i++) { if (vpd_buf->data[i] == 0x0) scsi_update_vpd_page(sdev, 0x0, &sdev->vpd_pg0); if (vpd_buf->data[i] == 0x80) scsi_update_vpd_page(sdev, 0x80, &sdev->vpd_pg80); if (vpd_buf->data[i] == 0x83) scsi_update_vpd_page(sdev, 0x83, &sdev->vpd_pg83); if (vpd_buf->data[i] == 0x89) scsi_update_vpd_page(sdev, 0x89, &sdev->vpd_pg89); } kfree(vpd_buf); } /** * scsi_report_opcode - Find out if a given command opcode is supported * @sdev: scsi device to query * @buffer: scratch buffer (must be at least 20 bytes long) * @len: length of buffer * @opcode: opcode for command to look up * * Uses the REPORT SUPPORTED OPERATION CODES to look up the given * opcode. Returns -EINVAL if RSOC fails, 0 if the command opcode is * unsupported and 1 if the device claims to support the command. */ int scsi_report_opcode(struct scsi_device *sdev, unsigned char *buffer, unsigned int len, unsigned char opcode) { unsigned char cmd[16]; struct scsi_sense_hdr sshdr; int result; if (sdev->no_report_opcodes || sdev->scsi_level < SCSI_SPC_3) return -EINVAL; memset(cmd, 0, 16); cmd[0] = MAINTENANCE_IN; cmd[1] = MI_REPORT_SUPPORTED_OPERATION_CODES; cmd[2] = 1; /* One command format */ cmd[3] = opcode; put_unaligned_be32(len, &cmd[6]); memset(buffer, 0, len); result = scsi_execute_req(sdev, cmd, DMA_FROM_DEVICE, buffer, len, &sshdr, 30 * HZ, 3, NULL); if (result && scsi_sense_valid(&sshdr) && sshdr.sense_key == ILLEGAL_REQUEST && (sshdr.asc == 0x20 || sshdr.asc == 0x24) && sshdr.ascq == 0x00) return -EINVAL; if ((buffer[1] & 3) == 3) /* Command supported */ return 1; return 0; } EXPORT_SYMBOL(scsi_report_opcode); /** * scsi_device_get - get an additional reference to a scsi_device * @sdev: device to get a reference to * * Description: Gets a reference to the scsi_device and increments the use count * of the underlying LLDD module. You must hold host_lock of the * parent Scsi_Host or already have a reference when calling this. * * This will fail if a device is deleted or cancelled, or when the LLD module * is in the process of being unloaded. */ int scsi_device_get(struct scsi_device *sdev) { if (sdev->sdev_state == SDEV_DEL || sdev->sdev_state == SDEV_CANCEL) goto fail; if (!get_device(&sdev->sdev_gendev)) goto fail; if (!try_module_get(sdev->host->hostt->module)) goto fail_put_device; return 0; fail_put_device: put_device(&sdev->sdev_gendev); fail: return -ENXIO; } EXPORT_SYMBOL(scsi_device_get); /** * scsi_device_put - release a reference to a scsi_device * @sdev: device to release a reference on. * * Description: Release a reference to the scsi_device and decrements the use * count of the underlying LLDD module. The device is freed once the last * user vanishes. */ void scsi_device_put(struct scsi_device *sdev) { module_put(sdev->host->hostt->module); put_device(&sdev->sdev_gendev); } EXPORT_SYMBOL(scsi_device_put); /* helper for shost_for_each_device, see that for documentation */ struct scsi_device *__scsi_iterate_devices(struct Scsi_Host *shost, struct scsi_device *prev) { struct list_head *list = (prev ? &prev->siblings : &shost->__devices); struct scsi_device *next = NULL; unsigned long flags; spin_lock_irqsave(shost->host_lock, flags); while (list->next != &shost->__devices) { next = list_entry(list->next, struct scsi_device, siblings); /* skip devices that we can't get a reference to */ if (!scsi_device_get(next)) break; next = NULL; list = list->next; } spin_unlock_irqrestore(shost->host_lock, flags); if (prev) scsi_device_put(prev); return next; } EXPORT_SYMBOL(__scsi_iterate_devices); /** * starget_for_each_device - helper to walk all devices of a target * @starget: target whose devices we want to iterate over. * @data: Opaque passed to each function call. * @fn: Function to call on each device * * This traverses over each device of @starget. The devices have * a reference that must be released by scsi_host_put when breaking * out of the loop. */ void starget_for_each_device(struct scsi_target *starget, void *data, void (*fn)(struct scsi_device *, void *)) { struct Scsi_Host *shost = dev_to_shost(starget->dev.parent); struct scsi_device *sdev; shost_for_each_device(sdev, shost) { if ((sdev->channel == starget->channel) && (sdev->id == starget->id)) fn(sdev, data); } } EXPORT_SYMBOL(starget_for_each_device); /** * __starget_for_each_device - helper to walk all devices of a target (UNLOCKED) * @starget: target whose devices we want to iterate over. * @data: parameter for callback @fn() * @fn: callback function that is invoked for each device * * This traverses over each device of @starget. It does _not_ * take a reference on the scsi_device, so the whole loop must be * protected by shost->host_lock. * * Note: The only reason why drivers would want to use this is because * they need to access the device list in irq context. Otherwise you * really want to use starget_for_each_device instead. **/ void __starget_for_each_device(struct scsi_target *starget, void *data, void (*fn)(struct scsi_device *, void *)) { struct Scsi_Host *shost = dev_to_shost(starget->dev.parent); struct scsi_device *sdev; __shost_for_each_device(sdev, shost) { if ((sdev->channel == starget->channel) && (sdev->id == starget->id)) fn(sdev, data); } } EXPORT_SYMBOL(__starget_for_each_device); /** * __scsi_device_lookup_by_target - find a device given the target (UNLOCKED) * @starget: SCSI target pointer * @lun: SCSI Logical Unit Number * * Description: Looks up the scsi_device with the specified @lun for a given * @starget. The returned scsi_device does not have an additional * reference. You must hold the host's host_lock over this call and * any access to the returned scsi_device. A scsi_device in state * SDEV_DEL is skipped. * * Note: The only reason why drivers should use this is because * they need to access the device list in irq context. Otherwise you * really want to use scsi_device_lookup_by_target instead. **/ struct scsi_device *__scsi_device_lookup_by_target(struct scsi_target *starget, u64 lun) { struct scsi_device *sdev; list_for_each_entry(sdev, &starget->devices, same_target_siblings) { if (sdev->sdev_state == SDEV_DEL) continue; if (sdev->lun ==lun) return sdev; } return NULL; } EXPORT_SYMBOL(__scsi_device_lookup_by_target); /** * scsi_device_lookup_by_target - find a device given the target * @starget: SCSI target pointer * @lun: SCSI Logical Unit Number * * Description: Looks up the scsi_device with the specified @lun for a given * @starget. The returned scsi_device has an additional reference that * needs to be released with scsi_device_put once you're done with it. **/ struct scsi_device *scsi_device_lookup_by_target(struct scsi_target *starget, u64 lun) { struct scsi_device *sdev; struct Scsi_Host *shost = dev_to_shost(starget->dev.parent); unsigned long flags; spin_lock_irqsave(shost->host_lock, flags); sdev = __scsi_device_lookup_by_target(starget, lun); if (sdev && scsi_device_get(sdev)) sdev = NULL; spin_unlock_irqrestore(shost->host_lock, flags); return sdev; } EXPORT_SYMBOL(scsi_device_lookup_by_target); /** * __scsi_device_lookup - find a device given the host (UNLOCKED) * @shost: SCSI host pointer * @channel: SCSI channel (zero if only one channel) * @id: SCSI target number (physical unit number) * @lun: SCSI Logical Unit Number * * Description: Looks up the scsi_device with the specified @channel, @id, @lun * for a given host. The returned scsi_device does not have an additional * reference. You must hold the host's host_lock over this call and any access * to the returned scsi_device. * * Note: The only reason why drivers would want to use this is because * they need to access the device list in irq context. Otherwise you * really want to use scsi_device_lookup instead. **/ struct scsi_device *__scsi_device_lookup(struct Scsi_Host *shost, uint channel, uint id, u64 lun) { struct scsi_device *sdev; list_for_each_entry(sdev, &shost->__devices, siblings) { if (sdev->sdev_state == SDEV_DEL) continue; if (sdev->channel == channel && sdev->id == id && sdev->lun ==lun) return sdev; } return NULL; } EXPORT_SYMBOL(__scsi_device_lookup); /** * scsi_device_lookup - find a device given the host * @shost: SCSI host pointer * @channel: SCSI channel (zero if only one channel) * @id: SCSI target number (physical unit number) * @lun: SCSI Logical Unit Number * * Description: Looks up the scsi_device with the specified @channel, @id, @lun * for a given host. The returned scsi_device has an additional reference that * needs to be released with scsi_device_put once you're done with it. **/ struct scsi_device *scsi_device_lookup(struct Scsi_Host *shost, uint channel, uint id, u64 lun) { struct scsi_device *sdev; unsigned long flags; spin_lock_irqsave(shost->host_lock, flags); sdev = __scsi_device_lookup(shost, channel, id, lun); if (sdev && scsi_device_get(sdev)) sdev = NULL; spin_unlock_irqrestore(shost->host_lock, flags); return sdev; } EXPORT_SYMBOL(scsi_device_lookup); MODULE_DESCRIPTION("SCSI core"); MODULE_LICENSE("GPL"); module_param(scsi_logging_level, int, S_IRUGO|S_IWUSR); MODULE_PARM_DESC(scsi_logging_level, "a bit mask of logging levels"); static int __init init_scsi(void) { int error; error = scsi_init_procfs(); if (error) goto cleanup_queue; error = scsi_init_devinfo(); if (error) goto cleanup_procfs; error = scsi_init_hosts(); if (error) goto cleanup_devlist; error = scsi_init_sysctl(); if (error) goto cleanup_hosts; error = scsi_sysfs_register(); if (error) goto cleanup_sysctl; scsi_netlink_init(); printk(KERN_NOTICE "SCSI subsystem initialized\n"); return 0; cleanup_sysctl: scsi_exit_sysctl(); cleanup_hosts: scsi_exit_hosts(); cleanup_devlist: scsi_exit_devinfo(); cleanup_procfs: scsi_exit_procfs(); cleanup_queue: scsi_exit_queue(); printk(KERN_ERR "SCSI subsystem failed to initialize, error = %d\n", -error); return error; } static void __exit exit_scsi(void) { scsi_netlink_exit(); scsi_sysfs_unregister(); scsi_exit_sysctl(); scsi_exit_hosts(); scsi_exit_devinfo(); scsi_exit_procfs(); scsi_exit_queue(); } subsys_initcall(init_scsi); module_exit(exit_scsi);
18 188 2451 133 13 279 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RMAP_H #define _LINUX_RMAP_H /* * Declarations for Reverse Mapping functions in mm/rmap.c */ #include <linux/list.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/rwsem.h> #include <linux/memcontrol.h> #include <linux/highmem.h> /* * The anon_vma heads a list of private "related" vmas, to scan if * an anonymous page pointing to this anon_vma needs to be unmapped: * the vmas on the list will be related by forking, or by splitting. * * Since vmas come and go as they are split and merged (particularly * in mprotect), the mapping field of an anonymous page cannot point * directly to a vma: instead it points to an anon_vma, on whose list * the related vmas can be easily linked or unlinked. * * After unlinking the last vma on the list, we must garbage collect * the anon_vma object itself: we're guaranteed no page can be * pointing to this anon_vma once its vma list is empty. */ struct anon_vma { struct anon_vma *root; /* Root of this anon_vma tree */ struct rw_semaphore rwsem; /* W: modification, R: walking the list */ /* * The refcount is taken on an anon_vma when there is no * guarantee that the vma of page tables will exist for * the duration of the operation. A caller that takes * the reference is responsible for clearing up the * anon_vma if they are the last user on release */ atomic_t refcount; /* * Count of child anon_vmas and VMAs which points to this anon_vma. * * This counter is used for making decision about reusing anon_vma * instead of forking new one. See comments in function anon_vma_clone. */ unsigned degree; struct anon_vma *parent; /* Parent of this anon_vma */ /* * NOTE: the LSB of the rb_root.rb_node is set by * mm_take_all_locks() _after_ taking the above lock. So the * rb_root must only be read/written after taking the above lock * to be sure to see a valid next pointer. The LSB bit itself * is serialized by a system wide lock only visible to * mm_take_all_locks() (mm_all_locks_mutex). */ /* Interval tree of private "related" vmas */ struct rb_root_cached rb_root; }; /* * The copy-on-write semantics of fork mean that an anon_vma * can become associated with multiple processes. Furthermore, * each child process will have its own anon_vma, where new * pages for that process are instantiated. * * This structure allows us to find the anon_vmas associated * with a VMA, or the VMAs associated with an anon_vma. * The "same_vma" list contains the anon_vma_chains linking * all the anon_vmas associated with this VMA. * The "rb" field indexes on an interval tree the anon_vma_chains * which link all the VMAs associated with this anon_vma. */ struct anon_vma_chain { struct vm_area_struct *vma; struct anon_vma *anon_vma; struct list_head same_vma; /* locked by mmap_lock & page_table_lock */ struct rb_node rb; /* locked by anon_vma->rwsem */ unsigned long rb_subtree_last; #ifdef CONFIG_DEBUG_VM_RB unsigned long cached_vma_start, cached_vma_last; #endif }; enum ttu_flags { TTU_MIGRATION = 0x1, /* migration mode */ TTU_MUNLOCK = 0x2, /* munlock mode */ TTU_SPLIT_HUGE_PMD = 0x4, /* split huge PMD if any */ TTU_IGNORE_MLOCK = 0x8, /* ignore mlock */ TTU_IGNORE_HWPOISON = 0x20, /* corrupted page is recoverable */ TTU_BATCH_FLUSH = 0x40, /* Batch TLB flushes where possible * and caller guarantees they will * do a final flush if necessary */ TTU_RMAP_LOCKED = 0x80, /* do not grab rmap lock: * caller holds it */ TTU_SPLIT_FREEZE = 0x100, /* freeze pte under splitting thp */ }; #ifdef CONFIG_MMU static inline void get_anon_vma(struct anon_vma *anon_vma) { atomic_inc(&anon_vma->refcount); } void __put_anon_vma(struct anon_vma *anon_vma); static inline void put_anon_vma(struct anon_vma *anon_vma) { if (atomic_dec_and_test(&anon_vma->refcount)) __put_anon_vma(anon_vma); } static inline void anon_vma_lock_write(struct anon_vma *anon_vma) { down_write(&anon_vma->root->rwsem); } static inline void anon_vma_unlock_write(struct anon_vma *anon_vma) { up_write(&anon_vma->root->rwsem); } static inline void anon_vma_lock_read(struct anon_vma *anon_vma) { down_read(&anon_vma->root->rwsem); } static inline void anon_vma_unlock_read(struct anon_vma *anon_vma) { up_read(&anon_vma->root->rwsem); } /* * anon_vma helper functions. */ void anon_vma_init(void); /* create anon_vma_cachep */ int __anon_vma_prepare(struct vm_area_struct *); void unlink_anon_vmas(struct vm_area_struct *); int anon_vma_clone(struct vm_area_struct *, struct vm_area_struct *); int anon_vma_fork(struct vm_area_struct *, struct vm_area_struct *); static inline int anon_vma_prepare(struct vm_area_struct *vma) { if (likely(vma->anon_vma)) return 0; return __anon_vma_prepare(vma); } static inline void anon_vma_merge(struct vm_area_struct *vma, struct vm_area_struct *next) { VM_BUG_ON_VMA(vma->anon_vma != next->anon_vma, vma); unlink_anon_vmas(next); } struct anon_vma *page_get_anon_vma(struct page *page); /* bitflags for do_page_add_anon_rmap() */ #define RMAP_EXCLUSIVE 0x01 #define RMAP_COMPOUND 0x02 /* * rmap interfaces called when adding or removing pte of page */ void page_move_anon_rmap(struct page *, struct vm_area_struct *); void page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long, bool); void do_page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long, int); void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long, bool); void page_add_file_rmap(struct page *, bool); void page_remove_rmap(struct page *, bool); void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long); void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long); static inline void page_dup_rmap(struct page *page, bool compound) { atomic_inc(compound ? compound_mapcount_ptr(page) : &page->_mapcount); } /* * Called from mm/vmscan.c to handle paging out */ int page_referenced(struct page *, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags); bool try_to_unmap(struct page *, enum ttu_flags flags); /* Avoid racy checks */ #define PVMW_SYNC (1 << 0) /* Look for migarion entries rather than present PTEs */ #define PVMW_MIGRATION (1 << 1) struct page_vma_mapped_walk { struct page *page; struct vm_area_struct *vma; unsigned long address; pmd_t *pmd; pte_t *pte; spinlock_t *ptl; unsigned int flags; }; static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw) { /* HugeTLB pte is set to the relevant page table entry without pte_mapped. */ if (pvmw->pte && !PageHuge(pvmw->page)) pte_unmap(pvmw->pte); if (pvmw->ptl) spin_unlock(pvmw->ptl); } bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw); /* * Used by swapoff to help locate where page is expected in vma. */ unsigned long page_address_in_vma(struct page *, struct vm_area_struct *); /* * Cleans the PTEs of shared mappings. * (and since clean PTEs should also be readonly, write protects them too) * * returns the number of cleaned PTEs. */ int page_mkclean(struct page *); /* * called in munlock()/munmap() path to check for other vmas holding * the page mlocked. */ void try_to_munlock(struct page *); void remove_migration_ptes(struct page *old, struct page *new, bool locked); /* * Called by memory-failure.c to kill processes. */ struct anon_vma *page_lock_anon_vma_read(struct page *page); void page_unlock_anon_vma_read(struct anon_vma *anon_vma); int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); /* * rmap_walk_control: To control rmap traversing for specific needs * * arg: passed to rmap_one() and invalid_vma() * rmap_one: executed on each vma where page is mapped * done: for checking traversing termination condition * anon_lock: for getting anon_lock by optimized way rather than default * invalid_vma: for skipping uninterested vma */ struct rmap_walk_control { void *arg; /* * Return false if page table scanning in rmap_walk should be stopped. * Otherwise, return true. */ bool (*rmap_one)(struct page *page, struct vm_area_struct *vma, unsigned long addr, void *arg); int (*done)(struct page *page); struct anon_vma *(*anon_lock)(struct page *page); bool (*invalid_vma)(struct vm_area_struct *vma, void *arg); }; void rmap_walk(struct page *page, struct rmap_walk_control *rwc); void rmap_walk_locked(struct page *page, struct rmap_walk_control *rwc); #else /* !CONFIG_MMU */ #define anon_vma_init() do {} while (0) #define anon_vma_prepare(vma) (0) #define anon_vma_link(vma) do {} while (0) static inline int page_referenced(struct page *page, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags) { *vm_flags = 0; return 0; } #define try_to_unmap(page, refs) false static inline int page_mkclean(struct page *page) { return 0; } #endif /* CONFIG_MMU */ #endif /* _LINUX_RMAP_H */
65 42 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MBCACHE_H #define _LINUX_MBCACHE_H #include <linux/hash.h> #include <linux/list_bl.h> #include <linux/list.h> #include <linux/atomic.h> #include <linux/fs.h> struct mb_cache; struct mb_cache_entry { /* List of entries in cache - protected by cache->c_list_lock */ struct list_head e_list; /* Hash table list - protected by hash chain bitlock */ struct hlist_bl_node e_hash_list; atomic_t e_refcnt; /* Key in hash - stable during lifetime of the entry */ u32 e_key; u32 e_referenced:1; u32 e_reusable:1; /* User provided value - stable during lifetime of the entry */ u64 e_value; }; struct mb_cache *mb_cache_create(int bucket_bits); void mb_cache_destroy(struct mb_cache *cache); int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, u64 value, bool reusable); void __mb_cache_entry_free(struct mb_cache_entry *entry); static inline int mb_cache_entry_put(struct mb_cache *cache, struct mb_cache_entry *entry) { if (!atomic_dec_and_test(&entry->e_refcnt)) return 0; __mb_cache_entry_free(entry); return 1; } void mb_cache_entry_delete(struct mb_cache *cache, u32 key, u64 value); struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *cache, u32 key, u64 value); struct mb_cache_entry *mb_cache_entry_find_first(struct mb_cache *cache, u32 key); struct mb_cache_entry *mb_cache_entry_find_next(struct mb_cache *cache, struct mb_cache_entry *entry); void mb_cache_entry_touch(struct mb_cache *cache, struct mb_cache_entry *entry); #endif /* _LINUX_MBCACHE_H */
110 2 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _SOCK_REUSEPORT_H #define _SOCK_REUSEPORT_H #include <linux/filter.h> #include <linux/skbuff.h> #include <linux/types.h> #include <linux/spinlock.h> #include <net/sock.h> extern spinlock_t reuseport_lock; struct sock_reuseport { struct rcu_head rcu; u16 max_socks; /* length of socks */ u16 num_socks; /* elements in socks */ /* The last synq overflow event timestamp of this * reuse->socks[] group. */ unsigned int synq_overflow_ts; /* ID stays the same even after the size of socks[] grows. */ unsigned int reuseport_id; unsigned int bind_inany:1; unsigned int has_conns:1; struct bpf_prog __rcu *prog; /* optional BPF sock selector */ struct sock *socks[]; /* array of sock pointers */ }; extern int reuseport_alloc(struct sock *sk, bool bind_inany); extern int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany); extern void reuseport_detach_sock(struct sock *sk); extern struct sock *reuseport_select_sock(struct sock *sk, u32 hash, struct sk_buff *skb, int hdr_len); extern int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog); extern int reuseport_detach_prog(struct sock *sk); static inline bool reuseport_has_conns(struct sock *sk, bool set) { struct sock_reuseport *reuse; bool ret = false; rcu_read_lock(); reuse = rcu_dereference(sk->sk_reuseport_cb); if (reuse) { if (set) reuse->has_conns = 1; ret = reuse->has_conns; } rcu_read_unlock(); return ret; } #endif /* _SOCK_REUSEPORT_H */
42 42 1 1 40 2 59 170 113 59 59 58 40 59 59 8 4 5 13 13 9 19 19 16 7 70 11 59 16 10 3 5 22 4 3 8 7 2 3 8 6 2 6 2 6 8 7 1 11 10 8 4 2 2 2 4 2 2 4 27 4 10 11 28 28 254 168 397 397 255 255 3 3 2 2 254 160 86 86 8 8 402 402 402 402 255 144 116 252 142 115 24 12 13 197 93 112 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 9 21 29 2 2 2 2 2 2 2 // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2006 Jens Axboe <axboe@kernel.dk> * */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/blkdev.h> #include <linux/blktrace_api.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/debugfs.h> #include <linux/export.h> #include <linux/time.h> #include <linux/uaccess.h> #include <linux/list.h> #include <linux/blk-cgroup.h> #include "../../block/blk.h" #include <trace/events/block.h> #include "trace_output.h" #ifdef CONFIG_BLK_DEV_IO_TRACE static unsigned int blktrace_seq __read_mostly = 1; static struct trace_array *blk_tr; static bool blk_tracer_enabled __read_mostly; static LIST_HEAD(running_trace_list); static __cacheline_aligned_in_smp DEFINE_SPINLOCK(running_trace_lock); /* Select an alternative, minimalistic output than the original one */ #define TRACE_BLK_OPT_CLASSIC 0x1 #define TRACE_BLK_OPT_CGROUP 0x2 #define TRACE_BLK_OPT_CGNAME 0x4 static struct tracer_opt blk_tracer_opts[] = { /* Default disable the minimalistic output */ { TRACER_OPT(blk_classic, TRACE_BLK_OPT_CLASSIC) }, #ifdef CONFIG_BLK_CGROUP { TRACER_OPT(blk_cgroup, TRACE_BLK_OPT_CGROUP) }, { TRACER_OPT(blk_cgname, TRACE_BLK_OPT_CGNAME) }, #endif { } }; static struct tracer_flags blk_tracer_flags = { .val = 0, .opts = blk_tracer_opts, }; /* Global reference count of probes */ static DEFINE_MUTEX(blk_probe_mutex); static int blk_probes_ref; static void blk_register_tracepoints(void); static void blk_unregister_tracepoints(void); /* * Send out a notify message. */ static void trace_note(struct blk_trace *bt, pid_t pid, int action, const void *data, size_t len, u64 cgid) { struct blk_io_trace *t; struct ring_buffer_event *event = NULL; struct trace_buffer *buffer = NULL; unsigned int trace_ctx = 0; int cpu = smp_processor_id(); bool blk_tracer = blk_tracer_enabled; ssize_t cgid_len = cgid ? sizeof(cgid) : 0; if (blk_tracer) { buffer = blk_tr->array_buffer.buffer; trace_ctx = tracing_gen_ctx_flags(0); event = trace_buffer_lock_reserve(buffer, TRACE_BLK, sizeof(*t) + len + cgid_len, trace_ctx); if (!event) return; t = ring_buffer_event_data(event); goto record_it; } if (!bt->rchan) return; t = relay_reserve(bt->rchan, sizeof(*t) + len + cgid_len); if (t) { t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION; t->time = ktime_to_ns(ktime_get()); record_it: t->device = bt->dev; t->action = action | (cgid ? __BLK_TN_CGROUP : 0); t->pid = pid; t->cpu = cpu; t->pdu_len = len + cgid_len; if (cgid_len) memcpy((void *)t + sizeof(*t), &cgid, cgid_len); memcpy((void *) t + sizeof(*t) + cgid_len, data, len); if (blk_tracer) trace_buffer_unlock_commit(blk_tr, buffer, event, trace_ctx); } } /* * Send out a notify for this process, if we haven't done so since a trace * started */ static void trace_note_tsk(struct task_struct *tsk) { unsigned long flags; struct blk_trace *bt; tsk->btrace_seq = blktrace_seq; spin_lock_irqsave(&running_trace_lock, flags); list_for_each_entry(bt, &running_trace_list, running_list) { trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm, sizeof(tsk->comm), 0); } spin_unlock_irqrestore(&running_trace_lock, flags); } static void trace_note_time(struct blk_trace *bt) { struct timespec64 now; unsigned long flags; u32 words[2]; /* need to check user space to see if this breaks in y2038 or y2106 */ ktime_get_real_ts64(&now); words[0] = (u32)now.tv_sec; words[1] = now.tv_nsec; local_irq_save(flags); trace_note(bt, 0, BLK_TN_TIMESTAMP, words, sizeof(words), 0); local_irq_restore(flags); } void __trace_note_message(struct blk_trace *bt, struct blkcg *blkcg, const char *fmt, ...) { int n; va_list args; unsigned long flags; char *buf; if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer_enabled)) return; /* * If the BLK_TC_NOTIFY action mask isn't set, don't send any note * message to the trace. */ if (!(bt->act_mask & BLK_TC_NOTIFY)) return; local_irq_save(flags); buf = this_cpu_ptr(bt->msg_data); va_start(args, fmt); n = vscnprintf(buf, BLK_TN_MAX_MSG, fmt, args); va_end(args); if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) blkcg = NULL; #ifdef CONFIG_BLK_CGROUP trace_note(bt, current->pid, BLK_TN_MESSAGE, buf, n, blkcg ? cgroup_id(blkcg->css.cgroup) : 1); #else trace_note(bt, current->pid, BLK_TN_MESSAGE, buf, n, 0); #endif local_irq_restore(flags); } EXPORT_SYMBOL_GPL(__trace_note_message); static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector, pid_t pid) { if (((bt->act_mask << BLK_TC_SHIFT) & what) == 0) return 1; if (sector && (sector < bt->start_lba || sector > bt->end_lba)) return 1; if (bt->pid && pid != bt->pid) return 1; return 0; } /* * Data direction bit lookup */ static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ), BLK_TC_ACT(BLK_TC_WRITE) }; #define BLK_TC_RAHEAD BLK_TC_AHEAD #define BLK_TC_PREFLUSH BLK_TC_FLUSH /* The ilog2() calls fall out because they're constant */ #define MASK_TC_BIT(rw, __name) ((rw & REQ_ ## __name) << \ (ilog2(BLK_TC_ ## __name) + BLK_TC_SHIFT - __REQ_ ## __name)) /* * The worker for the various blk_add_trace*() types. Fills out a * blk_io_trace structure and places it in a per-cpu subbuffer. */ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, int op, int op_flags, u32 what, int error, int pdu_len, void *pdu_data, u64 cgid) { struct task_struct *tsk = current; struct ring_buffer_event *event = NULL; struct trace_buffer *buffer = NULL; struct blk_io_trace *t; unsigned long flags = 0; unsigned long *sequence; unsigned int trace_ctx = 0; pid_t pid; int cpu; bool blk_tracer = blk_tracer_enabled; ssize_t cgid_len = cgid ? sizeof(cgid) : 0; if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer)) return; what |= ddir_act[op_is_write(op) ? WRITE : READ]; what |= MASK_TC_BIT(op_flags, SYNC); what |= MASK_TC_BIT(op_flags, RAHEAD); what |= MASK_TC_BIT(op_flags, META); what |= MASK_TC_BIT(op_flags, PREFLUSH); what |= MASK_TC_BIT(op_flags, FUA); if (op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE) what |= BLK_TC_ACT(BLK_TC_DISCARD); if (op == REQ_OP_FLUSH) what |= BLK_TC_ACT(BLK_TC_FLUSH); if (cgid) what |= __BLK_TA_CGROUP; pid = tsk->pid; if (act_log_check(bt, what, sector, pid)) return; cpu = raw_smp_processor_id(); if (blk_tracer) { tracing_record_cmdline(current); buffer = blk_tr->array_buffer.buffer; trace_ctx = tracing_gen_ctx_flags(0); event = trace_buffer_lock_reserve(buffer, TRACE_BLK, sizeof(*t) + pdu_len + cgid_len, trace_ctx); if (!event) return; t = ring_buffer_event_data(event); goto record_it; } if (unlikely(tsk->btrace_seq != blktrace_seq)) trace_note_tsk(tsk); /* * A word about the locking here - we disable interrupts to reserve * some space in the relay per-cpu buffer, to prevent an irq * from coming in and stepping on our toes. */ local_irq_save(flags); t = relay_reserve(bt->rchan, sizeof(*t) + pdu_len + cgid_len); if (t) { sequence = per_cpu_ptr(bt->sequence, cpu); t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION; t->sequence = ++(*sequence); t->time = ktime_to_ns(ktime_get()); record_it: /* * These two are not needed in ftrace as they are in the * generic trace_entry, filled by tracing_generic_entry_update, * but for the trace_event->bin() synthesizer benefit we do it * here too. */ t->cpu = cpu; t->pid = pid; t->sector = sector; t->bytes = bytes; t->action = what; t->device = bt->dev; t->error = error; t->pdu_len = pdu_len + cgid_len; if (cgid_len) memcpy((void *)t + sizeof(*t), &cgid, cgid_len); if (pdu_len) memcpy((void *)t + sizeof(*t) + cgid_len, pdu_data, pdu_len); if (blk_tracer) { trace_buffer_unlock_commit(blk_tr, buffer, event, trace_ctx); return; } } local_irq_restore(flags); } static void blk_trace_free(struct blk_trace *bt) { relay_close(bt->rchan); debugfs_remove(bt->dir); free_percpu(bt->sequence); free_percpu(bt->msg_data); kfree(bt); } static void get_probe_ref(void) { mutex_lock(&blk_probe_mutex); if (++blk_probes_ref == 1) blk_register_tracepoints(); mutex_unlock(&blk_probe_mutex); } static void put_probe_ref(void) { mutex_lock(&blk_probe_mutex); if (!--blk_probes_ref) blk_unregister_tracepoints(); mutex_unlock(&blk_probe_mutex); } static void blk_trace_cleanup(struct blk_trace *bt) { synchronize_rcu(); blk_trace_free(bt); put_probe_ref(); } static int __blk_trace_remove(struct request_queue *q) { struct blk_trace *bt; bt = rcu_replace_pointer(q->blk_trace, NULL, lockdep_is_held(&q->debugfs_mutex)); if (!bt) return -EINVAL; if (bt->trace_state != Blktrace_running) blk_trace_cleanup(bt); return 0; } int blk_trace_remove(struct request_queue *q) { int ret; mutex_lock(&q->debugfs_mutex); ret = __blk_trace_remove(q); mutex_unlock(&q->debugfs_mutex); return ret; } EXPORT_SYMBOL_GPL(blk_trace_remove); static ssize_t blk_dropped_read(struct file *filp, char __user *buffer, size_t count, loff_t *ppos) { struct blk_trace *bt = filp->private_data; char buf[16]; snprintf(buf, sizeof(buf), "%u\n", atomic_read(&bt->dropped)); return simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf)); } static const struct file_operations blk_dropped_fops = { .owner = THIS_MODULE, .open = simple_open, .read = blk_dropped_read, .llseek = default_llseek, }; static ssize_t blk_msg_write(struct file *filp, const char __user *buffer, size_t count, loff_t *ppos) { char *msg; struct blk_trace *bt; if (count >= BLK_TN_MAX_MSG) return -EINVAL; msg = memdup_user_nul(buffer, count); if (IS_ERR(msg)) return PTR_ERR(msg); bt = filp->private_data; __trace_note_message(bt, NULL, "%s", msg); kfree(msg); return count; } static const struct file_operations blk_msg_fops = { .owner = THIS_MODULE, .open = simple_open, .write = blk_msg_write, .llseek = noop_llseek, }; /* * Keep track of how many times we encountered a full subbuffer, to aid * the user space app in telling how many lost events there were. */ static int blk_subbuf_start_callback(struct rchan_buf *buf, void *subbuf, void *prev_subbuf, size_t prev_padding) { struct blk_trace *bt; if (!relay_buf_full(buf)) return 1; bt = buf->chan->private_data; atomic_inc(&bt->dropped); return 0; } static int blk_remove_buf_file_callback(struct dentry *dentry) { debugfs_remove(dentry); return 0; } static struct dentry *blk_create_buf_file_callback(const char *filename, struct dentry *parent, umode_t mode, struct rchan_buf *buf, int *is_global) { return debugfs_create_file(filename, mode, parent, buf, &relay_file_operations); } static const struct rchan_callbacks blk_relay_callbacks = { .subbuf_start = blk_subbuf_start_callback, .create_buf_file = blk_create_buf_file_callback, .remove_buf_file = blk_remove_buf_file_callback, }; static void blk_trace_setup_lba(struct blk_trace *bt, struct block_device *bdev) { if (bdev) { bt->start_lba = bdev->bd_start_sect; bt->end_lba = bdev->bd_start_sect + bdev_nr_sectors(bdev); } else { bt->start_lba = 0; bt->end_lba = -1ULL; } } /* * Setup everything required to start tracing */ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, struct block_device *bdev, struct blk_user_trace_setup *buts) { struct blk_trace *bt = NULL; struct dentry *dir = NULL; int ret; lockdep_assert_held(&q->debugfs_mutex); if (!buts->buf_size || !buts->buf_nr) return -EINVAL; strncpy(buts->name, name, BLKTRACE_BDEV_SIZE); buts->name[BLKTRACE_BDEV_SIZE - 1] = '\0'; /* * some device names have larger paths - convert the slashes * to underscores for this to work as expected */ strreplace(buts->name, '/', '_'); /* * bdev can be NULL, as with scsi-generic, this is a helpful as * we can be. */ if (rcu_dereference_protected(q->blk_trace, lockdep_is_held(&q->debugfs_mutex))) { pr_warn("Concurrent blktraces are not allowed on %s\n", buts->name); return -EBUSY; } bt = kzalloc(sizeof(*bt), GFP_KERNEL); if (!bt) return -ENOMEM; ret = -ENOMEM; bt->sequence = alloc_percpu(unsigned long); if (!bt->sequence) goto err; bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG, __alignof__(char)); if (!bt->msg_data) goto err; /* * When tracing the whole disk reuse the existing debugfs directory * created by the block layer on init. For partitions block devices, * and scsi-generic block devices we create a temporary new debugfs * directory that will be removed once the trace ends. */ if (bdev && !bdev_is_partition(bdev)) dir = q->debugfs_dir; else bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root); /* * As blktrace relies on debugfs for its interface the debugfs directory * is required, contrary to the usual mantra of not checking for debugfs * files or directories. */ if (IS_ERR_OR_NULL(dir)) { pr_warn("debugfs_dir not present for %s so skipping\n", buts->name); ret = -ENOENT; goto err; } bt->dev = dev; atomic_set(&bt->dropped, 0); INIT_LIST_HEAD(&bt->running_list); ret = -EIO; debugfs_create_file("dropped", 0444, dir, bt, &blk_dropped_fops); debugfs_create_file("msg", 0222, dir, bt, &blk_msg_fops); bt->rchan = relay_open("trace", dir, buts->buf_size, buts->buf_nr, &blk_relay_callbacks, bt); if (!bt->rchan) goto err; bt->act_mask = buts->act_mask; if (!bt->act_mask) bt->act_mask = (u16) -1; blk_trace_setup_lba(bt, bdev); /* overwrite with user settings */ if (buts->start_lba) bt->start_lba = buts->start_lba; if (buts->end_lba) bt->end_lba = buts->end_lba; bt->pid = buts->pid; bt->trace_state = Blktrace_setup; rcu_assign_pointer(q->blk_trace, bt); get_probe_ref(); ret = 0; err: if (ret) blk_trace_free(bt); return ret; } static int __blk_trace_setup(struct request_queue *q, char *name, dev_t dev, struct block_device *bdev, char __user *arg) { struct blk_user_trace_setup buts; int ret; ret = copy_from_user(&buts, arg, sizeof(buts)); if (ret) return -EFAULT; ret = do_blk_trace_setup(q, name, dev, bdev, &buts); if (ret) return ret; if (copy_to_user(arg, &buts, sizeof(buts))) { __blk_trace_remove(q); return -EFAULT; } return 0; } int blk_trace_setup(struct request_queue *q, char *name, dev_t dev, struct block_device *bdev, char __user *arg) { int ret; mutex_lock(&q->debugfs_mutex); ret = __blk_trace_setup(q, name, dev, bdev, arg); mutex_unlock(&q->debugfs_mutex); return ret; } EXPORT_SYMBOL_GPL(blk_trace_setup); #if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64) static int compat_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, struct block_device *bdev, char __user *arg) { struct blk_user_trace_setup buts; struct compat_blk_user_trace_setup cbuts; int ret; if (copy_from_user(&cbuts, arg, sizeof(cbuts))) return -EFAULT; buts = (struct blk_user_trace_setup) { .act_mask = cbuts.act_mask, .buf_size = cbuts.buf_size, .buf_nr = cbuts.buf_nr, .start_lba = cbuts.start_lba, .end_lba = cbuts.end_lba, .pid = cbuts.pid, }; ret = do_blk_trace_setup(q, name, dev, bdev, &buts); if (ret) return ret; if (copy_to_user(arg, &buts.name, ARRAY_SIZE(buts.name))) { __blk_trace_remove(q); return -EFAULT; } return 0; } #endif static int __blk_trace_startstop(struct request_queue *q, int start) { int ret; struct blk_trace *bt; bt = rcu_dereference_protected(q->blk_trace, lockdep_is_held(&q->debugfs_mutex)); if (bt == NULL) return -EINVAL; /* * For starting a trace, we can transition from a setup or stopped * trace. For stopping a trace, the state must be running */ ret = -EINVAL; if (start) { if (bt->trace_state == Blktrace_setup || bt->trace_state == Blktrace_stopped) { blktrace_seq++; smp_mb(); bt->trace_state = Blktrace_running; spin_lock_irq(&running_trace_lock); list_add(&bt->running_list, &running_trace_list); spin_unlock_irq(&running_trace_lock); trace_note_time(bt); ret = 0; } } else { if (bt->trace_state == Blktrace_running) { bt->trace_state = Blktrace_stopped; spin_lock_irq(&running_trace_lock); list_del_init(&bt->running_list); spin_unlock_irq(&running_trace_lock); relay_flush(bt->rchan); ret = 0; } } return ret; } int blk_trace_startstop(struct request_queue *q, int start) { int ret; mutex_lock(&q->debugfs_mutex); ret = __blk_trace_startstop(q, start); mutex_unlock(&q->debugfs_mutex); return ret; } EXPORT_SYMBOL_GPL(blk_trace_startstop); /* * When reading or writing the blktrace sysfs files, the references to the * opened sysfs or device files should prevent the underlying block device * from being removed. So no further delete protection is really needed. */ /** * blk_trace_ioctl: - handle the ioctls associated with tracing * @bdev: the block device * @cmd: the ioctl cmd * @arg: the argument data, if any * **/ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) { struct request_queue *q; int ret, start = 0; char b[BDEVNAME_SIZE]; q = bdev_get_queue(bdev); if (!q) return -ENXIO; mutex_lock(&q->debugfs_mutex); switch (cmd) { case BLKTRACESETUP: bdevname(bdev, b); ret = __blk_trace_setup(q, b, bdev->bd_dev, bdev, arg); break; #if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64) case BLKTRACESETUP32: bdevname(bdev, b); ret = compat_blk_trace_setup(q, b, bdev->bd_dev, bdev, arg); break; #endif case BLKTRACESTART: start = 1; fallthrough; case BLKTRACESTOP: ret = __blk_trace_startstop(q, start); break; case BLKTRACETEARDOWN: ret = __blk_trace_remove(q); break; default: ret = -ENOTTY; break; } mutex_unlock(&q->debugfs_mutex); return ret; } /** * blk_trace_shutdown: - stop and cleanup trace structures * @q: the request queue associated with the device * **/ void blk_trace_shutdown(struct request_queue *q) { mutex_lock(&q->debugfs_mutex); if (rcu_dereference_protected(q->blk_trace, lockdep_is_held(&q->debugfs_mutex))) { __blk_trace_startstop(q, 0); __blk_trace_remove(q); } mutex_unlock(&q->debugfs_mutex); } #ifdef CONFIG_BLK_CGROUP static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) { struct blk_trace *bt; /* We don't use the 'bt' value here except as an optimization... */ bt = rcu_dereference_protected(q->blk_trace, 1); if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) return 0; if (!bio->bi_blkg) return 0; return cgroup_id(bio_blkcg(bio)->css.cgroup); } #else static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) { return 0; } #endif static u64 blk_trace_request_get_cgid(struct request *rq) { if (!rq->bio) return 0; /* Use the first bio */ return blk_trace_bio_get_cgid(rq->q, rq->bio); } /* * blktrace probes */ /** * blk_add_trace_rq - Add a trace for a request oriented action * @rq: the source request * @error: return status to log * @nr_bytes: number of completed bytes * @what: the action * @cgid: the cgroup info * * Description: * Records an action against a request. Will log the bio offset + size. * **/ static void blk_add_trace_rq(struct request *rq, int error, unsigned int nr_bytes, u32 what, u64 cgid) { struct blk_trace *bt; rcu_read_lock(); bt = rcu_dereference(rq->q->blk_trace); if (likely(!bt)) { rcu_read_unlock(); return; } if (blk_rq_is_passthrough(rq)) what |= BLK_TC_ACT(BLK_TC_PC); else what |= BLK_TC_ACT(BLK_TC_FS); __blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq), rq->cmd_flags, what, error, 0, NULL, cgid); rcu_read_unlock(); } static void blk_add_trace_rq_insert(void *ignore, struct request *rq) { blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_INSERT, blk_trace_request_get_cgid(rq)); } static void blk_add_trace_rq_issue(void *ignore, struct request *rq) { blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_ISSUE, blk_trace_request_get_cgid(rq)); } static void blk_add_trace_rq_merge(void *ignore, struct request *rq) { blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_BACKMERGE, blk_trace_request_get_cgid(rq)); } static void blk_add_trace_rq_requeue(void *ignore, struct request *rq) { blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_REQUEUE, blk_trace_request_get_cgid(rq)); } static void blk_add_trace_rq_complete(void *ignore, struct request *rq, int error, unsigned int nr_bytes) { blk_add_trace_rq(rq, error, nr_bytes, BLK_TA_COMPLETE, blk_trace_request_get_cgid(rq)); } /** * blk_add_trace_bio - Add a trace for a bio oriented action * @q: queue the io is for * @bio: the source bio * @what: the action * @error: error, if any * * Description: * Records an action against a bio. Will log the bio offset + size. * **/ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio, u32 what, int error) { struct blk_trace *bt; rcu_read_lock(); bt = rcu_dereference(q->blk_trace); if (likely(!bt)) { rcu_read_unlock(); return; } __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, what, error, 0, NULL, blk_trace_bio_get_cgid(q, bio)); rcu_read_unlock(); } static void blk_add_trace_bio_bounce(void *ignore, struct bio *bio) { blk_add_trace_bio(bio->bi_bdev->bd_disk->queue, bio, BLK_TA_BOUNCE, 0); } static void blk_add_trace_bio_complete(void *ignore, struct request_queue *q, struct bio *bio) { blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, blk_status_to_errno(bio->bi_status)); } static void blk_add_trace_bio_backmerge(void *ignore, struct bio *bio) { blk_add_trace_bio(bio->bi_bdev->bd_disk->queue, bio, BLK_TA_BACKMERGE, 0); } static void blk_add_trace_bio_frontmerge(void *ignore, struct bio *bio) { blk_add_trace_bio(bio->bi_bdev->bd_disk->queue, bio, BLK_TA_FRONTMERGE, 0); } static void blk_add_trace_bio_queue(void *ignore, struct bio *bio) { blk_add_trace_bio(bio->bi_bdev->bd_disk->queue, bio, BLK_TA_QUEUE, 0); } static void blk_add_trace_getrq(void *ignore, struct bio *bio) { blk_add_trace_bio(bio->bi_bdev->bd_disk->queue, bio, BLK_TA_GETRQ, 0); } static void blk_add_trace_plug(void *ignore, struct request_queue *q) { struct blk_trace *bt; rcu_read_lock(); bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, 0); rcu_read_unlock(); } static void blk_add_trace_unplug(void *ignore, struct request_queue *q, unsigned int depth, bool explicit) { struct blk_trace *bt; rcu_read_lock(); bt = rcu_dereference(q->blk_trace); if (bt) { __be64 rpdu = cpu_to_be64(depth); u32 what; if (explicit) what = BLK_TA_UNPLUG_IO; else what = BLK_TA_UNPLUG_TIMER; __blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, 0); } rcu_read_unlock(); } static void blk_add_trace_split(void *ignore, struct bio *bio, unsigned int pdu) { struct request_queue *q = bio->bi_bdev->bd_disk->queue; struct blk_trace *bt; rcu_read_lock(); bt = rcu_dereference(q->blk_trace); if (bt) { __be64 rpdu = cpu_to_be64(pdu); __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, BLK_TA_SPLIT, blk_status_to_errno(bio->bi_status), sizeof(rpdu), &rpdu, blk_trace_bio_get_cgid(q, bio)); } rcu_read_unlock(); } /** * blk_add_trace_bio_remap - Add a trace for a bio-remap operation * @ignore: trace callback data parameter (not used) * @bio: the source bio * @dev: source device * @from: source sector * * Called after a bio is remapped to a different device and/or sector. **/ static void blk_add_trace_bio_remap(void *ignore, struct bio *bio, dev_t dev, sector_t from) { struct request_queue *q = bio->bi_bdev->bd_disk->queue; struct blk_trace *bt; struct blk_io_trace_remap r; rcu_read_lock(); bt = rcu_dereference(q->blk_trace); if (likely(!bt)) { rcu_read_unlock(); return; } r.device_from = cpu_to_be32(dev); r.device_to = cpu_to_be32(bio_dev(bio)); r.sector_from = cpu_to_be64(from); __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, BLK_TA_REMAP, blk_status_to_errno(bio->bi_status), sizeof(r), &r, blk_trace_bio_get_cgid(q, bio)); rcu_read_unlock(); } /** * blk_add_trace_rq_remap - Add a trace for a request-remap operation * @ignore: trace callback data parameter (not used) * @rq: the source request * @dev: target device * @from: source sector * * Description: * Device mapper remaps request to other devices. * Add a trace for that action. * **/ static void blk_add_trace_rq_remap(void *ignore, struct request *rq, dev_t dev, sector_t from) { struct blk_trace *bt; struct blk_io_trace_remap r; rcu_read_lock(); bt = rcu_dereference(rq->q->blk_trace); if (likely(!bt)) { rcu_read_unlock(); return; } r.device_from = cpu_to_be32(dev); r.device_to = cpu_to_be32(disk_devt(rq->rq_disk)); r.sector_from = cpu_to_be64(from); __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), rq_data_dir(rq), 0, BLK_TA_REMAP, 0, sizeof(r), &r, blk_trace_request_get_cgid(rq)); rcu_read_unlock(); } /** * blk_add_driver_data - Add binary message with driver-specific data * @rq: io request * @data: driver-specific data * @len: length of driver-specific data * * Description: * Some drivers might want to write driver-specific data per request. * **/ void blk_add_driver_data(struct request *rq, void *data, size_t len) { struct blk_trace *bt; rcu_read_lock(); bt = rcu_dereference(rq->q->blk_trace); if (likely(!bt)) { rcu_read_unlock(); return; } __blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0, BLK_TA_DRV_DATA, 0, len, data, blk_trace_request_get_cgid(rq)); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(blk_add_driver_data); static void blk_register_tracepoints(void) { int ret; ret = register_trace_block_rq_insert(blk_add_trace_rq_insert, NULL); WARN_ON(ret); ret = register_trace_block_rq_issue(blk_add_trace_rq_issue, NULL); WARN_ON(ret); ret = register_trace_block_rq_merge(blk_add_trace_rq_merge, NULL); WARN_ON(ret); ret = register_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL); WARN_ON(ret); ret = register_trace_block_rq_complete(blk_add_trace_rq_complete, NULL); WARN_ON(ret); ret = register_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL); WARN_ON(ret); ret = register_trace_block_bio_complete(blk_add_trace_bio_complete, NULL); WARN_ON(ret); ret = register_trace_block_bio_backmerge(blk_add_trace_bio_backmerge, NULL); WARN_ON(ret); ret = register_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge, NULL); WARN_ON(ret); ret = register_trace_block_bio_queue(blk_add_trace_bio_queue, NULL); WARN_ON(ret); ret = register_trace_block_getrq(blk_add_trace_getrq, NULL); WARN_ON(ret); ret = register_trace_block_plug(blk_add_trace_plug, NULL); WARN_ON(ret); ret = register_trace_block_unplug(blk_add_trace_unplug, NULL); WARN_ON(ret); ret = register_trace_block_split(blk_add_trace_split, NULL); WARN_ON(ret); ret = register_trace_block_bio_remap(blk_add_trace_bio_remap, NULL); WARN_ON(ret); ret = register_trace_block_rq_remap(blk_add_trace_rq_remap, NULL); WARN_ON(ret); } static void blk_unregister_tracepoints(void) { unregister_trace_block_rq_remap(blk_add_trace_rq_remap, NULL); unregister_trace_block_bio_remap(blk_add_trace_bio_remap, NULL); unregister_trace_block_split(blk_add_trace_split, NULL); unregister_trace_block_unplug(blk_add_trace_unplug, NULL); unregister_trace_block_plug(blk_add_trace_plug, NULL); unregister_trace_block_getrq(blk_add_trace_getrq, NULL); unregister_trace_block_bio_queue(blk_add_trace_bio_queue, NULL); unregister_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge, NULL); unregister_trace_block_bio_backmerge(blk_add_trace_bio_backmerge, NULL); unregister_trace_block_bio_complete(blk_add_trace_bio_complete, NULL); unregister_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL); unregister_trace_block_rq_complete(blk_add_trace_rq_complete, NULL); unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL); unregister_trace_block_rq_merge(blk_add_trace_rq_merge, NULL); unregister_trace_block_rq_issue(blk_add_trace_rq_issue, NULL); unregister_trace_block_rq_insert(blk_add_trace_rq_insert, NULL); tracepoint_synchronize_unregister(); } /* * struct blk_io_tracer formatting routines */ static void fill_rwbs(char *rwbs, const struct blk_io_trace *t) { int i = 0; int tc = t->action >> BLK_TC_SHIFT; if ((t->action & ~__BLK_TN_CGROUP) == BLK_TN_MESSAGE) { rwbs[i++] = 'N'; goto out; } if (tc & BLK_TC_FLUSH) rwbs[i++] = 'F'; if (tc & BLK_TC_DISCARD) rwbs[i++] = 'D'; else if (tc & BLK_TC_WRITE) rwbs[i++] = 'W'; else if (t->bytes) rwbs[i++] = 'R'; else rwbs[i++] = 'N'; if (tc & BLK_TC_FUA) rwbs[i++] = 'F'; if (tc & BLK_TC_AHEAD) rwbs[i++] = 'A'; if (tc & BLK_TC_SYNC) rwbs[i++] = 'S'; if (tc & BLK_TC_META) rwbs[i++] = 'M'; out: rwbs[i] = '\0'; } static inline const struct blk_io_trace *te_blk_io_trace(const struct trace_entry *ent) { return (const struct blk_io_trace *)ent; } static inline const void *pdu_start(const struct trace_entry *ent, bool has_cg) { return (void *)(te_blk_io_trace(ent) + 1) + (has_cg ? sizeof(u64) : 0); } static inline u64 t_cgid(const struct trace_entry *ent) { return *(u64 *)(te_blk_io_trace(ent) + 1); } static inline int pdu_real_len(const struct trace_entry *ent, bool has_cg) { return te_blk_io_trace(ent)->pdu_len - (has_cg ? sizeof(u64) : 0); } static inline u32 t_action(const struct trace_entry *ent) { return te_blk_io_trace(ent)->action; } static inline u32 t_bytes(const struct trace_entry *ent) { return te_blk_io_trace(ent)->bytes; } static inline u32 t_sec(const struct trace_entry *ent) { return te_blk_io_trace(ent)->bytes >> 9; } static inline unsigned long long t_sector(const struct trace_entry *ent) { return te_blk_io_trace(ent)->sector; } static inline __u16 t_error(const struct trace_entry *ent) { return te_blk_io_trace(ent)->error; } static __u64 get_pdu_int(const struct trace_entry *ent, bool has_cg) { const __be64 *val = pdu_start(ent, has_cg); return be64_to_cpu(*val); } typedef void (blk_log_action_t) (struct trace_iterator *iter, const char *act, bool has_cg); static void blk_log_action_classic(struct trace_iterator *iter, const char *act, bool has_cg) { char rwbs[RWBS_LEN]; unsigned long long ts = iter->ts; unsigned long nsec_rem = do_div(ts, NSEC_PER_SEC); unsigned secs = (unsigned long)ts; const struct blk_io_trace *t = te_blk_io_trace(iter->ent); fill_rwbs(rwbs, t); trace_seq_printf(&iter->seq, "%3d,%-3d %2d %5d.%09lu %5u %2s %3s ", MAJOR(t->device), MINOR(t->device), iter->cpu, secs, nsec_rem, iter->ent->pid, act, rwbs); } static void blk_log_action(struct trace_iterator *iter, const char *act, bool has_cg) { char rwbs[RWBS_LEN]; const struct blk_io_trace *t = te_blk_io_trace(iter->ent); fill_rwbs(rwbs, t); if (has_cg) { u64 id = t_cgid(iter->ent); if (blk_tracer_flags.val & TRACE_BLK_OPT_CGNAME) { char blkcg_name_buf[NAME_MAX + 1] = "<...>"; cgroup_path_from_kernfs_id(id, blkcg_name_buf, sizeof(blkcg_name_buf)); trace_seq_printf(&iter->seq, "%3d,%-3d %s %2s %3s ", MAJOR(t->device), MINOR(t->device), blkcg_name_buf, act, rwbs); } else { /* * The cgid portion used to be "INO,GEN". Userland * builds a FILEID_INO32_GEN fid out of them and * opens the cgroup using open_by_handle_at(2). * While 32bit ino setups are still the same, 64bit * ones now use the 64bit ino as the whole ID and * no longer use generation. * * Regardless of the content, always output * "LOW32,HIGH32" so that FILEID_INO32_GEN fid can * be mapped back to @id on both 64 and 32bit ino * setups. See __kernfs_fh_to_dentry(). */ trace_seq_printf(&iter->seq, "%3d,%-3d %llx,%-llx %2s %3s ", MAJOR(t->device), MINOR(t->device), id & U32_MAX, id >> 32, act, rwbs); } } else trace_seq_printf(&iter->seq, "%3d,%-3d %2s %3s ", MAJOR(t->device), MINOR(t->device), act, rwbs); } static void blk_log_dump_pdu(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { const unsigned char *pdu_buf; int pdu_len; int i, end; pdu_buf = pdu_start(ent, has_cg); pdu_len = pdu_real_len(ent, has_cg); if (!pdu_len) return; /* find the last zero that needs to be printed */ for (end = pdu_len - 1; end >= 0; end--) if (pdu_buf[end]) break; end++; trace_seq_putc(s, '('); for (i = 0; i < pdu_len; i++) { trace_seq_printf(s, "%s%02x", i == 0 ? "" : " ", pdu_buf[i]); /* * stop when the rest is just zeros and indicate so * with a ".." appended */ if (i == end && end != pdu_len - 1) { trace_seq_puts(s, " ..) "); return; } } trace_seq_puts(s, ") "); } static void blk_log_generic(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { char cmd[TASK_COMM_LEN]; trace_find_cmdline(ent->pid, cmd); if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) { trace_seq_printf(s, "%u ", t_bytes(ent)); blk_log_dump_pdu(s, ent, has_cg); trace_seq_printf(s, "[%s]\n", cmd); } else { if (t_sec(ent)) trace_seq_printf(s, "%llu + %u [%s]\n", t_sector(ent), t_sec(ent), cmd); else trace_seq_printf(s, "[%s]\n", cmd); } } static void blk_log_with_error(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) { blk_log_dump_pdu(s, ent, has_cg); trace_seq_printf(s, "[%d]\n", t_error(ent)); } else { if (t_sec(ent)) trace_seq_printf(s, "%llu + %u [%d]\n", t_sector(ent), t_sec(ent), t_error(ent)); else trace_seq_printf(s, "%llu [%d]\n", t_sector(ent), t_error(ent)); } } static void blk_log_remap(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { const struct blk_io_trace_remap *__r = pdu_start(ent, has_cg); trace_seq_printf(s, "%llu + %u <- (%d,%d) %llu\n", t_sector(ent), t_sec(ent), MAJOR(be32_to_cpu(__r->device_from)), MINOR(be32_to_cpu(__r->device_from)), be64_to_cpu(__r->sector_from)); } static void blk_log_plug(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { char cmd[TASK_COMM_LEN]; trace_find_cmdline(ent->pid, cmd); trace_seq_printf(s, "[%s]\n", cmd); } static void blk_log_unplug(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { char cmd[TASK_COMM_LEN]; trace_find_cmdline(ent->pid, cmd); trace_seq_printf(s, "[%s] %llu\n", cmd, get_pdu_int(ent, has_cg)); } static void blk_log_split(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { char cmd[TASK_COMM_LEN]; trace_find_cmdline(ent->pid, cmd); trace_seq_printf(s, "%llu / %llu [%s]\n", t_sector(ent), get_pdu_int(ent, has_cg), cmd); } static void blk_log_msg(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { trace_seq_putmem(s, pdu_start(ent, has_cg), pdu_real_len(ent, has_cg)); trace_seq_putc(s, '\n'); } /* * struct tracer operations */ static void blk_tracer_print_header(struct seq_file *m) { if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC)) return; seq_puts(m, "# DEV CPU TIMESTAMP PID ACT FLG\n" "# | | | | | |\n"); } static void blk_tracer_start(struct trace_array *tr) { blk_tracer_enabled = true; } static int blk_tracer_init(struct trace_array *tr) { blk_tr = tr; blk_tracer_start(tr); return 0; } static void blk_tracer_stop(struct trace_array *tr) { blk_tracer_enabled = false; } static void blk_tracer_reset(struct trace_array *tr) { blk_tracer_stop(tr); } static const struct { const char *act[2]; void (*print)(struct trace_seq *s, const struct trace_entry *ent, bool has_cg); } what2act[] = { [__BLK_TA_QUEUE] = {{ "Q", "queue" }, blk_log_generic }, [__BLK_TA_BACKMERGE] = {{ "M", "backmerge" }, blk_log_generic }, [__BLK_TA_FRONTMERGE] = {{ "F", "frontmerge" }, blk_log_generic }, [__BLK_TA_GETRQ] = {{ "G", "getrq" }, blk_log_generic }, [__BLK_TA_SLEEPRQ] = {{ "S", "sleeprq" }, blk_log_generic }, [__BLK_TA_REQUEUE] = {{ "R", "requeue" }, blk_log_with_error }, [__BLK_TA_ISSUE] = {{ "D", "issue" }, blk_log_generic }, [__BLK_TA_COMPLETE] = {{ "C", "complete" }, blk_log_with_error }, [__BLK_TA_PLUG] = {{ "P", "plug" }, blk_log_plug }, [__BLK_TA_UNPLUG_IO] = {{ "U", "unplug_io" }, blk_log_unplug }, [__BLK_TA_UNPLUG_TIMER] = {{ "UT", "unplug_timer" }, blk_log_unplug }, [__BLK_TA_INSERT] = {{ "I", "insert" }, blk_log_generic }, [__BLK_TA_SPLIT] = {{ "X", "split" }, blk_log_split }, [__BLK_TA_BOUNCE] = {{ "B", "bounce" }, blk_log_generic }, [__BLK_TA_REMAP] = {{ "A", "remap" }, blk_log_remap }, }; static enum print_line_t print_one_line(struct trace_iterator *iter, bool classic) { struct trace_array *tr = iter->tr; struct trace_seq *s = &iter->seq; const struct blk_io_trace *t; u16 what; bool long_act; blk_log_action_t *log_action; bool has_cg; t = te_blk_io_trace(iter->ent); what = (t->action & ((1 << BLK_TC_SHIFT) - 1)) & ~__BLK_TA_CGROUP; long_act = !!(tr->trace_flags & TRACE_ITER_VERBOSE); log_action = classic ? &blk_log_action_classic : &blk_log_action; has_cg = t->action & __BLK_TA_CGROUP; if ((t->action & ~__BLK_TN_CGROUP) == BLK_TN_MESSAGE) { log_action(iter, long_act ? "message" : "m", has_cg); blk_log_msg(s, iter->ent, has_cg); return trace_handle_return(s); } if (unlikely(what == 0 || what >= ARRAY_SIZE(what2act))) trace_seq_printf(s, "Unknown action %x\n", what); else { log_action(iter, what2act[what].act[long_act], has_cg); what2act[what].print(s, iter->ent, has_cg); } return trace_handle_return(s); } static enum print_line_t blk_trace_event_print(struct trace_iterator *iter, int flags, struct trace_event *event) { return print_one_line(iter, false); } static void blk_trace_synthesize_old_trace(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; struct blk_io_trace *t = (struct blk_io_trace *)iter->ent; const int offset = offsetof(struct blk_io_trace, sector); struct blk_io_trace old = { .magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION, .time = iter->ts, }; trace_seq_putmem(s, &old, offset); trace_seq_putmem(s, &t->sector, sizeof(old) - offset + t->pdu_len); } static enum print_line_t blk_trace_event_print_binary(struct trace_iterator *iter, int flags, struct trace_event *event) { blk_trace_synthesize_old_trace(iter); return trace_handle_return(&iter->seq); } static enum print_line_t blk_tracer_print_line(struct trace_iterator *iter) { if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC)) return TRACE_TYPE_UNHANDLED; return print_one_line(iter, true); } static int blk_tracer_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { /* don't output context-info for blk_classic output */ if (bit == TRACE_BLK_OPT_CLASSIC) { if (set) tr->trace_flags &= ~TRACE_ITER_CONTEXT_INFO; else tr->trace_flags |= TRACE_ITER_CONTEXT_INFO; } return 0; } static struct tracer blk_tracer __read_mostly = { .name = "blk", .init = blk_tracer_init, .reset = blk_tracer_reset, .start = blk_tracer_start, .stop = blk_tracer_stop, .print_header = blk_tracer_print_header, .print_line = blk_tracer_print_line, .flags = &blk_tracer_flags, .set_flag = blk_tracer_set_flag, }; static struct trace_event_functions trace_blk_event_funcs = { .trace = blk_trace_event_print, .binary = blk_trace_event_print_binary, }; static struct trace_event trace_blk_event = { .type = TRACE_BLK, .funcs = &trace_blk_event_funcs, }; static int __init init_blk_tracer(void) { if (!register_trace_event(&trace_blk_event)) { pr_warn("Warning: could not register block events\n"); return 1; } if (register_tracer(&blk_tracer) != 0) { pr_warn("Warning: could not register the block tracer\n"); unregister_trace_event(&trace_blk_event); return 1; } return 0; } device_initcall(init_blk_tracer); static int blk_trace_remove_queue(struct request_queue *q) { struct blk_trace *bt; bt = rcu_replace_pointer(q->blk_trace, NULL, lockdep_is_held(&q->debugfs_mutex)); if (bt == NULL) return -EINVAL; put_probe_ref(); synchronize_rcu(); blk_trace_free(bt); return 0; } /* * Setup everything required to start tracing */ static int blk_trace_setup_queue(struct request_queue *q, struct block_device *bdev) { struct blk_trace *bt = NULL; int ret = -ENOMEM; bt = kzalloc(sizeof(*bt), GFP_KERNEL); if (!bt) return -ENOMEM; bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG, __alignof__(char)); if (!bt->msg_data) goto free_bt; bt->dev = bdev->bd_dev; bt->act_mask = (u16)-1; blk_trace_setup_lba(bt, bdev); rcu_assign_pointer(q->blk_trace, bt); get_probe_ref(); return 0; free_bt: blk_trace_free(bt); return ret; } /* * sysfs interface to enable and configure tracing */ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, struct device_attribute *attr, char *buf); static ssize_t sysfs_blk_trace_attr_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); #define BLK_TRACE_DEVICE_ATTR(_name) \ DEVICE_ATTR(_name, S_IRUGO | S_IWUSR, \ sysfs_blk_trace_attr_show, \ sysfs_blk_trace_attr_store) static BLK_TRACE_DEVICE_ATTR(enable); static BLK_TRACE_DEVICE_ATTR(act_mask); static BLK_TRACE_DEVICE_ATTR(pid); static BLK_TRACE_DEVICE_ATTR(start_lba); static BLK_TRACE_DEVICE_ATTR(end_lba); static struct attribute *blk_trace_attrs[] = { &dev_attr_enable.attr, &dev_attr_act_mask.attr, &dev_attr_pid.attr, &dev_attr_start_lba.attr, &dev_attr_end_lba.attr, NULL }; struct attribute_group blk_trace_attr_group = { .name = "trace", .attrs = blk_trace_attrs, }; static const struct { int mask; const char *str; } mask_maps[] = { { BLK_TC_READ, "read" }, { BLK_TC_WRITE, "write" }, { BLK_TC_FLUSH, "flush" }, { BLK_TC_SYNC, "sync" }, { BLK_TC_QUEUE, "queue" }, { BLK_TC_REQUEUE, "requeue" }, { BLK_TC_ISSUE, "issue" }, { BLK_TC_COMPLETE, "complete" }, { BLK_TC_FS, "fs" }, { BLK_TC_PC, "pc" }, { BLK_TC_NOTIFY, "notify" }, { BLK_TC_AHEAD, "ahead" }, { BLK_TC_META, "meta" }, { BLK_TC_DISCARD, "discard" }, { BLK_TC_DRV_DATA, "drv_data" }, { BLK_TC_FUA, "fua" }, }; static int blk_trace_str2mask(const char *str) { int i; int mask = 0; char *buf, *s, *token; buf = kstrdup(str, GFP_KERNEL); if (buf == NULL) return -ENOMEM; s = strstrip(buf); while (1) { token = strsep(&s, ","); if (token == NULL) break; if (*token == '\0') continue; for (i = 0; i < ARRAY_SIZE(mask_maps); i++) { if (strcasecmp(token, mask_maps[i].str) == 0) { mask |= mask_maps[i].mask; break; } } if (i == ARRAY_SIZE(mask_maps)) { mask = -EINVAL; break; } } kfree(buf); return mask; } static ssize_t blk_trace_mask2str(char *buf, int mask) { int i; char *p = buf; for (i = 0; i < ARRAY_SIZE(mask_maps); i++) { if (mask & mask_maps[i].mask) { p += sprintf(p, "%s%s", (p == buf) ? "" : ",", mask_maps[i].str); } } *p++ = '\n'; return p - buf; } static ssize_t sysfs_blk_trace_attr_show(struct device *dev, struct device_attribute *attr, char *buf) { struct block_device *bdev = dev_to_bdev(dev); struct request_queue *q = bdev_get_queue(bdev); struct blk_trace *bt; ssize_t ret = -ENXIO; mutex_lock(&q->debugfs_mutex); bt = rcu_dereference_protected(q->blk_trace, lockdep_is_held(&q->debugfs_mutex)); if (attr == &dev_attr_enable) { ret = sprintf(buf, "%u\n", !!bt); goto out_unlock_bdev; } if (bt == NULL) ret = sprintf(buf, "disabled\n"); else if (attr == &dev_attr_act_mask) ret = blk_trace_mask2str(buf, bt->act_mask); else if (attr == &dev_attr_pid) ret = sprintf(buf, "%u\n", bt->pid); else if (attr == &dev_attr_start_lba) ret = sprintf(buf, "%llu\n", bt->start_lba); else if (attr == &dev_attr_end_lba) ret = sprintf(buf, "%llu\n", bt->end_lba); out_unlock_bdev: mutex_unlock(&q->debugfs_mutex); return ret; } static ssize_t sysfs_blk_trace_attr_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct block_device *bdev = dev_to_bdev(dev); struct request_queue *q = bdev_get_queue(bdev); struct blk_trace *bt; u64 value; ssize_t ret = -EINVAL; if (count == 0) goto out; if (attr == &dev_attr_act_mask) { if (kstrtoull(buf, 0, &value)) { /* Assume it is a list of trace category names */ ret = blk_trace_str2mask(buf); if (ret < 0) goto out; value = ret; } } else { if (kstrtoull(buf, 0, &value)) goto out; } mutex_lock(&q->debugfs_mutex); bt = rcu_dereference_protected(q->blk_trace, lockdep_is_held(&q->debugfs_mutex)); if (attr == &dev_attr_enable) { if (!!value == !!bt) { ret = 0; goto out_unlock_bdev; } if (value) ret = blk_trace_setup_queue(q, bdev); else ret = blk_trace_remove_queue(q); goto out_unlock_bdev; } ret = 0; if (bt == NULL) { ret = blk_trace_setup_queue(q, bdev); bt = rcu_dereference_protected(q->blk_trace, lockdep_is_held(&q->debugfs_mutex)); } if (ret == 0) { if (attr == &dev_attr_act_mask) bt->act_mask = value; else if (attr == &dev_attr_pid) bt->pid = value; else if (attr == &dev_attr_start_lba) bt->start_lba = value; else if (attr == &dev_attr_end_lba) bt->end_lba = value; } out_unlock_bdev: mutex_unlock(&q->debugfs_mutex); out: return ret ? ret : count; } int blk_trace_init_sysfs(struct device *dev) { return sysfs_create_group(&dev->kobj, &blk_trace_attr_group); } void blk_trace_remove_sysfs(struct device *dev) { sysfs_remove_group(&dev->kobj, &blk_trace_attr_group); } #endif /* CONFIG_BLK_DEV_IO_TRACE */ #ifdef CONFIG_EVENT_TRACING /** * blk_fill_rwbs - Fill the buffer rwbs by mapping op to character string. * @rwbs: buffer to be filled * @op: REQ_OP_XXX for the tracepoint * * Description: * Maps the REQ_OP_XXX to character and fills the buffer provided by the * caller with resulting string. * **/ void blk_fill_rwbs(char *rwbs, unsigned int op) { int i = 0; if (op & REQ_PREFLUSH) rwbs[i++] = 'F'; switch (op & REQ_OP_MASK) { case REQ_OP_WRITE: case REQ_OP_WRITE_SAME: rwbs[i++] = 'W'; break; case REQ_OP_DISCARD: rwbs[i++] = 'D'; break; case REQ_OP_SECURE_ERASE: rwbs[i++] = 'D'; rwbs[i++] = 'E'; break; case REQ_OP_FLUSH: rwbs[i++] = 'F'; break; case REQ_OP_READ: rwbs[i++] = 'R'; break; default: rwbs[i++] = 'N'; } if (op & REQ_FUA) rwbs[i++] = 'F'; if (op & REQ_RAHEAD) rwbs[i++] = 'A'; if (op & REQ_SYNC) rwbs[i++] = 'S'; if (op & REQ_META) rwbs[i++] = 'M'; rwbs[i] = '\0'; } EXPORT_SYMBOL_GPL(blk_fill_rwbs); #endif /* CONFIG_EVENT_TRACING */
61 61 188 // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/nfs/inode.c * * Copyright (C) 1992 Rick Sladkey * * nfs inode and superblock handling functions * * Modularised by Alan Cox <alan@lxorguk.ukuu.org.uk>, while hacking some * experimental NFS changes. Modularisation taken straight from SYS5 fs. * * Change to nfs_read_super() to permit NFS mounts to multi-homed hosts. * J.S.Peatfield@damtp.cam.ac.uk * */ #include <linux/module.h> #include <linux/init.h> #include <linux/sched/signal.h> #include <linux/time.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/stat.h> #include <linux/errno.h> #include <linux/unistd.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/stats.h> #include <linux/sunrpc/metrics.h> #include <linux/nfs_fs.h> #include <linux/nfs_mount.h> #include <linux/nfs4_mount.h> #include <linux/lockd/bind.h> #include <linux/seq_file.h> #include <linux/mount.h> #include <linux/vfs.h> #include <linux/inet.h> #include <linux/nfs_xdr.h> #include <linux/slab.h> #include <linux/compat.h> #include <linux/freezer.h> #include <linux/uaccess.h> #include <linux/iversion.h> #include "nfs4_fs.h" #include "callback.h" #include "delegation.h" #include "iostat.h" #include "internal.h" #include "fscache.h" #include "pnfs.h" #include "nfs.h" #include "netns.h" #include "sysfs.h" #include "nfstrace.h" #define NFSDBG_FACILITY NFSDBG_VFS #define NFS_64_BIT_INODE_NUMBERS_ENABLED 1 /* Default is to see 64-bit inode numbers */ static bool enable_ino64 = NFS_64_BIT_INODE_NUMBERS_ENABLED; static int nfs_update_inode(struct inode *, struct nfs_fattr *); static struct kmem_cache * nfs_inode_cachep; static inline unsigned long nfs_fattr_to_ino_t(struct nfs_fattr *fattr) { return nfs_fileid_to_ino_t(fattr->fileid); } static int nfs_wait_killable(int mode) { freezable_schedule_unsafe(); if (signal_pending_state(mode, current)) return -ERESTARTSYS; return 0; } int nfs_wait_bit_killable(struct wait_bit_key *key, int mode) { return nfs_wait_killable(mode); } EXPORT_SYMBOL_GPL(nfs_wait_bit_killable); /** * nfs_compat_user_ino64 - returns the user-visible inode number * @fileid: 64-bit fileid * * This function returns a 32-bit inode number if the boot parameter * nfs.enable_ino64 is zero. */ u64 nfs_compat_user_ino64(u64 fileid) { #ifdef CONFIG_COMPAT compat_ulong_t ino; #else unsigned long ino; #endif if (enable_ino64) return fileid; ino = fileid; if (sizeof(ino) < sizeof(fileid)) ino ^= fileid >> (sizeof(fileid)-sizeof(ino)) * 8; return ino; } int nfs_drop_inode(struct inode *inode) { return NFS_STALE(inode) || generic_drop_inode(inode); } EXPORT_SYMBOL_GPL(nfs_drop_inode); void nfs_clear_inode(struct inode *inode) { /* * The following should never happen... */ WARN_ON_ONCE(nfs_have_writebacks(inode)); WARN_ON_ONCE(!list_empty(&NFS_I(inode)->open_files)); nfs_zap_acl_cache(inode); nfs_access_zap_cache(inode); nfs_fscache_clear_inode(inode); } EXPORT_SYMBOL_GPL(nfs_clear_inode); void nfs_evict_inode(struct inode *inode) { truncate_inode_pages_final(&inode->i_data); clear_inode(inode); nfs_clear_inode(inode); } int nfs_sync_inode(struct inode *inode) { inode_dio_wait(inode); return nfs_wb_all(inode); } EXPORT_SYMBOL_GPL(nfs_sync_inode); /** * nfs_sync_mapping - helper to flush all mmapped dirty data to disk * @mapping: pointer to struct address_space */ int nfs_sync_mapping(struct address_space *mapping) { int ret = 0; if (mapping->nrpages != 0) { unmap_mapping_range(mapping, 0, 0, 0); ret = nfs_wb_all(mapping->host); } return ret; } static int nfs_attribute_timeout(struct inode *inode) { struct nfs_inode *nfsi = NFS_I(inode); return !time_in_range_open(jiffies, nfsi->read_cache_jiffies, nfsi->read_cache_jiffies + nfsi->attrtimeo); } static bool nfs_check_cache_flags_invalid(struct inode *inode, unsigned long flags) { unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity); return (cache_validity & flags) != 0; } bool nfs_check_cache_invalid(struct inode *inode, unsigned long flags) { if (nfs_check_cache_flags_invalid(inode, flags)) return true; return nfs_attribute_cache_expired(inode); } EXPORT_SYMBOL_GPL(nfs_check_cache_invalid); #ifdef CONFIG_NFS_V4_2 static bool nfs_has_xattr_cache(const struct nfs_inode *nfsi) { return nfsi->xattr_cache != NULL; } #else static bool nfs_has_xattr_cache(const struct nfs_inode *nfsi) { return false; } #endif void nfs_set_cache_invalid(struct inode *inode, unsigned long flags) { struct nfs_inode *nfsi = NFS_I(inode); bool have_delegation = NFS_PROTO(inode)->have_delegation(inode, FMODE_READ); if (have_delegation) { if (!(flags & NFS_INO_REVAL_FORCED)) flags &= ~(NFS_INO_INVALID_MODE | NFS_INO_INVALID_OTHER | NFS_INO_INVALID_XATTR); flags &= ~(NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE); } else if (flags & NFS_INO_REVAL_PAGECACHE) flags |= NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE; if (!nfs_has_xattr_cache(nfsi)) flags &= ~NFS_INO_INVALID_XATTR; if (flags & NFS_INO_INVALID_DATA) nfs_fscache_invalidate(inode); if (inode->i_mapping->nrpages == 0) flags &= ~(NFS_INO_INVALID_DATA|NFS_INO_DATA_INVAL_DEFER); flags &= ~(NFS_INO_REVAL_PAGECACHE | NFS_INO_REVAL_FORCED); nfsi->cache_validity |= flags; } EXPORT_SYMBOL_GPL(nfs_set_cache_invalid); /* * Invalidate the local caches */ static void nfs_zap_caches_locked(struct inode *inode) { struct nfs_inode *nfsi = NFS_I(inode); int mode = inode->i_mode; nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE); nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); nfsi->attrtimeo_timestamp = jiffies; if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) { nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR | NFS_INO_INVALID_DATA | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_INVALID_XATTR | NFS_INO_REVAL_PAGECACHE); } else nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_INVALID_XATTR | NFS_INO_REVAL_PAGECACHE); nfs_zap_label_cache_locked(nfsi); } void nfs_zap_caches(struct inode *inode) { spin_lock(&inode->i_lock); nfs_zap_caches_locked(inode); spin_unlock(&inode->i_lock); } void nfs_zap_mapping(struct inode *inode, struct address_space *mapping) { if (mapping->nrpages != 0) { spin_lock(&inode->i_lock); nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA); spin_unlock(&inode->i_lock); } } void nfs_zap_acl_cache(struct inode *inode) { void (*clear_acl_cache)(struct inode *); clear_acl_cache = NFS_PROTO(inode)->clear_acl_cache; if (clear_acl_cache != NULL) clear_acl_cache(inode); spin_lock(&inode->i_lock); NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_ACL; spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_zap_acl_cache); void nfs_invalidate_atime(struct inode *inode) { spin_lock(&inode->i_lock); nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_invalidate_atime); /* * Invalidate, but do not unhash, the inode. * NB: must be called with inode->i_lock held! */ static void nfs_set_inode_stale_locked(struct inode *inode) { set_bit(NFS_INO_STALE, &NFS_I(inode)->flags); nfs_zap_caches_locked(inode); trace_nfs_set_inode_stale(inode); } void nfs_set_inode_stale(struct inode *inode) { spin_lock(&inode->i_lock); nfs_set_inode_stale_locked(inode); spin_unlock(&inode->i_lock); } struct nfs_find_desc { struct nfs_fh *fh; struct nfs_fattr *fattr; }; /* * In NFSv3 we can have 64bit inode numbers. In order to support * this, and re-exported directories (also seen in NFSv2) * we are forced to allow 2 different inodes to have the same * i_ino. */ static int nfs_find_actor(struct inode *inode, void *opaque) { struct nfs_find_desc *desc = (struct nfs_find_desc *)opaque; struct nfs_fh *fh = desc->fh; struct nfs_fattr *fattr = desc->fattr; if (NFS_FILEID(inode) != fattr->fileid) return 0; if (inode_wrong_type(inode, fattr->mode)) return 0; if (nfs_compare_fh(NFS_FH(inode), fh)) return 0; if (is_bad_inode(inode) || NFS_STALE(inode)) return 0; return 1; } static int nfs_init_locked(struct inode *inode, void *opaque) { struct nfs_find_desc *desc = (struct nfs_find_desc *)opaque; struct nfs_fattr *fattr = desc->fattr; set_nfs_fileid(inode, fattr->fileid); inode->i_mode = fattr->mode; nfs_copy_fh(NFS_FH(inode), desc->fh); return 0; } #ifdef CONFIG_NFS_V4_SECURITY_LABEL static void nfs_clear_label_invalid(struct inode *inode) { spin_lock(&inode->i_lock); NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_LABEL; spin_unlock(&inode->i_lock); } void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, struct nfs4_label *label) { int error; if (label == NULL) return; if ((fattr->valid & NFS_ATTR_FATTR_V4_SECURITY_LABEL) && inode->i_security) { error = security_inode_notifysecctx(inode, label->label, label->len); if (error) printk(KERN_ERR "%s() %s %d " "security_inode_notifysecctx() %d\n", __func__, (char *)label->label, label->len, error); nfs_clear_label_invalid(inode); } } struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { struct nfs4_label *label = NULL; int minor_version = server->nfs_client->cl_minorversion; if (minor_version < 2) return label; if (!(server->caps & NFS_CAP_SECURITY_LABEL)) return label; label = kzalloc(sizeof(struct nfs4_label), flags); if (label == NULL) return ERR_PTR(-ENOMEM); label->label = kzalloc(NFS4_MAXLABELLEN, flags); if (label->label == NULL) { kfree(label); return ERR_PTR(-ENOMEM); } label->len = NFS4_MAXLABELLEN; return label; } EXPORT_SYMBOL_GPL(nfs4_label_alloc); #else void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, struct nfs4_label *label) { } #endif EXPORT_SYMBOL_GPL(nfs_setsecurity); /* Search for inode identified by fh, fileid and i_mode in inode cache. */ struct inode * nfs_ilookup(struct super_block *sb, struct nfs_fattr *fattr, struct nfs_fh *fh) { struct nfs_find_desc desc = { .fh = fh, .fattr = fattr, }; struct inode *inode; unsigned long hash; if (!(fattr->valid & NFS_ATTR_FATTR_FILEID) || !(fattr->valid & NFS_ATTR_FATTR_TYPE)) return NULL; hash = nfs_fattr_to_ino_t(fattr); inode = ilookup5(sb, hash, nfs_find_actor, &desc); dprintk("%s: returning %p\n", __func__, inode); return inode; } /* * This is our front-end to iget that looks up inodes by file handle * instead of inode number. */ struct inode * nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, struct nfs4_label *label) { struct nfs_find_desc desc = { .fh = fh, .fattr = fattr }; struct inode *inode = ERR_PTR(-ENOENT); u64 fattr_supported = NFS_SB(sb)->fattr_valid; unsigned long hash; nfs_attr_check_mountpoint(sb, fattr); if (nfs_attr_use_mounted_on_fileid(fattr)) fattr->fileid = fattr->mounted_on_fileid; else if ((fattr->valid & NFS_ATTR_FATTR_FILEID) == 0) goto out_no_inode; if ((fattr->valid & NFS_ATTR_FATTR_TYPE) == 0) goto out_no_inode; hash = nfs_fattr_to_ino_t(fattr); inode = iget5_locked(sb, hash, nfs_find_actor, nfs_init_locked, &desc); if (inode == NULL) { inode = ERR_PTR(-ENOMEM); goto out_no_inode; } if (inode->i_state & I_NEW) { struct nfs_inode *nfsi = NFS_I(inode); unsigned long now = jiffies; /* We set i_ino for the few things that still rely on it, * such as stat(2) */ inode->i_ino = hash; /* We can't support update_atime(), since the server will reset it */ inode->i_flags |= S_NOATIME|S_NOCMTIME; inode->i_mode = fattr->mode; nfsi->cache_validity = 0; if ((fattr->valid & NFS_ATTR_FATTR_MODE) == 0 && (fattr_supported & NFS_ATTR_FATTR_MODE)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_MODE); /* Why so? Because we want revalidate for devices/FIFOs, and * that's precisely what we have in nfs_file_inode_operations. */ inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->file_inode_ops; if (S_ISREG(inode->i_mode)) { inode->i_fop = NFS_SB(sb)->nfs_client->rpc_ops->file_ops; inode->i_data.a_ops = &nfs_file_aops; } else if (S_ISDIR(inode->i_mode)) { inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops; inode->i_fop = &nfs_dir_operations; inode->i_data.a_ops = &nfs_dir_aops; /* Deal with crossing mountpoints */ if (fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT || fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) { if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) inode->i_op = &nfs_referral_inode_operations; else inode->i_op = &nfs_mountpoint_inode_operations; inode->i_fop = NULL; inode->i_flags |= S_AUTOMOUNT; } } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &nfs_symlink_inode_operations; inode_nohighmem(inode); } else init_special_inode(inode, inode->i_mode, fattr->rdev); memset(&inode->i_atime, 0, sizeof(inode->i_atime)); memset(&inode->i_mtime, 0, sizeof(inode->i_mtime)); memset(&inode->i_ctime, 0, sizeof(inode->i_ctime)); inode_set_iversion_raw(inode, 0); inode->i_size = 0; clear_nlink(inode); inode->i_uid = make_kuid(&init_user_ns, -2); inode->i_gid = make_kgid(&init_user_ns, -2); inode->i_blocks = 0; memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf)); nfsi->write_io = 0; nfsi->read_io = 0; nfsi->read_cache_jiffies = fattr->time_start; nfsi->attr_gencount = fattr->gencount; if (fattr->valid & NFS_ATTR_FATTR_ATIME) inode->i_atime = fattr->atime; else if (fattr_supported & NFS_ATTR_FATTR_ATIME) nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME); if (fattr->valid & NFS_ATTR_FATTR_MTIME) inode->i_mtime = fattr->mtime; else if (fattr_supported & NFS_ATTR_FATTR_MTIME) nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME); if (fattr->valid & NFS_ATTR_FATTR_CTIME) inode->i_ctime = fattr->ctime; else if (fattr_supported & NFS_ATTR_FATTR_CTIME) nfs_set_cache_invalid(inode, NFS_INO_INVALID_CTIME); if (fattr->valid & NFS_ATTR_FATTR_CHANGE) inode_set_iversion_raw(inode, fattr->change_attr); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE); if (fattr->valid & NFS_ATTR_FATTR_SIZE) inode->i_size = nfs_size_to_loff_t(fattr->size); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_SIZE); if (fattr->valid & NFS_ATTR_FATTR_NLINK) set_nlink(inode, fattr->nlink); else if (fattr_supported & NFS_ATTR_FATTR_NLINK) nfs_set_cache_invalid(inode, NFS_INO_INVALID_NLINK); if (fattr->valid & NFS_ATTR_FATTR_OWNER) inode->i_uid = fattr->uid; else if (fattr_supported & NFS_ATTR_FATTR_OWNER) nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER); if (fattr->valid & NFS_ATTR_FATTR_GROUP) inode->i_gid = fattr->gid; else if (fattr_supported & NFS_ATTR_FATTR_GROUP) nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER); if (nfs_server_capable(inode, NFS_CAP_XATTR)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_XATTR); if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) inode->i_blocks = fattr->du.nfs2.blocks; else if (fattr_supported & NFS_ATTR_FATTR_BLOCKS_USED && fattr->size != 0) nfs_set_cache_invalid(inode, NFS_INO_INVALID_BLOCKS); if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { /* * report the blocks in 512byte units */ inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used); } else if (fattr_supported & NFS_ATTR_FATTR_SPACE_USED && fattr->size != 0) nfs_set_cache_invalid(inode, NFS_INO_INVALID_BLOCKS); nfs_setsecurity(inode, fattr, label); nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); nfsi->attrtimeo_timestamp = now; nfsi->access_cache = RB_ROOT; nfs_fscache_init_inode(inode); unlock_new_inode(inode); } else { int err = nfs_refresh_inode(inode, fattr); if (err < 0) { iput(inode); inode = ERR_PTR(err); goto out_no_inode; } } dprintk("NFS: nfs_fhget(%s/%Lu fh_crc=0x%08x ct=%d)\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode), nfs_display_fhandle_hash(fh), atomic_read(&inode->i_count)); out: return inode; out_no_inode: dprintk("nfs_fhget: iget failed with error %ld\n", PTR_ERR(inode)); goto out; } EXPORT_SYMBOL_GPL(nfs_fhget); #define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET|ATTR_FILE|ATTR_OPEN) int nfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); struct nfs_fattr *fattr; int error = 0; nfs_inc_stats(inode, NFSIOS_VFSSETATTR); /* skip mode change if it's just for clearing setuid/setgid */ if (attr->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) attr->ia_valid &= ~ATTR_MODE; if (attr->ia_valid & ATTR_SIZE) { BUG_ON(!S_ISREG(inode->i_mode)); error = inode_newsize_ok(inode, attr->ia_size); if (error) return error; if (attr->ia_size == i_size_read(inode)) attr->ia_valid &= ~ATTR_SIZE; } /* Optimization: if the end result is no change, don't RPC */ if (((attr->ia_valid & NFS_VALID_ATTRS) & ~(ATTR_FILE|ATTR_OPEN)) == 0) return 0; trace_nfs_setattr_enter(inode); /* Write all dirty data */ if (S_ISREG(inode->i_mode)) nfs_sync_inode(inode); fattr = nfs_alloc_fattr(); if (fattr == NULL) { error = -ENOMEM; goto out; } error = NFS_PROTO(inode)->setattr(dentry, fattr, attr); if (error == 0) error = nfs_refresh_inode(inode, fattr); nfs_free_fattr(fattr); out: trace_nfs_setattr_exit(inode, error); return error; } EXPORT_SYMBOL_GPL(nfs_setattr); /** * nfs_vmtruncate - unmap mappings "freed" by truncate() syscall * @inode: inode of the file used * @offset: file offset to start truncating * * This is a copy of the common vmtruncate, but with the locking * corrected to take into account the fact that NFS requires * inode->i_size to be updated under the inode->i_lock. * Note: must be called with inode->i_lock held! */ static int nfs_vmtruncate(struct inode * inode, loff_t offset) { int err; err = inode_newsize_ok(inode, offset); if (err) goto out; i_size_write(inode, offset); /* Optimisation */ if (offset == 0) NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_DATA | NFS_INO_DATA_INVAL_DEFER); NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_SIZE; spin_unlock(&inode->i_lock); truncate_pagecache(inode, offset); spin_lock(&inode->i_lock); out: return err; } /** * nfs_setattr_update_inode - Update inode metadata after a setattr call. * @inode: pointer to struct inode * @attr: pointer to struct iattr * @fattr: pointer to struct nfs_fattr * * Note: we do this in the *proc.c in order to ensure that * it works for things like exclusive creates too. */ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, struct nfs_fattr *fattr) { /* Barrier: bump the attribute generation count. */ nfs_fattr_set_barrier(fattr); spin_lock(&inode->i_lock); NFS_I(inode)->attr_gencount = fattr->gencount; if ((attr->ia_valid & ATTR_SIZE) != 0) { nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME | NFS_INO_INVALID_BLOCKS); nfs_inc_stats(inode, NFSIOS_SETATTRTRUNC); nfs_vmtruncate(inode, attr->ia_size); } if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0) { NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_CTIME; if ((attr->ia_valid & ATTR_KILL_SUID) != 0 && inode->i_mode & S_ISUID) inode->i_mode &= ~S_ISUID; if ((attr->ia_valid & ATTR_KILL_SGID) != 0 && (inode->i_mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) inode->i_mode &= ~S_ISGID; if ((attr->ia_valid & ATTR_MODE) != 0) { int mode = attr->ia_mode & S_IALLUGO; mode |= inode->i_mode & ~S_IALLUGO; inode->i_mode = mode; } if ((attr->ia_valid & ATTR_UID) != 0) inode->i_uid = attr->ia_uid; if ((attr->ia_valid & ATTR_GID) != 0) inode->i_gid = attr->ia_gid; if (fattr->valid & NFS_ATTR_FATTR_CTIME) inode->i_ctime = fattr->ctime; else nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME); nfs_set_cache_invalid(inode, NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL); } if (attr->ia_valid & (ATTR_ATIME_SET|ATTR_ATIME)) { NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_ATIME | NFS_INO_INVALID_CTIME); if (fattr->valid & NFS_ATTR_FATTR_ATIME) inode->i_atime = fattr->atime; else if (attr->ia_valid & ATTR_ATIME_SET) inode->i_atime = attr->ia_atime; else nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME); if (fattr->valid & NFS_ATTR_FATTR_CTIME) inode->i_ctime = fattr->ctime; else nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME); } if (attr->ia_valid & (ATTR_MTIME_SET|ATTR_MTIME)) { NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_MTIME | NFS_INO_INVALID_CTIME); if (fattr->valid & NFS_ATTR_FATTR_MTIME) inode->i_mtime = fattr->mtime; else if (attr->ia_valid & ATTR_MTIME_SET) inode->i_mtime = attr->ia_mtime; else nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME); if (fattr->valid & NFS_ATTR_FATTR_CTIME) inode->i_ctime = fattr->ctime; else nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME); } if (fattr->valid) nfs_update_inode(inode, fattr); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_setattr_update_inode); static void nfs_readdirplus_parent_cache_miss(struct dentry *dentry) { struct dentry *parent; if (!nfs_server_capable(d_inode(dentry), NFS_CAP_READDIRPLUS)) return; parent = dget_parent(dentry); nfs_force_use_readdirplus(d_inode(parent)); dput(parent); } static void nfs_readdirplus_parent_cache_hit(struct dentry *dentry) { struct dentry *parent; if (!nfs_server_capable(d_inode(dentry), NFS_CAP_READDIRPLUS)) return; parent = dget_parent(dentry); nfs_advise_use_readdirplus(d_inode(parent)); dput(parent); } static u32 nfs_get_valid_attrmask(struct inode *inode) { unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity); u32 reply_mask = STATX_INO | STATX_TYPE; if (!(cache_validity & NFS_INO_INVALID_ATIME)) reply_mask |= STATX_ATIME; if (!(cache_validity & NFS_INO_INVALID_CTIME)) reply_mask |= STATX_CTIME; if (!(cache_validity & NFS_INO_INVALID_MTIME)) reply_mask |= STATX_MTIME; if (!(cache_validity & NFS_INO_INVALID_SIZE)) reply_mask |= STATX_SIZE; if (!(cache_validity & NFS_INO_INVALID_NLINK)) reply_mask |= STATX_NLINK; if (!(cache_validity & NFS_INO_INVALID_MODE)) reply_mask |= STATX_MODE; if (!(cache_validity & NFS_INO_INVALID_OTHER)) reply_mask |= STATX_UID | STATX_GID; if (!(cache_validity & NFS_INO_INVALID_BLOCKS)) reply_mask |= STATX_BLOCKS; return reply_mask; } int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct nfs_server *server = NFS_SERVER(inode); unsigned long cache_validity; int err = 0; bool force_sync = query_flags & AT_STATX_FORCE_SYNC; bool do_update = false; trace_nfs_getattr_enter(inode); request_mask &= STATX_TYPE | STATX_MODE | STATX_NLINK | STATX_UID | STATX_GID | STATX_ATIME | STATX_MTIME | STATX_CTIME | STATX_INO | STATX_SIZE | STATX_BLOCKS; if ((query_flags & AT_STATX_DONT_SYNC) && !force_sync) { nfs_readdirplus_parent_cache_hit(path->dentry); goto out_no_revalidate; } /* Flush out writes to the server in order to update c/mtime. */ if ((request_mask & (STATX_CTIME|STATX_MTIME)) && S_ISREG(inode->i_mode)) { err = filemap_write_and_wait(inode->i_mapping); if (err) goto out; } /* * We may force a getattr if the user cares about atime. * * Note that we only have to check the vfsmount flags here: * - NFS always sets S_NOATIME by so checking it would give a * bogus result * - NFS never sets SB_NOATIME or SB_NODIRATIME so there is * no point in checking those. */ if ((path->mnt->mnt_flags & MNT_NOATIME) || ((path->mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode))) request_mask &= ~STATX_ATIME; /* Is the user requesting attributes that might need revalidation? */ if (!(request_mask & (STATX_MODE|STATX_NLINK|STATX_ATIME|STATX_CTIME| STATX_MTIME|STATX_UID|STATX_GID| STATX_SIZE|STATX_BLOCKS))) goto out_no_revalidate; /* Check whether the cached attributes are stale */ do_update |= force_sync || nfs_attribute_cache_expired(inode); cache_validity = READ_ONCE(NFS_I(inode)->cache_validity); do_update |= cache_validity & NFS_INO_INVALID_CHANGE; if (request_mask & STATX_ATIME) do_update |= cache_validity & NFS_INO_INVALID_ATIME; if (request_mask & STATX_CTIME) do_update |= cache_validity & NFS_INO_INVALID_CTIME; if (request_mask & STATX_MTIME) do_update |= cache_validity & NFS_INO_INVALID_MTIME; if (request_mask & STATX_SIZE) do_update |= cache_validity & NFS_INO_INVALID_SIZE; if (request_mask & STATX_NLINK) do_update |= cache_validity & NFS_INO_INVALID_NLINK; if (request_mask & STATX_MODE) do_update |= cache_validity & NFS_INO_INVALID_MODE; if (request_mask & (STATX_UID | STATX_GID)) do_update |= cache_validity & NFS_INO_INVALID_OTHER; if (request_mask & STATX_BLOCKS) do_update |= cache_validity & NFS_INO_INVALID_BLOCKS; if (do_update) { /* Update the attribute cache */ if (!(server->flags & NFS_MOUNT_NOAC)) nfs_readdirplus_parent_cache_miss(path->dentry); else nfs_readdirplus_parent_cache_hit(path->dentry); err = __nfs_revalidate_inode(server, inode); if (err) goto out; } else nfs_readdirplus_parent_cache_hit(path->dentry); out_no_revalidate: /* Only return attributes that were revalidated. */ stat->result_mask = nfs_get_valid_attrmask(inode) | request_mask; generic_fillattr(&init_user_ns, inode, stat); stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode)); if (S_ISDIR(inode->i_mode)) stat->blksize = NFS_SERVER(inode)->dtsize; out: trace_nfs_getattr_exit(inode, err); return err; } EXPORT_SYMBOL_GPL(nfs_getattr); static void nfs_init_lock_context(struct nfs_lock_context *l_ctx) { refcount_set(&l_ctx->count, 1); l_ctx->lockowner = current->files; INIT_LIST_HEAD(&l_ctx->list); atomic_set(&l_ctx->io_count, 0); } static struct nfs_lock_context *__nfs_find_lock_context(struct nfs_open_context *ctx) { struct nfs_lock_context *pos; list_for_each_entry_rcu(pos, &ctx->lock_context.list, list) { if (pos->lockowner != current->files) continue; if (refcount_inc_not_zero(&pos->count)) return pos; } return NULL; } struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx) { struct nfs_lock_context *res, *new = NULL; struct inode *inode = d_inode(ctx->dentry); rcu_read_lock(); res = __nfs_find_lock_context(ctx); rcu_read_unlock(); if (res == NULL) { new = kmalloc(sizeof(*new), GFP_KERNEL); if (new == NULL) return ERR_PTR(-ENOMEM); nfs_init_lock_context(new); spin_lock(&inode->i_lock); res = __nfs_find_lock_context(ctx); if (res == NULL) { new->open_context = get_nfs_open_context(ctx); if (new->open_context) { list_add_tail_rcu(&new->list, &ctx->lock_context.list); res = new; new = NULL; } else res = ERR_PTR(-EBADF); } spin_unlock(&inode->i_lock); kfree(new); } return res; } EXPORT_SYMBOL_GPL(nfs_get_lock_context); void nfs_put_lock_context(struct nfs_lock_context *l_ctx) { struct nfs_open_context *ctx = l_ctx->open_context; struct inode *inode = d_inode(ctx->dentry); if (!refcount_dec_and_lock(&l_ctx->count, &inode->i_lock)) return; list_del_rcu(&l_ctx->list); spin_unlock(&inode->i_lock); put_nfs_open_context(ctx); kfree_rcu(l_ctx, rcu_head); } EXPORT_SYMBOL_GPL(nfs_put_lock_context); /** * nfs_close_context - Common close_context() routine NFSv2/v3 * @ctx: pointer to context * @is_sync: is this a synchronous close * * Ensure that the attributes are up to date if we're mounted * with close-to-open semantics and we have cached data that will * need to be revalidated on open. */ void nfs_close_context(struct nfs_open_context *ctx, int is_sync) { struct nfs_inode *nfsi; struct inode *inode; if (!(ctx->mode & FMODE_WRITE)) return; if (!is_sync) return; inode = d_inode(ctx->dentry); if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ)) return; nfsi = NFS_I(inode); if (inode->i_mapping->nrpages == 0) return; if (nfsi->cache_validity & NFS_INO_INVALID_DATA) return; if (!list_empty(&nfsi->open_files)) return; if (NFS_SERVER(inode)->flags & NFS_MOUNT_NOCTO) return; nfs_revalidate_inode(inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE); } EXPORT_SYMBOL_GPL(nfs_close_context); struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, fmode_t f_mode, struct file *filp) { struct nfs_open_context *ctx; ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return ERR_PTR(-ENOMEM); nfs_sb_active(dentry->d_sb); ctx->dentry = dget(dentry); if (filp) ctx->cred = get_cred(filp->f_cred); else ctx->cred = get_current_cred(); ctx->ll_cred = NULL; ctx->state = NULL; ctx->mode = f_mode; ctx->flags = 0; ctx->error = 0; ctx->flock_owner = (fl_owner_t)filp; nfs_init_lock_context(&ctx->lock_context); ctx->lock_context.open_context = ctx; INIT_LIST_HEAD(&ctx->list); ctx->mdsthreshold = NULL; return ctx; } EXPORT_SYMBOL_GPL(alloc_nfs_open_context); struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx) { if (ctx != NULL && refcount_inc_not_zero(&ctx->lock_context.count)) return ctx; return NULL; } EXPORT_SYMBOL_GPL(get_nfs_open_context); static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync) { struct inode *inode = d_inode(ctx->dentry); struct super_block *sb = ctx->dentry->d_sb; if (!refcount_dec_and_test(&ctx->lock_context.count)) return; if (!list_empty(&ctx->list)) { spin_lock(&inode->i_lock); list_del_rcu(&ctx->list); spin_unlock(&inode->i_lock); } if (inode != NULL) NFS_PROTO(inode)->close_context(ctx, is_sync); put_cred(ctx->cred); dput(ctx->dentry); nfs_sb_deactive(sb); put_rpccred(ctx->ll_cred); kfree(ctx->mdsthreshold); kfree_rcu(ctx, rcu_head); } void put_nfs_open_context(struct nfs_open_context *ctx) { __put_nfs_open_context(ctx, 0); } EXPORT_SYMBOL_GPL(put_nfs_open_context); static void put_nfs_open_context_sync(struct nfs_open_context *ctx) { __put_nfs_open_context(ctx, 1); } /* * Ensure that mmap has a recent RPC credential for use when writing out * shared pages */ void nfs_inode_attach_open_context(struct nfs_open_context *ctx) { struct inode *inode = d_inode(ctx->dentry); struct nfs_inode *nfsi = NFS_I(inode); spin_lock(&inode->i_lock); if (list_empty(&nfsi->open_files) && (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA | NFS_INO_REVAL_FORCED); list_add_tail_rcu(&ctx->list, &nfsi->open_files); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_inode_attach_open_context); void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx) { filp->private_data = get_nfs_open_context(ctx); if (list_empty(&ctx->list)) nfs_inode_attach_open_context(ctx); } EXPORT_SYMBOL_GPL(nfs_file_set_open_context); /* * Given an inode, search for an open context with the desired characteristics */ struct nfs_open_context *nfs_find_open_context(struct inode *inode, const struct cred *cred, fmode_t mode) { struct nfs_inode *nfsi = NFS_I(inode); struct nfs_open_context *pos, *ctx = NULL; rcu_read_lock(); list_for_each_entry_rcu(pos, &nfsi->open_files, list) { if (cred != NULL && cred_fscmp(pos->cred, cred) != 0) continue; if ((pos->mode & (FMODE_READ|FMODE_WRITE)) != mode) continue; ctx = get_nfs_open_context(pos); if (ctx) break; } rcu_read_unlock(); return ctx; } void nfs_file_clear_open_context(struct file *filp) { struct nfs_open_context *ctx = nfs_file_open_context(filp); if (ctx) { struct inode *inode = d_inode(ctx->dentry); /* * We fatal error on write before. Try to writeback * every page again. */ if (ctx->error < 0) invalidate_inode_pages2(inode->i_mapping); filp->private_data = NULL; put_nfs_open_context_sync(ctx); } } /* * These allocate and release file read/write context information. */ int nfs_open(struct inode *inode, struct file *filp) { struct nfs_open_context *ctx; ctx = alloc_nfs_open_context(file_dentry(filp), filp->f_mode, filp); if (IS_ERR(ctx)) return PTR_ERR(ctx); nfs_file_set_open_context(filp, ctx); put_nfs_open_context(ctx); nfs_fscache_open_file(inode, filp); return 0; } EXPORT_SYMBOL_GPL(nfs_open); /* * This function is called whenever some part of NFS notices that * the cached attributes have to be refreshed. */ int __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) { int status = -ESTALE; struct nfs4_label *label = NULL; struct nfs_fattr *fattr = NULL; struct nfs_inode *nfsi = NFS_I(inode); dfprintk(PAGECACHE, "NFS: revalidating (%s/%Lu)\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode)); trace_nfs_revalidate_inode_enter(inode); if (is_bad_inode(inode)) goto out; if (NFS_STALE(inode)) goto out; /* pNFS: Attributes aren't updated until we layoutcommit */ if (S_ISREG(inode->i_mode)) { status = pnfs_sync_inode(inode, false); if (status) goto out; } status = -ENOMEM; fattr = nfs_alloc_fattr(); if (fattr == NULL) goto out; nfs_inc_stats(inode, NFSIOS_INODEREVALIDATE); label = nfs4_label_alloc(NFS_SERVER(inode), GFP_KERNEL); if (IS_ERR(label)) { status = PTR_ERR(label); goto out; } status = NFS_PROTO(inode)->getattr(server, NFS_FH(inode), fattr, label, inode); if (status != 0) { dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Lu) getattr failed, error=%d\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode), status); switch (status) { case -ETIMEDOUT: /* A soft timeout occurred. Use cached information? */ if (server->flags & NFS_MOUNT_SOFTREVAL) status = 0; break; case -ESTALE: if (!S_ISDIR(inode->i_mode)) nfs_set_inode_stale(inode); else nfs_zap_caches(inode); } goto err_out; } status = nfs_refresh_inode(inode, fattr); if (status) { dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Lu) refresh failed, error=%d\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode), status); goto err_out; } if (nfsi->cache_validity & NFS_INO_INVALID_ACL) nfs_zap_acl_cache(inode); nfs_setsecurity(inode, fattr, label); dfprintk(PAGECACHE, "NFS: (%s/%Lu) revalidation complete\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode)); err_out: nfs4_label_free(label); out: nfs_free_fattr(fattr); trace_nfs_revalidate_inode_exit(inode, status); return status; } int nfs_attribute_cache_expired(struct inode *inode) { if (nfs_have_delegated_attributes(inode)) return 0; return nfs_attribute_timeout(inode); } /** * nfs_revalidate_inode - Revalidate the inode attributes * @inode: pointer to inode struct * @flags: cache flags to check * * Updates inode attribute information by retrieving the data from the server. */ int nfs_revalidate_inode(struct inode *inode, unsigned long flags) { if (!nfs_check_cache_invalid(inode, flags)) return NFS_STALE(inode) ? -ESTALE : 0; return __nfs_revalidate_inode(NFS_SERVER(inode), inode); } EXPORT_SYMBOL_GPL(nfs_revalidate_inode); static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping) { int ret; if (mapping->nrpages != 0) { if (S_ISREG(inode->i_mode)) { ret = nfs_sync_mapping(mapping); if (ret < 0) return ret; } ret = invalidate_inode_pages2(mapping); if (ret < 0) return ret; } nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE); nfs_fscache_wait_on_invalidate(inode); dfprintk(PAGECACHE, "NFS: (%s/%Lu) data cache invalidated\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode)); return 0; } /** * nfs_clear_invalid_mapping - Conditionally clear a mapping * @mapping: pointer to mapping * * If the NFS_INO_INVALID_DATA inode flag is set, clear the mapping. */ int nfs_clear_invalid_mapping(struct address_space *mapping) { struct inode *inode = mapping->host; struct nfs_inode *nfsi = NFS_I(inode); unsigned long *bitlock = &nfsi->flags; int ret = 0; /* * We must clear NFS_INO_INVALID_DATA first to ensure that * invalidations that come in while we're shooting down the mappings * are respected. But, that leaves a race window where one revalidator * can clear the flag, and then another checks it before the mapping * gets invalidated. Fix that by serializing access to this part of * the function. * * At the same time, we need to allow other tasks to see whether we * might be in the middle of invalidating the pages, so we only set * the bit lock here if it looks like we're going to be doing that. */ for (;;) { ret = wait_on_bit_action(bitlock, NFS_INO_INVALIDATING, nfs_wait_bit_killable, TASK_KILLABLE); if (ret) goto out; spin_lock(&inode->i_lock); if (test_bit(NFS_INO_INVALIDATING, bitlock)) { spin_unlock(&inode->i_lock); continue; } if (nfsi->cache_validity & NFS_INO_INVALID_DATA) break; spin_unlock(&inode->i_lock); goto out; } set_bit(NFS_INO_INVALIDATING, bitlock); smp_wmb(); nfsi->cache_validity &= ~(NFS_INO_INVALID_DATA | NFS_INO_DATA_INVAL_DEFER); spin_unlock(&inode->i_lock); trace_nfs_invalidate_mapping_enter(inode); ret = nfs_invalidate_mapping(inode, mapping); trace_nfs_invalidate_mapping_exit(inode, ret); clear_bit_unlock(NFS_INO_INVALIDATING, bitlock); smp_mb__after_atomic(); wake_up_bit(bitlock, NFS_INO_INVALIDATING); out: return ret; } bool nfs_mapping_need_revalidate_inode(struct inode *inode) { return nfs_check_cache_invalid(inode, NFS_INO_INVALID_CHANGE) || NFS_STALE(inode); } int nfs_revalidate_mapping_rcu(struct inode *inode) { struct nfs_inode *nfsi = NFS_I(inode); unsigned long *bitlock = &nfsi->flags; int ret = 0; if (IS_SWAPFILE(inode)) goto out; if (nfs_mapping_need_revalidate_inode(inode)) { ret = -ECHILD; goto out; } spin_lock(&inode->i_lock); if (test_bit(NFS_INO_INVALIDATING, bitlock) || (nfsi->cache_validity & NFS_INO_INVALID_DATA)) ret = -ECHILD; spin_unlock(&inode->i_lock); out: return ret; } /** * nfs_revalidate_mapping - Revalidate the pagecache * @inode: pointer to host inode * @mapping: pointer to mapping */ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping) { /* swapfiles are not supposed to be shared. */ if (IS_SWAPFILE(inode)) return 0; if (nfs_mapping_need_revalidate_inode(inode)) { int ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode); if (ret < 0) return ret; } return nfs_clear_invalid_mapping(mapping); } static bool nfs_file_has_writers(struct nfs_inode *nfsi) { struct inode *inode = &nfsi->vfs_inode; if (!S_ISREG(inode->i_mode)) return false; if (list_empty(&nfsi->open_files)) return false; return inode_is_open_for_write(inode); } static bool nfs_file_has_buffered_writers(struct nfs_inode *nfsi) { return nfs_file_has_writers(nfsi) && nfs_file_io_is_buffered(nfsi); } static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr) { struct timespec64 ts; if ((fattr->valid & NFS_ATTR_FATTR_PRECHANGE) && (fattr->valid & NFS_ATTR_FATTR_CHANGE) && inode_eq_iversion_raw(inode, fattr->pre_change_attr)) { inode_set_iversion_raw(inode, fattr->change_attr); if (S_ISDIR(inode->i_mode)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA); else if (nfs_server_capable(inode, NFS_CAP_XATTR)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_XATTR); } /* If we have atomic WCC data, we may update some attributes */ ts = inode->i_ctime; if ((fattr->valid & NFS_ATTR_FATTR_PRECTIME) && (fattr->valid & NFS_ATTR_FATTR_CTIME) && timespec64_equal(&ts, &fattr->pre_ctime)) { inode->i_ctime = fattr->ctime; } ts = inode->i_mtime; if ((fattr->valid & NFS_ATTR_FATTR_PREMTIME) && (fattr->valid & NFS_ATTR_FATTR_MTIME) && timespec64_equal(&ts, &fattr->pre_mtime)) { inode->i_mtime = fattr->mtime; if (S_ISDIR(inode->i_mode)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA); } if ((fattr->valid & NFS_ATTR_FATTR_PRESIZE) && (fattr->valid & NFS_ATTR_FATTR_SIZE) && i_size_read(inode) == nfs_size_to_loff_t(fattr->pre_size) && !nfs_have_writebacks(inode)) { i_size_write(inode, nfs_size_to_loff_t(fattr->size)); } } /** * nfs_check_inode_attributes - verify consistency of the inode attribute cache * @inode: pointer to inode * @fattr: updated attributes * * Verifies the attribute cache. If we have just changed the attributes, * so that fattr carries weak cache consistency data, then it may * also update the ctime/mtime/change_attribute. */ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fattr) { struct nfs_inode *nfsi = NFS_I(inode); loff_t cur_size, new_isize; unsigned long invalid = 0; struct timespec64 ts; if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ)) return 0; if (!(fattr->valid & NFS_ATTR_FATTR_FILEID)) { /* Only a mounted-on-fileid? Just exit */ if (fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) return 0; /* Has the inode gone and changed behind our back? */ } else if (nfsi->fileid != fattr->fileid) { /* Is this perhaps the mounted-on fileid? */ if ((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) && nfsi->fileid == fattr->mounted_on_fileid) return 0; return -ESTALE; } if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && inode_wrong_type(inode, fattr->mode)) return -ESTALE; if (!nfs_file_has_buffered_writers(nfsi)) { /* Verify a few of the more important attributes */ if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && !inode_eq_iversion_raw(inode, fattr->change_attr)) invalid |= NFS_INO_INVALID_CHANGE; ts = inode->i_mtime; if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec64_equal(&ts, &fattr->mtime)) invalid |= NFS_INO_INVALID_MTIME; ts = inode->i_ctime; if ((fattr->valid & NFS_ATTR_FATTR_CTIME) && !timespec64_equal(&ts, &fattr->ctime)) invalid |= NFS_INO_INVALID_CTIME; if (fattr->valid & NFS_ATTR_FATTR_SIZE) { cur_size = i_size_read(inode); new_isize = nfs_size_to_loff_t(fattr->size); if (cur_size != new_isize) invalid |= NFS_INO_INVALID_SIZE; } } /* Have any file permissions changed? */ if ((fattr->valid & NFS_ATTR_FATTR_MODE) && (inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) invalid |= NFS_INO_INVALID_MODE; if ((fattr->valid & NFS_ATTR_FATTR_OWNER) && !uid_eq(inode->i_uid, fattr->uid)) invalid |= NFS_INO_INVALID_OTHER; if ((fattr->valid & NFS_ATTR_FATTR_GROUP) && !gid_eq(inode->i_gid, fattr->gid)) invalid |= NFS_INO_INVALID_OTHER; /* Has the link count changed? */ if ((fattr->valid & NFS_ATTR_FATTR_NLINK) && inode->i_nlink != fattr->nlink) invalid |= NFS_INO_INVALID_NLINK; ts = inode->i_atime; if ((fattr->valid & NFS_ATTR_FATTR_ATIME) && !timespec64_equal(&ts, &fattr->atime)) invalid |= NFS_INO_INVALID_ATIME; if (invalid != 0) nfs_set_cache_invalid(inode, invalid); nfsi->read_cache_jiffies = fattr->time_start; return 0; } static atomic_long_t nfs_attr_generation_counter; static unsigned long nfs_read_attr_generation_counter(void) { return atomic_long_read(&nfs_attr_generation_counter); } unsigned long nfs_inc_attr_generation_counter(void) { return atomic_long_inc_return(&nfs_attr_generation_counter); } EXPORT_SYMBOL_GPL(nfs_inc_attr_generation_counter); void nfs_fattr_init(struct nfs_fattr *fattr) { fattr->valid = 0; fattr->time_start = jiffies; fattr->gencount = nfs_inc_attr_generation_counter(); fattr->owner_name = NULL; fattr->group_name = NULL; } EXPORT_SYMBOL_GPL(nfs_fattr_init); /** * nfs_fattr_set_barrier * @fattr: attributes * * Used to set a barrier after an attribute was updated. This * barrier ensures that older attributes from RPC calls that may * have raced with our update cannot clobber these new values. * Note that you are still responsible for ensuring that other * operations which change the attribute on the server do not * collide. */ void nfs_fattr_set_barrier(struct nfs_fattr *fattr) { fattr->gencount = nfs_inc_attr_generation_counter(); } struct nfs_fattr *nfs_alloc_fattr(void) { struct nfs_fattr *fattr; fattr = kmalloc(sizeof(*fattr), GFP_NOFS); if (fattr != NULL) nfs_fattr_init(fattr); return fattr; } EXPORT_SYMBOL_GPL(nfs_alloc_fattr); struct nfs_fh *nfs_alloc_fhandle(void) { struct nfs_fh *fh; fh = kmalloc(sizeof(struct nfs_fh), GFP_NOFS); if (fh != NULL) fh->size = 0; return fh; } EXPORT_SYMBOL_GPL(nfs_alloc_fhandle); #ifdef NFS_DEBUG /* * _nfs_display_fhandle_hash - calculate the crc32 hash for the filehandle * in the same way that wireshark does * * @fh: file handle * * For debugging only. */ u32 _nfs_display_fhandle_hash(const struct nfs_fh *fh) { /* wireshark uses 32-bit AUTODIN crc and does a bitwise * not on the result */ return nfs_fhandle_hash(fh); } EXPORT_SYMBOL_GPL(_nfs_display_fhandle_hash); /* * _nfs_display_fhandle - display an NFS file handle on the console * * @fh: file handle to display * @caption: display caption * * For debugging only. */ void _nfs_display_fhandle(const struct nfs_fh *fh, const char *caption) { unsigned short i; if (fh == NULL || fh->size == 0) { printk(KERN_DEFAULT "%s at %p is empty\n", caption, fh); return; } printk(KERN_DEFAULT "%s at %p is %u bytes, crc: 0x%08x:\n", caption, fh, fh->size, _nfs_display_fhandle_hash(fh)); for (i = 0; i < fh->size; i += 16) { __be32 *pos = (__be32 *)&fh->data[i]; switch ((fh->size - i - 1) >> 2) { case 0: printk(KERN_DEFAULT " %08x\n", be32_to_cpup(pos)); break; case 1: printk(KERN_DEFAULT " %08x %08x\n", be32_to_cpup(pos), be32_to_cpup(pos + 1)); break; case 2: printk(KERN_DEFAULT " %08x %08x %08x\n", be32_to_cpup(pos), be32_to_cpup(pos + 1), be32_to_cpup(pos + 2)); break; default: printk(KERN_DEFAULT " %08x %08x %08x %08x\n", be32_to_cpup(pos), be32_to_cpup(pos + 1), be32_to_cpup(pos + 2), be32_to_cpup(pos + 3)); } } } EXPORT_SYMBOL_GPL(_nfs_display_fhandle); #endif /** * nfs_inode_attrs_cmp_generic - compare attributes * @fattr: attributes * @inode: pointer to inode * * Attempt to divine whether or not an RPC call reply carrying stale * attributes got scheduled after another call carrying updated ones. * Note also the check for wraparound of 'attr_gencount' * * The function returns '1' if it thinks the attributes in @fattr are * more recent than the ones cached in @inode. Otherwise it returns * the value '0'. */ static int nfs_inode_attrs_cmp_generic(const struct nfs_fattr *fattr, const struct inode *inode) { unsigned long attr_gencount = NFS_I(inode)->attr_gencount; return (long)(fattr->gencount - attr_gencount) > 0 || (long)(attr_gencount - nfs_read_attr_generation_counter()) > 0; } /** * nfs_inode_attrs_cmp_monotonic - compare attributes * @fattr: attributes * @inode: pointer to inode * * Attempt to divine whether or not an RPC call reply carrying stale * attributes got scheduled after another call carrying updated ones. * * We assume that the server observes monotonic semantics for * the change attribute, so a larger value means that the attributes in * @fattr are more recent, in which case the function returns the * value '1'. * A return value of '0' indicates no measurable change * A return value of '-1' means that the attributes in @inode are * more recent. */ static int nfs_inode_attrs_cmp_monotonic(const struct nfs_fattr *fattr, const struct inode *inode) { s64 diff = fattr->change_attr - inode_peek_iversion_raw(inode); if (diff > 0) return 1; return diff == 0 ? 0 : -1; } /** * nfs_inode_attrs_cmp_strict_monotonic - compare attributes * @fattr: attributes * @inode: pointer to inode * * Attempt to divine whether or not an RPC call reply carrying stale * attributes got scheduled after another call carrying updated ones. * * We assume that the server observes strictly monotonic semantics for * the change attribute, so a larger value means that the attributes in * @fattr are more recent, in which case the function returns the * value '1'. * A return value of '-1' means that the attributes in @inode are * more recent or unchanged. */ static int nfs_inode_attrs_cmp_strict_monotonic(const struct nfs_fattr *fattr, const struct inode *inode) { return nfs_inode_attrs_cmp_monotonic(fattr, inode) > 0 ? 1 : -1; } /** * nfs_inode_attrs_cmp - compare attributes * @fattr: attributes * @inode: pointer to inode * * This function returns '1' if it thinks the attributes in @fattr are * more recent than the ones cached in @inode. It returns '-1' if * the attributes in @inode are more recent than the ones in @fattr, * and it returns 0 if not sure. */ static int nfs_inode_attrs_cmp(const struct nfs_fattr *fattr, const struct inode *inode) { if (nfs_inode_attrs_cmp_generic(fattr, inode) > 0) return 1; switch (NFS_SERVER(inode)->change_attr_type) { case NFS4_CHANGE_TYPE_IS_UNDEFINED: break; case NFS4_CHANGE_TYPE_IS_TIME_METADATA: if (!(fattr->valid & NFS_ATTR_FATTR_CHANGE)) break; return nfs_inode_attrs_cmp_monotonic(fattr, inode); default: if (!(fattr->valid & NFS_ATTR_FATTR_CHANGE)) break; return nfs_inode_attrs_cmp_strict_monotonic(fattr, inode); } return 0; } /** * nfs_inode_finish_partial_attr_update - complete a previous inode update * @fattr: attributes * @inode: pointer to inode * * Returns '1' if the last attribute update left the inode cached * attributes in a partially unrevalidated state, and @fattr * matches the change attribute of that partial update. * Otherwise returns '0'. */ static int nfs_inode_finish_partial_attr_update(const struct nfs_fattr *fattr, const struct inode *inode) { const unsigned long check_valid = NFS_INO_INVALID_ATIME | NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME | NFS_INO_INVALID_SIZE | NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_OTHER | NFS_INO_INVALID_NLINK; unsigned long cache_validity = NFS_I(inode)->cache_validity; if (!(cache_validity & NFS_INO_INVALID_CHANGE) && (cache_validity & check_valid) != 0 && (fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && nfs_inode_attrs_cmp_monotonic(fattr, inode) == 0) return 1; return 0; } static int nfs_refresh_inode_locked(struct inode *inode, struct nfs_fattr *fattr) { int attr_cmp = nfs_inode_attrs_cmp(fattr, inode); int ret = 0; trace_nfs_refresh_inode_enter(inode); if (attr_cmp > 0 || nfs_inode_finish_partial_attr_update(fattr, inode)) ret = nfs_update_inode(inode, fattr); else if (attr_cmp == 0) ret = nfs_check_inode_attributes(inode, fattr); trace_nfs_refresh_inode_exit(inode, ret); return ret; } /** * nfs_refresh_inode - try to update the inode attribute cache * @inode: pointer to inode * @fattr: updated attributes * * Check that an RPC call that returned attributes has not overlapped with * other recent updates of the inode metadata, then decide whether it is * safe to do a full update of the inode attributes, or whether just to * call nfs_check_inode_attributes. */ int nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr) { int status; if ((fattr->valid & NFS_ATTR_FATTR) == 0) return 0; spin_lock(&inode->i_lock); status = nfs_refresh_inode_locked(inode, fattr); spin_unlock(&inode->i_lock); return status; } EXPORT_SYMBOL_GPL(nfs_refresh_inode); static int nfs_post_op_update_inode_locked(struct inode *inode, struct nfs_fattr *fattr, unsigned int invalid) { if (S_ISDIR(inode->i_mode)) invalid |= NFS_INO_INVALID_DATA; nfs_set_cache_invalid(inode, invalid); if ((fattr->valid & NFS_ATTR_FATTR) == 0) return 0; return nfs_refresh_inode_locked(inode, fattr); } /** * nfs_post_op_update_inode - try to update the inode attribute cache * @inode: pointer to inode * @fattr: updated attributes * * After an operation that has changed the inode metadata, mark the * attribute cache as being invalid, then try to update it. * * NB: if the server didn't return any post op attributes, this * function will force the retrieval of attributes before the next * NFS request. Thus it should be used only for operations that * are expected to change one or more attributes, to avoid * unnecessary NFS requests and trips through nfs_update_inode(). */ int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr) { int status; spin_lock(&inode->i_lock); nfs_fattr_set_barrier(fattr); status = nfs_post_op_update_inode_locked(inode, fattr, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME | NFS_INO_REVAL_FORCED); spin_unlock(&inode->i_lock); return status; } EXPORT_SYMBOL_GPL(nfs_post_op_update_inode); /** * nfs_post_op_update_inode_force_wcc_locked - update the inode attribute cache * @inode: pointer to inode * @fattr: updated attributes * * After an operation that has changed the inode metadata, mark the * attribute cache as being invalid, then try to update it. Fake up * weak cache consistency data, if none exist. * * This function is mainly designed to be used by the ->write_done() functions. */ int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr) { int attr_cmp = nfs_inode_attrs_cmp(fattr, inode); int status; /* Don't do a WCC update if these attributes are already stale */ if (attr_cmp < 0) return 0; if ((fattr->valid & NFS_ATTR_FATTR) == 0 || !attr_cmp) { fattr->valid &= ~(NFS_ATTR_FATTR_PRECHANGE | NFS_ATTR_FATTR_PRESIZE | NFS_ATTR_FATTR_PREMTIME | NFS_ATTR_FATTR_PRECTIME); goto out_noforce; } if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && (fattr->valid & NFS_ATTR_FATTR_PRECHANGE) == 0) { fattr->pre_change_attr = inode_peek_iversion_raw(inode); fattr->valid |= NFS_ATTR_FATTR_PRECHANGE; } if ((fattr->valid & NFS_ATTR_FATTR_CTIME) != 0 && (fattr->valid & NFS_ATTR_FATTR_PRECTIME) == 0) { fattr->pre_ctime = inode->i_ctime; fattr->valid |= NFS_ATTR_FATTR_PRECTIME; } if ((fattr->valid & NFS_ATTR_FATTR_MTIME) != 0 && (fattr->valid & NFS_ATTR_FATTR_PREMTIME) == 0) { fattr->pre_mtime = inode->i_mtime; fattr->valid |= NFS_ATTR_FATTR_PREMTIME; } if ((fattr->valid & NFS_ATTR_FATTR_SIZE) != 0 && (fattr->valid & NFS_ATTR_FATTR_PRESIZE) == 0) { fattr->pre_size = i_size_read(inode); fattr->valid |= NFS_ATTR_FATTR_PRESIZE; } out_noforce: status = nfs_post_op_update_inode_locked(inode, fattr, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME | NFS_INO_INVALID_BLOCKS); return status; } /** * nfs_post_op_update_inode_force_wcc - try to update the inode attribute cache * @inode: pointer to inode * @fattr: updated attributes * * After an operation that has changed the inode metadata, mark the * attribute cache as being invalid, then try to update it. Fake up * weak cache consistency data, if none exist. * * This function is mainly designed to be used by the ->write_done() functions. */ int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr) { int status; spin_lock(&inode->i_lock); nfs_fattr_set_barrier(fattr); status = nfs_post_op_update_inode_force_wcc_locked(inode, fattr); spin_unlock(&inode->i_lock); return status; } EXPORT_SYMBOL_GPL(nfs_post_op_update_inode_force_wcc); /* * Many nfs protocol calls return the new file attributes after * an operation. Here we update the inode to reflect the state * of the server's inode. * * This is a bit tricky because we have to make sure all dirty pages * have been sent off to the server before calling invalidate_inode_pages. * To make sure no other process adds more write requests while we try * our best to flush them, we make them sleep during the attribute refresh. * * A very similar scenario holds for the dir cache. */ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) { struct nfs_server *server = NFS_SERVER(inode); struct nfs_inode *nfsi = NFS_I(inode); loff_t cur_isize, new_isize; u64 fattr_supported = server->fattr_valid; unsigned long invalid = 0; unsigned long now = jiffies; unsigned long save_cache_validity; bool have_writers = nfs_file_has_buffered_writers(nfsi); bool cache_revalidated = true; bool attr_changed = false; bool have_delegation; dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%x)\n", __func__, inode->i_sb->s_id, inode->i_ino, nfs_display_fhandle_hash(NFS_FH(inode)), atomic_read(&inode->i_count), fattr->valid); if (!(fattr->valid & NFS_ATTR_FATTR_FILEID)) { /* Only a mounted-on-fileid? Just exit */ if (fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) return 0; /* Has the inode gone and changed behind our back? */ } else if (nfsi->fileid != fattr->fileid) { /* Is this perhaps the mounted-on fileid? */ if ((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) && nfsi->fileid == fattr->mounted_on_fileid) return 0; printk(KERN_ERR "NFS: server %s error: fileid changed\n" "fsid %s: expected fileid 0x%Lx, got 0x%Lx\n", NFS_SERVER(inode)->nfs_client->cl_hostname, inode->i_sb->s_id, (long long)nfsi->fileid, (long long)fattr->fileid); goto out_err; } /* * Make sure the inode's type hasn't changed. */ if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && inode_wrong_type(inode, fattr->mode)) { /* * Big trouble! The inode has become a different object. */ printk(KERN_DEBUG "NFS: %s: inode %lu mode changed, %07o to %07o\n", __func__, inode->i_ino, inode->i_mode, fattr->mode); goto out_err; } /* Update the fsid? */ if (S_ISDIR(inode->i_mode) && (fattr->valid & NFS_ATTR_FATTR_FSID) && !nfs_fsid_equal(&server->fsid, &fattr->fsid) && !IS_AUTOMOUNT(inode)) server->fsid = fattr->fsid; /* Save the delegation state before clearing cache_validity */ have_delegation = nfs_have_delegated_attributes(inode); /* * Update the read time so we don't revalidate too often. */ nfsi->read_cache_jiffies = fattr->time_start; save_cache_validity = nfsi->cache_validity; nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ATIME | NFS_INO_REVAL_FORCED | NFS_INO_INVALID_BLOCKS); /* Do atomic weak cache consistency updates */ nfs_wcc_update_inode(inode, fattr); if (pnfs_layoutcommit_outstanding(inode)) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME | NFS_INO_INVALID_SIZE | NFS_INO_INVALID_BLOCKS); cache_revalidated = false; } /* More cache consistency checks */ if (fattr->valid & NFS_ATTR_FATTR_CHANGE) { if (!inode_eq_iversion_raw(inode, fattr->change_attr)) { /* Could it be a race with writeback? */ if (!(have_writers || have_delegation)) { invalid |= NFS_INO_INVALID_DATA | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_INVALID_XATTR; /* Force revalidate of all attributes */ save_cache_validity |= NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME | NFS_INO_INVALID_SIZE | NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_NLINK | NFS_INO_INVALID_MODE | NFS_INO_INVALID_OTHER; if (S_ISDIR(inode->i_mode)) nfs_force_lookup_revalidate(inode); dprintk("NFS: change_attr change on server for file %s/%ld\n", inode->i_sb->s_id, inode->i_ino); } else if (!have_delegation) nfsi->cache_validity |= NFS_INO_DATA_INVAL_DEFER; inode_set_iversion_raw(inode, fattr->change_attr); attr_changed = true; } } else { nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_CHANGE; cache_revalidated = false; } if (fattr->valid & NFS_ATTR_FATTR_MTIME) { inode->i_mtime = fattr->mtime; } else if (fattr_supported & NFS_ATTR_FATTR_MTIME) { nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_MTIME; cache_revalidated = false; } if (fattr->valid & NFS_ATTR_FATTR_CTIME) { inode->i_ctime = fattr->ctime; } else if (fattr_supported & NFS_ATTR_FATTR_CTIME) { nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_CTIME; cache_revalidated = false; } /* Check if our cached file size is stale */ if (fattr->valid & NFS_ATTR_FATTR_SIZE) { new_isize = nfs_size_to_loff_t(fattr->size); cur_isize = i_size_read(inode); if (new_isize != cur_isize && !have_delegation) { /* Do we perhaps have any outstanding writes, or has * the file grown beyond our last write? */ if (!nfs_have_writebacks(inode) || new_isize > cur_isize) { i_size_write(inode, new_isize); if (!have_writers) invalid |= NFS_INO_INVALID_DATA; attr_changed = true; } dprintk("NFS: isize change on server for file %s/%ld " "(%Ld to %Ld)\n", inode->i_sb->s_id, inode->i_ino, (long long)cur_isize, (long long)new_isize); } if (new_isize == 0 && !(fattr->valid & (NFS_ATTR_FATTR_SPACE_USED | NFS_ATTR_FATTR_BLOCKS_USED))) { fattr->du.nfs3.used = 0; fattr->valid |= NFS_ATTR_FATTR_SPACE_USED; } } else { nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_SIZE; cache_revalidated = false; } if (fattr->valid & NFS_ATTR_FATTR_ATIME) inode->i_atime = fattr->atime; else if (fattr_supported & NFS_ATTR_FATTR_ATIME) { nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_ATIME; cache_revalidated = false; } if (fattr->valid & NFS_ATTR_FATTR_MODE) { if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) { umode_t newmode = inode->i_mode & S_IFMT; newmode |= fattr->mode & S_IALLUGO; inode->i_mode = newmode; invalid |= NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL; attr_changed = true; } } else if (fattr_supported & NFS_ATTR_FATTR_MODE) { nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_MODE; cache_revalidated = false; } if (fattr->valid & NFS_ATTR_FATTR_OWNER) { if (!uid_eq(inode->i_uid, fattr->uid)) { invalid |= NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL; inode->i_uid = fattr->uid; attr_changed = true; } } else if (fattr_supported & NFS_ATTR_FATTR_OWNER) { nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_OTHER; cache_revalidated = false; } if (fattr->valid & NFS_ATTR_FATTR_GROUP) { if (!gid_eq(inode->i_gid, fattr->gid)) { invalid |= NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL; inode->i_gid = fattr->gid; attr_changed = true; } } else if (fattr_supported & NFS_ATTR_FATTR_GROUP) { nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_OTHER; cache_revalidated = false; } if (fattr->valid & NFS_ATTR_FATTR_NLINK) { if (inode->i_nlink != fattr->nlink) { if (S_ISDIR(inode->i_mode)) invalid |= NFS_INO_INVALID_DATA; set_nlink(inode, fattr->nlink); attr_changed = true; } } else if (fattr_supported & NFS_ATTR_FATTR_NLINK) { nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_NLINK; cache_revalidated = false; } if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { /* * report the blocks in 512byte units */ inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used); } else if (fattr_supported & NFS_ATTR_FATTR_SPACE_USED) { nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_BLOCKS; cache_revalidated = false; } if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) { inode->i_blocks = fattr->du.nfs2.blocks; } else if (fattr_supported & NFS_ATTR_FATTR_BLOCKS_USED) { nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_BLOCKS; cache_revalidated = false; } /* Update attrtimeo value if we're out of the unstable period */ if (attr_changed) { nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE); nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); nfsi->attrtimeo_timestamp = now; /* Set barrier to be more recent than all outstanding updates */ nfsi->attr_gencount = nfs_inc_attr_generation_counter(); } else { if (cache_revalidated) { if (!time_in_range_open(now, nfsi->attrtimeo_timestamp, nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) { nfsi->attrtimeo <<= 1; if (nfsi->attrtimeo > NFS_MAXATTRTIMEO(inode)) nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode); } nfsi->attrtimeo_timestamp = now; } /* Set the barrier to be more recent than this fattr */ if ((long)(fattr->gencount - nfsi->attr_gencount) > 0) nfsi->attr_gencount = fattr->gencount; } /* Don't invalidate the data if we were to blame */ if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) invalid &= ~NFS_INO_INVALID_DATA; nfs_set_cache_invalid(inode, invalid); return 0; out_err: /* * No need to worry about unhashing the dentry, as the * lookup validation will know that the inode is bad. * (But we fall through to invalidate the caches.) */ nfs_set_inode_stale_locked(inode); return -ESTALE; } struct inode *nfs_alloc_inode(struct super_block *sb) { struct nfs_inode *nfsi; nfsi = kmem_cache_alloc(nfs_inode_cachep, GFP_KERNEL); if (!nfsi) return NULL; nfsi->flags = 0UL; nfsi->cache_validity = 0UL; #if IS_ENABLED(CONFIG_NFS_V4) nfsi->nfs4_acl = NULL; #endif /* CONFIG_NFS_V4 */ #ifdef CONFIG_NFS_V4_2 nfsi->xattr_cache = NULL; #endif return &nfsi->vfs_inode; } EXPORT_SYMBOL_GPL(nfs_alloc_inode); void nfs_free_inode(struct inode *inode) { kmem_cache_free(nfs_inode_cachep, NFS_I(inode)); } EXPORT_SYMBOL_GPL(nfs_free_inode); static inline void nfs4_init_once(struct nfs_inode *nfsi) { #if IS_ENABLED(CONFIG_NFS_V4) INIT_LIST_HEAD(&nfsi->open_states); nfsi->delegation = NULL; init_rwsem(&nfsi->rwsem); nfsi->layout = NULL; #endif } static void init_once(void *foo) { struct nfs_inode *nfsi = (struct nfs_inode *) foo; inode_init_once(&nfsi->vfs_inode); INIT_LIST_HEAD(&nfsi->open_files); INIT_LIST_HEAD(&nfsi->access_cache_entry_lru); INIT_LIST_HEAD(&nfsi->access_cache_inode_lru); INIT_LIST_HEAD(&nfsi->commit_info.list); atomic_long_set(&nfsi->nrequests, 0); atomic_long_set(&nfsi->commit_info.ncommit, 0); atomic_set(&nfsi->commit_info.rpcs_out, 0); init_rwsem(&nfsi->rmdir_sem); mutex_init(&nfsi->commit_mutex); nfs4_init_once(nfsi); nfsi->cache_change_attribute = 0; } static int __init nfs_init_inodecache(void) { nfs_inode_cachep = kmem_cache_create("nfs_inode_cache", sizeof(struct nfs_inode), 0, (SLAB_RECLAIM_ACCOUNT| SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (nfs_inode_cachep == NULL) return -ENOMEM; return 0; } static void nfs_destroy_inodecache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(nfs_inode_cachep); } struct workqueue_struct *nfsiod_workqueue; EXPORT_SYMBOL_GPL(nfsiod_workqueue); /* * start up the nfsiod workqueue */ static int nfsiod_start(void) { struct workqueue_struct *wq; dprintk("RPC: creating workqueue nfsiod\n"); wq = alloc_workqueue("nfsiod", WQ_MEM_RECLAIM | WQ_UNBOUND, 0); if (wq == NULL) return -ENOMEM; nfsiod_workqueue = wq; return 0; } /* * Destroy the nfsiod workqueue */ static void nfsiod_stop(void) { struct workqueue_struct *wq; wq = nfsiod_workqueue; if (wq == NULL) return; nfsiod_workqueue = NULL; destroy_workqueue(wq); } unsigned int nfs_net_id; EXPORT_SYMBOL_GPL(nfs_net_id); static int nfs_net_init(struct net *net) { nfs_clients_init(net); return nfs_fs_proc_net_init(net); } static void nfs_net_exit(struct net *net) { nfs_fs_proc_net_exit(net); nfs_clients_exit(net); } static struct pernet_operations nfs_net_ops = { .init = nfs_net_init, .exit = nfs_net_exit, .id = &nfs_net_id, .size = sizeof(struct nfs_net), }; /* * Initialize NFS */ static int __init init_nfs_fs(void) { int err; err = nfs_sysfs_init(); if (err < 0) goto out10; err = register_pernet_subsys(&nfs_net_ops); if (err < 0) goto out9; err = nfs_fscache_register(); if (err < 0) goto out8; err = nfsiod_start(); if (err) goto out7; err = nfs_fs_proc_init(); if (err) goto out6; err = nfs_init_nfspagecache(); if (err) goto out5; err = nfs_init_inodecache(); if (err) goto out4; err = nfs_init_readpagecache(); if (err) goto out3; err = nfs_init_writepagecache(); if (err) goto out2; err = nfs_init_directcache(); if (err) goto out1; rpc_proc_register(&init_net, &nfs_rpcstat); err = register_nfs_fs(); if (err) goto out0; return 0; out0: rpc_proc_unregister(&init_net, "nfs"); nfs_destroy_directcache(); out1: nfs_destroy_writepagecache(); out2: nfs_destroy_readpagecache(); out3: nfs_destroy_inodecache(); out4: nfs_destroy_nfspagecache(); out5: nfs_fs_proc_exit(); out6: nfsiod_stop(); out7: nfs_fscache_unregister(); out8: unregister_pernet_subsys(&nfs_net_ops); out9: nfs_sysfs_exit(); out10: return err; } static void __exit exit_nfs_fs(void) { nfs_destroy_directcache(); nfs_destroy_writepagecache(); nfs_destroy_readpagecache(); nfs_destroy_inodecache(); nfs_destroy_nfspagecache(); nfs_fscache_unregister(); unregister_pernet_subsys(&nfs_net_ops); rpc_proc_unregister(&init_net, "nfs"); unregister_nfs_fs(); nfs_fs_proc_exit(); nfsiod_stop(); nfs_sysfs_exit(); } /* Not quite true; I just maintain it */ MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>"); MODULE_LICENSE("GPL"); module_param(enable_ino64, bool, 0644); module_init(init_nfs_fs) module_exit(exit_nfs_fs)