| 174 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FILELOCK_H #define _LINUX_FILELOCK_H #include <linux/fs.h> #define FL_POSIX 1 #define FL_FLOCK 2 #define FL_DELEG 4 /* NFSv4 delegation */ #define FL_ACCESS 8 /* not trying to lock, just looking */ #define FL_EXISTS 16 /* when unlocking, test for existence */ #define FL_LEASE 32 /* lease held on this file */ #define FL_CLOSE 64 /* unlock on close */ #define FL_SLEEP 128 /* A blocking lock */ #define FL_DOWNGRADE_PENDING 256 /* Lease is being downgraded */ #define FL_UNLOCK_PENDING 512 /* Lease is being broken */ #define FL_OFDLCK 1024 /* lock is "owned" by struct file */ #define FL_LAYOUT 2048 /* outstanding pNFS layout */ #define FL_RECLAIM 4096 /* reclaiming from a reboot server */ #define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE) /* * Special return value from posix_lock_file() and vfs_lock_file() for * asynchronous locking. */ #define FILE_LOCK_DEFERRED 1 struct file_lock; struct file_lease; struct file_lock_operations { void (*fl_copy_lock)(struct file_lock *, struct file_lock *); void (*fl_release_private)(struct file_lock *); }; struct lock_manager_operations { void *lm_mod_owner; fl_owner_t (*lm_get_owner)(fl_owner_t); void (*lm_put_owner)(fl_owner_t); void (*lm_notify)(struct file_lock *); /* unblock callback */ int (*lm_grant)(struct file_lock *, int); bool (*lm_lock_expirable)(struct file_lock *cfl); void (*lm_expire_lock)(void); }; struct lease_manager_operations { bool (*lm_break)(struct file_lease *); int (*lm_change)(struct file_lease *, int, struct list_head *); void (*lm_setup)(struct file_lease *, void **); bool (*lm_breaker_owns_lease)(struct file_lease *); }; struct lock_manager { struct list_head list; /* * NFSv4 and up also want opens blocked during the grace period; * NLM doesn't care: */ bool block_opens; }; struct net; void locks_start_grace(struct net *, struct lock_manager *); void locks_end_grace(struct lock_manager *); bool locks_in_grace(struct net *); bool opens_in_grace(struct net *); /* * struct file_lock has a union that some filesystems use to track * their own private info. The NFS side of things is defined here: */ #include <linux/nfs_fs_i.h> /* * struct file_lock represents a generic "file lock". It's used to represent * POSIX byte range locks, BSD (flock) locks, and leases. It's important to * note that the same struct is used to represent both a request for a lock and * the lock itself, but the same object is never used for both. * * FIXME: should we create a separate "struct lock_request" to help distinguish * these two uses? * * The varous i_flctx lists are ordered by: * * 1) lock owner * 2) lock range start * 3) lock range end * * Obviously, the last two criteria only matter for POSIX locks. */ struct file_lock_core { struct file_lock_core *flc_blocker; /* The lock that is blocking us */ struct list_head flc_list; /* link into file_lock_context */ struct hlist_node flc_link; /* node in global lists */ struct list_head flc_blocked_requests; /* list of requests with * ->fl_blocker pointing here */ struct list_head flc_blocked_member; /* node in * ->fl_blocker->fl_blocked_requests */ fl_owner_t flc_owner; unsigned int flc_flags; unsigned char flc_type; pid_t flc_pid; int flc_link_cpu; /* what cpu's list is this on? */ wait_queue_head_t flc_wait; struct file *flc_file; }; struct file_lock { struct file_lock_core c; loff_t fl_start; loff_t fl_end; const struct file_lock_operations *fl_ops; /* Callbacks for filesystems */ const struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */ union { struct nfs_lock_info nfs_fl; struct nfs4_lock_info nfs4_fl; struct { struct list_head link; /* link in AFS vnode's pending_locks list */ int state; /* state of grant or error if -ve */ unsigned int debug_id; } afs; struct { struct inode *inode; } ceph; } fl_u; } __randomize_layout; struct file_lease { struct file_lock_core c; struct fasync_struct * fl_fasync; /* for lease break notifications */ /* for lease breaks: */ unsigned long fl_break_time; unsigned long fl_downgrade_time; const struct lease_manager_operations *fl_lmops; /* Callbacks for lease managers */ } __randomize_layout; struct file_lock_context { spinlock_t flc_lock; struct list_head flc_flock; struct list_head flc_posix; struct list_head flc_lease; }; #ifdef CONFIG_FILE_LOCKING int fcntl_getlk(struct file *, unsigned int, struct flock *); int fcntl_setlk(unsigned int, struct file *, unsigned int, struct flock *); #if BITS_PER_LONG == 32 int fcntl_getlk64(struct file *, unsigned int, struct flock64 *); int fcntl_setlk64(unsigned int, struct file *, unsigned int, struct flock64 *); #endif int fcntl_setlease(unsigned int fd, struct file *filp, int arg); int fcntl_getlease(struct file *filp); static inline bool lock_is_unlock(struct file_lock *fl) { return fl->c.flc_type == F_UNLCK; } static inline bool lock_is_read(struct file_lock *fl) { return fl->c.flc_type == F_RDLCK; } static inline bool lock_is_write(struct file_lock *fl) { return fl->c.flc_type == F_WRLCK; } static inline void locks_wake_up(struct file_lock *fl) { wake_up(&fl->c.flc_wait); } static inline bool locks_can_async_lock(const struct file_operations *fops) { return !fops->lock || fops->fop_flags & FOP_ASYNC_LOCK; } /* fs/locks.c */ void locks_free_lock_context(struct inode *inode); void locks_free_lock(struct file_lock *fl); void locks_init_lock(struct file_lock *); struct file_lock *locks_alloc_lock(void); void locks_copy_lock(struct file_lock *, struct file_lock *); void locks_copy_conflock(struct file_lock *, struct file_lock *); void locks_remove_posix(struct file *, fl_owner_t); void locks_remove_file(struct file *); void locks_release_private(struct file_lock *); void posix_test_lock(struct file *, struct file_lock *); int posix_lock_file(struct file *, struct file_lock *, struct file_lock *); int locks_delete_block(struct file_lock *); int vfs_test_lock(struct file *, struct file_lock *); int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *); int vfs_cancel_lock(struct file *filp, struct file_lock *fl); bool vfs_inode_has_locks(struct inode *inode); int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl); void locks_init_lease(struct file_lease *); void locks_free_lease(struct file_lease *fl); struct file_lease *locks_alloc_lease(void); int __break_lease(struct inode *inode, unsigned int flags, unsigned int type); void lease_get_mtime(struct inode *, struct timespec64 *time); int generic_setlease(struct file *, int, struct file_lease **, void **priv); int kernel_setlease(struct file *, int, struct file_lease **, void **); int vfs_setlease(struct file *, int, struct file_lease **, void **); int lease_modify(struct file_lease *, int, struct list_head *); struct notifier_block; int lease_register_notifier(struct notifier_block *); void lease_unregister_notifier(struct notifier_block *); struct files_struct; void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files); bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner); static inline struct file_lock_context * locks_inode_context(const struct inode *inode) { return smp_load_acquire(&inode->i_flctx); } #else /* !CONFIG_FILE_LOCKING */ static inline int fcntl_getlk(struct file *file, unsigned int cmd, struct flock __user *user) { return -EINVAL; } static inline int fcntl_setlk(unsigned int fd, struct file *file, unsigned int cmd, struct flock __user *user) { return -EACCES; } #if BITS_PER_LONG == 32 static inline int fcntl_getlk64(struct file *file, unsigned int cmd, struct flock64 *user) { return -EINVAL; } static inline int fcntl_setlk64(unsigned int fd, struct file *file, unsigned int cmd, struct flock64 *user) { return -EACCES; } #endif static inline int fcntl_setlease(unsigned int fd, struct file *filp, int arg) { return -EINVAL; } static inline int fcntl_getlease(struct file *filp) { return F_UNLCK; } static inline bool lock_is_unlock(struct file_lock *fl) { return false; } static inline bool lock_is_read(struct file_lock *fl) { return false; } static inline bool lock_is_write(struct file_lock *fl) { return false; } static inline void locks_wake_up(struct file_lock *fl) { } static inline void locks_free_lock_context(struct inode *inode) { } static inline void locks_init_lock(struct file_lock *fl) { return; } static inline void locks_init_lease(struct file_lease *fl) { return; } static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl) { return; } static inline void locks_copy_lock(struct file_lock *new, struct file_lock *fl) { return; } static inline void locks_remove_posix(struct file *filp, fl_owner_t owner) { return; } static inline void locks_remove_file(struct file *filp) { return; } static inline void posix_test_lock(struct file *filp, struct file_lock *fl) { return; } static inline int posix_lock_file(struct file *filp, struct file_lock *fl, struct file_lock *conflock) { return -ENOLCK; } static inline int locks_delete_block(struct file_lock *waiter) { return -ENOENT; } static inline int vfs_test_lock(struct file *filp, struct file_lock *fl) { return 0; } static inline int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf) { return -ENOLCK; } static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl) { return 0; } static inline bool vfs_inode_has_locks(struct inode *inode) { return false; } static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) { return -ENOLCK; } static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) { return 0; } static inline void lease_get_mtime(struct inode *inode, struct timespec64 *time) { return; } static inline int generic_setlease(struct file *filp, int arg, struct file_lease **flp, void **priv) { return -EINVAL; } static inline int kernel_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) { return -EINVAL; } static inline int vfs_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) { return -EINVAL; } static inline int lease_modify(struct file_lease *fl, int arg, struct list_head *dispose) { return -EINVAL; } struct files_struct; static inline void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) {} static inline bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner) { return false; } static inline struct file_lock_context * locks_inode_context(const struct inode *inode) { return NULL; } #endif /* !CONFIG_FILE_LOCKING */ /* for walking lists of file_locks linked by fl_list */ #define for_each_file_lock(_fl, _head) list_for_each_entry(_fl, _head, c.flc_list) static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) { return locks_lock_inode_wait(file_inode(filp), fl); } #ifdef CONFIG_FILE_LOCKING static inline int break_lease(struct inode *inode, unsigned int mode) { struct file_lock_context *flctx; /* * Since this check is lockless, we must ensure that any refcounts * taken are done before checking i_flctx->flc_lease. Otherwise, we * could end up racing with tasks trying to set a new lease on this * file. */ flctx = READ_ONCE(inode->i_flctx); if (!flctx) return 0; smp_mb(); if (!list_empty_careful(&flctx->flc_lease)) return __break_lease(inode, mode, FL_LEASE); return 0; } static inline int break_deleg(struct inode *inode, unsigned int mode) { struct file_lock_context *flctx; /* * Since this check is lockless, we must ensure that any refcounts * taken are done before checking i_flctx->flc_lease. Otherwise, we * could end up racing with tasks trying to set a new lease on this * file. */ flctx = READ_ONCE(inode->i_flctx); if (!flctx) return 0; smp_mb(); if (!list_empty_careful(&flctx->flc_lease)) return __break_lease(inode, mode, FL_DELEG); return 0; } static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) { int ret; ret = break_deleg(inode, O_WRONLY|O_NONBLOCK); if (ret == -EWOULDBLOCK && delegated_inode) { *delegated_inode = inode; ihold(inode); } return ret; } static inline int break_deleg_wait(struct inode **delegated_inode) { int ret; ret = break_deleg(*delegated_inode, O_WRONLY); iput(*delegated_inode); *delegated_inode = NULL; return ret; } static inline int break_layout(struct inode *inode, bool wait) { smp_mb(); if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) return __break_lease(inode, wait ? O_WRONLY : O_WRONLY | O_NONBLOCK, FL_LAYOUT); return 0; } #else /* !CONFIG_FILE_LOCKING */ static inline int break_lease(struct inode *inode, unsigned int mode) { return 0; } static inline int break_deleg(struct inode *inode, unsigned int mode) { return 0; } static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) { return 0; } static inline int break_deleg_wait(struct inode **delegated_inode) { BUG(); return 0; } static inline int break_layout(struct inode *inode, bool wait) { return 0; } #endif /* CONFIG_FILE_LOCKING */ #endif /* _LINUX_FILELOCK_H */ |
| 52 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 | /* SPDX-License-Identifier: GPL-2.0 */ #if !defined(_TRACE_VGIC_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_VGIC_H #include <linux/tracepoint.h> #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm TRACE_EVENT(vgic_update_irq_pending, TP_PROTO(unsigned long vcpu_id, __u32 irq, bool level), TP_ARGS(vcpu_id, irq, level), TP_STRUCT__entry( __field( unsigned long, vcpu_id ) __field( __u32, irq ) __field( bool, level ) ), TP_fast_assign( __entry->vcpu_id = vcpu_id; __entry->irq = irq; __entry->level = level; ), TP_printk("VCPU: %ld, IRQ %d, level: %d", __entry->vcpu_id, __entry->irq, __entry->level) ); #endif /* _TRACE_VGIC_H */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH ../../arch/arm64/kvm/vgic #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE trace /* This part must be outside protection */ #include <trace/define_trace.h> |
| 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 | // SPDX-License-Identifier: GPL-2.0-only /* * Network interface table. * * Network interfaces (devices) do not have a security field, so we * maintain a table associating each interface with a SID. * * Author: James Morris <jmorris@redhat.com> * * Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com> * Copyright (C) 2007 Hewlett-Packard Development Company, L.P. * Paul Moore <paul@paul-moore.com> */ #include <linux/init.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/stddef.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/rcupdate.h> #include <net/net_namespace.h> #include "security.h" #include "objsec.h" #include "netif.h" #define SEL_NETIF_HASH_SIZE 64 #define SEL_NETIF_HASH_MAX 1024 struct sel_netif { struct list_head list; struct netif_security_struct nsec; struct rcu_head rcu_head; }; static u32 sel_netif_total; static DEFINE_SPINLOCK(sel_netif_lock); static struct list_head sel_netif_hash[SEL_NETIF_HASH_SIZE]; /** * sel_netif_hashfn - Hashing function for the interface table * @ns: the network namespace * @ifindex: the network interface * * Description: * This is the hashing function for the network interface table, it returns the * bucket number for the given interface. * */ static inline u32 sel_netif_hashfn(const struct net *ns, int ifindex) { return (((uintptr_t)ns + ifindex) & (SEL_NETIF_HASH_SIZE - 1)); } /** * sel_netif_find - Search for an interface record * @ns: the network namespace * @ifindex: the network interface * * Description: * Search the network interface table and return the record matching @ifindex. * If an entry can not be found in the table return NULL. * */ static inline struct sel_netif *sel_netif_find(const struct net *ns, int ifindex) { u32 idx = sel_netif_hashfn(ns, ifindex); struct sel_netif *netif; list_for_each_entry_rcu(netif, &sel_netif_hash[idx], list) if (net_eq(netif->nsec.ns, ns) && netif->nsec.ifindex == ifindex) return netif; return NULL; } /** * sel_netif_insert - Insert a new interface into the table * @netif: the new interface record * * Description: * Add a new interface record to the network interface hash table. Returns * zero on success, negative values on failure. * */ static int sel_netif_insert(struct sel_netif *netif) { u32 idx; if (sel_netif_total >= SEL_NETIF_HASH_MAX) return -ENOSPC; idx = sel_netif_hashfn(netif->nsec.ns, netif->nsec.ifindex); list_add_rcu(&netif->list, &sel_netif_hash[idx]); sel_netif_total++; return 0; } /** * sel_netif_destroy - Remove an interface record from the table * @netif: the existing interface record * * Description: * Remove an existing interface record from the network interface table. * */ static void sel_netif_destroy(struct sel_netif *netif) { list_del_rcu(&netif->list); sel_netif_total--; kfree_rcu(netif, rcu_head); } /** * sel_netif_sid_slow - Lookup the SID of a network interface using the policy * @ns: the network namespace * @ifindex: the network interface * @sid: interface SID * * Description: * This function determines the SID of a network interface by querying the * security policy. The result is added to the network interface table to * speedup future queries. Returns zero on success, negative values on * failure. * */ static int sel_netif_sid_slow(struct net *ns, int ifindex, u32 *sid) { int ret = 0; struct sel_netif *netif; struct sel_netif *new; struct net_device *dev; /* NOTE: we always use init's network namespace since we don't * currently support containers */ dev = dev_get_by_index(ns, ifindex); if (unlikely(dev == NULL)) { pr_warn("SELinux: failure in %s(), invalid network interface (%d)\n", __func__, ifindex); return -ENOENT; } spin_lock_bh(&sel_netif_lock); netif = sel_netif_find(ns, ifindex); if (netif != NULL) { *sid = netif->nsec.sid; goto out; } ret = security_netif_sid(dev->name, sid); if (ret != 0) goto out; new = kzalloc(sizeof(*new), GFP_ATOMIC); if (new) { new->nsec.ns = ns; new->nsec.ifindex = ifindex; new->nsec.sid = *sid; if (sel_netif_insert(new)) kfree(new); } out: spin_unlock_bh(&sel_netif_lock); dev_put(dev); if (unlikely(ret)) pr_warn("SELinux: failure in %s(), unable to determine network interface label (%d)\n", __func__, ifindex); return ret; } /** * sel_netif_sid - Lookup the SID of a network interface * @ns: the network namespace * @ifindex: the network interface * @sid: interface SID * * Description: * This function determines the SID of a network interface using the fastest * method possible. First the interface table is queried, but if an entry * can't be found then the policy is queried and the result is added to the * table to speedup future queries. Returns zero on success, negative values * on failure. * */ int sel_netif_sid(struct net *ns, int ifindex, u32 *sid) { struct sel_netif *netif; rcu_read_lock(); netif = sel_netif_find(ns, ifindex); if (likely(netif != NULL)) { *sid = netif->nsec.sid; rcu_read_unlock(); return 0; } rcu_read_unlock(); return sel_netif_sid_slow(ns, ifindex, sid); } /** * sel_netif_kill - Remove an entry from the network interface table * @ns: the network namespace * @ifindex: the network interface * * Description: * This function removes the entry matching @ifindex from the network interface * table if it exists. * */ static void sel_netif_kill(const struct net *ns, int ifindex) { struct sel_netif *netif; rcu_read_lock(); spin_lock_bh(&sel_netif_lock); netif = sel_netif_find(ns, ifindex); if (netif) sel_netif_destroy(netif); spin_unlock_bh(&sel_netif_lock); rcu_read_unlock(); } /** * sel_netif_flush - Flush the entire network interface table * * Description: * Remove all entries from the network interface table. * */ void sel_netif_flush(void) { int idx; struct sel_netif *netif; spin_lock_bh(&sel_netif_lock); for (idx = 0; idx < SEL_NETIF_HASH_SIZE; idx++) list_for_each_entry(netif, &sel_netif_hash[idx], list) sel_netif_destroy(netif); spin_unlock_bh(&sel_netif_lock); } static int sel_netif_netdev_notifier_handler(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (event == NETDEV_DOWN) sel_netif_kill(dev_net(dev), dev->ifindex); return NOTIFY_DONE; } static struct notifier_block sel_netif_netdev_notifier = { .notifier_call = sel_netif_netdev_notifier_handler, }; static __init int sel_netif_init(void) { int i; if (!selinux_enabled_boot) return 0; for (i = 0; i < SEL_NETIF_HASH_SIZE; i++) INIT_LIST_HEAD(&sel_netif_hash[i]); register_netdevice_notifier(&sel_netif_netdev_notifier); return 0; } __initcall(sel_netif_init); |
| 6 6 6 6 6 6 6 6 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Fast Userspace Mutexes (which I call "Futexes!"). * (C) Rusty Russell, IBM 2002 * * Generalized futexes, futex requeueing, misc fixes by Ingo Molnar * (C) Copyright 2003 Red Hat Inc, All Rights Reserved * * Removed page pinning, fix privately mapped COW pages and other cleanups * (C) Copyright 2003, 2004 Jamie Lokier * * Robust futex support started by Ingo Molnar * (C) Copyright 2006 Red Hat Inc, All Rights Reserved * Thanks to Thomas Gleixner for suggestions, analysis and fixes. * * PI-futex support started by Ingo Molnar and Thomas Gleixner * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> * Copyright (C) 2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com> * * PRIVATE futexes by Eric Dumazet * Copyright (C) 2007 Eric Dumazet <dada1@cosmosbay.com> * * Requeue-PI support by Darren Hart <dvhltc@us.ibm.com> * Copyright (C) IBM Corporation, 2009 * Thanks to Thomas Gleixner for conceptual design and careful reviews. * * Thanks to Ben LaHaise for yelling "hashed waitqueues" loudly * enough at me, Linus for the original (flawed) idea, Matthew * Kirkwood for proof-of-concept implementation. * * "The futexes are also cursed." * "But they come in a choice of three flavours!" */ #include <linux/compat.h> #include <linux/jhash.h> #include <linux/pagemap.h> #include <linux/debugfs.h> #include <linux/plist.h> #include <linux/memblock.h> #include <linux/fault-inject.h> #include <linux/slab.h> #include "futex.h" #include "../locking/rtmutex_common.h" /* * The base of the bucket array and its size are always used together * (after initialization only in futex_hash()), so ensure that they * reside in the same cacheline. */ static struct { struct futex_hash_bucket *queues; unsigned long hashsize; } __futex_data __read_mostly __aligned(2*sizeof(long)); #define futex_queues (__futex_data.queues) #define futex_hashsize (__futex_data.hashsize) /* * Fault injections for futexes. */ #ifdef CONFIG_FAIL_FUTEX static struct { struct fault_attr attr; bool ignore_private; } fail_futex = { .attr = FAULT_ATTR_INITIALIZER, .ignore_private = false, }; static int __init setup_fail_futex(char *str) { return setup_fault_attr(&fail_futex.attr, str); } __setup("fail_futex=", setup_fail_futex); bool should_fail_futex(bool fshared) { if (fail_futex.ignore_private && !fshared) return false; return should_fail(&fail_futex.attr, 1); } #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS static int __init fail_futex_debugfs(void) { umode_t mode = S_IFREG | S_IRUSR | S_IWUSR; struct dentry *dir; dir = fault_create_debugfs_attr("fail_futex", NULL, &fail_futex.attr); if (IS_ERR(dir)) return PTR_ERR(dir); debugfs_create_bool("ignore-private", mode, dir, &fail_futex.ignore_private); return 0; } late_initcall(fail_futex_debugfs); #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ #endif /* CONFIG_FAIL_FUTEX */ /** * futex_hash - Return the hash bucket in the global hash * @key: Pointer to the futex key for which the hash is calculated * * We hash on the keys returned from get_futex_key (see below) and return the * corresponding hash bucket in the global hash. */ struct futex_hash_bucket *futex_hash(union futex_key *key) { u32 hash = jhash2((u32 *)key, offsetof(typeof(*key), both.offset) / 4, key->both.offset); return &futex_queues[hash & (futex_hashsize - 1)]; } /** * futex_setup_timer - set up the sleeping hrtimer. * @time: ptr to the given timeout value * @timeout: the hrtimer_sleeper structure to be set up * @flags: futex flags * @range_ns: optional range in ns * * Return: Initialized hrtimer_sleeper structure or NULL if no timeout * value given */ struct hrtimer_sleeper * futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout, int flags, u64 range_ns) { if (!time) return NULL; hrtimer_setup_sleeper_on_stack(timeout, (flags & FLAGS_CLOCKRT) ? CLOCK_REALTIME : CLOCK_MONOTONIC, HRTIMER_MODE_ABS); /* * If range_ns is 0, calling hrtimer_set_expires_range_ns() is * effectively the same as calling hrtimer_set_expires(). */ hrtimer_set_expires_range_ns(&timeout->timer, *time, range_ns); return timeout; } /* * Generate a machine wide unique identifier for this inode. * * This relies on u64 not wrapping in the life-time of the machine; which with * 1ns resolution means almost 585 years. * * This further relies on the fact that a well formed program will not unmap * the file while it has a (shared) futex waiting on it. This mapping will have * a file reference which pins the mount and inode. * * If for some reason an inode gets evicted and read back in again, it will get * a new sequence number and will _NOT_ match, even though it is the exact same * file. * * It is important that futex_match() will never have a false-positive, esp. * for PI futexes that can mess up the state. The above argues that false-negatives * are only possible for malformed programs. */ static u64 get_inode_sequence_number(struct inode *inode) { static atomic64_t i_seq; u64 old; /* Does the inode already have a sequence number? */ old = atomic64_read(&inode->i_sequence); if (likely(old)) return old; for (;;) { u64 new = atomic64_inc_return(&i_seq); if (WARN_ON_ONCE(!new)) continue; old = 0; if (!atomic64_try_cmpxchg_relaxed(&inode->i_sequence, &old, new)) return old; return new; } } /** * get_futex_key() - Get parameters which are the keys for a futex * @uaddr: virtual address of the futex * @flags: FLAGS_* * @key: address where result is stored. * @rw: mapping needs to be read/write (values: FUTEX_READ, * FUTEX_WRITE) * * Return: a negative error code or 0 * * The key words are stored in @key on success. * * For shared mappings (when @fshared), the key is: * * ( inode->i_sequence, page->index, offset_within_page ) * * [ also see get_inode_sequence_number() ] * * For private mappings (or when !@fshared), the key is: * * ( current->mm, address, 0 ) * * This allows (cross process, where applicable) identification of the futex * without keeping the page pinned for the duration of the FUTEX_WAIT. * * lock_page() might sleep, the caller should not hold a spinlock. */ int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key, enum futex_access rw) { unsigned long address = (unsigned long)uaddr; struct mm_struct *mm = current->mm; struct page *page; struct folio *folio; struct address_space *mapping; int err, ro = 0; bool fshared; fshared = flags & FLAGS_SHARED; /* * The futex address must be "naturally" aligned. */ key->both.offset = address % PAGE_SIZE; if (unlikely((address % sizeof(u32)) != 0)) return -EINVAL; address -= key->both.offset; if (unlikely(!access_ok(uaddr, sizeof(u32)))) return -EFAULT; if (unlikely(should_fail_futex(fshared))) return -EFAULT; /* * PROCESS_PRIVATE futexes are fast. * As the mm cannot disappear under us and the 'key' only needs * virtual address, we dont even have to find the underlying vma. * Note : We do have to check 'uaddr' is a valid user address, * but access_ok() should be faster than find_vma() */ if (!fshared) { /* * On no-MMU, shared futexes are treated as private, therefore * we must not include the current process in the key. Since * there is only one address space, the address is a unique key * on its own. */ if (IS_ENABLED(CONFIG_MMU)) key->private.mm = mm; else key->private.mm = NULL; key->private.address = address; return 0; } again: /* Ignore any VERIFY_READ mapping (futex common case) */ if (unlikely(should_fail_futex(true))) return -EFAULT; err = get_user_pages_fast(address, 1, FOLL_WRITE, &page); /* * If write access is not required (eg. FUTEX_WAIT), try * and get read-only access. */ if (err == -EFAULT && rw == FUTEX_READ) { err = get_user_pages_fast(address, 1, 0, &page); ro = 1; } if (err < 0) return err; else err = 0; /* * The treatment of mapping from this point on is critical. The folio * lock protects many things but in this context the folio lock * stabilizes mapping, prevents inode freeing in the shared * file-backed region case and guards against movement to swap cache. * * Strictly speaking the folio lock is not needed in all cases being * considered here and folio lock forces unnecessarily serialization. * From this point on, mapping will be re-verified if necessary and * folio lock will be acquired only if it is unavoidable * * Mapping checks require the folio so it is looked up now. For * anonymous pages, it does not matter if the folio is split * in the future as the key is based on the address. For * filesystem-backed pages, the precise page is required as the * index of the page determines the key. */ folio = page_folio(page); mapping = READ_ONCE(folio->mapping); /* * If folio->mapping is NULL, then it cannot be an anonymous * page; but it might be the ZERO_PAGE or in the gate area or * in a special mapping (all cases which we are happy to fail); * or it may have been a good file page when get_user_pages_fast * found it, but truncated or holepunched or subjected to * invalidate_complete_page2 before we got the folio lock (also * cases which we are happy to fail). And we hold a reference, * so refcount care in invalidate_inode_page's remove_mapping * prevents drop_caches from setting mapping to NULL beneath us. * * The case we do have to guard against is when memory pressure made * shmem_writepage move it from filecache to swapcache beneath us: * an unlikely race, but we do need to retry for folio->mapping. */ if (unlikely(!mapping)) { int shmem_swizzled; /* * Folio lock is required to identify which special case above * applies. If this is really a shmem page then the folio lock * will prevent unexpected transitions. */ folio_lock(folio); shmem_swizzled = folio_test_swapcache(folio) || folio->mapping; folio_unlock(folio); folio_put(folio); if (shmem_swizzled) goto again; return -EFAULT; } /* * Private mappings are handled in a simple way. * * If the futex key is stored in anonymous memory, then the associated * object is the mm which is implicitly pinned by the calling process. * * NOTE: When userspace waits on a MAP_SHARED mapping, even if * it's a read-only handle, it's expected that futexes attach to * the object not the particular process. */ if (folio_test_anon(folio)) { /* * A RO anonymous page will never change and thus doesn't make * sense for futex operations. */ if (unlikely(should_fail_futex(true)) || ro) { err = -EFAULT; goto out; } key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */ key->private.mm = mm; key->private.address = address; } else { struct inode *inode; /* * The associated futex object in this case is the inode and * the folio->mapping must be traversed. Ordinarily this should * be stabilised under folio lock but it's not strictly * necessary in this case as we just want to pin the inode, not * update i_pages or anything like that. * * The RCU read lock is taken as the inode is finally freed * under RCU. If the mapping still matches expectations then the * mapping->host can be safely accessed as being a valid inode. */ rcu_read_lock(); if (READ_ONCE(folio->mapping) != mapping) { rcu_read_unlock(); folio_put(folio); goto again; } inode = READ_ONCE(mapping->host); if (!inode) { rcu_read_unlock(); folio_put(folio); goto again; } key->both.offset |= FUT_OFF_INODE; /* inode-based key */ key->shared.i_seq = get_inode_sequence_number(inode); key->shared.pgoff = page_pgoff(folio, page); rcu_read_unlock(); } out: folio_put(folio); return err; } /** * fault_in_user_writeable() - Fault in user address and verify RW access * @uaddr: pointer to faulting user space address * * Slow path to fixup the fault we just took in the atomic write * access to @uaddr. * * We have no generic implementation of a non-destructive write to the * user address. We know that we faulted in the atomic pagefault * disabled section so we can as well avoid the #PF overhead by * calling get_user_pages() right away. */ int fault_in_user_writeable(u32 __user *uaddr) { struct mm_struct *mm = current->mm; int ret; mmap_read_lock(mm); ret = fixup_user_fault(mm, (unsigned long)uaddr, FAULT_FLAG_WRITE, NULL); mmap_read_unlock(mm); return ret < 0 ? ret : 0; } /** * futex_top_waiter() - Return the highest priority waiter on a futex * @hb: the hash bucket the futex_q's reside in * @key: the futex key (to distinguish it from other futex futex_q's) * * Must be called with the hb lock held. */ struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb, union futex_key *key) { struct futex_q *this; plist_for_each_entry(this, &hb->chain, list) { if (futex_match(&this->key, key)) return this; } return NULL; } /** * wait_for_owner_exiting - Block until the owner has exited * @ret: owner's current futex lock status * @exiting: Pointer to the exiting task * * Caller must hold a refcount on @exiting. */ void wait_for_owner_exiting(int ret, struct task_struct *exiting) { if (ret != -EBUSY) { WARN_ON_ONCE(exiting); return; } if (WARN_ON_ONCE(ret == -EBUSY && !exiting)) return; mutex_lock(&exiting->futex_exit_mutex); /* * No point in doing state checking here. If the waiter got here * while the task was in exec()->exec_futex_release() then it can * have any FUTEX_STATE_* value when the waiter has acquired the * mutex. OK, if running, EXITING or DEAD if it reached exit() * already. Highly unlikely and not a problem. Just one more round * through the futex maze. */ mutex_unlock(&exiting->futex_exit_mutex); put_task_struct(exiting); } /** * __futex_unqueue() - Remove the futex_q from its futex_hash_bucket * @q: The futex_q to unqueue * * The q->lock_ptr must not be NULL and must be held by the caller. */ void __futex_unqueue(struct futex_q *q) { struct futex_hash_bucket *hb; if (WARN_ON_SMP(!q->lock_ptr) || WARN_ON(plist_node_empty(&q->list))) return; lockdep_assert_held(q->lock_ptr); hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock); plist_del(&q->list, &hb->chain); futex_hb_waiters_dec(hb); } /* The key must be already stored in q->key. */ struct futex_hash_bucket *futex_q_lock(struct futex_q *q) __acquires(&hb->lock) { struct futex_hash_bucket *hb; hb = futex_hash(&q->key); /* * Increment the counter before taking the lock so that * a potential waker won't miss a to-be-slept task that is * waiting for the spinlock. This is safe as all futex_q_lock() * users end up calling futex_queue(). Similarly, for housekeeping, * decrement the counter at futex_q_unlock() when some error has * occurred and we don't end up adding the task to the list. */ futex_hb_waiters_inc(hb); /* implies smp_mb(); (A) */ q->lock_ptr = &hb->lock; spin_lock(&hb->lock); return hb; } void futex_q_unlock(struct futex_hash_bucket *hb) __releases(&hb->lock) { spin_unlock(&hb->lock); futex_hb_waiters_dec(hb); } void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb) { int prio; /* * The priority used to register this element is * - either the real thread-priority for the real-time threads * (i.e. threads with a priority lower than MAX_RT_PRIO) * - or MAX_RT_PRIO for non-RT threads. * Thus, all RT-threads are woken first in priority order, and * the others are woken last, in FIFO order. */ prio = min(current->normal_prio, MAX_RT_PRIO); plist_node_init(&q->list, prio); plist_add(&q->list, &hb->chain); q->task = current; } /** * futex_unqueue() - Remove the futex_q from its futex_hash_bucket * @q: The futex_q to unqueue * * The q->lock_ptr must not be held by the caller. A call to futex_unqueue() must * be paired with exactly one earlier call to futex_queue(). * * Return: * - 1 - if the futex_q was still queued (and we removed unqueued it); * - 0 - if the futex_q was already removed by the waking thread */ int futex_unqueue(struct futex_q *q) { spinlock_t *lock_ptr; int ret = 0; /* In the common case we don't take the spinlock, which is nice. */ retry: /* * q->lock_ptr can change between this read and the following spin_lock. * Use READ_ONCE to forbid the compiler from reloading q->lock_ptr and * optimizing lock_ptr out of the logic below. */ lock_ptr = READ_ONCE(q->lock_ptr); if (lock_ptr != NULL) { spin_lock(lock_ptr); /* * q->lock_ptr can change between reading it and * spin_lock(), causing us to take the wrong lock. This * corrects the race condition. * * Reasoning goes like this: if we have the wrong lock, * q->lock_ptr must have changed (maybe several times) * between reading it and the spin_lock(). It can * change again after the spin_lock() but only if it was * already changed before the spin_lock(). It cannot, * however, change back to the original value. Therefore * we can detect whether we acquired the correct lock. */ if (unlikely(lock_ptr != q->lock_ptr)) { spin_unlock(lock_ptr); goto retry; } __futex_unqueue(q); BUG_ON(q->pi_state); spin_unlock(lock_ptr); ret = 1; } return ret; } /* * PI futexes can not be requeued and must remove themselves from the hash * bucket. The hash bucket lock (i.e. lock_ptr) is held. */ void futex_unqueue_pi(struct futex_q *q) { /* * If the lock was not acquired (due to timeout or signal) then the * rt_waiter is removed before futex_q is. If this is observed by * an unlocker after dropping the rtmutex wait lock and before * acquiring the hash bucket lock, then the unlocker dequeues the * futex_q from the hash bucket list to guarantee consistent state * vs. userspace. Therefore the dequeue here must be conditional. */ if (!plist_node_empty(&q->list)) __futex_unqueue(q); BUG_ON(!q->pi_state); put_pi_state(q->pi_state); q->pi_state = NULL; } /* Constants for the pending_op argument of handle_futex_death */ #define HANDLE_DEATH_PENDING true #define HANDLE_DEATH_LIST false /* * Process a futex-list entry, check whether it's owned by the * dying task, and do notification if so: */ static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, bool pi, bool pending_op) { u32 uval, nval, mval; pid_t owner; int err; /* Futex address must be 32bit aligned */ if ((((unsigned long)uaddr) % sizeof(*uaddr)) != 0) return -1; retry: if (get_user(uval, uaddr)) return -1; /* * Special case for regular (non PI) futexes. The unlock path in * user space has two race scenarios: * * 1. The unlock path releases the user space futex value and * before it can execute the futex() syscall to wake up * waiters it is killed. * * 2. A woken up waiter is killed before it can acquire the * futex in user space. * * In the second case, the wake up notification could be generated * by the unlock path in user space after setting the futex value * to zero or by the kernel after setting the OWNER_DIED bit below. * * In both cases the TID validation below prevents a wakeup of * potential waiters which can cause these waiters to block * forever. * * In both cases the following conditions are met: * * 1) task->robust_list->list_op_pending != NULL * @pending_op == true * 2) The owner part of user space futex value == 0 * 3) Regular futex: @pi == false * * If these conditions are met, it is safe to attempt waking up a * potential waiter without touching the user space futex value and * trying to set the OWNER_DIED bit. If the futex value is zero, * the rest of the user space mutex state is consistent, so a woken * waiter will just take over the uncontended futex. Setting the * OWNER_DIED bit would create inconsistent state and malfunction * of the user space owner died handling. Otherwise, the OWNER_DIED * bit is already set, and the woken waiter is expected to deal with * this. */ owner = uval & FUTEX_TID_MASK; if (pending_op && !pi && !owner) { futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1, FUTEX_BITSET_MATCH_ANY); return 0; } if (owner != task_pid_vnr(curr)) return 0; /* * Ok, this dying thread is truly holding a futex * of interest. Set the OWNER_DIED bit atomically * via cmpxchg, and if the value had FUTEX_WAITERS * set, wake up a waiter (if any). (We have to do a * futex_wake() even if OWNER_DIED is already set - * to handle the rare but possible case of recursive * thread-death.) The rest of the cleanup is done in * userspace. */ mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED; /* * We are not holding a lock here, but we want to have * the pagefault_disable/enable() protection because * we want to handle the fault gracefully. If the * access fails we try to fault in the futex with R/W * verification via get_user_pages. get_user() above * does not guarantee R/W access. If that fails we * give up and leave the futex locked. */ if ((err = futex_cmpxchg_value_locked(&nval, uaddr, uval, mval))) { switch (err) { case -EFAULT: if (fault_in_user_writeable(uaddr)) return -1; goto retry; case -EAGAIN: cond_resched(); goto retry; default: WARN_ON_ONCE(1); return err; } } if (nval != uval) goto retry; /* * Wake robust non-PI futexes here. The wakeup of * PI futexes happens in exit_pi_state(): */ if (!pi && (uval & FUTEX_WAITERS)) { futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1, FUTEX_BITSET_MATCH_ANY); } return 0; } /* * Fetch a robust-list pointer. Bit 0 signals PI futexes: */ static inline int fetch_robust_entry(struct robust_list __user **entry, struct robust_list __user * __user *head, unsigned int *pi) { unsigned long uentry; if (get_user(uentry, (unsigned long __user *)head)) return -EFAULT; *entry = (void __user *)(uentry & ~1UL); *pi = uentry & 1; return 0; } /* * Walk curr->robust_list (very carefully, it's a userspace list!) * and mark any locks found there dead, and notify any waiters. * * We silently return on any sign of list-walking problem. */ static void exit_robust_list(struct task_struct *curr) { struct robust_list_head __user *head = curr->robust_list; struct robust_list __user *entry, *next_entry, *pending; unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; unsigned int next_pi; unsigned long futex_offset; int rc; /* * Fetch the list head (which was registered earlier, via * sys_set_robust_list()): */ if (fetch_robust_entry(&entry, &head->list.next, &pi)) return; /* * Fetch the relative futex offset: */ if (get_user(futex_offset, &head->futex_offset)) return; /* * Fetch any possibly pending lock-add first, and handle it * if it exists: */ if (fetch_robust_entry(&pending, &head->list_op_pending, &pip)) return; next_entry = NULL; /* avoid warning with gcc */ while (entry != &head->list) { /* * Fetch the next entry in the list before calling * handle_futex_death: */ rc = fetch_robust_entry(&next_entry, &entry->next, &next_pi); /* * A pending lock might already be on the list, so * don't process it twice: */ if (entry != pending) { if (handle_futex_death((void __user *)entry + futex_offset, curr, pi, HANDLE_DEATH_LIST)) return; } if (rc) return; entry = next_entry; pi = next_pi; /* * Avoid excessively long or circular lists: */ if (!--limit) break; cond_resched(); } if (pending) { handle_futex_death((void __user *)pending + futex_offset, curr, pip, HANDLE_DEATH_PENDING); } } #ifdef CONFIG_COMPAT static void __user *futex_uaddr(struct robust_list __user *entry, compat_long_t futex_offset) { compat_uptr_t base = ptr_to_compat(entry); void __user *uaddr = compat_ptr(base + futex_offset); return uaddr; } /* * Fetch a robust-list pointer. Bit 0 signals PI futexes: */ static inline int compat_fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry, compat_uptr_t __user *head, unsigned int *pi) { if (get_user(*uentry, head)) return -EFAULT; *entry = compat_ptr((*uentry) & ~1); *pi = (unsigned int)(*uentry) & 1; return 0; } /* * Walk curr->robust_list (very carefully, it's a userspace list!) * and mark any locks found there dead, and notify any waiters. * * We silently return on any sign of list-walking problem. */ static void compat_exit_robust_list(struct task_struct *curr) { struct compat_robust_list_head __user *head = curr->compat_robust_list; struct robust_list __user *entry, *next_entry, *pending; unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; unsigned int next_pi; compat_uptr_t uentry, next_uentry, upending; compat_long_t futex_offset; int rc; /* * Fetch the list head (which was registered earlier, via * sys_set_robust_list()): */ if (compat_fetch_robust_entry(&uentry, &entry, &head->list.next, &pi)) return; /* * Fetch the relative futex offset: */ if (get_user(futex_offset, &head->futex_offset)) return; /* * Fetch any possibly pending lock-add first, and handle it * if it exists: */ if (compat_fetch_robust_entry(&upending, &pending, &head->list_op_pending, &pip)) return; next_entry = NULL; /* avoid warning with gcc */ while (entry != (struct robust_list __user *) &head->list) { /* * Fetch the next entry in the list before calling * handle_futex_death: */ rc = compat_fetch_robust_entry(&next_uentry, &next_entry, (compat_uptr_t __user *)&entry->next, &next_pi); /* * A pending lock might already be on the list, so * dont process it twice: */ if (entry != pending) { void __user *uaddr = futex_uaddr(entry, futex_offset); if (handle_futex_death(uaddr, curr, pi, HANDLE_DEATH_LIST)) return; } if (rc) return; uentry = next_uentry; entry = next_entry; pi = next_pi; /* * Avoid excessively long or circular lists: */ if (!--limit) break; cond_resched(); } if (pending) { void __user *uaddr = futex_uaddr(pending, futex_offset); handle_futex_death(uaddr, curr, pip, HANDLE_DEATH_PENDING); } } #endif #ifdef CONFIG_FUTEX_PI /* * This task is holding PI mutexes at exit time => bad. * Kernel cleans up PI-state, but userspace is likely hosed. * (Robust-futex cleanup is separate and might save the day for userspace.) */ static void exit_pi_state_list(struct task_struct *curr) { struct list_head *next, *head = &curr->pi_state_list; struct futex_pi_state *pi_state; struct futex_hash_bucket *hb; union futex_key key = FUTEX_KEY_INIT; /* * We are a ZOMBIE and nobody can enqueue itself on * pi_state_list anymore, but we have to be careful * versus waiters unqueueing themselves: */ raw_spin_lock_irq(&curr->pi_lock); while (!list_empty(head)) { next = head->next; pi_state = list_entry(next, struct futex_pi_state, list); key = pi_state->key; hb = futex_hash(&key); /* * We can race against put_pi_state() removing itself from the * list (a waiter going away). put_pi_state() will first * decrement the reference count and then modify the list, so * its possible to see the list entry but fail this reference * acquire. * * In that case; drop the locks to let put_pi_state() make * progress and retry the loop. */ if (!refcount_inc_not_zero(&pi_state->refcount)) { raw_spin_unlock_irq(&curr->pi_lock); cpu_relax(); raw_spin_lock_irq(&curr->pi_lock); continue; } raw_spin_unlock_irq(&curr->pi_lock); spin_lock(&hb->lock); raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); raw_spin_lock(&curr->pi_lock); /* * We dropped the pi-lock, so re-check whether this * task still owns the PI-state: */ if (head->next != next) { /* retain curr->pi_lock for the loop invariant */ raw_spin_unlock(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); put_pi_state(pi_state); continue; } WARN_ON(pi_state->owner != curr); WARN_ON(list_empty(&pi_state->list)); list_del_init(&pi_state->list); pi_state->owner = NULL; raw_spin_unlock(&curr->pi_lock); raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); rt_mutex_futex_unlock(&pi_state->pi_mutex); put_pi_state(pi_state); raw_spin_lock_irq(&curr->pi_lock); } raw_spin_unlock_irq(&curr->pi_lock); } #else static inline void exit_pi_state_list(struct task_struct *curr) { } #endif static void futex_cleanup(struct task_struct *tsk) { if (unlikely(tsk->robust_list)) { exit_robust_list(tsk); tsk->robust_list = NULL; } #ifdef CONFIG_COMPAT if (unlikely(tsk->compat_robust_list)) { compat_exit_robust_list(tsk); tsk->compat_robust_list = NULL; } #endif if (unlikely(!list_empty(&tsk->pi_state_list))) exit_pi_state_list(tsk); } /** * futex_exit_recursive - Set the tasks futex state to FUTEX_STATE_DEAD * @tsk: task to set the state on * * Set the futex exit state of the task lockless. The futex waiter code * observes that state when a task is exiting and loops until the task has * actually finished the futex cleanup. The worst case for this is that the * waiter runs through the wait loop until the state becomes visible. * * This is called from the recursive fault handling path in make_task_dead(). * * This is best effort. Either the futex exit code has run already or * not. If the OWNER_DIED bit has been set on the futex then the waiter can * take it over. If not, the problem is pushed back to user space. If the * futex exit code did not run yet, then an already queued waiter might * block forever, but there is nothing which can be done about that. */ void futex_exit_recursive(struct task_struct *tsk) { /* If the state is FUTEX_STATE_EXITING then futex_exit_mutex is held */ if (tsk->futex_state == FUTEX_STATE_EXITING) mutex_unlock(&tsk->futex_exit_mutex); tsk->futex_state = FUTEX_STATE_DEAD; } static void futex_cleanup_begin(struct task_struct *tsk) { /* * Prevent various race issues against a concurrent incoming waiter * including live locks by forcing the waiter to block on * tsk->futex_exit_mutex when it observes FUTEX_STATE_EXITING in * attach_to_pi_owner(). */ mutex_lock(&tsk->futex_exit_mutex); /* * Switch the state to FUTEX_STATE_EXITING under tsk->pi_lock. * * This ensures that all subsequent checks of tsk->futex_state in * attach_to_pi_owner() must observe FUTEX_STATE_EXITING with * tsk->pi_lock held. * * It guarantees also that a pi_state which was queued right before * the state change under tsk->pi_lock by a concurrent waiter must * be observed in exit_pi_state_list(). */ raw_spin_lock_irq(&tsk->pi_lock); tsk->futex_state = FUTEX_STATE_EXITING; raw_spin_unlock_irq(&tsk->pi_lock); } static void futex_cleanup_end(struct task_struct *tsk, int state) { /* * Lockless store. The only side effect is that an observer might * take another loop until it becomes visible. */ tsk->futex_state = state; /* * Drop the exit protection. This unblocks waiters which observed * FUTEX_STATE_EXITING to reevaluate the state. */ mutex_unlock(&tsk->futex_exit_mutex); } void futex_exec_release(struct task_struct *tsk) { /* * The state handling is done for consistency, but in the case of * exec() there is no way to prevent further damage as the PID stays * the same. But for the unlikely and arguably buggy case that a * futex is held on exec(), this provides at least as much state * consistency protection which is possible. */ futex_cleanup_begin(tsk); futex_cleanup(tsk); /* * Reset the state to FUTEX_STATE_OK. The task is alive and about * exec a new binary. */ futex_cleanup_end(tsk, FUTEX_STATE_OK); } void futex_exit_release(struct task_struct *tsk) { futex_cleanup_begin(tsk); futex_cleanup(tsk); futex_cleanup_end(tsk, FUTEX_STATE_DEAD); } static int __init futex_init(void) { unsigned int futex_shift; unsigned long i; #ifdef CONFIG_BASE_SMALL futex_hashsize = 16; #else futex_hashsize = roundup_pow_of_two(256 * num_possible_cpus()); #endif futex_queues = alloc_large_system_hash("futex", sizeof(*futex_queues), futex_hashsize, 0, 0, &futex_shift, NULL, futex_hashsize, futex_hashsize); futex_hashsize = 1UL << futex_shift; for (i = 0; i < futex_hashsize; i++) { atomic_set(&futex_queues[i].waiters, 0); plist_head_init(&futex_queues[i].chain); spin_lock_init(&futex_queues[i].lock); } return 0; } core_initcall(futex_init); |
| 3 3 3 3 3 3 3 3 3 3 3 3 3 3 12 1 10 12 12 12 12 11 12 11 12 12 12 12 12 12 12 12 12 12 12 11 2 9 2 10 12 11 12 12 12 12 11 12 12 12 12 3 3 3 1 1 1 3 3 3 3 3 3 3 3 3 3 3 3 3 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 20 20 19 20 20 3 7 6 7 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 9635 9636 9637 9638 9639 9640 9641 9642 9643 9644 9645 9646 9647 9648 9649 9650 9651 9652 9653 9654 9655 9656 9657 9658 9659 9660 9661 9662 9663 9664 9665 9666 9667 9668 9669 9670 9671 9672 9673 9674 9675 9676 9677 9678 9679 9680 9681 9682 9683 9684 9685 9686 9687 9688 9689 9690 9691 9692 9693 9694 9695 9696 9697 9698 9699 9700 9701 9702 9703 9704 9705 9706 9707 9708 9709 9710 9711 9712 9713 9714 9715 9716 9717 9718 9719 9720 9721 9722 9723 9724 9725 9726 9727 9728 9729 9730 9731 9732 9733 9734 9735 9736 9737 9738 9739 9740 9741 9742 9743 9744 9745 9746 9747 9748 9749 9750 9751 9752 9753 9754 9755 9756 9757 9758 9759 9760 9761 9762 9763 9764 9765 9766 9767 9768 9769 9770 9771 9772 9773 9774 9775 9776 9777 9778 9779 9780 9781 9782 9783 9784 9785 9786 9787 9788 9789 9790 9791 9792 9793 9794 9795 9796 9797 9798 9799 9800 9801 9802 9803 9804 9805 9806 9807 9808 9809 9810 9811 9812 9813 9814 9815 9816 9817 9818 9819 9820 9821 9822 9823 9824 9825 9826 9827 9828 9829 9830 9831 9832 9833 9834 9835 9836 9837 9838 9839 9840 9841 9842 9843 9844 9845 9846 9847 9848 9849 9850 9851 9852 9853 9854 9855 9856 9857 9858 9859 9860 9861 9862 9863 9864 9865 9866 9867 9868 9869 9870 9871 9872 9873 9874 9875 9876 9877 9878 9879 9880 9881 9882 9883 9884 9885 9886 9887 9888 9889 9890 9891 9892 9893 9894 9895 9896 9897 9898 9899 9900 9901 9902 9903 9904 9905 9906 9907 9908 9909 9910 9911 9912 9913 9914 9915 9916 9917 9918 9919 9920 9921 9922 9923 9924 9925 9926 9927 9928 9929 9930 9931 9932 9933 9934 9935 9936 9937 9938 9939 9940 9941 9942 9943 9944 9945 9946 9947 9948 9949 9950 9951 9952 9953 9954 9955 9956 9957 9958 9959 9960 9961 9962 9963 9964 9965 9966 9967 9968 9969 9970 9971 9972 9973 9974 9975 9976 9977 9978 9979 9980 9981 9982 9983 9984 9985 9986 9987 9988 9989 9990 9991 9992 9993 9994 9995 9996 9997 9998 9999 10000 10001 10002 10003 10004 10005 10006 10007 10008 10009 10010 10011 10012 10013 10014 10015 10016 10017 10018 10019 10020 10021 10022 10023 10024 10025 10026 10027 10028 10029 10030 10031 10032 10033 10034 10035 10036 10037 10038 10039 10040 10041 10042 10043 10044 10045 10046 10047 10048 10049 10050 10051 10052 10053 10054 10055 10056 10057 10058 10059 10060 10061 10062 10063 10064 10065 10066 10067 10068 10069 10070 10071 10072 10073 10074 10075 10076 10077 10078 10079 10080 10081 10082 10083 10084 10085 10086 10087 10088 10089 10090 10091 10092 10093 10094 10095 10096 10097 10098 10099 10100 10101 10102 10103 10104 10105 10106 10107 10108 10109 10110 10111 10112 10113 10114 10115 10116 10117 10118 10119 10120 10121 10122 10123 10124 10125 10126 10127 10128 10129 10130 10131 10132 10133 10134 10135 10136 10137 10138 10139 10140 10141 10142 10143 10144 10145 10146 10147 10148 10149 10150 10151 10152 10153 10154 10155 10156 10157 10158 10159 10160 10161 10162 10163 10164 10165 10166 10167 10168 10169 10170 10171 10172 10173 10174 10175 10176 10177 10178 10179 10180 10181 10182 10183 10184 10185 10186 10187 10188 10189 10190 10191 10192 10193 10194 10195 10196 10197 10198 10199 10200 10201 10202 10203 10204 10205 10206 10207 10208 10209 10210 10211 10212 10213 10214 10215 10216 10217 10218 10219 10220 10221 10222 10223 10224 10225 10226 10227 10228 10229 10230 10231 10232 10233 10234 10235 10236 10237 10238 10239 10240 10241 10242 10243 10244 10245 10246 10247 10248 10249 10250 10251 10252 10253 10254 10255 10256 10257 10258 10259 10260 10261 10262 10263 10264 10265 10266 10267 10268 10269 10270 10271 10272 10273 10274 10275 10276 10277 10278 10279 10280 10281 10282 10283 10284 10285 10286 10287 10288 10289 10290 10291 10292 10293 10294 10295 10296 10297 10298 10299 10300 10301 10302 10303 10304 10305 10306 10307 10308 10309 10310 10311 10312 10313 10314 10315 10316 10317 10318 10319 10320 10321 10322 10323 10324 10325 10326 10327 10328 10329 10330 10331 10332 10333 10334 10335 10336 10337 10338 10339 10340 10341 10342 10343 10344 10345 10346 10347 10348 10349 10350 10351 10352 10353 10354 10355 10356 10357 10358 10359 10360 10361 10362 10363 10364 10365 10366 10367 10368 10369 10370 10371 10372 10373 10374 10375 10376 10377 10378 10379 10380 10381 10382 10383 10384 10385 10386 10387 10388 10389 10390 10391 10392 10393 10394 10395 10396 10397 10398 10399 10400 10401 10402 10403 10404 10405 10406 10407 10408 10409 10410 10411 10412 10413 10414 10415 10416 10417 10418 10419 10420 10421 10422 10423 10424 10425 10426 10427 10428 10429 10430 10431 10432 10433 10434 10435 10436 10437 10438 10439 10440 10441 10442 10443 10444 10445 10446 10447 10448 10449 10450 10451 10452 10453 10454 10455 10456 10457 10458 10459 10460 10461 10462 10463 10464 10465 10466 10467 10468 10469 10470 10471 10472 10473 10474 10475 10476 10477 10478 10479 10480 10481 10482 10483 10484 10485 10486 10487 10488 10489 10490 10491 10492 10493 10494 10495 10496 10497 10498 10499 10500 10501 10502 10503 10504 10505 10506 10507 10508 10509 10510 10511 10512 10513 10514 10515 10516 10517 10518 10519 10520 10521 10522 10523 10524 10525 10526 10527 10528 10529 10530 10531 10532 10533 10534 10535 10536 10537 10538 10539 10540 10541 10542 10543 10544 10545 10546 10547 10548 10549 10550 10551 10552 10553 10554 10555 10556 10557 10558 10559 10560 10561 10562 10563 10564 10565 10566 10567 10568 10569 10570 10571 10572 10573 10574 10575 10576 10577 10578 10579 10580 10581 10582 10583 10584 10585 10586 10587 10588 10589 10590 10591 10592 10593 10594 10595 10596 10597 10598 10599 10600 10601 10602 10603 10604 10605 10606 10607 10608 10609 10610 10611 10612 10613 10614 10615 10616 10617 10618 10619 10620 10621 10622 10623 10624 10625 10626 10627 10628 10629 10630 10631 10632 10633 10634 10635 10636 10637 10638 10639 10640 10641 10642 10643 10644 10645 10646 10647 10648 10649 10650 10651 10652 10653 10654 10655 10656 10657 10658 10659 10660 10661 10662 10663 10664 10665 10666 10667 10668 10669 10670 10671 10672 10673 10674 10675 10676 10677 10678 10679 10680 10681 10682 10683 10684 10685 10686 10687 10688 10689 10690 10691 10692 10693 10694 10695 10696 10697 10698 10699 10700 10701 10702 10703 10704 10705 10706 10707 10708 10709 10710 10711 10712 10713 10714 10715 10716 10717 10718 10719 10720 10721 10722 10723 10724 10725 10726 10727 10728 10729 10730 10731 10732 10733 10734 10735 10736 10737 10738 10739 10740 10741 10742 10743 10744 10745 10746 10747 10748 10749 10750 10751 10752 10753 10754 10755 10756 10757 10758 10759 10760 10761 10762 10763 10764 10765 10766 10767 10768 10769 10770 10771 10772 10773 10774 10775 10776 10777 10778 10779 10780 10781 10782 10783 10784 10785 10786 10787 10788 10789 10790 10791 10792 10793 10794 10795 10796 10797 10798 10799 10800 10801 10802 10803 10804 10805 10806 10807 10808 10809 10810 10811 10812 10813 10814 10815 10816 10817 10818 10819 10820 10821 10822 10823 10824 10825 10826 10827 10828 10829 10830 10831 10832 10833 10834 10835 10836 10837 10838 10839 10840 10841 10842 10843 10844 10845 10846 10847 10848 10849 10850 10851 10852 10853 10854 10855 10856 10857 10858 10859 10860 10861 10862 10863 10864 10865 10866 10867 10868 10869 10870 10871 10872 10873 10874 10875 10876 10877 10878 10879 10880 10881 10882 10883 10884 10885 10886 10887 10888 10889 10890 10891 10892 10893 10894 10895 10896 10897 10898 10899 10900 10901 10902 10903 10904 10905 10906 10907 10908 10909 10910 10911 10912 10913 10914 10915 10916 10917 10918 10919 10920 10921 10922 10923 10924 10925 10926 10927 10928 10929 10930 10931 10932 10933 10934 10935 10936 10937 10938 10939 10940 10941 10942 10943 10944 10945 10946 10947 10948 10949 10950 10951 10952 10953 10954 10955 10956 10957 10958 10959 10960 10961 10962 10963 10964 10965 10966 10967 10968 10969 10970 10971 10972 10973 10974 10975 10976 10977 10978 10979 10980 10981 10982 10983 10984 10985 10986 10987 10988 10989 10990 10991 10992 10993 10994 10995 10996 10997 10998 10999 11000 11001 11002 11003 11004 11005 11006 11007 11008 11009 11010 11011 11012 11013 11014 11015 11016 11017 11018 11019 11020 11021 11022 11023 11024 11025 11026 11027 11028 11029 11030 11031 11032 11033 11034 11035 11036 11037 11038 11039 11040 11041 11042 11043 11044 11045 11046 11047 11048 11049 11050 11051 11052 11053 11054 11055 11056 11057 11058 11059 11060 11061 11062 11063 11064 11065 11066 11067 11068 11069 11070 11071 11072 11073 11074 11075 11076 11077 11078 11079 11080 11081 11082 11083 11084 11085 11086 11087 11088 11089 11090 11091 11092 11093 11094 11095 11096 11097 11098 11099 11100 11101 11102 11103 11104 11105 11106 11107 11108 11109 11110 11111 11112 11113 11114 11115 11116 11117 11118 11119 11120 11121 11122 11123 11124 11125 11126 11127 11128 11129 11130 11131 11132 11133 11134 11135 11136 11137 11138 11139 11140 11141 11142 11143 11144 11145 11146 11147 11148 11149 11150 11151 11152 11153 11154 11155 11156 11157 11158 11159 11160 11161 11162 11163 11164 11165 11166 11167 11168 11169 11170 11171 11172 11173 11174 11175 11176 11177 11178 11179 11180 11181 11182 11183 11184 11185 11186 11187 11188 11189 11190 11191 11192 11193 11194 11195 11196 11197 11198 11199 11200 11201 11202 11203 11204 11205 11206 11207 11208 11209 11210 11211 11212 11213 11214 11215 11216 11217 11218 11219 11220 11221 11222 11223 11224 11225 11226 11227 11228 11229 11230 11231 11232 11233 11234 11235 11236 11237 11238 11239 11240 11241 11242 11243 11244 11245 11246 11247 11248 11249 11250 11251 11252 11253 11254 11255 11256 11257 11258 11259 11260 11261 11262 11263 11264 11265 11266 11267 11268 11269 11270 11271 11272 11273 11274 11275 11276 11277 11278 11279 11280 11281 11282 11283 11284 11285 11286 11287 11288 11289 11290 11291 11292 11293 11294 11295 11296 11297 11298 11299 11300 11301 11302 11303 11304 11305 11306 11307 11308 11309 11310 11311 11312 11313 11314 11315 11316 11317 11318 11319 11320 11321 11322 11323 11324 11325 11326 11327 11328 11329 11330 11331 11332 11333 11334 11335 11336 11337 11338 11339 11340 11341 11342 11343 11344 11345 11346 11347 11348 11349 11350 11351 11352 11353 11354 11355 11356 11357 11358 11359 11360 11361 11362 11363 11364 11365 11366 11367 11368 11369 11370 11371 11372 11373 11374 11375 11376 11377 11378 11379 11380 11381 11382 11383 11384 11385 11386 11387 11388 11389 11390 11391 11392 11393 11394 11395 11396 11397 11398 11399 11400 11401 11402 11403 11404 11405 11406 11407 11408 11409 11410 11411 11412 11413 11414 11415 11416 11417 11418 11419 11420 11421 11422 11423 11424 11425 11426 11427 11428 11429 11430 11431 11432 11433 11434 11435 11436 11437 11438 11439 11440 11441 11442 11443 11444 11445 11446 11447 11448 11449 11450 11451 11452 11453 11454 11455 11456 11457 11458 11459 11460 11461 11462 11463 11464 11465 11466 11467 11468 11469 11470 11471 11472 11473 11474 11475 11476 11477 11478 11479 11480 11481 11482 11483 11484 11485 11486 11487 11488 11489 11490 11491 11492 11493 11494 11495 11496 11497 11498 11499 11500 11501 11502 11503 11504 11505 11506 11507 11508 11509 11510 11511 11512 11513 11514 11515 11516 11517 11518 11519 11520 11521 11522 11523 11524 11525 11526 11527 11528 11529 11530 11531 11532 11533 11534 11535 11536 11537 11538 11539 11540 11541 11542 11543 11544 11545 11546 11547 11548 11549 11550 11551 11552 11553 11554 11555 11556 11557 11558 11559 11560 11561 11562 11563 11564 11565 11566 11567 11568 11569 11570 11571 11572 11573 11574 11575 11576 11577 11578 11579 11580 11581 11582 11583 11584 11585 11586 11587 11588 11589 11590 11591 11592 11593 11594 11595 11596 11597 11598 11599 11600 11601 11602 11603 11604 11605 11606 11607 11608 11609 11610 11611 11612 11613 11614 11615 11616 11617 11618 11619 11620 11621 11622 11623 11624 11625 11626 11627 11628 11629 11630 11631 11632 11633 11634 11635 11636 11637 11638 11639 11640 11641 11642 11643 11644 11645 11646 11647 11648 11649 11650 11651 11652 11653 11654 11655 11656 11657 11658 11659 11660 11661 11662 11663 11664 11665 11666 11667 11668 11669 11670 11671 11672 11673 11674 11675 11676 11677 11678 11679 11680 11681 11682 11683 11684 11685 11686 11687 11688 11689 11690 11691 11692 11693 11694 11695 11696 11697 11698 11699 11700 11701 11702 11703 11704 11705 11706 11707 11708 11709 11710 11711 11712 11713 11714 11715 11716 11717 11718 11719 11720 11721 11722 11723 11724 11725 11726 11727 11728 11729 11730 11731 11732 11733 11734 11735 11736 11737 11738 11739 11740 11741 11742 11743 11744 11745 11746 11747 11748 11749 11750 11751 11752 11753 11754 11755 11756 11757 11758 11759 11760 11761 11762 11763 11764 11765 11766 11767 11768 11769 11770 11771 11772 11773 11774 11775 11776 11777 11778 11779 11780 11781 11782 11783 11784 11785 11786 11787 11788 11789 11790 11791 11792 11793 11794 11795 11796 11797 11798 11799 11800 11801 11802 11803 11804 11805 11806 11807 11808 11809 11810 11811 11812 11813 11814 11815 11816 11817 11818 11819 11820 11821 11822 11823 11824 11825 11826 11827 11828 11829 11830 11831 11832 11833 11834 11835 11836 11837 11838 11839 11840 11841 11842 11843 11844 11845 11846 11847 11848 11849 11850 11851 11852 11853 11854 11855 11856 11857 11858 11859 11860 11861 11862 11863 11864 11865 11866 11867 11868 11869 11870 11871 11872 11873 11874 11875 11876 11877 11878 11879 11880 11881 11882 11883 11884 11885 11886 11887 11888 11889 11890 11891 11892 11893 11894 11895 11896 11897 11898 11899 11900 11901 11902 11903 11904 11905 11906 11907 11908 11909 11910 11911 11912 11913 11914 11915 11916 11917 11918 11919 11920 11921 11922 11923 11924 11925 11926 11927 11928 11929 11930 11931 11932 11933 11934 11935 11936 11937 11938 11939 11940 11941 11942 11943 11944 11945 11946 11947 11948 11949 11950 11951 11952 11953 11954 11955 11956 11957 11958 11959 11960 11961 11962 11963 11964 11965 11966 11967 11968 11969 11970 11971 11972 11973 11974 11975 11976 11977 11978 11979 11980 11981 11982 11983 11984 11985 11986 11987 11988 11989 11990 11991 11992 11993 11994 11995 11996 11997 11998 11999 12000 12001 12002 12003 12004 12005 12006 12007 12008 12009 12010 12011 12012 12013 12014 12015 12016 12017 12018 12019 12020 12021 12022 12023 12024 12025 12026 12027 12028 12029 12030 12031 12032 12033 12034 12035 12036 12037 12038 12039 12040 12041 12042 12043 12044 12045 12046 12047 12048 12049 12050 12051 12052 12053 12054 12055 12056 12057 12058 12059 12060 12061 12062 12063 12064 12065 12066 12067 12068 12069 12070 12071 12072 12073 12074 12075 12076 12077 12078 12079 12080 12081 12082 12083 12084 12085 12086 12087 12088 12089 12090 12091 12092 12093 12094 12095 12096 12097 12098 12099 12100 12101 12102 12103 12104 12105 12106 12107 12108 12109 12110 12111 12112 12113 12114 12115 12116 12117 12118 12119 12120 12121 12122 12123 12124 12125 12126 12127 12128 12129 12130 12131 12132 12133 12134 12135 12136 12137 12138 12139 12140 12141 12142 12143 12144 12145 12146 12147 12148 12149 12150 12151 12152 12153 12154 12155 12156 12157 12158 12159 12160 12161 12162 12163 12164 12165 12166 12167 12168 12169 12170 12171 12172 12173 12174 12175 12176 12177 12178 12179 12180 12181 12182 12183 12184 12185 12186 12187 12188 12189 12190 12191 12192 12193 12194 12195 12196 12197 12198 12199 12200 12201 12202 12203 12204 12205 12206 12207 12208 12209 12210 12211 12212 12213 12214 12215 12216 12217 12218 12219 12220 12221 12222 12223 12224 12225 12226 12227 12228 12229 12230 12231 12232 12233 12234 12235 12236 12237 12238 12239 12240 12241 12242 12243 12244 12245 12246 12247 12248 12249 12250 12251 12252 12253 12254 12255 12256 12257 12258 12259 12260 12261 12262 12263 12264 12265 12266 12267 12268 12269 12270 12271 12272 12273 12274 12275 12276 12277 12278 12279 12280 12281 12282 12283 12284 12285 12286 12287 12288 12289 12290 12291 12292 12293 12294 12295 12296 12297 12298 12299 12300 12301 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NET3 Protocol independent device support routines. * * Derived from the non IP parts of dev.c 1.0.19 * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * * Additional Authors: * Florian la Roche <rzsfl@rz.uni-sb.de> * Alan Cox <gw4pts@gw4pts.ampr.org> * David Hinds <dahinds@users.sourceforge.net> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * Adam Sulmicki <adam@cfar.umd.edu> * Pekka Riikonen <priikone@poesidon.pspt.fi> * * Changes: * D.J. Barrow : Fixed bug where dev->refcnt gets set * to 2 if register_netdev gets called * before net_dev_init & also removed a * few lines of code in the process. * Alan Cox : device private ioctl copies fields back. * Alan Cox : Transmit queue code does relevant * stunts to keep the queue safe. * Alan Cox : Fixed double lock. * Alan Cox : Fixed promisc NULL pointer trap * ???????? : Support the full private ioctl range * Alan Cox : Moved ioctl permission check into * drivers * Tim Kordas : SIOCADDMULTI/SIOCDELMULTI * Alan Cox : 100 backlog just doesn't cut it when * you start doing multicast video 8) * Alan Cox : Rewrote net_bh and list manager. * Alan Cox : Fix ETH_P_ALL echoback lengths. * Alan Cox : Took out transmit every packet pass * Saved a few bytes in the ioctl handler * Alan Cox : Network driver sets packet type before * calling netif_rx. Saves a function * call a packet. * Alan Cox : Hashed net_bh() * Richard Kooijman: Timestamp fixes. * Alan Cox : Wrong field in SIOCGIFDSTADDR * Alan Cox : Device lock protection. * Alan Cox : Fixed nasty side effect of device close * changes. * Rudi Cilibrasi : Pass the right thing to * set_mac_address() * Dave Miller : 32bit quantity for the device lock to * make it work out on a Sparc. * Bjorn Ekwall : Added KERNELD hack. * Alan Cox : Cleaned up the backlog initialise. * Craig Metz : SIOCGIFCONF fix if space for under * 1 device. * Thomas Bogendoerfer : Return ENODEV for dev_open, if there * is no device open function. * Andi Kleen : Fix error reporting for SIOCGIFCONF * Michael Chastain : Fix signed/unsigned for SIOCGIFCONF * Cyrus Durgin : Cleaned for KMOD * Adam Sulmicki : Bug Fix : Network Device Unload * A network device unload needs to purge * the backlog queue. * Paul Rusty Russell : SIOCSIFNAME * Pekka Riikonen : Netdev boot-time settings code * Andrew Morton : Make unregister_netdevice wait * indefinitely on dev->refcnt * J Hadi Salim : - Backlog queue sampling * - netif_rx() feedback */ #include <linux/uaccess.h> #include <linux/bitmap.h> #include <linux/capability.h> #include <linux/cpu.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/hash.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/sched/isolation.h> #include <linux/sched/mm.h> #include <linux/smpboot.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/errno.h> #include <linux/interrupt.h> #include <linux/if_ether.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/skbuff.h> #include <linux/kthread.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/busy_poll.h> #include <linux/rtnetlink.h> #include <linux/stat.h> #include <net/dsa.h> #include <net/dst.h> #include <net/dst_metadata.h> #include <net/gro.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/checksum.h> #include <net/xfrm.h> #include <net/tcx.h> #include <linux/highmem.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netpoll.h> #include <linux/rcupdate.h> #include <linux/delay.h> #include <net/iw_handler.h> #include <asm/current.h> #include <linux/audit.h> #include <linux/dmaengine.h> #include <linux/err.h> #include <linux/ctype.h> #include <linux/if_arp.h> #include <linux/if_vlan.h> #include <linux/ip.h> #include <net/ip.h> #include <net/mpls.h> #include <linux/ipv6.h> #include <linux/in.h> #include <linux/jhash.h> #include <linux/random.h> #include <trace/events/napi.h> #include <trace/events/net.h> #include <trace/events/skb.h> #include <trace/events/qdisc.h> #include <trace/events/xdp.h> #include <linux/inetdevice.h> #include <linux/cpu_rmap.h> #include <linux/static_key.h> #include <linux/hashtable.h> #include <linux/vmalloc.h> #include <linux/if_macvlan.h> #include <linux/errqueue.h> #include <linux/hrtimer.h> #include <linux/netfilter_netdev.h> #include <linux/crash_dump.h> #include <linux/sctp.h> #include <net/udp_tunnel.h> #include <linux/net_namespace.h> #include <linux/indirect_call_wrapper.h> #include <net/devlink.h> #include <linux/pm_runtime.h> #include <linux/prandom.h> #include <linux/once_lite.h> #include <net/netdev_rx_queue.h> #include <net/page_pool/types.h> #include <net/page_pool/helpers.h> #include <net/rps.h> #include <linux/phy_link_topology.h> #include "dev.h" #include "devmem.h" #include "net-sysfs.h" static DEFINE_SPINLOCK(ptype_lock); struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; static int netif_rx_internal(struct sk_buff *skb); static int call_netdevice_notifiers_extack(unsigned long val, struct net_device *dev, struct netlink_ext_ack *extack); static DEFINE_MUTEX(ifalias_mutex); /* protects napi_hash addition/deletion and napi_gen_id */ static DEFINE_SPINLOCK(napi_hash_lock); static unsigned int napi_gen_id = NR_CPUS; static DEFINE_READ_MOSTLY_HASHTABLE(napi_hash, 8); static DECLARE_RWSEM(devnet_rename_sem); static inline void dev_base_seq_inc(struct net *net) { unsigned int val = net->dev_base_seq + 1; WRITE_ONCE(net->dev_base_seq, val ?: 1); } static inline struct hlist_head *dev_name_hash(struct net *net, const char *name) { unsigned int hash = full_name_hash(net, name, strnlen(name, IFNAMSIZ)); return &net->dev_name_head[hash_32(hash, NETDEV_HASHBITS)]; } static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex) { return &net->dev_index_head[ifindex & (NETDEV_HASHENTRIES - 1)]; } #ifndef CONFIG_PREEMPT_RT static DEFINE_STATIC_KEY_FALSE(use_backlog_threads_key); static int __init setup_backlog_napi_threads(char *arg) { static_branch_enable(&use_backlog_threads_key); return 0; } early_param("thread_backlog_napi", setup_backlog_napi_threads); static bool use_backlog_threads(void) { return static_branch_unlikely(&use_backlog_threads_key); } #else static bool use_backlog_threads(void) { return true; } #endif static inline void backlog_lock_irq_save(struct softnet_data *sd, unsigned long *flags) { if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_lock_irqsave(&sd->input_pkt_queue.lock, *flags); else local_irq_save(*flags); } static inline void backlog_lock_irq_disable(struct softnet_data *sd) { if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_lock_irq(&sd->input_pkt_queue.lock); else local_irq_disable(); } static inline void backlog_unlock_irq_restore(struct softnet_data *sd, unsigned long *flags) { if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_unlock_irqrestore(&sd->input_pkt_queue.lock, *flags); else local_irq_restore(*flags); } static inline void backlog_unlock_irq_enable(struct softnet_data *sd) { if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_unlock_irq(&sd->input_pkt_queue.lock); else local_irq_enable(); } static struct netdev_name_node *netdev_name_node_alloc(struct net_device *dev, const char *name) { struct netdev_name_node *name_node; name_node = kmalloc(sizeof(*name_node), GFP_KERNEL); if (!name_node) return NULL; INIT_HLIST_NODE(&name_node->hlist); name_node->dev = dev; name_node->name = name; return name_node; } static struct netdev_name_node * netdev_name_node_head_alloc(struct net_device *dev) { struct netdev_name_node *name_node; name_node = netdev_name_node_alloc(dev, dev->name); if (!name_node) return NULL; INIT_LIST_HEAD(&name_node->list); return name_node; } static void netdev_name_node_free(struct netdev_name_node *name_node) { kfree(name_node); } static void netdev_name_node_add(struct net *net, struct netdev_name_node *name_node) { hlist_add_head_rcu(&name_node->hlist, dev_name_hash(net, name_node->name)); } static void netdev_name_node_del(struct netdev_name_node *name_node) { hlist_del_rcu(&name_node->hlist); } static struct netdev_name_node *netdev_name_node_lookup(struct net *net, const char *name) { struct hlist_head *head = dev_name_hash(net, name); struct netdev_name_node *name_node; hlist_for_each_entry(name_node, head, hlist) if (!strcmp(name_node->name, name)) return name_node; return NULL; } static struct netdev_name_node *netdev_name_node_lookup_rcu(struct net *net, const char *name) { struct hlist_head *head = dev_name_hash(net, name); struct netdev_name_node *name_node; hlist_for_each_entry_rcu(name_node, head, hlist) if (!strcmp(name_node->name, name)) return name_node; return NULL; } bool netdev_name_in_use(struct net *net, const char *name) { return netdev_name_node_lookup(net, name); } EXPORT_SYMBOL(netdev_name_in_use); int netdev_name_node_alt_create(struct net_device *dev, const char *name) { struct netdev_name_node *name_node; struct net *net = dev_net(dev); name_node = netdev_name_node_lookup(net, name); if (name_node) return -EEXIST; name_node = netdev_name_node_alloc(dev, name); if (!name_node) return -ENOMEM; netdev_name_node_add(net, name_node); /* The node that holds dev->name acts as a head of per-device list. */ list_add_tail_rcu(&name_node->list, &dev->name_node->list); return 0; } static void netdev_name_node_alt_free(struct rcu_head *head) { struct netdev_name_node *name_node = container_of(head, struct netdev_name_node, rcu); kfree(name_node->name); netdev_name_node_free(name_node); } static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node) { netdev_name_node_del(name_node); list_del(&name_node->list); call_rcu(&name_node->rcu, netdev_name_node_alt_free); } int netdev_name_node_alt_destroy(struct net_device *dev, const char *name) { struct netdev_name_node *name_node; struct net *net = dev_net(dev); name_node = netdev_name_node_lookup(net, name); if (!name_node) return -ENOENT; /* lookup might have found our primary name or a name belonging * to another device. */ if (name_node == dev->name_node || name_node->dev != dev) return -EINVAL; __netdev_name_node_alt_destroy(name_node); return 0; } static void netdev_name_node_alt_flush(struct net_device *dev) { struct netdev_name_node *name_node, *tmp; list_for_each_entry_safe(name_node, tmp, &dev->name_node->list, list) { list_del(&name_node->list); netdev_name_node_alt_free(&name_node->rcu); } } /* Device list insertion */ static void list_netdevice(struct net_device *dev) { struct netdev_name_node *name_node; struct net *net = dev_net(dev); ASSERT_RTNL(); list_add_tail_rcu(&dev->dev_list, &net->dev_base_head); netdev_name_node_add(net, dev->name_node); hlist_add_head_rcu(&dev->index_hlist, dev_index_hash(net, dev->ifindex)); netdev_for_each_altname(dev, name_node) netdev_name_node_add(net, name_node); /* We reserved the ifindex, this can't fail */ WARN_ON(xa_store(&net->dev_by_index, dev->ifindex, dev, GFP_KERNEL)); dev_base_seq_inc(net); } /* Device list removal * caller must respect a RCU grace period before freeing/reusing dev */ static void unlist_netdevice(struct net_device *dev) { struct netdev_name_node *name_node; struct net *net = dev_net(dev); ASSERT_RTNL(); xa_erase(&net->dev_by_index, dev->ifindex); netdev_for_each_altname(dev, name_node) netdev_name_node_del(name_node); /* Unlink dev from the device chain */ list_del_rcu(&dev->dev_list); netdev_name_node_del(dev->name_node); hlist_del_rcu(&dev->index_hlist); dev_base_seq_inc(dev_net(dev)); } /* * Our notifier list */ static RAW_NOTIFIER_HEAD(netdev_chain); /* * Device drivers call our routines to queue packets here. We empty the * queue in the local softnet handler. */ DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data) = { .process_queue_bh_lock = INIT_LOCAL_LOCK(process_queue_bh_lock), }; EXPORT_PER_CPU_SYMBOL(softnet_data); /* Page_pool has a lockless array/stack to alloc/recycle pages. * PP consumers must pay attention to run APIs in the appropriate context * (e.g. NAPI context). */ static DEFINE_PER_CPU(struct page_pool *, system_page_pool); #ifdef CONFIG_LOCKDEP /* * register_netdevice() inits txq->_xmit_lock and sets lockdep class * according to dev->type */ static const unsigned short netdev_lock_type[] = { ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25, ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET, ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM, ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP, ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD, ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25, ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP, ARPHRD_RAWHDLC, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD, ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI, ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE, ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET, ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL, ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM, ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE, ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE}; static const char *const netdev_lock_name[] = { "_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25", "_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET", "_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM", "_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP", "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD", "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25", "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP", "_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD", "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI", "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE", "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET", "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL", "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM", "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE", "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"}; static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)]; static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)]; static inline unsigned short netdev_lock_pos(unsigned short dev_type) { int i; for (i = 0; i < ARRAY_SIZE(netdev_lock_type); i++) if (netdev_lock_type[i] == dev_type) return i; /* the last key is used by default */ return ARRAY_SIZE(netdev_lock_type) - 1; } static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, unsigned short dev_type) { int i; i = netdev_lock_pos(dev_type); lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i], netdev_lock_name[i]); } static inline void netdev_set_addr_lockdep_class(struct net_device *dev) { int i; i = netdev_lock_pos(dev->type); lockdep_set_class_and_name(&dev->addr_list_lock, &netdev_addr_lock_key[i], netdev_lock_name[i]); } #else static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, unsigned short dev_type) { } static inline void netdev_set_addr_lockdep_class(struct net_device *dev) { } #endif /******************************************************************************* * * Protocol management and registration routines * *******************************************************************************/ /* * Add a protocol ID to the list. Now that the input handler is * smarter we can dispense with all the messy stuff that used to be * here. * * BEWARE!!! Protocol handlers, mangling input packets, * MUST BE last in hash buckets and checking protocol handlers * MUST start from promiscuous ptype_all chain in net_bh. * It is true now, do not change it. * Explanation follows: if protocol handler, mangling packet, will * be the first on list, it is not able to sense, that packet * is cloned and should be copied-on-write, so that it will * change it and subsequent readers will get broken packet. * --ANK (980803) */ static inline struct list_head *ptype_head(const struct packet_type *pt) { if (pt->type == htons(ETH_P_ALL)) return pt->dev ? &pt->dev->ptype_all : &net_hotdata.ptype_all; else return pt->dev ? &pt->dev->ptype_specific : &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK]; } /** * dev_add_pack - add packet handler * @pt: packet type declaration * * Add a protocol handler to the networking stack. The passed &packet_type * is linked into kernel lists and may not be freed until it has been * removed from the kernel lists. * * This call does not sleep therefore it can not * guarantee all CPU's that are in middle of receiving packets * will see the new packet type (until the next received packet). */ void dev_add_pack(struct packet_type *pt) { struct list_head *head = ptype_head(pt); spin_lock(&ptype_lock); list_add_rcu(&pt->list, head); spin_unlock(&ptype_lock); } EXPORT_SYMBOL(dev_add_pack); /** * __dev_remove_pack - remove packet handler * @pt: packet type declaration * * Remove a protocol handler that was previously added to the kernel * protocol handlers by dev_add_pack(). The passed &packet_type is removed * from the kernel lists and can be freed or reused once this function * returns. * * The packet type might still be in use by receivers * and must not be freed until after all the CPU's have gone * through a quiescent state. */ void __dev_remove_pack(struct packet_type *pt) { struct list_head *head = ptype_head(pt); struct packet_type *pt1; spin_lock(&ptype_lock); list_for_each_entry(pt1, head, list) { if (pt == pt1) { list_del_rcu(&pt->list); goto out; } } pr_warn("dev_remove_pack: %p not found\n", pt); out: spin_unlock(&ptype_lock); } EXPORT_SYMBOL(__dev_remove_pack); /** * dev_remove_pack - remove packet handler * @pt: packet type declaration * * Remove a protocol handler that was previously added to the kernel * protocol handlers by dev_add_pack(). The passed &packet_type is removed * from the kernel lists and can be freed or reused once this function * returns. * * This call sleeps to guarantee that no CPU is looking at the packet * type after return. */ void dev_remove_pack(struct packet_type *pt) { __dev_remove_pack(pt); synchronize_net(); } EXPORT_SYMBOL(dev_remove_pack); /******************************************************************************* * * Device Interface Subroutines * *******************************************************************************/ /** * dev_get_iflink - get 'iflink' value of a interface * @dev: targeted interface * * Indicates the ifindex the interface is linked to. * Physical interfaces have the same 'ifindex' and 'iflink' values. */ int dev_get_iflink(const struct net_device *dev) { if (dev->netdev_ops && dev->netdev_ops->ndo_get_iflink) return dev->netdev_ops->ndo_get_iflink(dev); return READ_ONCE(dev->ifindex); } EXPORT_SYMBOL(dev_get_iflink); /** * dev_fill_metadata_dst - Retrieve tunnel egress information. * @dev: targeted interface * @skb: The packet. * * For better visibility of tunnel traffic OVS needs to retrieve * egress tunnel information for a packet. Following API allows * user to get this info. */ int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct ip_tunnel_info *info; if (!dev->netdev_ops || !dev->netdev_ops->ndo_fill_metadata_dst) return -EINVAL; info = skb_tunnel_info_unclone(skb); if (!info) return -ENOMEM; if (unlikely(!(info->mode & IP_TUNNEL_INFO_TX))) return -EINVAL; return dev->netdev_ops->ndo_fill_metadata_dst(dev, skb); } EXPORT_SYMBOL_GPL(dev_fill_metadata_dst); static struct net_device_path *dev_fwd_path(struct net_device_path_stack *stack) { int k = stack->num_paths++; if (WARN_ON_ONCE(k >= NET_DEVICE_PATH_STACK_MAX)) return NULL; return &stack->path[k]; } int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr, struct net_device_path_stack *stack) { const struct net_device *last_dev; struct net_device_path_ctx ctx = { .dev = dev, }; struct net_device_path *path; int ret = 0; memcpy(ctx.daddr, daddr, sizeof(ctx.daddr)); stack->num_paths = 0; while (ctx.dev && ctx.dev->netdev_ops->ndo_fill_forward_path) { last_dev = ctx.dev; path = dev_fwd_path(stack); if (!path) return -1; memset(path, 0, sizeof(struct net_device_path)); ret = ctx.dev->netdev_ops->ndo_fill_forward_path(&ctx, path); if (ret < 0) return -1; if (WARN_ON_ONCE(last_dev == ctx.dev)) return -1; } if (!ctx.dev) return ret; path = dev_fwd_path(stack); if (!path) return -1; path->type = DEV_PATH_ETHERNET; path->dev = ctx.dev; return ret; } EXPORT_SYMBOL_GPL(dev_fill_forward_path); /** * __dev_get_by_name - find a device by its name * @net: the applicable net namespace * @name: name to find * * Find an interface by name. Must be called under RTNL semaphore. * If the name is found a pointer to the device is returned. * If the name is not found then %NULL is returned. The * reference counters are not incremented so the caller must be * careful with locks. */ struct net_device *__dev_get_by_name(struct net *net, const char *name) { struct netdev_name_node *node_name; node_name = netdev_name_node_lookup(net, name); return node_name ? node_name->dev : NULL; } EXPORT_SYMBOL(__dev_get_by_name); /** * dev_get_by_name_rcu - find a device by its name * @net: the applicable net namespace * @name: name to find * * Find an interface by name. * If the name is found a pointer to the device is returned. * If the name is not found then %NULL is returned. * The reference counters are not incremented so the caller must be * careful with locks. The caller must hold RCU lock. */ struct net_device *dev_get_by_name_rcu(struct net *net, const char *name) { struct netdev_name_node *node_name; node_name = netdev_name_node_lookup_rcu(net, name); return node_name ? node_name->dev : NULL; } EXPORT_SYMBOL(dev_get_by_name_rcu); /* Deprecated for new users, call netdev_get_by_name() instead */ struct net_device *dev_get_by_name(struct net *net, const char *name) { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_name_rcu(net, name); dev_hold(dev); rcu_read_unlock(); return dev; } EXPORT_SYMBOL(dev_get_by_name); /** * netdev_get_by_name() - find a device by its name * @net: the applicable net namespace * @name: name to find * @tracker: tracking object for the acquired reference * @gfp: allocation flags for the tracker * * Find an interface by name. This can be called from any * context and does its own locking. The returned handle has * the usage count incremented and the caller must use netdev_put() to * release it when it is no longer needed. %NULL is returned if no * matching device is found. */ struct net_device *netdev_get_by_name(struct net *net, const char *name, netdevice_tracker *tracker, gfp_t gfp) { struct net_device *dev; dev = dev_get_by_name(net, name); if (dev) netdev_tracker_alloc(dev, tracker, gfp); return dev; } EXPORT_SYMBOL(netdev_get_by_name); /** * __dev_get_by_index - find a device by its ifindex * @net: the applicable net namespace * @ifindex: index of device * * Search for an interface by index. Returns %NULL if the device * is not found or a pointer to the device. The device has not * had its reference counter increased so the caller must be careful * about locking. The caller must hold the RTNL semaphore. */ struct net_device *__dev_get_by_index(struct net *net, int ifindex) { struct net_device *dev; struct hlist_head *head = dev_index_hash(net, ifindex); hlist_for_each_entry(dev, head, index_hlist) if (dev->ifindex == ifindex) return dev; return NULL; } EXPORT_SYMBOL(__dev_get_by_index); /** * dev_get_by_index_rcu - find a device by its ifindex * @net: the applicable net namespace * @ifindex: index of device * * Search for an interface by index. Returns %NULL if the device * is not found or a pointer to the device. The device has not * had its reference counter increased so the caller must be careful * about locking. The caller must hold RCU lock. */ struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex) { struct net_device *dev; struct hlist_head *head = dev_index_hash(net, ifindex); hlist_for_each_entry_rcu(dev, head, index_hlist) if (dev->ifindex == ifindex) return dev; return NULL; } EXPORT_SYMBOL(dev_get_by_index_rcu); /* Deprecated for new users, call netdev_get_by_index() instead */ struct net_device *dev_get_by_index(struct net *net, int ifindex) { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); dev_hold(dev); rcu_read_unlock(); return dev; } EXPORT_SYMBOL(dev_get_by_index); /** * netdev_get_by_index() - find a device by its ifindex * @net: the applicable net namespace * @ifindex: index of device * @tracker: tracking object for the acquired reference * @gfp: allocation flags for the tracker * * Search for an interface by index. Returns NULL if the device * is not found or a pointer to the device. The device returned has * had a reference added and the pointer is safe until the user calls * netdev_put() to indicate they have finished with it. */ struct net_device *netdev_get_by_index(struct net *net, int ifindex, netdevice_tracker *tracker, gfp_t gfp) { struct net_device *dev; dev = dev_get_by_index(net, ifindex); if (dev) netdev_tracker_alloc(dev, tracker, gfp); return dev; } EXPORT_SYMBOL(netdev_get_by_index); /** * dev_get_by_napi_id - find a device by napi_id * @napi_id: ID of the NAPI struct * * Search for an interface by NAPI ID. Returns %NULL if the device * is not found or a pointer to the device. The device has not had * its reference counter increased so the caller must be careful * about locking. The caller must hold RCU lock. */ struct net_device *dev_get_by_napi_id(unsigned int napi_id) { struct napi_struct *napi; WARN_ON_ONCE(!rcu_read_lock_held()); if (napi_id < MIN_NAPI_ID) return NULL; napi = napi_by_id(napi_id); return napi ? napi->dev : NULL; } EXPORT_SYMBOL(dev_get_by_napi_id); static DEFINE_SEQLOCK(netdev_rename_lock); void netdev_copy_name(struct net_device *dev, char *name) { unsigned int seq; do { seq = read_seqbegin(&netdev_rename_lock); strscpy(name, dev->name, IFNAMSIZ); } while (read_seqretry(&netdev_rename_lock, seq)); } /** * netdev_get_name - get a netdevice name, knowing its ifindex. * @net: network namespace * @name: a pointer to the buffer where the name will be stored. * @ifindex: the ifindex of the interface to get the name from. */ int netdev_get_name(struct net *net, char *name, int ifindex) { struct net_device *dev; int ret; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (!dev) { ret = -ENODEV; goto out; } netdev_copy_name(dev, name); ret = 0; out: rcu_read_unlock(); return ret; } /** * dev_getbyhwaddr_rcu - find a device by its hardware address * @net: the applicable net namespace * @type: media type of device * @ha: hardware address * * Search for an interface by MAC address. Returns NULL if the device * is not found or a pointer to the device. * The caller must hold RCU or RTNL. * The returned device has not had its ref count increased * and the caller must therefore be careful about locking * */ struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, const char *ha) { struct net_device *dev; for_each_netdev_rcu(net, dev) if (dev->type == type && !memcmp(dev->dev_addr, ha, dev->addr_len)) return dev; return NULL; } EXPORT_SYMBOL(dev_getbyhwaddr_rcu); struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type) { struct net_device *dev, *ret = NULL; rcu_read_lock(); for_each_netdev_rcu(net, dev) if (dev->type == type) { dev_hold(dev); ret = dev; break; } rcu_read_unlock(); return ret; } EXPORT_SYMBOL(dev_getfirstbyhwtype); /** * __dev_get_by_flags - find any device with given flags * @net: the applicable net namespace * @if_flags: IFF_* values * @mask: bitmask of bits in if_flags to check * * Search for any interface with the given flags. Returns NULL if a device * is not found or a pointer to the device. Must be called inside * rtnl_lock(), and result refcount is unchanged. */ struct net_device *__dev_get_by_flags(struct net *net, unsigned short if_flags, unsigned short mask) { struct net_device *dev, *ret; ASSERT_RTNL(); ret = NULL; for_each_netdev(net, dev) { if (((dev->flags ^ if_flags) & mask) == 0) { ret = dev; break; } } return ret; } EXPORT_SYMBOL(__dev_get_by_flags); /** * dev_valid_name - check if name is okay for network device * @name: name string * * Network device names need to be valid file names to * allow sysfs to work. We also disallow any kind of * whitespace. */ bool dev_valid_name(const char *name) { if (*name == '\0') return false; if (strnlen(name, IFNAMSIZ) == IFNAMSIZ) return false; if (!strcmp(name, ".") || !strcmp(name, "..")) return false; while (*name) { if (*name == '/' || *name == ':' || isspace(*name)) return false; name++; } return true; } EXPORT_SYMBOL(dev_valid_name); /** * __dev_alloc_name - allocate a name for a device * @net: network namespace to allocate the device name in * @name: name format string * @res: result name string * * Passed a format string - eg "lt%d" it will try and find a suitable * id. It scans list of devices to build up a free map, then chooses * the first empty slot. The caller must hold the dev_base or rtnl lock * while allocating the name and adding the device in order to avoid * duplicates. * Limited to bits_per_byte * page size devices (ie 32K on most platforms). * Returns the number of the unit assigned or a negative errno code. */ static int __dev_alloc_name(struct net *net, const char *name, char *res) { int i = 0; const char *p; const int max_netdevices = 8*PAGE_SIZE; unsigned long *inuse; struct net_device *d; char buf[IFNAMSIZ]; /* Verify the string as this thing may have come from the user. * There must be one "%d" and no other "%" characters. */ p = strchr(name, '%'); if (!p || p[1] != 'd' || strchr(p + 2, '%')) return -EINVAL; /* Use one page as a bit array of possible slots */ inuse = bitmap_zalloc(max_netdevices, GFP_ATOMIC); if (!inuse) return -ENOMEM; for_each_netdev(net, d) { struct netdev_name_node *name_node; netdev_for_each_altname(d, name_node) { if (!sscanf(name_node->name, name, &i)) continue; if (i < 0 || i >= max_netdevices) continue; /* avoid cases where sscanf is not exact inverse of printf */ snprintf(buf, IFNAMSIZ, name, i); if (!strncmp(buf, name_node->name, IFNAMSIZ)) __set_bit(i, inuse); } if (!sscanf(d->name, name, &i)) continue; if (i < 0 || i >= max_netdevices) continue; /* avoid cases where sscanf is not exact inverse of printf */ snprintf(buf, IFNAMSIZ, name, i); if (!strncmp(buf, d->name, IFNAMSIZ)) __set_bit(i, inuse); } i = find_first_zero_bit(inuse, max_netdevices); bitmap_free(inuse); if (i == max_netdevices) return -ENFILE; /* 'res' and 'name' could overlap, use 'buf' as an intermediate buffer */ strscpy(buf, name, IFNAMSIZ); snprintf(res, IFNAMSIZ, buf, i); return i; } /* Returns negative errno or allocated unit id (see __dev_alloc_name()) */ static int dev_prep_valid_name(struct net *net, struct net_device *dev, const char *want_name, char *out_name, int dup_errno) { if (!dev_valid_name(want_name)) return -EINVAL; if (strchr(want_name, '%')) return __dev_alloc_name(net, want_name, out_name); if (netdev_name_in_use(net, want_name)) return -dup_errno; if (out_name != want_name) strscpy(out_name, want_name, IFNAMSIZ); return 0; } /** * dev_alloc_name - allocate a name for a device * @dev: device * @name: name format string * * Passed a format string - eg "lt%d" it will try and find a suitable * id. It scans list of devices to build up a free map, then chooses * the first empty slot. The caller must hold the dev_base or rtnl lock * while allocating the name and adding the device in order to avoid * duplicates. * Limited to bits_per_byte * page size devices (ie 32K on most platforms). * Returns the number of the unit assigned or a negative errno code. */ int dev_alloc_name(struct net_device *dev, const char *name) { return dev_prep_valid_name(dev_net(dev), dev, name, dev->name, ENFILE); } EXPORT_SYMBOL(dev_alloc_name); static int dev_get_valid_name(struct net *net, struct net_device *dev, const char *name) { int ret; ret = dev_prep_valid_name(net, dev, name, dev->name, EEXIST); return ret < 0 ? ret : 0; } /** * dev_change_name - change name of a device * @dev: device * @newname: name (or format string) must be at least IFNAMSIZ * * Change name of a device, can pass format strings "eth%d". * for wildcarding. */ int dev_change_name(struct net_device *dev, const char *newname) { unsigned char old_assign_type; char oldname[IFNAMSIZ]; int err = 0; int ret; struct net *net; ASSERT_RTNL(); BUG_ON(!dev_net(dev)); net = dev_net(dev); down_write(&devnet_rename_sem); if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { up_write(&devnet_rename_sem); return 0; } memcpy(oldname, dev->name, IFNAMSIZ); write_seqlock_bh(&netdev_rename_lock); err = dev_get_valid_name(net, dev, newname); write_sequnlock_bh(&netdev_rename_lock); if (err < 0) { up_write(&devnet_rename_sem); return err; } if (oldname[0] && !strchr(oldname, '%')) netdev_info(dev, "renamed from %s%s\n", oldname, dev->flags & IFF_UP ? " (while UP)" : ""); old_assign_type = dev->name_assign_type; WRITE_ONCE(dev->name_assign_type, NET_NAME_RENAMED); rollback: ret = device_rename(&dev->dev, dev->name); if (ret) { memcpy(dev->name, oldname, IFNAMSIZ); WRITE_ONCE(dev->name_assign_type, old_assign_type); up_write(&devnet_rename_sem); return ret; } up_write(&devnet_rename_sem); netdev_adjacent_rename_links(dev, oldname); netdev_name_node_del(dev->name_node); synchronize_net(); netdev_name_node_add(net, dev->name_node); ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev); ret = notifier_to_errno(ret); if (ret) { /* err >= 0 after dev_alloc_name() or stores the first errno */ if (err >= 0) { err = ret; down_write(&devnet_rename_sem); write_seqlock_bh(&netdev_rename_lock); memcpy(dev->name, oldname, IFNAMSIZ); write_sequnlock_bh(&netdev_rename_lock); memcpy(oldname, newname, IFNAMSIZ); WRITE_ONCE(dev->name_assign_type, old_assign_type); old_assign_type = NET_NAME_RENAMED; goto rollback; } else { netdev_err(dev, "name change rollback failed: %d\n", ret); } } return err; } /** * dev_set_alias - change ifalias of a device * @dev: device * @alias: name up to IFALIASZ * @len: limit of bytes to copy from info * * Set ifalias for a device, */ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) { struct dev_ifalias *new_alias = NULL; if (len >= IFALIASZ) return -EINVAL; if (len) { new_alias = kmalloc(sizeof(*new_alias) + len + 1, GFP_KERNEL); if (!new_alias) return -ENOMEM; memcpy(new_alias->ifalias, alias, len); new_alias->ifalias[len] = 0; } mutex_lock(&ifalias_mutex); new_alias = rcu_replace_pointer(dev->ifalias, new_alias, mutex_is_locked(&ifalias_mutex)); mutex_unlock(&ifalias_mutex); if (new_alias) kfree_rcu(new_alias, rcuhead); return len; } EXPORT_SYMBOL(dev_set_alias); /** * dev_get_alias - get ifalias of a device * @dev: device * @name: buffer to store name of ifalias * @len: size of buffer * * get ifalias for a device. Caller must make sure dev cannot go * away, e.g. rcu read lock or own a reference count to device. */ int dev_get_alias(const struct net_device *dev, char *name, size_t len) { const struct dev_ifalias *alias; int ret = 0; rcu_read_lock(); alias = rcu_dereference(dev->ifalias); if (alias) ret = snprintf(name, len, "%s", alias->ifalias); rcu_read_unlock(); return ret; } /** * netdev_features_change - device changes features * @dev: device to cause notification * * Called to indicate a device has changed features. */ void netdev_features_change(struct net_device *dev) { call_netdevice_notifiers(NETDEV_FEAT_CHANGE, dev); } EXPORT_SYMBOL(netdev_features_change); /** * netdev_state_change - device changes state * @dev: device to cause notification * * Called to indicate a device has changed state. This function calls * the notifier chains for netdev_chain and sends a NEWLINK message * to the routing socket. */ void netdev_state_change(struct net_device *dev) { if (dev->flags & IFF_UP) { struct netdev_notifier_change_info change_info = { .info.dev = dev, }; call_netdevice_notifiers_info(NETDEV_CHANGE, &change_info.info); rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL, 0, NULL); } } EXPORT_SYMBOL(netdev_state_change); /** * __netdev_notify_peers - notify network peers about existence of @dev, * to be called when rtnl lock is already held. * @dev: network device * * Generate traffic such that interested network peers are aware of * @dev, such as by generating a gratuitous ARP. This may be used when * a device wants to inform the rest of the network about some sort of * reconfiguration such as a failover event or virtual machine * migration. */ void __netdev_notify_peers(struct net_device *dev) { ASSERT_RTNL(); call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev); call_netdevice_notifiers(NETDEV_RESEND_IGMP, dev); } EXPORT_SYMBOL(__netdev_notify_peers); /** * netdev_notify_peers - notify network peers about existence of @dev * @dev: network device * * Generate traffic such that interested network peers are aware of * @dev, such as by generating a gratuitous ARP. This may be used when * a device wants to inform the rest of the network about some sort of * reconfiguration such as a failover event or virtual machine * migration. */ void netdev_notify_peers(struct net_device *dev) { rtnl_lock(); __netdev_notify_peers(dev); rtnl_unlock(); } EXPORT_SYMBOL(netdev_notify_peers); static int napi_threaded_poll(void *data); static int napi_kthread_create(struct napi_struct *n) { int err = 0; /* Create and wake up the kthread once to put it in * TASK_INTERRUPTIBLE mode to avoid the blocked task * warning and work with loadavg. */ n->thread = kthread_run(napi_threaded_poll, n, "napi/%s-%d", n->dev->name, n->napi_id); if (IS_ERR(n->thread)) { err = PTR_ERR(n->thread); pr_err("kthread_run failed with err %d\n", err); n->thread = NULL; } return err; } static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; int ret; ASSERT_RTNL(); dev_addr_check(dev); if (!netif_device_present(dev)) { /* may be detached because parent is runtime-suspended */ if (dev->dev.parent) pm_runtime_resume(dev->dev.parent); if (!netif_device_present(dev)) return -ENODEV; } /* Block netpoll from trying to do any rx path servicing. * If we don't do this there is a chance ndo_poll_controller * or ndo_poll may be running while we open the device */ netpoll_poll_disable(dev); ret = call_netdevice_notifiers_extack(NETDEV_PRE_UP, dev, extack); ret = notifier_to_errno(ret); if (ret) return ret; set_bit(__LINK_STATE_START, &dev->state); if (ops->ndo_validate_addr) ret = ops->ndo_validate_addr(dev); if (!ret && ops->ndo_open) ret = ops->ndo_open(dev); netpoll_poll_enable(dev); if (ret) clear_bit(__LINK_STATE_START, &dev->state); else { dev->flags |= IFF_UP; dev_set_rx_mode(dev); dev_activate(dev); add_device_randomness(dev->dev_addr, dev->addr_len); } return ret; } /** * dev_open - prepare an interface for use. * @dev: device to open * @extack: netlink extended ack * * Takes a device from down to up state. The device's private open * function is invoked and then the multicast lists are loaded. Finally * the device is moved into the up state and a %NETDEV_UP message is * sent to the netdev notifier chain. * * Calling this function on an active interface is a nop. On a failure * a negative errno code is returned. */ int dev_open(struct net_device *dev, struct netlink_ext_ack *extack) { int ret; if (dev->flags & IFF_UP) return 0; ret = __dev_open(dev, extack); if (ret < 0) return ret; rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP | IFF_RUNNING, GFP_KERNEL, 0, NULL); call_netdevice_notifiers(NETDEV_UP, dev); return ret; } EXPORT_SYMBOL(dev_open); static void __dev_close_many(struct list_head *head) { struct net_device *dev; ASSERT_RTNL(); might_sleep(); list_for_each_entry(dev, head, close_list) { /* Temporarily disable netpoll until the interface is down */ netpoll_poll_disable(dev); call_netdevice_notifiers(NETDEV_GOING_DOWN, dev); clear_bit(__LINK_STATE_START, &dev->state); /* Synchronize to scheduled poll. We cannot touch poll list, it * can be even on different cpu. So just clear netif_running(). * * dev->stop() will invoke napi_disable() on all of it's * napi_struct instances on this device. */ smp_mb__after_atomic(); /* Commit netif_running(). */ } dev_deactivate_many(head); list_for_each_entry(dev, head, close_list) { const struct net_device_ops *ops = dev->netdev_ops; /* * Call the device specific close. This cannot fail. * Only if device is UP * * We allow it to be called even after a DETACH hot-plug * event. */ if (ops->ndo_stop) ops->ndo_stop(dev); dev->flags &= ~IFF_UP; netpoll_poll_enable(dev); } } static void __dev_close(struct net_device *dev) { LIST_HEAD(single); list_add(&dev->close_list, &single); __dev_close_many(&single); list_del(&single); } void dev_close_many(struct list_head *head, bool unlink) { struct net_device *dev, *tmp; /* Remove the devices that don't need to be closed */ list_for_each_entry_safe(dev, tmp, head, close_list) if (!(dev->flags & IFF_UP)) list_del_init(&dev->close_list); __dev_close_many(head); list_for_each_entry_safe(dev, tmp, head, close_list) { rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP | IFF_RUNNING, GFP_KERNEL, 0, NULL); call_netdevice_notifiers(NETDEV_DOWN, dev); if (unlink) list_del_init(&dev->close_list); } } EXPORT_SYMBOL(dev_close_many); /** * dev_close - shutdown an interface. * @dev: device to shutdown * * This function moves an active device into down state. A * %NETDEV_GOING_DOWN is sent to the netdev notifier chain. The device * is then deactivated and finally a %NETDEV_DOWN is sent to the notifier * chain. */ void dev_close(struct net_device *dev) { if (dev->flags & IFF_UP) { LIST_HEAD(single); list_add(&dev->close_list, &single); dev_close_many(&single, true); list_del(&single); } } EXPORT_SYMBOL(dev_close); /** * dev_disable_lro - disable Large Receive Offload on a device * @dev: device * * Disable Large Receive Offload (LRO) on a net device. Must be * called under RTNL. This is needed if received packets may be * forwarded to another interface. */ void dev_disable_lro(struct net_device *dev) { struct net_device *lower_dev; struct list_head *iter; dev->wanted_features &= ~NETIF_F_LRO; netdev_update_features(dev); if (unlikely(dev->features & NETIF_F_LRO)) netdev_WARN(dev, "failed to disable LRO!\n"); netdev_for_each_lower_dev(dev, lower_dev, iter) dev_disable_lro(lower_dev); } EXPORT_SYMBOL(dev_disable_lro); /** * dev_disable_gro_hw - disable HW Generic Receive Offload on a device * @dev: device * * Disable HW Generic Receive Offload (GRO_HW) on a net device. Must be * called under RTNL. This is needed if Generic XDP is installed on * the device. */ static void dev_disable_gro_hw(struct net_device *dev) { dev->wanted_features &= ~NETIF_F_GRO_HW; netdev_update_features(dev); if (unlikely(dev->features & NETIF_F_GRO_HW)) netdev_WARN(dev, "failed to disable GRO_HW!\n"); } const char *netdev_cmd_to_name(enum netdev_cmd cmd) { #define N(val) \ case NETDEV_##val: \ return "NETDEV_" __stringify(val); switch (cmd) { N(UP) N(DOWN) N(REBOOT) N(CHANGE) N(REGISTER) N(UNREGISTER) N(CHANGEMTU) N(CHANGEADDR) N(GOING_DOWN) N(CHANGENAME) N(FEAT_CHANGE) N(BONDING_FAILOVER) N(PRE_UP) N(PRE_TYPE_CHANGE) N(POST_TYPE_CHANGE) N(POST_INIT) N(PRE_UNINIT) N(RELEASE) N(NOTIFY_PEERS) N(JOIN) N(CHANGEUPPER) N(RESEND_IGMP) N(PRECHANGEMTU) N(CHANGEINFODATA) N(BONDING_INFO) N(PRECHANGEUPPER) N(CHANGELOWERSTATE) N(UDP_TUNNEL_PUSH_INFO) N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN) N(CVLAN_FILTER_PUSH_INFO) N(CVLAN_FILTER_DROP_INFO) N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO) N(PRE_CHANGEADDR) N(OFFLOAD_XSTATS_ENABLE) N(OFFLOAD_XSTATS_DISABLE) N(OFFLOAD_XSTATS_REPORT_USED) N(OFFLOAD_XSTATS_REPORT_DELTA) N(XDP_FEAT_CHANGE) } #undef N return "UNKNOWN_NETDEV_EVENT"; } EXPORT_SYMBOL_GPL(netdev_cmd_to_name); static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val, struct net_device *dev) { struct netdev_notifier_info info = { .dev = dev, }; return nb->notifier_call(nb, val, &info); } static int call_netdevice_register_notifiers(struct notifier_block *nb, struct net_device *dev) { int err; err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev); err = notifier_to_errno(err); if (err) return err; if (!(dev->flags & IFF_UP)) return 0; call_netdevice_notifier(nb, NETDEV_UP, dev); return 0; } static void call_netdevice_unregister_notifiers(struct notifier_block *nb, struct net_device *dev) { if (dev->flags & IFF_UP) { call_netdevice_notifier(nb, NETDEV_GOING_DOWN, dev); call_netdevice_notifier(nb, NETDEV_DOWN, dev); } call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev); } static int call_netdevice_register_net_notifiers(struct notifier_block *nb, struct net *net) { struct net_device *dev; int err; for_each_netdev(net, dev) { err = call_netdevice_register_notifiers(nb, dev); if (err) goto rollback; } return 0; rollback: for_each_netdev_continue_reverse(net, dev) call_netdevice_unregister_notifiers(nb, dev); return err; } static void call_netdevice_unregister_net_notifiers(struct notifier_block *nb, struct net *net) { struct net_device *dev; for_each_netdev(net, dev) call_netdevice_unregister_notifiers(nb, dev); } static int dev_boot_phase = 1; /** * register_netdevice_notifier - register a network notifier block * @nb: notifier * * Register a notifier to be called when network device events occur. * The notifier passed is linked into the kernel structures and must * not be reused until it has been unregistered. A negative errno code * is returned on a failure. * * When registered all registration and up events are replayed * to the new notifier to allow device to have a race free * view of the network device list. */ int register_netdevice_notifier(struct notifier_block *nb) { struct net *net; int err; /* Close race with setup_net() and cleanup_net() */ down_write(&pernet_ops_rwsem); rtnl_lock(); err = raw_notifier_chain_register(&netdev_chain, nb); if (err) goto unlock; if (dev_boot_phase) goto unlock; for_each_net(net) { err = call_netdevice_register_net_notifiers(nb, net); if (err) goto rollback; } unlock: rtnl_unlock(); up_write(&pernet_ops_rwsem); return err; rollback: for_each_net_continue_reverse(net) call_netdevice_unregister_net_notifiers(nb, net); raw_notifier_chain_unregister(&netdev_chain, nb); goto unlock; } EXPORT_SYMBOL(register_netdevice_notifier); /** * unregister_netdevice_notifier - unregister a network notifier block * @nb: notifier * * Unregister a notifier previously registered by * register_netdevice_notifier(). The notifier is unlinked into the * kernel structures and may then be reused. A negative errno code * is returned on a failure. * * After unregistering unregister and down device events are synthesized * for all devices on the device list to the removed notifier to remove * the need for special case cleanup code. */ int unregister_netdevice_notifier(struct notifier_block *nb) { struct net *net; int err; /* Close race with setup_net() and cleanup_net() */ down_write(&pernet_ops_rwsem); rtnl_lock(); err = raw_notifier_chain_unregister(&netdev_chain, nb); if (err) goto unlock; for_each_net(net) call_netdevice_unregister_net_notifiers(nb, net); unlock: rtnl_unlock(); up_write(&pernet_ops_rwsem); return err; } EXPORT_SYMBOL(unregister_netdevice_notifier); static int __register_netdevice_notifier_net(struct net *net, struct notifier_block *nb, bool ignore_call_fail) { int err; err = raw_notifier_chain_register(&net->netdev_chain, nb); if (err) return err; if (dev_boot_phase) return 0; err = call_netdevice_register_net_notifiers(nb, net); if (err && !ignore_call_fail) goto chain_unregister; return 0; chain_unregister: raw_notifier_chain_unregister(&net->netdev_chain, nb); return err; } static int __unregister_netdevice_notifier_net(struct net *net, struct notifier_block *nb) { int err; err = raw_notifier_chain_unregister(&net->netdev_chain, nb); if (err) return err; call_netdevice_unregister_net_notifiers(nb, net); return 0; } /** * register_netdevice_notifier_net - register a per-netns network notifier block * @net: network namespace * @nb: notifier * * Register a notifier to be called when network device events occur. * The notifier passed is linked into the kernel structures and must * not be reused until it has been unregistered. A negative errno code * is returned on a failure. * * When registered all registration and up events are replayed * to the new notifier to allow device to have a race free * view of the network device list. */ int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb) { int err; rtnl_lock(); err = __register_netdevice_notifier_net(net, nb, false); rtnl_unlock(); return err; } EXPORT_SYMBOL(register_netdevice_notifier_net); /** * unregister_netdevice_notifier_net - unregister a per-netns * network notifier block * @net: network namespace * @nb: notifier * * Unregister a notifier previously registered by * register_netdevice_notifier_net(). The notifier is unlinked from the * kernel structures and may then be reused. A negative errno code * is returned on a failure. * * After unregistering unregister and down device events are synthesized * for all devices on the device list to the removed notifier to remove * the need for special case cleanup code. */ int unregister_netdevice_notifier_net(struct net *net, struct notifier_block *nb) { int err; rtnl_lock(); err = __unregister_netdevice_notifier_net(net, nb); rtnl_unlock(); return err; } EXPORT_SYMBOL(unregister_netdevice_notifier_net); static void __move_netdevice_notifier_net(struct net *src_net, struct net *dst_net, struct notifier_block *nb) { __unregister_netdevice_notifier_net(src_net, nb); __register_netdevice_notifier_net(dst_net, nb, true); } int register_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) { int err; rtnl_lock(); err = __register_netdevice_notifier_net(dev_net(dev), nb, false); if (!err) { nn->nb = nb; list_add(&nn->list, &dev->net_notifier_list); } rtnl_unlock(); return err; } EXPORT_SYMBOL(register_netdevice_notifier_dev_net); int unregister_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) { int err; rtnl_lock(); list_del(&nn->list); err = __unregister_netdevice_notifier_net(dev_net(dev), nb); rtnl_unlock(); return err; } EXPORT_SYMBOL(unregister_netdevice_notifier_dev_net); static void move_netdevice_notifiers_dev_net(struct net_device *dev, struct net *net) { struct netdev_net_notifier *nn; list_for_each_entry(nn, &dev->net_notifier_list, list) __move_netdevice_notifier_net(dev_net(dev), net, nn->nb); } /** * call_netdevice_notifiers_info - call all network notifier blocks * @val: value passed unmodified to notifier function * @info: notifier information data * * Call all network notifier blocks. Parameters and return value * are as for raw_notifier_call_chain(). */ int call_netdevice_notifiers_info(unsigned long val, struct netdev_notifier_info *info) { struct net *net = dev_net(info->dev); int ret; ASSERT_RTNL(); /* Run per-netns notifier block chain first, then run the global one. * Hopefully, one day, the global one is going to be removed after * all notifier block registrators get converted to be per-netns. */ ret = raw_notifier_call_chain(&net->netdev_chain, val, info); if (ret & NOTIFY_STOP_MASK) return ret; return raw_notifier_call_chain(&netdev_chain, val, info); } /** * call_netdevice_notifiers_info_robust - call per-netns notifier blocks * for and rollback on error * @val_up: value passed unmodified to notifier function * @val_down: value passed unmodified to the notifier function when * recovering from an error on @val_up * @info: notifier information data * * Call all per-netns network notifier blocks, but not notifier blocks on * the global notifier chain. Parameters and return value are as for * raw_notifier_call_chain_robust(). */ static int call_netdevice_notifiers_info_robust(unsigned long val_up, unsigned long val_down, struct netdev_notifier_info *info) { struct net *net = dev_net(info->dev); ASSERT_RTNL(); return raw_notifier_call_chain_robust(&net->netdev_chain, val_up, val_down, info); } static int call_netdevice_notifiers_extack(unsigned long val, struct net_device *dev, struct netlink_ext_ack *extack) { struct netdev_notifier_info info = { .dev = dev, .extack = extack, }; return call_netdevice_notifiers_info(val, &info); } /** * call_netdevice_notifiers - call all network notifier blocks * @val: value passed unmodified to notifier function * @dev: net_device pointer passed unmodified to notifier function * * Call all network notifier blocks. Parameters and return value * are as for raw_notifier_call_chain(). */ int call_netdevice_notifiers(unsigned long val, struct net_device *dev) { return call_netdevice_notifiers_extack(val, dev, NULL); } EXPORT_SYMBOL(call_netdevice_notifiers); /** * call_netdevice_notifiers_mtu - call all network notifier blocks * @val: value passed unmodified to notifier function * @dev: net_device pointer passed unmodified to notifier function * @arg: additional u32 argument passed to the notifier function * * Call all network notifier blocks. Parameters and return value * are as for raw_notifier_call_chain(). */ static int call_netdevice_notifiers_mtu(unsigned long val, struct net_device *dev, u32 arg) { struct netdev_notifier_info_ext info = { .info.dev = dev, .ext.mtu = arg, }; BUILD_BUG_ON(offsetof(struct netdev_notifier_info_ext, info) != 0); return call_netdevice_notifiers_info(val, &info.info); } #ifdef CONFIG_NET_INGRESS static DEFINE_STATIC_KEY_FALSE(ingress_needed_key); void net_inc_ingress_queue(void) { static_branch_inc(&ingress_needed_key); } EXPORT_SYMBOL_GPL(net_inc_ingress_queue); void net_dec_ingress_queue(void) { static_branch_dec(&ingress_needed_key); } EXPORT_SYMBOL_GPL(net_dec_ingress_queue); #endif #ifdef CONFIG_NET_EGRESS static DEFINE_STATIC_KEY_FALSE(egress_needed_key); void net_inc_egress_queue(void) { static_branch_inc(&egress_needed_key); } EXPORT_SYMBOL_GPL(net_inc_egress_queue); void net_dec_egress_queue(void) { static_branch_dec(&egress_needed_key); } EXPORT_SYMBOL_GPL(net_dec_egress_queue); #endif #ifdef CONFIG_NET_CLS_ACT DEFINE_STATIC_KEY_FALSE(tcf_bypass_check_needed_key); EXPORT_SYMBOL(tcf_bypass_check_needed_key); #endif DEFINE_STATIC_KEY_FALSE(netstamp_needed_key); EXPORT_SYMBOL(netstamp_needed_key); #ifdef CONFIG_JUMP_LABEL static atomic_t netstamp_needed_deferred; static atomic_t netstamp_wanted; static void netstamp_clear(struct work_struct *work) { int deferred = atomic_xchg(&netstamp_needed_deferred, 0); int wanted; wanted = atomic_add_return(deferred, &netstamp_wanted); if (wanted > 0) static_branch_enable(&netstamp_needed_key); else static_branch_disable(&netstamp_needed_key); } static DECLARE_WORK(netstamp_work, netstamp_clear); #endif void net_enable_timestamp(void) { #ifdef CONFIG_JUMP_LABEL int wanted = atomic_read(&netstamp_wanted); while (wanted > 0) { if (atomic_try_cmpxchg(&netstamp_wanted, &wanted, wanted + 1)) return; } atomic_inc(&netstamp_needed_deferred); schedule_work(&netstamp_work); #else static_branch_inc(&netstamp_needed_key); #endif } EXPORT_SYMBOL(net_enable_timestamp); void net_disable_timestamp(void) { #ifdef CONFIG_JUMP_LABEL int wanted = atomic_read(&netstamp_wanted); while (wanted > 1) { if (atomic_try_cmpxchg(&netstamp_wanted, &wanted, wanted - 1)) return; } atomic_dec(&netstamp_needed_deferred); schedule_work(&netstamp_work); #else static_branch_dec(&netstamp_needed_key); #endif } EXPORT_SYMBOL(net_disable_timestamp); static inline void net_timestamp_set(struct sk_buff *skb) { skb->tstamp = 0; skb->tstamp_type = SKB_CLOCK_REALTIME; if (static_branch_unlikely(&netstamp_needed_key)) skb->tstamp = ktime_get_real(); } #define net_timestamp_check(COND, SKB) \ if (static_branch_unlikely(&netstamp_needed_key)) { \ if ((COND) && !(SKB)->tstamp) \ (SKB)->tstamp = ktime_get_real(); \ } \ bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb) { return __is_skb_forwardable(dev, skb, true); } EXPORT_SYMBOL_GPL(is_skb_forwardable); static int __dev_forward_skb2(struct net_device *dev, struct sk_buff *skb, bool check_mtu) { int ret = ____dev_forward_skb(dev, skb, check_mtu); if (likely(!ret)) { skb->protocol = eth_type_trans(skb, dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } return ret; } int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb) { return __dev_forward_skb2(dev, skb, true); } EXPORT_SYMBOL_GPL(__dev_forward_skb); /** * dev_forward_skb - loopback an skb to another netif * * @dev: destination network device * @skb: buffer to forward * * return values: * NET_RX_SUCCESS (no congestion) * NET_RX_DROP (packet was dropped, but freed) * * dev_forward_skb can be used for injecting an skb from the * start_xmit function of one device into the receive queue * of another device. * * The receiving device may be in another namespace, so * we have to clear all information in the skb that could * impact namespace isolation. */ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) { return __dev_forward_skb(dev, skb) ?: netif_rx_internal(skb); } EXPORT_SYMBOL_GPL(dev_forward_skb); int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb) { return __dev_forward_skb2(dev, skb, false) ?: netif_rx_internal(skb); } static inline int deliver_skb(struct sk_buff *skb, struct packet_type *pt_prev, struct net_device *orig_dev) { if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) return -ENOMEM; refcount_inc(&skb->users); return pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } static inline void deliver_ptype_list_skb(struct sk_buff *skb, struct packet_type **pt, struct net_device *orig_dev, __be16 type, struct list_head *ptype_list) { struct packet_type *ptype, *pt_prev = *pt; list_for_each_entry_rcu(ptype, ptype_list, list) { if (ptype->type != type) continue; if (pt_prev) deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } *pt = pt_prev; } static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb) { if (!ptype->af_packet_priv || !skb->sk) return false; if (ptype->id_match) return ptype->id_match(ptype, skb->sk); else if ((struct sock *)ptype->af_packet_priv == skb->sk) return true; return false; } /** * dev_nit_active - return true if any network interface taps are in use * * @dev: network device to check for the presence of taps */ bool dev_nit_active(struct net_device *dev) { return !list_empty(&net_hotdata.ptype_all) || !list_empty(&dev->ptype_all); } EXPORT_SYMBOL_GPL(dev_nit_active); /* * Support routine. Sends outgoing frames to any network * taps currently in use. */ void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) { struct list_head *ptype_list = &net_hotdata.ptype_all; struct packet_type *ptype, *pt_prev = NULL; struct sk_buff *skb2 = NULL; rcu_read_lock(); again: list_for_each_entry_rcu(ptype, ptype_list, list) { if (READ_ONCE(ptype->ignore_outgoing)) continue; /* Never send packets back to the socket * they originated from - MvS (miquels@drinkel.ow.org) */ if (skb_loop_sk(ptype, skb)) continue; if (pt_prev) { deliver_skb(skb2, pt_prev, skb->dev); pt_prev = ptype; continue; } /* need to clone skb, done only once */ skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) goto out_unlock; net_timestamp_set(skb2); /* skb->nh should be correctly * set by sender, so that the second statement is * just protection against buggy protocols. */ skb_reset_mac_header(skb2); if (skb_network_header(skb2) < skb2->data || skb_network_header(skb2) > skb_tail_pointer(skb2)) { net_crit_ratelimited("protocol %04x is buggy, dev %s\n", ntohs(skb2->protocol), dev->name); skb_reset_network_header(skb2); } skb2->transport_header = skb2->network_header; skb2->pkt_type = PACKET_OUTGOING; pt_prev = ptype; } if (ptype_list == &net_hotdata.ptype_all) { ptype_list = &dev->ptype_all; goto again; } out_unlock: if (pt_prev) { if (!skb_orphan_frags_rx(skb2, GFP_ATOMIC)) pt_prev->func(skb2, skb->dev, pt_prev, skb->dev); else kfree_skb(skb2); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(dev_queue_xmit_nit); /** * netif_setup_tc - Handle tc mappings on real_num_tx_queues change * @dev: Network device * @txq: number of queues available * * If real_num_tx_queues is changed the tc mappings may no longer be * valid. To resolve this verify the tc mapping remains valid and if * not NULL the mapping. With no priorities mapping to this * offset/count pair it will no longer be used. In the worst case TC0 * is invalid nothing can be done so disable priority mappings. If is * expected that drivers will fix this mapping if they can before * calling netif_set_real_num_tx_queues. */ static void netif_setup_tc(struct net_device *dev, unsigned int txq) { int i; struct netdev_tc_txq *tc = &dev->tc_to_txq[0]; /* If TC0 is invalidated disable TC mapping */ if (tc->offset + tc->count > txq) { netdev_warn(dev, "Number of in use tx queues changed invalidating tc mappings. Priority traffic classification disabled!\n"); dev->num_tc = 0; return; } /* Invalidated prio to tc mappings set to TC0 */ for (i = 1; i < TC_BITMASK + 1; i++) { int q = netdev_get_prio_tc_map(dev, i); tc = &dev->tc_to_txq[q]; if (tc->offset + tc->count > txq) { netdev_warn(dev, "Number of in use tx queues changed. Priority %i to tc mapping %i is no longer valid. Setting map to 0\n", i, q); netdev_set_prio_tc_map(dev, i, 0); } } } int netdev_txq_to_tc(struct net_device *dev, unsigned int txq) { if (dev->num_tc) { struct netdev_tc_txq *tc = &dev->tc_to_txq[0]; int i; /* walk through the TCs and see if it falls into any of them */ for (i = 0; i < TC_MAX_QUEUE; i++, tc++) { if ((txq - tc->offset) < tc->count) return i; } /* didn't find it, just return -1 to indicate no match */ return -1; } return 0; } EXPORT_SYMBOL(netdev_txq_to_tc); #ifdef CONFIG_XPS static struct static_key xps_needed __read_mostly; static struct static_key xps_rxqs_needed __read_mostly; static DEFINE_MUTEX(xps_map_mutex); #define xmap_dereference(P) \ rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex)) static bool remove_xps_queue(struct xps_dev_maps *dev_maps, struct xps_dev_maps *old_maps, int tci, u16 index) { struct xps_map *map = NULL; int pos; map = xmap_dereference(dev_maps->attr_map[tci]); if (!map) return false; for (pos = map->len; pos--;) { if (map->queues[pos] != index) continue; if (map->len > 1) { map->queues[pos] = map->queues[--map->len]; break; } if (old_maps) RCU_INIT_POINTER(old_maps->attr_map[tci], NULL); RCU_INIT_POINTER(dev_maps->attr_map[tci], NULL); kfree_rcu(map, rcu); return false; } return true; } static bool remove_xps_queue_cpu(struct net_device *dev, struct xps_dev_maps *dev_maps, int cpu, u16 offset, u16 count) { int num_tc = dev_maps->num_tc; bool active = false; int tci; for (tci = cpu * num_tc; num_tc--; tci++) { int i, j; for (i = count, j = offset; i--; j++) { if (!remove_xps_queue(dev_maps, NULL, tci, j)) break; } active |= i < 0; } return active; } static void reset_xps_maps(struct net_device *dev, struct xps_dev_maps *dev_maps, enum xps_map_type type) { static_key_slow_dec_cpuslocked(&xps_needed); if (type == XPS_RXQS) static_key_slow_dec_cpuslocked(&xps_rxqs_needed); RCU_INIT_POINTER(dev->xps_maps[type], NULL); kfree_rcu(dev_maps, rcu); } static void clean_xps_maps(struct net_device *dev, enum xps_map_type type, u16 offset, u16 count) { struct xps_dev_maps *dev_maps; bool active = false; int i, j; dev_maps = xmap_dereference(dev->xps_maps[type]); if (!dev_maps) return; for (j = 0; j < dev_maps->nr_ids; j++) active |= remove_xps_queue_cpu(dev, dev_maps, j, offset, count); if (!active) reset_xps_maps(dev, dev_maps, type); if (type == XPS_CPUS) { for (i = offset + (count - 1); count--; i--) netdev_queue_numa_node_write( netdev_get_tx_queue(dev, i), NUMA_NO_NODE); } } static void netif_reset_xps_queues(struct net_device *dev, u16 offset, u16 count) { if (!static_key_false(&xps_needed)) return; cpus_read_lock(); mutex_lock(&xps_map_mutex); if (static_key_false(&xps_rxqs_needed)) clean_xps_maps(dev, XPS_RXQS, offset, count); clean_xps_maps(dev, XPS_CPUS, offset, count); mutex_unlock(&xps_map_mutex); cpus_read_unlock(); } static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index) { netif_reset_xps_queues(dev, index, dev->num_tx_queues - index); } static struct xps_map *expand_xps_map(struct xps_map *map, int attr_index, u16 index, bool is_rxqs_map) { struct xps_map *new_map; int alloc_len = XPS_MIN_MAP_ALLOC; int i, pos; for (pos = 0; map && pos < map->len; pos++) { if (map->queues[pos] != index) continue; return map; } /* Need to add tx-queue to this CPU's/rx-queue's existing map */ if (map) { if (pos < map->alloc_len) return map; alloc_len = map->alloc_len * 2; } /* Need to allocate new map to store tx-queue on this CPU's/rx-queue's * map */ if (is_rxqs_map) new_map = kzalloc(XPS_MAP_SIZE(alloc_len), GFP_KERNEL); else new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL, cpu_to_node(attr_index)); if (!new_map) return NULL; for (i = 0; i < pos; i++) new_map->queues[i] = map->queues[i]; new_map->alloc_len = alloc_len; new_map->len = pos; return new_map; } /* Copy xps maps at a given index */ static void xps_copy_dev_maps(struct xps_dev_maps *dev_maps, struct xps_dev_maps *new_dev_maps, int index, int tc, bool skip_tc) { int i, tci = index * dev_maps->num_tc; struct xps_map *map; /* copy maps belonging to foreign traffic classes */ for (i = 0; i < dev_maps->num_tc; i++, tci++) { if (i == tc && skip_tc) continue; /* fill in the new device map from the old device map */ map = xmap_dereference(dev_maps->attr_map[tci]); RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); } } /* Must be called under cpus_read_lock */ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, u16 index, enum xps_map_type type) { struct xps_dev_maps *dev_maps, *new_dev_maps = NULL, *old_dev_maps = NULL; const unsigned long *online_mask = NULL; bool active = false, copy = false; int i, j, tci, numa_node_id = -2; int maps_sz, num_tc = 1, tc = 0; struct xps_map *map, *new_map; unsigned int nr_ids; WARN_ON_ONCE(index >= dev->num_tx_queues); if (dev->num_tc) { /* Do not allow XPS on subordinate device directly */ num_tc = dev->num_tc; if (num_tc < 0) return -EINVAL; /* If queue belongs to subordinate dev use its map */ dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; tc = netdev_txq_to_tc(dev, index); if (tc < 0) return -EINVAL; } mutex_lock(&xps_map_mutex); dev_maps = xmap_dereference(dev->xps_maps[type]); if (type == XPS_RXQS) { maps_sz = XPS_RXQ_DEV_MAPS_SIZE(num_tc, dev->num_rx_queues); nr_ids = dev->num_rx_queues; } else { maps_sz = XPS_CPU_DEV_MAPS_SIZE(num_tc); if (num_possible_cpus() > 1) online_mask = cpumask_bits(cpu_online_mask); nr_ids = nr_cpu_ids; } if (maps_sz < L1_CACHE_BYTES) maps_sz = L1_CACHE_BYTES; /* The old dev_maps could be larger or smaller than the one we're * setting up now, as dev->num_tc or nr_ids could have been updated in * between. We could try to be smart, but let's be safe instead and only * copy foreign traffic classes if the two map sizes match. */ if (dev_maps && dev_maps->num_tc == num_tc && dev_maps->nr_ids == nr_ids) copy = true; /* allocate memory for queue storage */ for (j = -1; j = netif_attrmask_next_and(j, online_mask, mask, nr_ids), j < nr_ids;) { if (!new_dev_maps) { new_dev_maps = kzalloc(maps_sz, GFP_KERNEL); if (!new_dev_maps) { mutex_unlock(&xps_map_mutex); return -ENOMEM; } new_dev_maps->nr_ids = nr_ids; new_dev_maps->num_tc = num_tc; } tci = j * num_tc + tc; map = copy ? xmap_dereference(dev_maps->attr_map[tci]) : NULL; map = expand_xps_map(map, j, index, type == XPS_RXQS); if (!map) goto error; RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); } if (!new_dev_maps) goto out_no_new_maps; if (!dev_maps) { /* Increment static keys at most once per type */ static_key_slow_inc_cpuslocked(&xps_needed); if (type == XPS_RXQS) static_key_slow_inc_cpuslocked(&xps_rxqs_needed); } for (j = 0; j < nr_ids; j++) { bool skip_tc = false; tci = j * num_tc + tc; if (netif_attr_test_mask(j, mask, nr_ids) && netif_attr_test_online(j, online_mask, nr_ids)) { /* add tx-queue to CPU/rx-queue maps */ int pos = 0; skip_tc = true; map = xmap_dereference(new_dev_maps->attr_map[tci]); while ((pos < map->len) && (map->queues[pos] != index)) pos++; if (pos == map->len) map->queues[map->len++] = index; #ifdef CONFIG_NUMA if (type == XPS_CPUS) { if (numa_node_id == -2) numa_node_id = cpu_to_node(j); else if (numa_node_id != cpu_to_node(j)) numa_node_id = -1; } #endif } if (copy) xps_copy_dev_maps(dev_maps, new_dev_maps, j, tc, skip_tc); } rcu_assign_pointer(dev->xps_maps[type], new_dev_maps); /* Cleanup old maps */ if (!dev_maps) goto out_no_old_maps; for (j = 0; j < dev_maps->nr_ids; j++) { for (i = num_tc, tci = j * dev_maps->num_tc; i--; tci++) { map = xmap_dereference(dev_maps->attr_map[tci]); if (!map) continue; if (copy) { new_map = xmap_dereference(new_dev_maps->attr_map[tci]); if (map == new_map) continue; } RCU_INIT_POINTER(dev_maps->attr_map[tci], NULL); kfree_rcu(map, rcu); } } old_dev_maps = dev_maps; out_no_old_maps: dev_maps = new_dev_maps; active = true; out_no_new_maps: if (type == XPS_CPUS) /* update Tx queue numa node */ netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index), (numa_node_id >= 0) ? numa_node_id : NUMA_NO_NODE); if (!dev_maps) goto out_no_maps; /* removes tx-queue from unused CPUs/rx-queues */ for (j = 0; j < dev_maps->nr_ids; j++) { tci = j * dev_maps->num_tc; for (i = 0; i < dev_maps->num_tc; i++, tci++) { if (i == tc && netif_attr_test_mask(j, mask, dev_maps->nr_ids) && netif_attr_test_online(j, online_mask, dev_maps->nr_ids)) continue; active |= remove_xps_queue(dev_maps, copy ? old_dev_maps : NULL, tci, index); } } if (old_dev_maps) kfree_rcu(old_dev_maps, rcu); /* free map if not active */ if (!active) reset_xps_maps(dev, dev_maps, type); out_no_maps: mutex_unlock(&xps_map_mutex); return 0; error: /* remove any maps that we added */ for (j = 0; j < nr_ids; j++) { for (i = num_tc, tci = j * num_tc; i--; tci++) { new_map = xmap_dereference(new_dev_maps->attr_map[tci]); map = copy ? xmap_dereference(dev_maps->attr_map[tci]) : NULL; if (new_map && new_map != map) kfree(new_map); } } mutex_unlock(&xps_map_mutex); kfree(new_dev_maps); return -ENOMEM; } EXPORT_SYMBOL_GPL(__netif_set_xps_queue); int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, u16 index) { int ret; cpus_read_lock(); ret = __netif_set_xps_queue(dev, cpumask_bits(mask), index, XPS_CPUS); cpus_read_unlock(); return ret; } EXPORT_SYMBOL(netif_set_xps_queue); #endif static void netdev_unbind_all_sb_channels(struct net_device *dev) { struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues]; /* Unbind any subordinate channels */ while (txq-- != &dev->_tx[0]) { if (txq->sb_dev) netdev_unbind_sb_channel(dev, txq->sb_dev); } } void netdev_reset_tc(struct net_device *dev) { #ifdef CONFIG_XPS netif_reset_xps_queues_gt(dev, 0); #endif netdev_unbind_all_sb_channels(dev); /* Reset TC configuration of device */ dev->num_tc = 0; memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq)); memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map)); } EXPORT_SYMBOL(netdev_reset_tc); int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset) { if (tc >= dev->num_tc) return -EINVAL; #ifdef CONFIG_XPS netif_reset_xps_queues(dev, offset, count); #endif dev->tc_to_txq[tc].count = count; dev->tc_to_txq[tc].offset = offset; return 0; } EXPORT_SYMBOL(netdev_set_tc_queue); int netdev_set_num_tc(struct net_device *dev, u8 num_tc) { if (num_tc > TC_MAX_QUEUE) return -EINVAL; #ifdef CONFIG_XPS netif_reset_xps_queues_gt(dev, 0); #endif netdev_unbind_all_sb_channels(dev); dev->num_tc = num_tc; return 0; } EXPORT_SYMBOL(netdev_set_num_tc); void netdev_unbind_sb_channel(struct net_device *dev, struct net_device *sb_dev) { struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues]; #ifdef CONFIG_XPS netif_reset_xps_queues_gt(sb_dev, 0); #endif memset(sb_dev->tc_to_txq, 0, sizeof(sb_dev->tc_to_txq)); memset(sb_dev->prio_tc_map, 0, sizeof(sb_dev->prio_tc_map)); while (txq-- != &dev->_tx[0]) { if (txq->sb_dev == sb_dev) txq->sb_dev = NULL; } } EXPORT_SYMBOL(netdev_unbind_sb_channel); int netdev_bind_sb_channel_queue(struct net_device *dev, struct net_device *sb_dev, u8 tc, u16 count, u16 offset) { /* Make certain the sb_dev and dev are already configured */ if (sb_dev->num_tc >= 0 || tc >= dev->num_tc) return -EINVAL; /* We cannot hand out queues we don't have */ if ((offset + count) > dev->real_num_tx_queues) return -EINVAL; /* Record the mapping */ sb_dev->tc_to_txq[tc].count = count; sb_dev->tc_to_txq[tc].offset = offset; /* Provide a way for Tx queue to find the tc_to_txq map or * XPS map for itself. */ while (count--) netdev_get_tx_queue(dev, count + offset)->sb_dev = sb_dev; return 0; } EXPORT_SYMBOL(netdev_bind_sb_channel_queue); int netdev_set_sb_channel(struct net_device *dev, u16 channel) { /* Do not use a multiqueue device to represent a subordinate channel */ if (netif_is_multiqueue(dev)) return -ENODEV; /* We allow channels 1 - 32767 to be used for subordinate channels. * Channel 0 is meant to be "native" mode and used only to represent * the main root device. We allow writing 0 to reset the device back * to normal mode after being used as a subordinate channel. */ if (channel > S16_MAX) return -EINVAL; dev->num_tc = -channel; return 0; } EXPORT_SYMBOL(netdev_set_sb_channel); /* * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues * greater than real_num_tx_queues stale skbs on the qdisc must be flushed. */ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) { bool disabling; int rc; disabling = txq < dev->real_num_tx_queues; if (txq < 1 || txq > dev->num_tx_queues) return -EINVAL; if (dev->reg_state == NETREG_REGISTERED || dev->reg_state == NETREG_UNREGISTERING) { ASSERT_RTNL(); rc = netdev_queue_update_kobjects(dev, dev->real_num_tx_queues, txq); if (rc) return rc; if (dev->num_tc) netif_setup_tc(dev, txq); net_shaper_set_real_num_tx_queues(dev, txq); dev_qdisc_change_real_num_tx(dev, txq); dev->real_num_tx_queues = txq; if (disabling) { synchronize_net(); qdisc_reset_all_tx_gt(dev, txq); #ifdef CONFIG_XPS netif_reset_xps_queues_gt(dev, txq); #endif } } else { dev->real_num_tx_queues = txq; } return 0; } EXPORT_SYMBOL(netif_set_real_num_tx_queues); #ifdef CONFIG_SYSFS /** * netif_set_real_num_rx_queues - set actual number of RX queues used * @dev: Network device * @rxq: Actual number of RX queues * * This must be called either with the rtnl_lock held or before * registration of the net device. Returns 0 on success, or a * negative error code. If called before registration, it always * succeeds. */ int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq) { int rc; if (rxq < 1 || rxq > dev->num_rx_queues) return -EINVAL; if (dev->reg_state == NETREG_REGISTERED) { ASSERT_RTNL(); rc = net_rx_queue_update_kobjects(dev, dev->real_num_rx_queues, rxq); if (rc) return rc; } dev->real_num_rx_queues = rxq; return 0; } EXPORT_SYMBOL(netif_set_real_num_rx_queues); #endif /** * netif_set_real_num_queues - set actual number of RX and TX queues used * @dev: Network device * @txq: Actual number of TX queues * @rxq: Actual number of RX queues * * Set the real number of both TX and RX queues. * Does nothing if the number of queues is already correct. */ int netif_set_real_num_queues(struct net_device *dev, unsigned int txq, unsigned int rxq) { unsigned int old_rxq = dev->real_num_rx_queues; int err; if (txq < 1 || txq > dev->num_tx_queues || rxq < 1 || rxq > dev->num_rx_queues) return -EINVAL; /* Start from increases, so the error path only does decreases - * decreases can't fail. */ if (rxq > dev->real_num_rx_queues) { err = netif_set_real_num_rx_queues(dev, rxq); if (err) return err; } if (txq > dev->real_num_tx_queues) { err = netif_set_real_num_tx_queues(dev, txq); if (err) goto undo_rx; } if (rxq < dev->real_num_rx_queues) WARN_ON(netif_set_real_num_rx_queues(dev, rxq)); if (txq < dev->real_num_tx_queues) WARN_ON(netif_set_real_num_tx_queues(dev, txq)); return 0; undo_rx: WARN_ON(netif_set_real_num_rx_queues(dev, old_rxq)); return err; } EXPORT_SYMBOL(netif_set_real_num_queues); /** * netif_set_tso_max_size() - set the max size of TSO frames supported * @dev: netdev to update * @size: max skb->len of a TSO frame * * Set the limit on the size of TSO super-frames the device can handle. * Unless explicitly set the stack will assume the value of * %GSO_LEGACY_MAX_SIZE. */ void netif_set_tso_max_size(struct net_device *dev, unsigned int size) { dev->tso_max_size = min(GSO_MAX_SIZE, size); if (size < READ_ONCE(dev->gso_max_size)) netif_set_gso_max_size(dev, size); if (size < READ_ONCE(dev->gso_ipv4_max_size)) netif_set_gso_ipv4_max_size(dev, size); } EXPORT_SYMBOL(netif_set_tso_max_size); /** * netif_set_tso_max_segs() - set the max number of segs supported for TSO * @dev: netdev to update * @segs: max number of TCP segments * * Set the limit on the number of TCP segments the device can generate from * a single TSO super-frame. * Unless explicitly set the stack will assume the value of %GSO_MAX_SEGS. */ void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs) { dev->tso_max_segs = segs; if (segs < READ_ONCE(dev->gso_max_segs)) netif_set_gso_max_segs(dev, segs); } EXPORT_SYMBOL(netif_set_tso_max_segs); /** * netif_inherit_tso_max() - copy all TSO limits from a lower device to an upper * @to: netdev to update * @from: netdev from which to copy the limits */ void netif_inherit_tso_max(struct net_device *to, const struct net_device *from) { netif_set_tso_max_size(to, from->tso_max_size); netif_set_tso_max_segs(to, from->tso_max_segs); } EXPORT_SYMBOL(netif_inherit_tso_max); /** * netif_get_num_default_rss_queues - default number of RSS queues * * Default value is the number of physical cores if there are only 1 or 2, or * divided by 2 if there are more. */ int netif_get_num_default_rss_queues(void) { cpumask_var_t cpus; int cpu, count = 0; if (unlikely(is_kdump_kernel() || !zalloc_cpumask_var(&cpus, GFP_KERNEL))) return 1; cpumask_copy(cpus, cpu_online_mask); for_each_cpu(cpu, cpus) { ++count; cpumask_andnot(cpus, cpus, topology_sibling_cpumask(cpu)); } free_cpumask_var(cpus); return count > 2 ? DIV_ROUND_UP(count, 2) : count; } EXPORT_SYMBOL(netif_get_num_default_rss_queues); static void __netif_reschedule(struct Qdisc *q) { struct softnet_data *sd; unsigned long flags; local_irq_save(flags); sd = this_cpu_ptr(&softnet_data); q->next_sched = NULL; *sd->output_queue_tailp = q; sd->output_queue_tailp = &q->next_sched; raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); } void __netif_schedule(struct Qdisc *q) { if (!test_and_set_bit(__QDISC_STATE_SCHED, &q->state)) __netif_reschedule(q); } EXPORT_SYMBOL(__netif_schedule); struct dev_kfree_skb_cb { enum skb_drop_reason reason; }; static struct dev_kfree_skb_cb *get_kfree_skb_cb(const struct sk_buff *skb) { return (struct dev_kfree_skb_cb *)skb->cb; } void netif_schedule_queue(struct netdev_queue *txq) { rcu_read_lock(); if (!netif_xmit_stopped(txq)) { struct Qdisc *q = rcu_dereference(txq->qdisc); __netif_schedule(q); } rcu_read_unlock(); } EXPORT_SYMBOL(netif_schedule_queue); void netif_tx_wake_queue(struct netdev_queue *dev_queue) { if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state)) { struct Qdisc *q; rcu_read_lock(); q = rcu_dereference(dev_queue->qdisc); __netif_schedule(q); rcu_read_unlock(); } } EXPORT_SYMBOL(netif_tx_wake_queue); void dev_kfree_skb_irq_reason(struct sk_buff *skb, enum skb_drop_reason reason) { unsigned long flags; if (unlikely(!skb)) return; if (likely(refcount_read(&skb->users) == 1)) { smp_rmb(); refcount_set(&skb->users, 0); } else if (likely(!refcount_dec_and_test(&skb->users))) { return; } get_kfree_skb_cb(skb)->reason = reason; local_irq_save(flags); skb->next = __this_cpu_read(softnet_data.completion_queue); __this_cpu_write(softnet_data.completion_queue, skb); raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); } EXPORT_SYMBOL(dev_kfree_skb_irq_reason); void dev_kfree_skb_any_reason(struct sk_buff *skb, enum skb_drop_reason reason) { if (in_hardirq() || irqs_disabled()) dev_kfree_skb_irq_reason(skb, reason); else kfree_skb_reason(skb, reason); } EXPORT_SYMBOL(dev_kfree_skb_any_reason); /** * netif_device_detach - mark device as removed * @dev: network device * * Mark device as removed from system and therefore no longer available. */ void netif_device_detach(struct net_device *dev) { if (test_and_clear_bit(__LINK_STATE_PRESENT, &dev->state) && netif_running(dev)) { netif_tx_stop_all_queues(dev); } } EXPORT_SYMBOL(netif_device_detach); /** * netif_device_attach - mark device as attached * @dev: network device * * Mark device as attached from system and restart if needed. */ void netif_device_attach(struct net_device *dev) { if (!test_and_set_bit(__LINK_STATE_PRESENT, &dev->state) && netif_running(dev)) { netif_tx_wake_all_queues(dev); __netdev_watchdog_up(dev); } } EXPORT_SYMBOL(netif_device_attach); /* * Returns a Tx hash based on the given packet descriptor a Tx queues' number * to be used as a distribution range. */ static u16 skb_tx_hash(const struct net_device *dev, const struct net_device *sb_dev, struct sk_buff *skb) { u32 hash; u16 qoffset = 0; u16 qcount = dev->real_num_tx_queues; if (dev->num_tc) { u8 tc = netdev_get_prio_tc_map(dev, skb->priority); qoffset = sb_dev->tc_to_txq[tc].offset; qcount = sb_dev->tc_to_txq[tc].count; if (unlikely(!qcount)) { net_warn_ratelimited("%s: invalid qcount, qoffset %u for tc %u\n", sb_dev->name, qoffset, tc); qoffset = 0; qcount = dev->real_num_tx_queues; } } if (skb_rx_queue_recorded(skb)) { DEBUG_NET_WARN_ON_ONCE(qcount == 0); hash = skb_get_rx_queue(skb); if (hash >= qoffset) hash -= qoffset; while (unlikely(hash >= qcount)) hash -= qcount; return hash + qoffset; } return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset; } void skb_warn_bad_offload(const struct sk_buff *skb) { static const netdev_features_t null_features; struct net_device *dev = skb->dev; const char *name = ""; if (!net_ratelimit()) return; if (dev) { if (dev->dev.parent) name = dev_driver_string(dev->dev.parent); else name = netdev_name(dev); } skb_dump(KERN_WARNING, skb, false); WARN(1, "%s: caps=(%pNF, %pNF)\n", name, dev ? &dev->features : &null_features, skb->sk ? &skb->sk->sk_route_caps : &null_features); } /* * Invalidate hardware checksum when packet is to be mangled, and * complete checksum manually on outgoing path. */ int skb_checksum_help(struct sk_buff *skb) { __wsum csum; int ret = 0, offset; if (skb->ip_summed == CHECKSUM_COMPLETE) goto out_set_summed; if (unlikely(skb_is_gso(skb))) { skb_warn_bad_offload(skb); return -EINVAL; } if (!skb_frags_readable(skb)) { return -EFAULT; } /* Before computing a checksum, we should make sure no frag could * be modified by an external entity : checksum could be wrong. */ if (skb_has_shared_frag(skb)) { ret = __skb_linearize(skb); if (ret) goto out; } offset = skb_checksum_start_offset(skb); ret = -EINVAL; if (unlikely(offset >= skb_headlen(skb))) { DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); WARN_ONCE(true, "offset (%d) >= skb_headlen() (%u)\n", offset, skb_headlen(skb)); goto out; } csum = skb_checksum(skb, offset, skb->len - offset, 0); offset += skb->csum_offset; if (unlikely(offset + sizeof(__sum16) > skb_headlen(skb))) { DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); WARN_ONCE(true, "offset+2 (%zu) > skb_headlen() (%u)\n", offset + sizeof(__sum16), skb_headlen(skb)); goto out; } ret = skb_ensure_writable(skb, offset + sizeof(__sum16)); if (ret) goto out; *(__sum16 *)(skb->data + offset) = csum_fold(csum) ?: CSUM_MANGLED_0; out_set_summed: skb->ip_summed = CHECKSUM_NONE; out: return ret; } EXPORT_SYMBOL(skb_checksum_help); int skb_crc32c_csum_help(struct sk_buff *skb) { __le32 crc32c_csum; int ret = 0, offset, start; if (skb->ip_summed != CHECKSUM_PARTIAL) goto out; if (unlikely(skb_is_gso(skb))) goto out; /* Before computing a checksum, we should make sure no frag could * be modified by an external entity : checksum could be wrong. */ if (unlikely(skb_has_shared_frag(skb))) { ret = __skb_linearize(skb); if (ret) goto out; } start = skb_checksum_start_offset(skb); offset = start + offsetof(struct sctphdr, checksum); if (WARN_ON_ONCE(offset >= skb_headlen(skb))) { ret = -EINVAL; goto out; } ret = skb_ensure_writable(skb, offset + sizeof(__le32)); if (ret) goto out; crc32c_csum = cpu_to_le32(~__skb_checksum(skb, start, skb->len - start, ~(__u32)0, crc32c_csum_stub)); *(__le32 *)(skb->data + offset) = crc32c_csum; skb_reset_csum_not_inet(skb); out: return ret; } EXPORT_SYMBOL(skb_crc32c_csum_help); __be16 skb_network_protocol(struct sk_buff *skb, int *depth) { __be16 type = skb->protocol; /* Tunnel gso handlers can set protocol to ethernet. */ if (type == htons(ETH_P_TEB)) { struct ethhdr *eth; if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr)))) return 0; eth = (struct ethhdr *)skb->data; type = eth->h_proto; } return vlan_get_protocol_and_depth(skb, type, depth); } /* Take action when hardware reception checksum errors are detected. */ #ifdef CONFIG_BUG static void do_netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb) { netdev_err(dev, "hw csum failure\n"); skb_dump(KERN_ERR, skb, true); dump_stack(); } void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb) { DO_ONCE_LITE(do_netdev_rx_csum_fault, dev, skb); } EXPORT_SYMBOL(netdev_rx_csum_fault); #endif /* XXX: check that highmem exists at all on the given machine. */ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_HIGHMEM int i; if (!(dev->features & NETIF_F_HIGHDMA)) { for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; struct page *page = skb_frag_page(frag); if (page && PageHighMem(page)) return 1; } } #endif return 0; } /* If MPLS offload request, verify we are testing hardware MPLS features * instead of standard features for the netdev. */ #if IS_ENABLED(CONFIG_NET_MPLS_GSO) static netdev_features_t net_mpls_features(struct sk_buff *skb, netdev_features_t features, __be16 type) { if (eth_p_mpls(type)) features &= skb->dev->mpls_features; return features; } #else static netdev_features_t net_mpls_features(struct sk_buff *skb, netdev_features_t features, __be16 type) { return features; } #endif static netdev_features_t harmonize_features(struct sk_buff *skb, netdev_features_t features) { __be16 type; type = skb_network_protocol(skb, NULL); features = net_mpls_features(skb, features, type); if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, type)) { features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); } if (illegal_highdma(skb->dev, skb)) features &= ~NETIF_F_SG; return features; } netdev_features_t passthru_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { return features; } EXPORT_SYMBOL(passthru_features_check); static netdev_features_t dflt_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { return vlan_features_check(skb, features); } static netdev_features_t gso_features_check(const struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { u16 gso_segs = skb_shinfo(skb)->gso_segs; if (gso_segs > READ_ONCE(dev->gso_max_segs)) return features & ~NETIF_F_GSO_MASK; if (unlikely(skb->len >= netif_get_gso_max_size(dev, skb))) return features & ~NETIF_F_GSO_MASK; if (!skb_shinfo(skb)->gso_type) { skb_warn_bad_offload(skb); return features & ~NETIF_F_GSO_MASK; } /* Support for GSO partial features requires software * intervention before we can actually process the packets * so we need to strip support for any partial features now * and we can pull them back in after we have partially * segmented the frame. */ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL)) features &= ~dev->gso_partial_features; /* Make sure to clear the IPv4 ID mangling feature if the * IPv4 header has the potential to be fragmented. */ if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) { struct iphdr *iph = skb->encapsulation ? inner_ip_hdr(skb) : ip_hdr(skb); if (!(iph->frag_off & htons(IP_DF))) features &= ~NETIF_F_TSO_MANGLEID; } return features; } netdev_features_t netif_skb_features(struct sk_buff *skb) { struct net_device *dev = skb->dev; netdev_features_t features = dev->features; if (skb_is_gso(skb)) features = gso_features_check(skb, dev, features); /* If encapsulation offload request, verify we are testing * hardware encapsulation features instead of standard * features for the netdev */ if (skb->encapsulation) features &= dev->hw_enc_features; if (skb_vlan_tagged(skb)) features = netdev_intersect_features(features, dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); if (dev->netdev_ops->ndo_features_check) features &= dev->netdev_ops->ndo_features_check(skb, dev, features); else features &= dflt_features_check(skb, dev, features); return harmonize_features(skb, features); } EXPORT_SYMBOL(netif_skb_features); static int xmit_one(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, bool more) { unsigned int len; int rc; if (dev_nit_active(dev)) dev_queue_xmit_nit(skb, dev); len = skb->len; trace_net_dev_start_xmit(skb, dev); rc = netdev_start_xmit(skb, dev, txq, more); trace_net_dev_xmit(skb, rc, dev, len); return rc; } struct sk_buff *dev_hard_start_xmit(struct sk_buff *first, struct net_device *dev, struct netdev_queue *txq, int *ret) { struct sk_buff *skb = first; int rc = NETDEV_TX_OK; while (skb) { struct sk_buff *next = skb->next; skb_mark_not_on_list(skb); rc = xmit_one(skb, dev, txq, next != NULL); if (unlikely(!dev_xmit_complete(rc))) { skb->next = next; goto out; } skb = next; if (netif_tx_queue_stopped(txq) && skb) { rc = NETDEV_TX_BUSY; break; } } out: *ret = rc; return skb; } static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb, netdev_features_t features) { if (skb_vlan_tag_present(skb) && !vlan_hw_offload_capable(features, skb->vlan_proto)) skb = __vlan_hwaccel_push_inside(skb); return skb; } int skb_csum_hwoffload_help(struct sk_buff *skb, const netdev_features_t features) { if (unlikely(skb_csum_is_sctp(skb))) return !!(features & NETIF_F_SCTP_CRC) ? 0 : skb_crc32c_csum_help(skb); if (features & NETIF_F_HW_CSUM) return 0; if (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) { if (vlan_get_protocol(skb) == htons(ETH_P_IPV6) && skb_network_header_len(skb) != sizeof(struct ipv6hdr)) goto sw_checksum; switch (skb->csum_offset) { case offsetof(struct tcphdr, check): case offsetof(struct udphdr, check): return 0; } } sw_checksum: return skb_checksum_help(skb); } EXPORT_SYMBOL(skb_csum_hwoffload_help); static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev, bool *again) { netdev_features_t features; features = netif_skb_features(skb); skb = validate_xmit_vlan(skb, features); if (unlikely(!skb)) goto out_null; skb = sk_validate_xmit_skb(skb, dev); if (unlikely(!skb)) goto out_null; if (netif_needs_gso(skb, features)) { struct sk_buff *segs; segs = skb_gso_segment(skb, features); if (IS_ERR(segs)) { goto out_kfree_skb; } else if (segs) { consume_skb(skb); skb = segs; } } else { if (skb_needs_linearize(skb, features) && __skb_linearize(skb)) goto out_kfree_skb; /* If packet is not checksummed and device does not * support checksumming for this protocol, complete * checksumming here. */ if (skb->ip_summed == CHECKSUM_PARTIAL) { if (skb->encapsulation) skb_set_inner_transport_header(skb, skb_checksum_start_offset(skb)); else skb_set_transport_header(skb, skb_checksum_start_offset(skb)); if (skb_csum_hwoffload_help(skb, features)) goto out_kfree_skb; } } skb = validate_xmit_xfrm(skb, features, again); return skb; out_kfree_skb: kfree_skb(skb); out_null: dev_core_stats_tx_dropped_inc(dev); return NULL; } struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again) { struct sk_buff *next, *head = NULL, *tail; for (; skb != NULL; skb = next) { next = skb->next; skb_mark_not_on_list(skb); /* in case skb won't be segmented, point to itself */ skb->prev = skb; skb = validate_xmit_skb(skb, dev, again); if (!skb) continue; if (!head) head = skb; else tail->next = skb; /* If skb was segmented, skb->prev points to * the last segment. If not, it still contains skb. */ tail = skb->prev; } return head; } EXPORT_SYMBOL_GPL(validate_xmit_skb_list); static void qdisc_pkt_len_init(struct sk_buff *skb) { const struct skb_shared_info *shinfo = skb_shinfo(skb); qdisc_skb_cb(skb)->pkt_len = skb->len; /* To get more precise estimation of bytes sent on wire, * we add to pkt_len the headers size of all segments */ if (shinfo->gso_size && skb_transport_header_was_set(skb)) { u16 gso_segs = shinfo->gso_segs; unsigned int hdr_len; /* mac layer + network layer */ hdr_len = skb_transport_offset(skb); /* + transport layer */ if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) { const struct tcphdr *th; struct tcphdr _tcphdr; th = skb_header_pointer(skb, hdr_len, sizeof(_tcphdr), &_tcphdr); if (likely(th)) hdr_len += __tcp_hdrlen(th); } else if (shinfo->gso_type & SKB_GSO_UDP_L4) { struct udphdr _udphdr; if (skb_header_pointer(skb, hdr_len, sizeof(_udphdr), &_udphdr)) hdr_len += sizeof(struct udphdr); } if (unlikely(shinfo->gso_type & SKB_GSO_DODGY)) { int payload = skb->len - hdr_len; /* Malicious packet. */ if (payload <= 0) return; gso_segs = DIV_ROUND_UP(payload, shinfo->gso_size); } qdisc_skb_cb(skb)->pkt_len += (gso_segs - 1) * hdr_len; } } static int dev_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *q, struct sk_buff **to_free, struct netdev_queue *txq) { int rc; rc = q->enqueue(skb, q, to_free) & NET_XMIT_MASK; if (rc == NET_XMIT_SUCCESS) trace_qdisc_enqueue(q, txq, skb); return rc; } static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, struct net_device *dev, struct netdev_queue *txq) { spinlock_t *root_lock = qdisc_lock(q); struct sk_buff *to_free = NULL; bool contended; int rc; qdisc_calculate_pkt_len(skb, q); tcf_set_drop_reason(skb, SKB_DROP_REASON_QDISC_DROP); if (q->flags & TCQ_F_NOLOCK) { if (q->flags & TCQ_F_CAN_BYPASS && nolock_qdisc_is_empty(q) && qdisc_run_begin(q)) { /* Retest nolock_qdisc_is_empty() within the protection * of q->seqlock to protect from racing with requeuing. */ if (unlikely(!nolock_qdisc_is_empty(q))) { rc = dev_qdisc_enqueue(skb, q, &to_free, txq); __qdisc_run(q); qdisc_run_end(q); goto no_lock_out; } qdisc_bstats_cpu_update(q, skb); if (sch_direct_xmit(skb, q, dev, txq, NULL, true) && !nolock_qdisc_is_empty(q)) __qdisc_run(q); qdisc_run_end(q); return NET_XMIT_SUCCESS; } rc = dev_qdisc_enqueue(skb, q, &to_free, txq); qdisc_run(q); no_lock_out: if (unlikely(to_free)) kfree_skb_list_reason(to_free, tcf_get_drop_reason(to_free)); return rc; } if (unlikely(READ_ONCE(q->owner) == smp_processor_id())) { kfree_skb_reason(skb, SKB_DROP_REASON_TC_RECLASSIFY_LOOP); return NET_XMIT_DROP; } /* * Heuristic to force contended enqueues to serialize on a * separate lock before trying to get qdisc main lock. * This permits qdisc->running owner to get the lock more * often and dequeue packets faster. * On PREEMPT_RT it is possible to preempt the qdisc owner during xmit * and then other tasks will only enqueue packets. The packets will be * sent after the qdisc owner is scheduled again. To prevent this * scenario the task always serialize on the lock. */ contended = qdisc_is_running(q) || IS_ENABLED(CONFIG_PREEMPT_RT); if (unlikely(contended)) spin_lock(&q->busylock); spin_lock(root_lock); if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { __qdisc_drop(skb, &to_free); rc = NET_XMIT_DROP; } else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) && qdisc_run_begin(q)) { /* * This is a work-conserving queue; there are no old skbs * waiting to be sent out; and the qdisc is not running - * xmit the skb directly. */ qdisc_bstats_update(q, skb); if (sch_direct_xmit(skb, q, dev, txq, root_lock, true)) { if (unlikely(contended)) { spin_unlock(&q->busylock); contended = false; } __qdisc_run(q); } qdisc_run_end(q); rc = NET_XMIT_SUCCESS; } else { WRITE_ONCE(q->owner, smp_processor_id()); rc = dev_qdisc_enqueue(skb, q, &to_free, txq); WRITE_ONCE(q->owner, -1); if (qdisc_run_begin(q)) { if (unlikely(contended)) { spin_unlock(&q->busylock); contended = false; } __qdisc_run(q); qdisc_run_end(q); } } spin_unlock(root_lock); if (unlikely(to_free)) kfree_skb_list_reason(to_free, tcf_get_drop_reason(to_free)); if (unlikely(contended)) spin_unlock(&q->busylock); return rc; } #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) static void skb_update_prio(struct sk_buff *skb) { const struct netprio_map *map; const struct sock *sk; unsigned int prioidx; if (skb->priority) return; map = rcu_dereference_bh(skb->dev->priomap); if (!map) return; sk = skb_to_full_sk(skb); if (!sk) return; prioidx = sock_cgroup_prioidx(&sk->sk_cgrp_data); if (prioidx < map->priomap_len) skb->priority = map->priomap[prioidx]; } #else #define skb_update_prio(skb) #endif /** * dev_loopback_xmit - loop back @skb * @net: network namespace this loopback is happening in * @sk: sk needed to be a netfilter okfn * @skb: buffer to transmit */ int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) { skb_reset_mac_header(skb); __skb_pull(skb, skb_network_offset(skb)); skb->pkt_type = PACKET_LOOPBACK; if (skb->ip_summed == CHECKSUM_NONE) skb->ip_summed = CHECKSUM_UNNECESSARY; DEBUG_NET_WARN_ON_ONCE(!skb_dst(skb)); skb_dst_force(skb); netif_rx(skb); return 0; } EXPORT_SYMBOL(dev_loopback_xmit); #ifdef CONFIG_NET_EGRESS static struct netdev_queue * netdev_tx_queue_mapping(struct net_device *dev, struct sk_buff *skb) { int qm = skb_get_queue_mapping(skb); return netdev_get_tx_queue(dev, netdev_cap_txqueue(dev, qm)); } #ifndef CONFIG_PREEMPT_RT static bool netdev_xmit_txqueue_skipped(void) { return __this_cpu_read(softnet_data.xmit.skip_txqueue); } void netdev_xmit_skip_txqueue(bool skip) { __this_cpu_write(softnet_data.xmit.skip_txqueue, skip); } EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue); #else static bool netdev_xmit_txqueue_skipped(void) { return current->net_xmit.skip_txqueue; } void netdev_xmit_skip_txqueue(bool skip) { current->net_xmit.skip_txqueue = skip; } EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue); #endif #endif /* CONFIG_NET_EGRESS */ #ifdef CONFIG_NET_XGRESS static int tc_run(struct tcx_entry *entry, struct sk_buff *skb, enum skb_drop_reason *drop_reason) { int ret = TC_ACT_UNSPEC; #ifdef CONFIG_NET_CLS_ACT struct mini_Qdisc *miniq = rcu_dereference_bh(entry->miniq); struct tcf_result res; if (!miniq) return ret; if (static_branch_unlikely(&tcf_bypass_check_needed_key)) { if (tcf_block_bypass_sw(miniq->block)) return ret; } tc_skb_cb(skb)->mru = 0; tc_skb_cb(skb)->post_ct = false; tcf_set_drop_reason(skb, *drop_reason); mini_qdisc_bstats_cpu_update(miniq, skb); ret = tcf_classify(skb, miniq->block, miniq->filter_list, &res, false); /* Only tcf related quirks below. */ switch (ret) { case TC_ACT_SHOT: *drop_reason = tcf_get_drop_reason(skb); mini_qdisc_qstats_cpu_drop(miniq); break; case TC_ACT_OK: case TC_ACT_RECLASSIFY: skb->tc_index = TC_H_MIN(res.classid); break; } #endif /* CONFIG_NET_CLS_ACT */ return ret; } static DEFINE_STATIC_KEY_FALSE(tcx_needed_key); void tcx_inc(void) { static_branch_inc(&tcx_needed_key); } void tcx_dec(void) { static_branch_dec(&tcx_needed_key); } static __always_inline enum tcx_action_base tcx_run(const struct bpf_mprog_entry *entry, struct sk_buff *skb, const bool needs_mac) { const struct bpf_mprog_fp *fp; const struct bpf_prog *prog; int ret = TCX_NEXT; if (needs_mac) __skb_push(skb, skb->mac_len); bpf_mprog_foreach_prog(entry, fp, prog) { bpf_compute_data_pointers(skb); ret = bpf_prog_run(prog, skb); if (ret != TCX_NEXT) break; } if (needs_mac) __skb_pull(skb, skb->mac_len); return tcx_action_code(skb, ret); } static __always_inline struct sk_buff * sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, struct net_device *orig_dev, bool *another) { struct bpf_mprog_entry *entry = rcu_dereference_bh(skb->dev->tcx_ingress); enum skb_drop_reason drop_reason = SKB_DROP_REASON_TC_INGRESS; struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; int sch_ret; if (!entry) return skb; bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); if (*pt_prev) { *ret = deliver_skb(skb, *pt_prev, orig_dev); *pt_prev = NULL; } qdisc_skb_cb(skb)->pkt_len = skb->len; tcx_set_ingress(skb, true); if (static_branch_unlikely(&tcx_needed_key)) { sch_ret = tcx_run(entry, skb, true); if (sch_ret != TC_ACT_UNSPEC) goto ingress_verdict; } sch_ret = tc_run(tcx_entry(entry), skb, &drop_reason); ingress_verdict: switch (sch_ret) { case TC_ACT_REDIRECT: /* skb_mac_header check was done by BPF, so we can safely * push the L2 header back before redirecting to another * netdev. */ __skb_push(skb, skb->mac_len); if (skb_do_redirect(skb) == -EAGAIN) { __skb_pull(skb, skb->mac_len); *another = true; break; } *ret = NET_RX_SUCCESS; bpf_net_ctx_clear(bpf_net_ctx); return NULL; case TC_ACT_SHOT: kfree_skb_reason(skb, drop_reason); *ret = NET_RX_DROP; bpf_net_ctx_clear(bpf_net_ctx); return NULL; /* used by tc_run */ case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: consume_skb(skb); fallthrough; case TC_ACT_CONSUMED: *ret = NET_RX_SUCCESS; bpf_net_ctx_clear(bpf_net_ctx); return NULL; } bpf_net_ctx_clear(bpf_net_ctx); return skb; } static __always_inline struct sk_buff * sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) { struct bpf_mprog_entry *entry = rcu_dereference_bh(dev->tcx_egress); enum skb_drop_reason drop_reason = SKB_DROP_REASON_TC_EGRESS; struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; int sch_ret; if (!entry) return skb; bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); /* qdisc_skb_cb(skb)->pkt_len & tcx_set_ingress() was * already set by the caller. */ if (static_branch_unlikely(&tcx_needed_key)) { sch_ret = tcx_run(entry, skb, false); if (sch_ret != TC_ACT_UNSPEC) goto egress_verdict; } sch_ret = tc_run(tcx_entry(entry), skb, &drop_reason); egress_verdict: switch (sch_ret) { case TC_ACT_REDIRECT: /* No need to push/pop skb's mac_header here on egress! */ skb_do_redirect(skb); *ret = NET_XMIT_SUCCESS; bpf_net_ctx_clear(bpf_net_ctx); return NULL; case TC_ACT_SHOT: kfree_skb_reason(skb, drop_reason); *ret = NET_XMIT_DROP; bpf_net_ctx_clear(bpf_net_ctx); return NULL; /* used by tc_run */ case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: consume_skb(skb); fallthrough; case TC_ACT_CONSUMED: *ret = NET_XMIT_SUCCESS; bpf_net_ctx_clear(bpf_net_ctx); return NULL; } bpf_net_ctx_clear(bpf_net_ctx); return skb; } #else static __always_inline struct sk_buff * sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, struct net_device *orig_dev, bool *another) { return skb; } static __always_inline struct sk_buff * sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) { return skb; } #endif /* CONFIG_NET_XGRESS */ #ifdef CONFIG_XPS static int __get_xps_queue_idx(struct net_device *dev, struct sk_buff *skb, struct xps_dev_maps *dev_maps, unsigned int tci) { int tc = netdev_get_prio_tc_map(dev, skb->priority); struct xps_map *map; int queue_index = -1; if (tc >= dev_maps->num_tc || tci >= dev_maps->nr_ids) return queue_index; tci *= dev_maps->num_tc; tci += tc; map = rcu_dereference(dev_maps->attr_map[tci]); if (map) { if (map->len == 1) queue_index = map->queues[0]; else queue_index = map->queues[reciprocal_scale( skb_get_hash(skb), map->len)]; if (unlikely(queue_index >= dev->real_num_tx_queues)) queue_index = -1; } return queue_index; } #endif static int get_xps_queue(struct net_device *dev, struct net_device *sb_dev, struct sk_buff *skb) { #ifdef CONFIG_XPS struct xps_dev_maps *dev_maps; struct sock *sk = skb->sk; int queue_index = -1; if (!static_key_false(&xps_needed)) return -1; rcu_read_lock(); if (!static_key_false(&xps_rxqs_needed)) goto get_cpus_map; dev_maps = rcu_dereference(sb_dev->xps_maps[XPS_RXQS]); if (dev_maps) { int tci = sk_rx_queue_get(sk); if (tci >= 0) queue_index = __get_xps_queue_idx(dev, skb, dev_maps, tci); } get_cpus_map: if (queue_index < 0) { dev_maps = rcu_dereference(sb_dev->xps_maps[XPS_CPUS]); if (dev_maps) { unsigned int tci = skb->sender_cpu - 1; queue_index = __get_xps_queue_idx(dev, skb, dev_maps, tci); } } rcu_read_unlock(); return queue_index; #else return -1; #endif } u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { return 0; } EXPORT_SYMBOL(dev_pick_tx_zero); u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { struct sock *sk = skb->sk; int queue_index = sk_tx_queue_get(sk); sb_dev = sb_dev ? : dev; if (queue_index < 0 || skb->ooo_okay || queue_index >= dev->real_num_tx_queues) { int new_index = get_xps_queue(dev, sb_dev, skb); if (new_index < 0) new_index = skb_tx_hash(dev, sb_dev, skb); if (queue_index != new_index && sk && sk_fullsock(sk) && rcu_access_pointer(sk->sk_dst_cache)) sk_tx_queue_set(sk, new_index); queue_index = new_index; } return queue_index; } EXPORT_SYMBOL(netdev_pick_tx); struct netdev_queue *netdev_core_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { int queue_index = 0; #ifdef CONFIG_XPS u32 sender_cpu = skb->sender_cpu - 1; if (sender_cpu >= (u32)NR_CPUS) skb->sender_cpu = raw_smp_processor_id() + 1; #endif if (dev->real_num_tx_queues != 1) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_select_queue) queue_index = ops->ndo_select_queue(dev, skb, sb_dev); else queue_index = netdev_pick_tx(dev, skb, sb_dev); queue_index = netdev_cap_txqueue(dev, queue_index); } skb_set_queue_mapping(skb, queue_index); return netdev_get_tx_queue(dev, queue_index); } /** * __dev_queue_xmit() - transmit a buffer * @skb: buffer to transmit * @sb_dev: suboordinate device used for L2 forwarding offload * * Queue a buffer for transmission to a network device. The caller must * have set the device and priority and built the buffer before calling * this function. The function can be called from an interrupt. * * When calling this method, interrupts MUST be enabled. This is because * the BH enable code must have IRQs enabled so that it will not deadlock. * * Regardless of the return value, the skb is consumed, so it is currently * difficult to retry a send to this method. (You can bump the ref count * before sending to hold a reference for retry if you are careful.) * * Return: * * 0 - buffer successfully transmitted * * positive qdisc return code - NET_XMIT_DROP etc. * * negative errno - other errors */ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) { struct net_device *dev = skb->dev; struct netdev_queue *txq = NULL; struct Qdisc *q; int rc = -ENOMEM; bool again = false; skb_reset_mac_header(skb); skb_assert_len(skb); if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP)) __skb_tstamp_tx(skb, NULL, NULL, skb->sk, SCM_TSTAMP_SCHED); /* Disable soft irqs for various locks below. Also * stops preemption for RCU. */ rcu_read_lock_bh(); skb_update_prio(skb); qdisc_pkt_len_init(skb); tcx_set_ingress(skb, false); #ifdef CONFIG_NET_EGRESS if (static_branch_unlikely(&egress_needed_key)) { if (nf_hook_egress_active()) { skb = nf_hook_egress(skb, &rc, dev); if (!skb) goto out; } netdev_xmit_skip_txqueue(false); nf_skip_egress(skb, true); skb = sch_handle_egress(skb, &rc, dev); if (!skb) goto out; nf_skip_egress(skb, false); if (netdev_xmit_txqueue_skipped()) txq = netdev_tx_queue_mapping(dev, skb); } #endif /* If device/qdisc don't need skb->dst, release it right now while * its hot in this cpu cache. */ if (dev->priv_flags & IFF_XMIT_DST_RELEASE) skb_dst_drop(skb); else skb_dst_force(skb); if (!txq) txq = netdev_core_pick_tx(dev, skb, sb_dev); q = rcu_dereference_bh(txq->qdisc); trace_net_dev_queue(skb); if (q->enqueue) { rc = __dev_xmit_skb(skb, q, dev, txq); goto out; } /* The device has no queue. Common case for software devices: * loopback, all the sorts of tunnels... * Really, it is unlikely that netif_tx_lock protection is necessary * here. (f.e. loopback and IP tunnels are clean ignoring statistics * counters.) * However, it is possible, that they rely on protection * made by us here. * Check this and shot the lock. It is not prone from deadlocks. *Either shot noqueue qdisc, it is even simpler 8) */ if (dev->flags & IFF_UP) { int cpu = smp_processor_id(); /* ok because BHs are off */ /* Other cpus might concurrently change txq->xmit_lock_owner * to -1 or to their cpu id, but not to our id. */ if (READ_ONCE(txq->xmit_lock_owner) != cpu) { if (dev_xmit_recursion()) goto recursion_alert; skb = validate_xmit_skb(skb, dev, &again); if (!skb) goto out; HARD_TX_LOCK(dev, txq, cpu); if (!netif_xmit_stopped(txq)) { dev_xmit_recursion_inc(); skb = dev_hard_start_xmit(skb, dev, txq, &rc); dev_xmit_recursion_dec(); if (dev_xmit_complete(rc)) { HARD_TX_UNLOCK(dev, txq); goto out; } } HARD_TX_UNLOCK(dev, txq); net_crit_ratelimited("Virtual device %s asks to queue packet!\n", dev->name); } else { /* Recursion is detected! It is possible, * unfortunately */ recursion_alert: net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n", dev->name); } } rc = -ENETDOWN; rcu_read_unlock_bh(); dev_core_stats_tx_dropped_inc(dev); kfree_skb_list(skb); return rc; out: rcu_read_unlock_bh(); return rc; } EXPORT_SYMBOL(__dev_queue_xmit); int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id) { struct net_device *dev = skb->dev; struct sk_buff *orig_skb = skb; struct netdev_queue *txq; int ret = NETDEV_TX_BUSY; bool again = false; if (unlikely(!netif_running(dev) || !netif_carrier_ok(dev))) goto drop; skb = validate_xmit_skb_list(skb, dev, &again); if (skb != orig_skb) goto drop; skb_set_queue_mapping(skb, queue_id); txq = skb_get_tx_queue(dev, skb); local_bh_disable(); dev_xmit_recursion_inc(); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_drv_stopped(txq)) ret = netdev_start_xmit(skb, dev, txq, false); HARD_TX_UNLOCK(dev, txq); dev_xmit_recursion_dec(); local_bh_enable(); return ret; drop: dev_core_stats_tx_dropped_inc(dev); kfree_skb_list(skb); return NET_XMIT_DROP; } EXPORT_SYMBOL(__dev_direct_xmit); /************************************************************************* * Receiver routines *************************************************************************/ static DEFINE_PER_CPU(struct task_struct *, backlog_napi); int weight_p __read_mostly = 64; /* old backlog weight */ int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ /* Called with irq disabled */ static inline void ____napi_schedule(struct softnet_data *sd, struct napi_struct *napi) { struct task_struct *thread; lockdep_assert_irqs_disabled(); if (test_bit(NAPI_STATE_THREADED, &napi->state)) { /* Paired with smp_mb__before_atomic() in * napi_enable()/dev_set_threaded(). * Use READ_ONCE() to guarantee a complete * read on napi->thread. Only call * wake_up_process() when it's not NULL. */ thread = READ_ONCE(napi->thread); if (thread) { if (use_backlog_threads() && thread == raw_cpu_read(backlog_napi)) goto use_local_napi; set_bit(NAPI_STATE_SCHED_THREADED, &napi->state); wake_up_process(thread); return; } } use_local_napi: list_add_tail(&napi->poll_list, &sd->poll_list); WRITE_ONCE(napi->list_owner, smp_processor_id()); /* If not called from net_rx_action() * we have to raise NET_RX_SOFTIRQ. */ if (!sd->in_net_rx_action) __raise_softirq_irqoff(NET_RX_SOFTIRQ); } #ifdef CONFIG_RPS struct static_key_false rps_needed __read_mostly; EXPORT_SYMBOL(rps_needed); struct static_key_false rfs_needed __read_mostly; EXPORT_SYMBOL(rfs_needed); static struct rps_dev_flow * set_rps_cpu(struct net_device *dev, struct sk_buff *skb, struct rps_dev_flow *rflow, u16 next_cpu) { if (next_cpu < nr_cpu_ids) { u32 head; #ifdef CONFIG_RFS_ACCEL struct netdev_rx_queue *rxqueue; struct rps_dev_flow_table *flow_table; struct rps_dev_flow *old_rflow; u16 rxq_index; u32 flow_id; int rc; /* Should we steer this flow to a different hardware queue? */ if (!skb_rx_queue_recorded(skb) || !dev->rx_cpu_rmap || !(dev->features & NETIF_F_NTUPLE)) goto out; rxq_index = cpu_rmap_lookup_index(dev->rx_cpu_rmap, next_cpu); if (rxq_index == skb_get_rx_queue(skb)) goto out; rxqueue = dev->_rx + rxq_index; flow_table = rcu_dereference(rxqueue->rps_flow_table); if (!flow_table) goto out; flow_id = skb_get_hash(skb) & flow_table->mask; rc = dev->netdev_ops->ndo_rx_flow_steer(dev, skb, rxq_index, flow_id); if (rc < 0) goto out; old_rflow = rflow; rflow = &flow_table->flows[flow_id]; WRITE_ONCE(rflow->filter, rc); if (old_rflow->filter == rc) WRITE_ONCE(old_rflow->filter, RPS_NO_FILTER); out: #endif head = READ_ONCE(per_cpu(softnet_data, next_cpu).input_queue_head); rps_input_queue_tail_save(&rflow->last_qtail, head); } WRITE_ONCE(rflow->cpu, next_cpu); return rflow; } /* * get_rps_cpu is called from netif_receive_skb and returns the target * CPU from the RPS map of the receiving queue for a given skb. * rcu_read_lock must be held on entry. */ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, struct rps_dev_flow **rflowp) { const struct rps_sock_flow_table *sock_flow_table; struct netdev_rx_queue *rxqueue = dev->_rx; struct rps_dev_flow_table *flow_table; struct rps_map *map; int cpu = -1; u32 tcpu; u32 hash; if (skb_rx_queue_recorded(skb)) { u16 index = skb_get_rx_queue(skb); if (unlikely(index >= dev->real_num_rx_queues)) { WARN_ONCE(dev->real_num_rx_queues > 1, "%s received packet on queue %u, but number " "of RX queues is %u\n", dev->name, index, dev->real_num_rx_queues); goto done; } rxqueue += index; } /* Avoid computing hash if RFS/RPS is not active for this rxqueue */ flow_table = rcu_dereference(rxqueue->rps_flow_table); map = rcu_dereference(rxqueue->rps_map); if (!flow_table && !map) goto done; skb_reset_network_header(skb); hash = skb_get_hash(skb); if (!hash) goto done; sock_flow_table = rcu_dereference(net_hotdata.rps_sock_flow_table); if (flow_table && sock_flow_table) { struct rps_dev_flow *rflow; u32 next_cpu; u32 ident; /* First check into global flow table if there is a match. * This READ_ONCE() pairs with WRITE_ONCE() from rps_record_sock_flow(). */ ident = READ_ONCE(sock_flow_table->ents[hash & sock_flow_table->mask]); if ((ident ^ hash) & ~net_hotdata.rps_cpu_mask) goto try_rps; next_cpu = ident & net_hotdata.rps_cpu_mask; /* OK, now we know there is a match, * we can look at the local (per receive queue) flow table */ rflow = &flow_table->flows[hash & flow_table->mask]; tcpu = rflow->cpu; /* * If the desired CPU (where last recvmsg was done) is * different from current CPU (one in the rx-queue flow * table entry), switch if one of the following holds: * - Current CPU is unset (>= nr_cpu_ids). * - Current CPU is offline. * - The current CPU's queue tail has advanced beyond the * last packet that was enqueued using this table entry. * This guarantees that all previous packets for the flow * have been dequeued, thus preserving in order delivery. */ if (unlikely(tcpu != next_cpu) && (tcpu >= nr_cpu_ids || !cpu_online(tcpu) || ((int)(READ_ONCE(per_cpu(softnet_data, tcpu).input_queue_head) - rflow->last_qtail)) >= 0)) { tcpu = next_cpu; rflow = set_rps_cpu(dev, skb, rflow, next_cpu); } if (tcpu < nr_cpu_ids && cpu_online(tcpu)) { *rflowp = rflow; cpu = tcpu; goto done; } } try_rps: if (map) { tcpu = map->cpus[reciprocal_scale(hash, map->len)]; if (cpu_online(tcpu)) { cpu = tcpu; goto done; } } done: return cpu; } #ifdef CONFIG_RFS_ACCEL /** * rps_may_expire_flow - check whether an RFS hardware filter may be removed * @dev: Device on which the filter was set * @rxq_index: RX queue index * @flow_id: Flow ID passed to ndo_rx_flow_steer() * @filter_id: Filter ID returned by ndo_rx_flow_steer() * * Drivers that implement ndo_rx_flow_steer() should periodically call * this function for each installed filter and remove the filters for * which it returns %true. */ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id, u16 filter_id) { struct netdev_rx_queue *rxqueue = dev->_rx + rxq_index; struct rps_dev_flow_table *flow_table; struct rps_dev_flow *rflow; bool expire = true; unsigned int cpu; rcu_read_lock(); flow_table = rcu_dereference(rxqueue->rps_flow_table); if (flow_table && flow_id <= flow_table->mask) { rflow = &flow_table->flows[flow_id]; cpu = READ_ONCE(rflow->cpu); if (READ_ONCE(rflow->filter) == filter_id && cpu < nr_cpu_ids && ((int)(READ_ONCE(per_cpu(softnet_data, cpu).input_queue_head) - READ_ONCE(rflow->last_qtail)) < (int)(10 * flow_table->mask))) expire = false; } rcu_read_unlock(); return expire; } EXPORT_SYMBOL(rps_may_expire_flow); #endif /* CONFIG_RFS_ACCEL */ /* Called from hardirq (IPI) context */ static void rps_trigger_softirq(void *data) { struct softnet_data *sd = data; ____napi_schedule(sd, &sd->backlog); sd->received_rps++; } #endif /* CONFIG_RPS */ /* Called from hardirq (IPI) context */ static void trigger_rx_softirq(void *data) { struct softnet_data *sd = data; __raise_softirq_irqoff(NET_RX_SOFTIRQ); smp_store_release(&sd->defer_ipi_scheduled, 0); } /* * After we queued a packet into sd->input_pkt_queue, * we need to make sure this queue is serviced soon. * * - If this is another cpu queue, link it to our rps_ipi_list, * and make sure we will process rps_ipi_list from net_rx_action(). * * - If this is our own queue, NAPI schedule our backlog. * Note that this also raises NET_RX_SOFTIRQ. */ static void napi_schedule_rps(struct softnet_data *sd) { struct softnet_data *mysd = this_cpu_ptr(&softnet_data); #ifdef CONFIG_RPS if (sd != mysd) { if (use_backlog_threads()) { __napi_schedule_irqoff(&sd->backlog); return; } sd->rps_ipi_next = mysd->rps_ipi_list; mysd->rps_ipi_list = sd; /* If not called from net_rx_action() or napi_threaded_poll() * we have to raise NET_RX_SOFTIRQ. */ if (!mysd->in_net_rx_action && !mysd->in_napi_threaded_poll) __raise_softirq_irqoff(NET_RX_SOFTIRQ); return; } #endif /* CONFIG_RPS */ __napi_schedule_irqoff(&mysd->backlog); } void kick_defer_list_purge(struct softnet_data *sd, unsigned int cpu) { unsigned long flags; if (use_backlog_threads()) { backlog_lock_irq_save(sd, &flags); if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) __napi_schedule_irqoff(&sd->backlog); backlog_unlock_irq_restore(sd, &flags); } else if (!cmpxchg(&sd->defer_ipi_scheduled, 0, 1)) { smp_call_function_single_async(cpu, &sd->defer_csd); } } #ifdef CONFIG_NET_FLOW_LIMIT int netdev_flow_limit_table_len __read_mostly = (1 << 12); #endif static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen) { #ifdef CONFIG_NET_FLOW_LIMIT struct sd_flow_limit *fl; struct softnet_data *sd; unsigned int old_flow, new_flow; if (qlen < (READ_ONCE(net_hotdata.max_backlog) >> 1)) return false; sd = this_cpu_ptr(&softnet_data); rcu_read_lock(); fl = rcu_dereference(sd->flow_limit); if (fl) { new_flow = skb_get_hash(skb) & (fl->num_buckets - 1); old_flow = fl->history[fl->history_head]; fl->history[fl->history_head] = new_flow; fl->history_head++; fl->history_head &= FLOW_LIMIT_HISTORY - 1; if (likely(fl->buckets[old_flow])) fl->buckets[old_flow]--; if (++fl->buckets[new_flow] > (FLOW_LIMIT_HISTORY >> 1)) { fl->count++; rcu_read_unlock(); return true; } } rcu_read_unlock(); #endif return false; } /* * enqueue_to_backlog is called to queue an skb to a per CPU backlog * queue (may be a remote CPU queue). */ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, unsigned int *qtail) { enum skb_drop_reason reason; struct softnet_data *sd; unsigned long flags; unsigned int qlen; int max_backlog; u32 tail; reason = SKB_DROP_REASON_DEV_READY; if (!netif_running(skb->dev)) goto bad_dev; reason = SKB_DROP_REASON_CPU_BACKLOG; sd = &per_cpu(softnet_data, cpu); qlen = skb_queue_len_lockless(&sd->input_pkt_queue); max_backlog = READ_ONCE(net_hotdata.max_backlog); if (unlikely(qlen > max_backlog)) goto cpu_backlog_drop; backlog_lock_irq_save(sd, &flags); qlen = skb_queue_len(&sd->input_pkt_queue); if (qlen <= max_backlog && !skb_flow_limit(skb, qlen)) { if (!qlen) { /* Schedule NAPI for backlog device. We can use * non atomic operation as we own the queue lock. */ if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) napi_schedule_rps(sd); } __skb_queue_tail(&sd->input_pkt_queue, skb); tail = rps_input_queue_tail_incr(sd); backlog_unlock_irq_restore(sd, &flags); /* save the tail outside of the critical section */ rps_input_queue_tail_save(qtail, tail); return NET_RX_SUCCESS; } backlog_unlock_irq_restore(sd, &flags); cpu_backlog_drop: atomic_inc(&sd->dropped); bad_dev: dev_core_stats_rx_dropped_inc(skb->dev); kfree_skb_reason(skb, reason); return NET_RX_DROP; } static struct netdev_rx_queue *netif_get_rxqueue(struct sk_buff *skb) { struct net_device *dev = skb->dev; struct netdev_rx_queue *rxqueue; rxqueue = dev->_rx; if (skb_rx_queue_recorded(skb)) { u16 index = skb_get_rx_queue(skb); if (unlikely(index >= dev->real_num_rx_queues)) { WARN_ONCE(dev->real_num_rx_queues > 1, "%s received packet on queue %u, but number " "of RX queues is %u\n", dev->name, index, dev->real_num_rx_queues); return rxqueue; /* Return first rxqueue */ } rxqueue += index; } return rxqueue; } u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { void *orig_data, *orig_data_end, *hard_start; struct netdev_rx_queue *rxqueue; bool orig_bcast, orig_host; u32 mac_len, frame_sz; __be16 orig_eth_type; struct ethhdr *eth; u32 metalen, act; int off; /* The XDP program wants to see the packet starting at the MAC * header. */ mac_len = skb->data - skb_mac_header(skb); hard_start = skb->data - skb_headroom(skb); /* SKB "head" area always have tailroom for skb_shared_info */ frame_sz = (void *)skb_end_pointer(skb) - hard_start; frame_sz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); rxqueue = netif_get_rxqueue(skb); xdp_init_buff(xdp, frame_sz, &rxqueue->xdp_rxq); xdp_prepare_buff(xdp, hard_start, skb_headroom(skb) - mac_len, skb_headlen(skb) + mac_len, true); if (skb_is_nonlinear(skb)) { skb_shinfo(skb)->xdp_frags_size = skb->data_len; xdp_buff_set_frags_flag(xdp); } else { xdp_buff_clear_frags_flag(xdp); } orig_data_end = xdp->data_end; orig_data = xdp->data; eth = (struct ethhdr *)xdp->data; orig_host = ether_addr_equal_64bits(eth->h_dest, skb->dev->dev_addr); orig_bcast = is_multicast_ether_addr_64bits(eth->h_dest); orig_eth_type = eth->h_proto; act = bpf_prog_run_xdp(xdp_prog, xdp); /* check if bpf_xdp_adjust_head was used */ off = xdp->data - orig_data; if (off) { if (off > 0) __skb_pull(skb, off); else if (off < 0) __skb_push(skb, -off); skb->mac_header += off; skb_reset_network_header(skb); } /* check if bpf_xdp_adjust_tail was used */ off = xdp->data_end - orig_data_end; if (off != 0) { skb_set_tail_pointer(skb, xdp->data_end - xdp->data); skb->len += off; /* positive on grow, negative on shrink */ } /* XDP frag metadata (e.g. nr_frags) are updated in eBPF helpers * (e.g. bpf_xdp_adjust_tail), we need to update data_len here. */ if (xdp_buff_has_frags(xdp)) skb->data_len = skb_shinfo(skb)->xdp_frags_size; else skb->data_len = 0; /* check if XDP changed eth hdr such SKB needs update */ eth = (struct ethhdr *)xdp->data; if ((orig_eth_type != eth->h_proto) || (orig_host != ether_addr_equal_64bits(eth->h_dest, skb->dev->dev_addr)) || (orig_bcast != is_multicast_ether_addr_64bits(eth->h_dest))) { __skb_push(skb, ETH_HLEN); skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, skb->dev); } /* Redirect/Tx gives L2 packet, code that will reuse skb must __skb_pull * before calling us again on redirect path. We do not call do_redirect * as we leave that up to the caller. * * Caller is responsible for managing lifetime of skb (i.e. calling * kfree_skb in response to actions it cannot handle/XDP_DROP). */ switch (act) { case XDP_REDIRECT: case XDP_TX: __skb_push(skb, mac_len); break; case XDP_PASS: metalen = xdp->data - xdp->data_meta; if (metalen) skb_metadata_set(skb, metalen); break; } return act; } static int netif_skb_check_for_xdp(struct sk_buff **pskb, struct bpf_prog *prog) { struct sk_buff *skb = *pskb; int err, hroom, troom; if (!skb_cow_data_for_xdp(this_cpu_read(system_page_pool), pskb, prog)) return 0; /* In case we have to go down the path and also linearize, * then lets do the pskb_expand_head() work just once here. */ hroom = XDP_PACKET_HEADROOM - skb_headroom(skb); troom = skb->tail + skb->data_len - skb->end; err = pskb_expand_head(skb, hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0, troom > 0 ? troom + 128 : 0, GFP_ATOMIC); if (err) return err; return skb_linearize(skb); } static u32 netif_receive_generic_xdp(struct sk_buff **pskb, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { struct sk_buff *skb = *pskb; u32 mac_len, act = XDP_DROP; /* Reinjected packets coming from act_mirred or similar should * not get XDP generic processing. */ if (skb_is_redirected(skb)) return XDP_PASS; /* XDP packets must have sufficient headroom of XDP_PACKET_HEADROOM * bytes. This is the guarantee that also native XDP provides, * thus we need to do it here as well. */ mac_len = skb->data - skb_mac_header(skb); __skb_push(skb, mac_len); if (skb_cloned(skb) || skb_is_nonlinear(skb) || skb_headroom(skb) < XDP_PACKET_HEADROOM) { if (netif_skb_check_for_xdp(pskb, xdp_prog)) goto do_drop; } __skb_pull(*pskb, mac_len); act = bpf_prog_run_generic_xdp(*pskb, xdp, xdp_prog); switch (act) { case XDP_REDIRECT: case XDP_TX: case XDP_PASS: break; default: bpf_warn_invalid_xdp_action((*pskb)->dev, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception((*pskb)->dev, xdp_prog, act); fallthrough; case XDP_DROP: do_drop: kfree_skb(*pskb); break; } return act; } /* When doing generic XDP we have to bypass the qdisc layer and the * network taps in order to match in-driver-XDP behavior. This also means * that XDP packets are able to starve other packets going through a qdisc, * and DDOS attacks will be more effective. In-driver-XDP use dedicated TX * queues, so they do not have this starvation issue. */ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) { struct net_device *dev = skb->dev; struct netdev_queue *txq; bool free_skb = true; int cpu, rc; txq = netdev_core_pick_tx(dev, skb, NULL); cpu = smp_processor_id(); HARD_TX_LOCK(dev, txq, cpu); if (!netif_xmit_frozen_or_drv_stopped(txq)) { rc = netdev_start_xmit(skb, dev, txq, 0); if (dev_xmit_complete(rc)) free_skb = false; } HARD_TX_UNLOCK(dev, txq); if (free_skb) { trace_xdp_exception(dev, xdp_prog, XDP_TX); dev_core_stats_tx_dropped_inc(dev); kfree_skb(skb); } } static DEFINE_STATIC_KEY_FALSE(generic_xdp_needed_key); int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff **pskb) { struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; if (xdp_prog) { struct xdp_buff xdp; u32 act; int err; bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); act = netif_receive_generic_xdp(pskb, &xdp, xdp_prog); if (act != XDP_PASS) { switch (act) { case XDP_REDIRECT: err = xdp_do_generic_redirect((*pskb)->dev, *pskb, &xdp, xdp_prog); if (err) goto out_redir; break; case XDP_TX: generic_xdp_tx(*pskb, xdp_prog); break; } bpf_net_ctx_clear(bpf_net_ctx); return XDP_DROP; } bpf_net_ctx_clear(bpf_net_ctx); } return XDP_PASS; out_redir: bpf_net_ctx_clear(bpf_net_ctx); kfree_skb_reason(*pskb, SKB_DROP_REASON_XDP); return XDP_DROP; } EXPORT_SYMBOL_GPL(do_xdp_generic); static int netif_rx_internal(struct sk_buff *skb) { int ret; net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), skb); trace_netif_rx(skb); #ifdef CONFIG_RPS if (static_branch_unlikely(&rps_needed)) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu; rcu_read_lock(); cpu = get_rps_cpu(skb->dev, skb, &rflow); if (cpu < 0) cpu = smp_processor_id(); ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); rcu_read_unlock(); } else #endif { unsigned int qtail; ret = enqueue_to_backlog(skb, smp_processor_id(), &qtail); } return ret; } /** * __netif_rx - Slightly optimized version of netif_rx * @skb: buffer to post * * This behaves as netif_rx except that it does not disable bottom halves. * As a result this function may only be invoked from the interrupt context * (either hard or soft interrupt). */ int __netif_rx(struct sk_buff *skb) { int ret; lockdep_assert_once(hardirq_count() | softirq_count()); trace_netif_rx_entry(skb); ret = netif_rx_internal(skb); trace_netif_rx_exit(ret); return ret; } EXPORT_SYMBOL(__netif_rx); /** * netif_rx - post buffer to the network code * @skb: buffer to post * * This function receives a packet from a device driver and queues it for * the upper (protocol) levels to process via the backlog NAPI device. It * always succeeds. The buffer may be dropped during processing for * congestion control or by the protocol layers. * The network buffer is passed via the backlog NAPI device. Modern NIC * driver should use NAPI and GRO. * This function can used from interrupt and from process context. The * caller from process context must not disable interrupts before invoking * this function. * * return values: * NET_RX_SUCCESS (no congestion) * NET_RX_DROP (packet was dropped) * */ int netif_rx(struct sk_buff *skb) { bool need_bh_off = !(hardirq_count() | softirq_count()); int ret; if (need_bh_off) local_bh_disable(); trace_netif_rx_entry(skb); ret = netif_rx_internal(skb); trace_netif_rx_exit(ret); if (need_bh_off) local_bh_enable(); return ret; } EXPORT_SYMBOL(netif_rx); static __latent_entropy void net_tx_action(void) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); if (sd->completion_queue) { struct sk_buff *clist; local_irq_disable(); clist = sd->completion_queue; sd->completion_queue = NULL; local_irq_enable(); while (clist) { struct sk_buff *skb = clist; clist = clist->next; WARN_ON(refcount_read(&skb->users)); if (likely(get_kfree_skb_cb(skb)->reason == SKB_CONSUMED)) trace_consume_skb(skb, net_tx_action); else trace_kfree_skb(skb, net_tx_action, get_kfree_skb_cb(skb)->reason, NULL); if (skb->fclone != SKB_FCLONE_UNAVAILABLE) __kfree_skb(skb); else __napi_kfree_skb(skb, get_kfree_skb_cb(skb)->reason); } } if (sd->output_queue) { struct Qdisc *head; local_irq_disable(); head = sd->output_queue; sd->output_queue = NULL; sd->output_queue_tailp = &sd->output_queue; local_irq_enable(); rcu_read_lock(); while (head) { struct Qdisc *q = head; spinlock_t *root_lock = NULL; head = head->next_sched; /* We need to make sure head->next_sched is read * before clearing __QDISC_STATE_SCHED */ smp_mb__before_atomic(); if (!(q->flags & TCQ_F_NOLOCK)) { root_lock = qdisc_lock(q); spin_lock(root_lock); } else if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { /* There is a synchronize_net() between * STATE_DEACTIVATED flag being set and * qdisc_reset()/some_qdisc_is_busy() in * dev_deactivate(), so we can safely bail out * early here to avoid data race between * qdisc_deactivate() and some_qdisc_is_busy() * for lockless qdisc. */ clear_bit(__QDISC_STATE_SCHED, &q->state); continue; } clear_bit(__QDISC_STATE_SCHED, &q->state); qdisc_run(q); if (root_lock) spin_unlock(root_lock); } rcu_read_unlock(); } xfrm_dev_backlog(sd); } #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_ATM_LANE) /* This hook is defined here for ATM LANE */ int (*br_fdb_test_addr_hook)(struct net_device *dev, unsigned char *addr) __read_mostly; EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook); #endif /** * netdev_is_rx_handler_busy - check if receive handler is registered * @dev: device to check * * Check if a receive handler is already registered for a given device. * Return true if there one. * * The caller must hold the rtnl_mutex. */ bool netdev_is_rx_handler_busy(struct net_device *dev) { ASSERT_RTNL(); return dev && rtnl_dereference(dev->rx_handler); } EXPORT_SYMBOL_GPL(netdev_is_rx_handler_busy); /** * netdev_rx_handler_register - register receive handler * @dev: device to register a handler for * @rx_handler: receive handler to register * @rx_handler_data: data pointer that is used by rx handler * * Register a receive handler for a device. This handler will then be * called from __netif_receive_skb. A negative errno code is returned * on a failure. * * The caller must hold the rtnl_mutex. * * For a general description of rx_handler, see enum rx_handler_result. */ int netdev_rx_handler_register(struct net_device *dev, rx_handler_func_t *rx_handler, void *rx_handler_data) { if (netdev_is_rx_handler_busy(dev)) return -EBUSY; if (dev->priv_flags & IFF_NO_RX_HANDLER) return -EINVAL; /* Note: rx_handler_data must be set before rx_handler */ rcu_assign_pointer(dev->rx_handler_data, rx_handler_data); rcu_assign_pointer(dev->rx_handler, rx_handler); return 0; } EXPORT_SYMBOL_GPL(netdev_rx_handler_register); /** * netdev_rx_handler_unregister - unregister receive handler * @dev: device to unregister a handler from * * Unregister a receive handler from a device. * * The caller must hold the rtnl_mutex. */ void netdev_rx_handler_unregister(struct net_device *dev) { ASSERT_RTNL(); RCU_INIT_POINTER(dev->rx_handler, NULL); /* a reader seeing a non NULL rx_handler in a rcu_read_lock() * section has a guarantee to see a non NULL rx_handler_data * as well. */ synchronize_net(); RCU_INIT_POINTER(dev->rx_handler_data, NULL); } EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister); /* * Limit the use of PFMEMALLOC reserves to those protocols that implement * the special handling of PFMEMALLOC skbs. */ static bool skb_pfmemalloc_protocol(struct sk_buff *skb) { switch (skb->protocol) { case htons(ETH_P_ARP): case htons(ETH_P_IP): case htons(ETH_P_IPV6): case htons(ETH_P_8021Q): case htons(ETH_P_8021AD): return true; default: return false; } } static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, struct net_device *orig_dev) { if (nf_hook_ingress_active(skb)) { int ingress_retval; if (*pt_prev) { *ret = deliver_skb(skb, *pt_prev, orig_dev); *pt_prev = NULL; } rcu_read_lock(); ingress_retval = nf_hook_ingress(skb); rcu_read_unlock(); return ingress_retval; } return 0; } static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc, struct packet_type **ppt_prev) { struct packet_type *ptype, *pt_prev; rx_handler_func_t *rx_handler; struct sk_buff *skb = *pskb; struct net_device *orig_dev; bool deliver_exact = false; int ret = NET_RX_DROP; __be16 type; net_timestamp_check(!READ_ONCE(net_hotdata.tstamp_prequeue), skb); trace_netif_receive_skb(skb); orig_dev = skb->dev; skb_reset_network_header(skb); if (!skb_transport_header_was_set(skb)) skb_reset_transport_header(skb); skb_reset_mac_len(skb); pt_prev = NULL; another_round: skb->skb_iif = skb->dev->ifindex; __this_cpu_inc(softnet_data.processed); if (static_branch_unlikely(&generic_xdp_needed_key)) { int ret2; migrate_disable(); ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), &skb); migrate_enable(); if (ret2 != XDP_PASS) { ret = NET_RX_DROP; goto out; } } if (eth_type_vlan(skb->protocol)) { skb = skb_vlan_untag(skb); if (unlikely(!skb)) goto out; } if (skb_skip_tc_classify(skb)) goto skip_classify; if (pfmemalloc) goto skip_taps; list_for_each_entry_rcu(ptype, &net_hotdata.ptype_all, list) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } list_for_each_entry_rcu(ptype, &skb->dev->ptype_all, list) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } skip_taps: #ifdef CONFIG_NET_INGRESS if (static_branch_unlikely(&ingress_needed_key)) { bool another = false; nf_skip_egress(skb, true); skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev, &another); if (another) goto another_round; if (!skb) goto out; nf_skip_egress(skb, false); if (nf_ingress(skb, &pt_prev, &ret, orig_dev) < 0) goto out; } #endif skb_reset_redirect(skb); skip_classify: if (pfmemalloc && !skb_pfmemalloc_protocol(skb)) goto drop; if (skb_vlan_tag_present(skb)) { if (pt_prev) { ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = NULL; } if (vlan_do_receive(&skb)) goto another_round; else if (unlikely(!skb)) goto out; } rx_handler = rcu_dereference(skb->dev->rx_handler); if (rx_handler) { if (pt_prev) { ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = NULL; } switch (rx_handler(&skb)) { case RX_HANDLER_CONSUMED: ret = NET_RX_SUCCESS; goto out; case RX_HANDLER_ANOTHER: goto another_round; case RX_HANDLER_EXACT: deliver_exact = true; break; case RX_HANDLER_PASS: break; default: BUG(); } } if (unlikely(skb_vlan_tag_present(skb)) && !netdev_uses_dsa(skb->dev)) { check_vlan_id: if (skb_vlan_tag_get_id(skb)) { /* Vlan id is non 0 and vlan_do_receive() above couldn't * find vlan device. */ skb->pkt_type = PACKET_OTHERHOST; } else if (eth_type_vlan(skb->protocol)) { /* Outer header is 802.1P with vlan 0, inner header is * 802.1Q or 802.1AD and vlan_do_receive() above could * not find vlan dev for vlan id 0. */ __vlan_hwaccel_clear_tag(skb); skb = skb_vlan_untag(skb); if (unlikely(!skb)) goto out; if (vlan_do_receive(&skb)) /* After stripping off 802.1P header with vlan 0 * vlan dev is found for inner header. */ goto another_round; else if (unlikely(!skb)) goto out; else /* We have stripped outer 802.1P vlan 0 header. * But could not find vlan dev. * check again for vlan id to set OTHERHOST. */ goto check_vlan_id; } /* Note: we might in the future use prio bits * and set skb->priority like in vlan_do_receive() * For the time being, just ignore Priority Code Point */ __vlan_hwaccel_clear_tag(skb); } type = skb->protocol; /* deliver only exact match when indicated */ if (likely(!deliver_exact)) { deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type, &ptype_base[ntohs(type) & PTYPE_HASH_MASK]); } deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type, &orig_dev->ptype_specific); if (unlikely(skb->dev != orig_dev)) { deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type, &skb->dev->ptype_specific); } if (pt_prev) { if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) goto drop; *ppt_prev = pt_prev; } else { drop: if (!deliver_exact) dev_core_stats_rx_dropped_inc(skb->dev); else dev_core_stats_rx_nohandler_inc(skb->dev); kfree_skb_reason(skb, SKB_DROP_REASON_UNHANDLED_PROTO); /* Jamal, now you will not able to escape explaining * me how you were going to use this. :-) */ ret = NET_RX_DROP; } out: /* The invariant here is that if *ppt_prev is not NULL * then skb should also be non-NULL. * * Apparently *ppt_prev assignment above holds this invariant due to * skb dereferencing near it. */ *pskb = skb; return ret; } static int __netif_receive_skb_one_core(struct sk_buff *skb, bool pfmemalloc) { struct net_device *orig_dev = skb->dev; struct packet_type *pt_prev = NULL; int ret; ret = __netif_receive_skb_core(&skb, pfmemalloc, &pt_prev); if (pt_prev) ret = INDIRECT_CALL_INET(pt_prev->func, ipv6_rcv, ip_rcv, skb, skb->dev, pt_prev, orig_dev); return ret; } /** * netif_receive_skb_core - special purpose version of netif_receive_skb * @skb: buffer to process * * More direct receive version of netif_receive_skb(). It should * only be used by callers that have a need to skip RPS and Generic XDP. * Caller must also take care of handling if ``(page_is_)pfmemalloc``. * * This function may only be called from softirq context and interrupts * should be enabled. * * Return values (usually ignored): * NET_RX_SUCCESS: no congestion * NET_RX_DROP: packet was dropped */ int netif_receive_skb_core(struct sk_buff *skb) { int ret; rcu_read_lock(); ret = __netif_receive_skb_one_core(skb, false); rcu_read_unlock(); return ret; } EXPORT_SYMBOL(netif_receive_skb_core); static inline void __netif_receive_skb_list_ptype(struct list_head *head, struct packet_type *pt_prev, struct net_device *orig_dev) { struct sk_buff *skb, *next; if (!pt_prev) return; if (list_empty(head)) return; if (pt_prev->list_func != NULL) INDIRECT_CALL_INET(pt_prev->list_func, ipv6_list_rcv, ip_list_rcv, head, pt_prev, orig_dev); else list_for_each_entry_safe(skb, next, head, list) { skb_list_del_init(skb); pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } } static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemalloc) { /* Fast-path assumptions: * - There is no RX handler. * - Only one packet_type matches. * If either of these fails, we will end up doing some per-packet * processing in-line, then handling the 'last ptype' for the whole * sublist. This can't cause out-of-order delivery to any single ptype, * because the 'last ptype' must be constant across the sublist, and all * other ptypes are handled per-packet. */ /* Current (common) ptype of sublist */ struct packet_type *pt_curr = NULL; /* Current (common) orig_dev of sublist */ struct net_device *od_curr = NULL; struct sk_buff *skb, *next; LIST_HEAD(sublist); list_for_each_entry_safe(skb, next, head, list) { struct net_device *orig_dev = skb->dev; struct packet_type *pt_prev = NULL; skb_list_del_init(skb); __netif_receive_skb_core(&skb, pfmemalloc, &pt_prev); if (!pt_prev) continue; if (pt_curr != pt_prev || od_curr != orig_dev) { /* dispatch old sublist */ __netif_receive_skb_list_ptype(&sublist, pt_curr, od_curr); /* start new sublist */ INIT_LIST_HEAD(&sublist); pt_curr = pt_prev; od_curr = orig_dev; } list_add_tail(&skb->list, &sublist); } /* dispatch final sublist */ __netif_receive_skb_list_ptype(&sublist, pt_curr, od_curr); } static int __netif_receive_skb(struct sk_buff *skb) { int ret; if (sk_memalloc_socks() && skb_pfmemalloc(skb)) { unsigned int noreclaim_flag; /* * PFMEMALLOC skbs are special, they should * - be delivered to SOCK_MEMALLOC sockets only * - stay away from userspace * - have bounded memory usage * * Use PF_MEMALLOC as this saves us from propagating the allocation * context down to all allocation sites. */ noreclaim_flag = memalloc_noreclaim_save(); ret = __netif_receive_skb_one_core(skb, true); memalloc_noreclaim_restore(noreclaim_flag); } else ret = __netif_receive_skb_one_core(skb, false); return ret; } static void __netif_receive_skb_list(struct list_head *head) { unsigned long noreclaim_flag = 0; struct sk_buff *skb, *next; bool pfmemalloc = false; /* Is current sublist PF_MEMALLOC? */ list_for_each_entry_safe(skb, next, head, list) { if ((sk_memalloc_socks() && skb_pfmemalloc(skb)) != pfmemalloc) { struct list_head sublist; /* Handle the previous sublist */ list_cut_before(&sublist, head, &skb->list); if (!list_empty(&sublist)) __netif_receive_skb_list_core(&sublist, pfmemalloc); pfmemalloc = !pfmemalloc; /* See comments in __netif_receive_skb */ if (pfmemalloc) noreclaim_flag = memalloc_noreclaim_save(); else memalloc_noreclaim_restore(noreclaim_flag); } } /* Handle the remaining sublist */ if (!list_empty(head)) __netif_receive_skb_list_core(head, pfmemalloc); /* Restore pflags */ if (pfmemalloc) memalloc_noreclaim_restore(noreclaim_flag); } static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp) { struct bpf_prog *old = rtnl_dereference(dev->xdp_prog); struct bpf_prog *new = xdp->prog; int ret = 0; switch (xdp->command) { case XDP_SETUP_PROG: rcu_assign_pointer(dev->xdp_prog, new); if (old) bpf_prog_put(old); if (old && !new) { static_branch_dec(&generic_xdp_needed_key); } else if (new && !old) { static_branch_inc(&generic_xdp_needed_key); dev_disable_lro(dev); dev_disable_gro_hw(dev); } break; default: ret = -EINVAL; break; } return ret; } static int netif_receive_skb_internal(struct sk_buff *skb) { int ret; net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), skb); if (skb_defer_rx_timestamp(skb)) return NET_RX_SUCCESS; rcu_read_lock(); #ifdef CONFIG_RPS if (static_branch_unlikely(&rps_needed)) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu = get_rps_cpu(skb->dev, skb, &rflow); if (cpu >= 0) { ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); rcu_read_unlock(); return ret; } } #endif ret = __netif_receive_skb(skb); rcu_read_unlock(); return ret; } void netif_receive_skb_list_internal(struct list_head *head) { struct sk_buff *skb, *next; LIST_HEAD(sublist); list_for_each_entry_safe(skb, next, head, list) { net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), skb); skb_list_del_init(skb); if (!skb_defer_rx_timestamp(skb)) list_add_tail(&skb->list, &sublist); } list_splice_init(&sublist, head); rcu_read_lock(); #ifdef CONFIG_RPS if (static_branch_unlikely(&rps_needed)) { list_for_each_entry_safe(skb, next, head, list) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu = get_rps_cpu(skb->dev, skb, &rflow); if (cpu >= 0) { /* Will be handled, remove from list */ skb_list_del_init(skb); enqueue_to_backlog(skb, cpu, &rflow->last_qtail); } } } #endif __netif_receive_skb_list(head); rcu_read_unlock(); } /** * netif_receive_skb - process receive buffer from network * @skb: buffer to process * * netif_receive_skb() is the main receive data processing function. * It always succeeds. The buffer may be dropped during processing * for congestion control or by the protocol layers. * * This function may only be called from softirq context and interrupts * should be enabled. * * Return values (usually ignored): * NET_RX_SUCCESS: no congestion * NET_RX_DROP: packet was dropped */ int netif_receive_skb(struct sk_buff *skb) { int ret; trace_netif_receive_skb_entry(skb); ret = netif_receive_skb_internal(skb); trace_netif_receive_skb_exit(ret); return ret; } EXPORT_SYMBOL(netif_receive_skb); /** * netif_receive_skb_list - process many receive buffers from network * @head: list of skbs to process. * * Since return value of netif_receive_skb() is normally ignored, and * wouldn't be meaningful for a list, this function returns void. * * This function may only be called from softirq context and interrupts * should be enabled. */ void netif_receive_skb_list(struct list_head *head) { struct sk_buff *skb; if (list_empty(head)) return; if (trace_netif_receive_skb_list_entry_enabled()) { list_for_each_entry(skb, head, list) trace_netif_receive_skb_list_entry(skb); } netif_receive_skb_list_internal(head); trace_netif_receive_skb_list_exit(0); } EXPORT_SYMBOL(netif_receive_skb_list); static DEFINE_PER_CPU(struct work_struct, flush_works); /* Network device is going away, flush any packets still pending */ static void flush_backlog(struct work_struct *work) { struct sk_buff *skb, *tmp; struct softnet_data *sd; local_bh_disable(); sd = this_cpu_ptr(&softnet_data); backlog_lock_irq_disable(sd); skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { if (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->input_pkt_queue); dev_kfree_skb_irq(skb); rps_input_queue_head_incr(sd); } } backlog_unlock_irq_enable(sd); local_lock_nested_bh(&softnet_data.process_queue_bh_lock); skb_queue_walk_safe(&sd->process_queue, skb, tmp) { if (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->process_queue); kfree_skb(skb); rps_input_queue_head_incr(sd); } } local_unlock_nested_bh(&softnet_data.process_queue_bh_lock); local_bh_enable(); } static bool flush_required(int cpu) { #if IS_ENABLED(CONFIG_RPS) struct softnet_data *sd = &per_cpu(softnet_data, cpu); bool do_flush; backlog_lock_irq_disable(sd); /* as insertion into process_queue happens with the rps lock held, * process_queue access may race only with dequeue */ do_flush = !skb_queue_empty(&sd->input_pkt_queue) || !skb_queue_empty_lockless(&sd->process_queue); backlog_unlock_irq_enable(sd); return do_flush; #endif /* without RPS we can't safely check input_pkt_queue: during a * concurrent remote skb_queue_splice() we can detect as empty both * input_pkt_queue and process_queue even if the latter could end-up * containing a lot of packets. */ return true; } static void flush_all_backlogs(void) { static cpumask_t flush_cpus; unsigned int cpu; /* since we are under rtnl lock protection we can use static data * for the cpumask and avoid allocating on stack the possibly * large mask */ ASSERT_RTNL(); cpus_read_lock(); cpumask_clear(&flush_cpus); for_each_online_cpu(cpu) { if (flush_required(cpu)) { queue_work_on(cpu, system_highpri_wq, per_cpu_ptr(&flush_works, cpu)); cpumask_set_cpu(cpu, &flush_cpus); } } /* we can have in flight packet[s] on the cpus we are not flushing, * synchronize_net() in unregister_netdevice_many() will take care of * them */ for_each_cpu(cpu, &flush_cpus) flush_work(per_cpu_ptr(&flush_works, cpu)); cpus_read_unlock(); } static void net_rps_send_ipi(struct softnet_data *remsd) { #ifdef CONFIG_RPS while (remsd) { struct softnet_data *next = remsd->rps_ipi_next; if (cpu_online(remsd->cpu)) smp_call_function_single_async(remsd->cpu, &remsd->csd); remsd = next; } #endif } /* * net_rps_action_and_irq_enable sends any pending IPI's for rps. * Note: called with local irq disabled, but exits with local irq enabled. */ static void net_rps_action_and_irq_enable(struct softnet_data *sd) { #ifdef CONFIG_RPS struct softnet_data *remsd = sd->rps_ipi_list; if (!use_backlog_threads() && remsd) { sd->rps_ipi_list = NULL; local_irq_enable(); /* Send pending IPI's to kick RPS processing on remote cpus. */ net_rps_send_ipi(remsd); } else #endif local_irq_enable(); } static bool sd_has_rps_ipi_waiting(struct softnet_data *sd) { #ifdef CONFIG_RPS return !use_backlog_threads() && sd->rps_ipi_list; #else return false; #endif } static int process_backlog(struct napi_struct *napi, int quota) { struct softnet_data *sd = container_of(napi, struct softnet_data, backlog); bool again = true; int work = 0; /* Check if we have pending ipi, its better to send them now, * not waiting net_rx_action() end. */ if (sd_has_rps_ipi_waiting(sd)) { local_irq_disable(); net_rps_action_and_irq_enable(sd); } napi->weight = READ_ONCE(net_hotdata.dev_rx_weight); while (again) { struct sk_buff *skb; local_lock_nested_bh(&softnet_data.process_queue_bh_lock); while ((skb = __skb_dequeue(&sd->process_queue))) { local_unlock_nested_bh(&softnet_data.process_queue_bh_lock); rcu_read_lock(); __netif_receive_skb(skb); rcu_read_unlock(); if (++work >= quota) { rps_input_queue_head_add(sd, work); return work; } local_lock_nested_bh(&softnet_data.process_queue_bh_lock); } local_unlock_nested_bh(&softnet_data.process_queue_bh_lock); backlog_lock_irq_disable(sd); if (skb_queue_empty(&sd->input_pkt_queue)) { /* * Inline a custom version of __napi_complete(). * only current cpu owns and manipulates this napi, * and NAPI_STATE_SCHED is the only possible flag set * on backlog. * We can use a plain write instead of clear_bit(), * and we dont need an smp_mb() memory barrier. */ napi->state &= NAPIF_STATE_THREADED; again = false; } else { local_lock_nested_bh(&softnet_data.process_queue_bh_lock); skb_queue_splice_tail_init(&sd->input_pkt_queue, &sd->process_queue); local_unlock_nested_bh(&softnet_data.process_queue_bh_lock); } backlog_unlock_irq_enable(sd); } if (work) rps_input_queue_head_add(sd, work); return work; } /** * __napi_schedule - schedule for receive * @n: entry to schedule * * The entry's receive function will be scheduled to run. * Consider using __napi_schedule_irqoff() if hard irqs are masked. */ void __napi_schedule(struct napi_struct *n) { unsigned long flags; local_irq_save(flags); ____napi_schedule(this_cpu_ptr(&softnet_data), n); local_irq_restore(flags); } EXPORT_SYMBOL(__napi_schedule); /** * napi_schedule_prep - check if napi can be scheduled * @n: napi context * * Test if NAPI routine is already running, and if not mark * it as running. This is used as a condition variable to * insure only one NAPI poll instance runs. We also make * sure there is no pending NAPI disable. */ bool napi_schedule_prep(struct napi_struct *n) { unsigned long new, val = READ_ONCE(n->state); do { if (unlikely(val & NAPIF_STATE_DISABLE)) return false; new = val | NAPIF_STATE_SCHED; /* Sets STATE_MISSED bit if STATE_SCHED was already set * This was suggested by Alexander Duyck, as compiler * emits better code than : * if (val & NAPIF_STATE_SCHED) * new |= NAPIF_STATE_MISSED; */ new |= (val & NAPIF_STATE_SCHED) / NAPIF_STATE_SCHED * NAPIF_STATE_MISSED; } while (!try_cmpxchg(&n->state, &val, new)); return !(val & NAPIF_STATE_SCHED); } EXPORT_SYMBOL(napi_schedule_prep); /** * __napi_schedule_irqoff - schedule for receive * @n: entry to schedule * * Variant of __napi_schedule() assuming hard irqs are masked. * * On PREEMPT_RT enabled kernels this maps to __napi_schedule() * because the interrupt disabled assumption might not be true * due to force-threaded interrupts and spinlock substitution. */ void __napi_schedule_irqoff(struct napi_struct *n) { if (!IS_ENABLED(CONFIG_PREEMPT_RT)) ____napi_schedule(this_cpu_ptr(&softnet_data), n); else __napi_schedule(n); } EXPORT_SYMBOL(__napi_schedule_irqoff); bool napi_complete_done(struct napi_struct *n, int work_done) { unsigned long flags, val, new, timeout = 0; bool ret = true; /* * 1) Don't let napi dequeue from the cpu poll list * just in case its running on a different cpu. * 2) If we are busy polling, do nothing here, we have * the guarantee we will be called later. */ if (unlikely(n->state & (NAPIF_STATE_NPSVC | NAPIF_STATE_IN_BUSY_POLL))) return false; if (work_done) { if (n->gro_bitmask) timeout = napi_get_gro_flush_timeout(n); n->defer_hard_irqs_count = napi_get_defer_hard_irqs(n); } if (n->defer_hard_irqs_count > 0) { n->defer_hard_irqs_count--; timeout = napi_get_gro_flush_timeout(n); if (timeout) ret = false; } if (n->gro_bitmask) { /* When the NAPI instance uses a timeout and keeps postponing * it, we need to bound somehow the time packets are kept in * the GRO layer */ napi_gro_flush(n, !!timeout); } gro_normal_list(n); if (unlikely(!list_empty(&n->poll_list))) { /* If n->poll_list is not empty, we need to mask irqs */ local_irq_save(flags); list_del_init(&n->poll_list); local_irq_restore(flags); } WRITE_ONCE(n->list_owner, -1); val = READ_ONCE(n->state); do { WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED)); new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED | NAPIF_STATE_SCHED_THREADED | NAPIF_STATE_PREFER_BUSY_POLL); /* If STATE_MISSED was set, leave STATE_SCHED set, * because we will call napi->poll() one more time. * This C code was suggested by Alexander Duyck to help gcc. */ new |= (val & NAPIF_STATE_MISSED) / NAPIF_STATE_MISSED * NAPIF_STATE_SCHED; } while (!try_cmpxchg(&n->state, &val, new)); if (unlikely(val & NAPIF_STATE_MISSED)) { __napi_schedule(n); return false; } if (timeout) hrtimer_start(&n->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED); return ret; } EXPORT_SYMBOL(napi_complete_done); /* must be called under rcu_read_lock(), as we dont take a reference */ struct napi_struct *napi_by_id(unsigned int napi_id) { unsigned int hash = napi_id % HASH_SIZE(napi_hash); struct napi_struct *napi; hlist_for_each_entry_rcu(napi, &napi_hash[hash], napi_hash_node) if (napi->napi_id == napi_id) return napi; return NULL; } static void skb_defer_free_flush(struct softnet_data *sd) { struct sk_buff *skb, *next; /* Paired with WRITE_ONCE() in skb_attempt_defer_free() */ if (!READ_ONCE(sd->defer_list)) return; spin_lock(&sd->defer_lock); skb = sd->defer_list; sd->defer_list = NULL; sd->defer_count = 0; spin_unlock(&sd->defer_lock); while (skb != NULL) { next = skb->next; napi_consume_skb(skb, 1); skb = next; } } #if defined(CONFIG_NET_RX_BUSY_POLL) static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule) { if (!skip_schedule) { gro_normal_list(napi); __napi_schedule(napi); return; } if (napi->gro_bitmask) { /* flush too old packets * If HZ < 1000, flush all packets. */ napi_gro_flush(napi, HZ >= 1000); } gro_normal_list(napi); clear_bit(NAPI_STATE_SCHED, &napi->state); } enum { NAPI_F_PREFER_BUSY_POLL = 1, NAPI_F_END_ON_RESCHED = 2, }; static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, unsigned flags, u16 budget) { struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; bool skip_schedule = false; unsigned long timeout; int rc; /* Busy polling means there is a high chance device driver hard irq * could not grab NAPI_STATE_SCHED, and that NAPI_STATE_MISSED was * set in napi_schedule_prep(). * Since we are about to call napi->poll() once more, we can safely * clear NAPI_STATE_MISSED. * * Note: x86 could use a single "lock and ..." instruction * to perform these two clear_bit() */ clear_bit(NAPI_STATE_MISSED, &napi->state); clear_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state); local_bh_disable(); bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); if (flags & NAPI_F_PREFER_BUSY_POLL) { napi->defer_hard_irqs_count = napi_get_defer_hard_irqs(napi); timeout = napi_get_gro_flush_timeout(napi); if (napi->defer_hard_irqs_count && timeout) { hrtimer_start(&napi->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED); skip_schedule = true; } } /* All we really want here is to re-enable device interrupts. * Ideally, a new ndo_busy_poll_stop() could avoid another round. */ rc = napi->poll(napi, budget); /* We can't gro_normal_list() here, because napi->poll() might have * rearmed the napi (napi_complete_done()) in which case it could * already be running on another CPU. */ trace_napi_poll(napi, rc, budget); netpoll_poll_unlock(have_poll_lock); if (rc == budget) __busy_poll_stop(napi, skip_schedule); bpf_net_ctx_clear(bpf_net_ctx); local_bh_enable(); } static void __napi_busy_loop(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), void *loop_end_arg, unsigned flags, u16 budget) { unsigned long start_time = loop_end ? busy_loop_current_time() : 0; int (*napi_poll)(struct napi_struct *napi, int budget); struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; void *have_poll_lock = NULL; struct napi_struct *napi; WARN_ON_ONCE(!rcu_read_lock_held()); restart: napi_poll = NULL; napi = napi_by_id(napi_id); if (!napi) return; if (!IS_ENABLED(CONFIG_PREEMPT_RT)) preempt_disable(); for (;;) { int work = 0; local_bh_disable(); bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); if (!napi_poll) { unsigned long val = READ_ONCE(napi->state); /* If multiple threads are competing for this napi, * we avoid dirtying napi->state as much as we can. */ if (val & (NAPIF_STATE_DISABLE | NAPIF_STATE_SCHED | NAPIF_STATE_IN_BUSY_POLL)) { if (flags & NAPI_F_PREFER_BUSY_POLL) set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state); goto count; } if (cmpxchg(&napi->state, val, val | NAPIF_STATE_IN_BUSY_POLL | NAPIF_STATE_SCHED) != val) { if (flags & NAPI_F_PREFER_BUSY_POLL) set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state); goto count; } have_poll_lock = netpoll_poll_lock(napi); napi_poll = napi->poll; } work = napi_poll(napi, budget); trace_napi_poll(napi, work, budget); gro_normal_list(napi); count: if (work > 0) __NET_ADD_STATS(dev_net(napi->dev), LINUX_MIB_BUSYPOLLRXPACKETS, work); skb_defer_free_flush(this_cpu_ptr(&softnet_data)); bpf_net_ctx_clear(bpf_net_ctx); local_bh_enable(); if (!loop_end || loop_end(loop_end_arg, start_time)) break; if (unlikely(need_resched())) { if (flags & NAPI_F_END_ON_RESCHED) break; if (napi_poll) busy_poll_stop(napi, have_poll_lock, flags, budget); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) preempt_enable(); rcu_read_unlock(); cond_resched(); rcu_read_lock(); if (loop_end(loop_end_arg, start_time)) return; goto restart; } cpu_relax(); } if (napi_poll) busy_poll_stop(napi, have_poll_lock, flags, budget); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) preempt_enable(); } void napi_busy_loop_rcu(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), void *loop_end_arg, bool prefer_busy_poll, u16 budget) { unsigned flags = NAPI_F_END_ON_RESCHED; if (prefer_busy_poll) flags |= NAPI_F_PREFER_BUSY_POLL; __napi_busy_loop(napi_id, loop_end, loop_end_arg, flags, budget); } void napi_busy_loop(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), void *loop_end_arg, bool prefer_busy_poll, u16 budget) { unsigned flags = prefer_busy_poll ? NAPI_F_PREFER_BUSY_POLL : 0; rcu_read_lock(); __napi_busy_loop(napi_id, loop_end, loop_end_arg, flags, budget); rcu_read_unlock(); } EXPORT_SYMBOL(napi_busy_loop); void napi_suspend_irqs(unsigned int napi_id) { struct napi_struct *napi; rcu_read_lock(); napi = napi_by_id(napi_id); if (napi) { unsigned long timeout = napi_get_irq_suspend_timeout(napi); if (timeout) hrtimer_start(&napi->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED); } rcu_read_unlock(); } void napi_resume_irqs(unsigned int napi_id) { struct napi_struct *napi; rcu_read_lock(); napi = napi_by_id(napi_id); if (napi) { /* If irq_suspend_timeout is set to 0 between the call to * napi_suspend_irqs and now, the original value still * determines the safety timeout as intended and napi_watchdog * will resume irq processing. */ if (napi_get_irq_suspend_timeout(napi)) { local_bh_disable(); napi_schedule(napi); local_bh_enable(); } } rcu_read_unlock(); } #endif /* CONFIG_NET_RX_BUSY_POLL */ static void __napi_hash_add_with_id(struct napi_struct *napi, unsigned int napi_id) { napi->napi_id = napi_id; hlist_add_head_rcu(&napi->napi_hash_node, &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]); } static void napi_hash_add_with_id(struct napi_struct *napi, unsigned int napi_id) { unsigned long flags; spin_lock_irqsave(&napi_hash_lock, flags); WARN_ON_ONCE(napi_by_id(napi_id)); __napi_hash_add_with_id(napi, napi_id); spin_unlock_irqrestore(&napi_hash_lock, flags); } static void napi_hash_add(struct napi_struct *napi) { unsigned long flags; if (test_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state)) return; spin_lock_irqsave(&napi_hash_lock, flags); /* 0..NR_CPUS range is reserved for sender_cpu use */ do { if (unlikely(++napi_gen_id < MIN_NAPI_ID)) napi_gen_id = MIN_NAPI_ID; } while (napi_by_id(napi_gen_id)); __napi_hash_add_with_id(napi, napi_gen_id); spin_unlock_irqrestore(&napi_hash_lock, flags); } /* Warning : caller is responsible to make sure rcu grace period * is respected before freeing memory containing @napi */ static void napi_hash_del(struct napi_struct *napi) { unsigned long flags; spin_lock_irqsave(&napi_hash_lock, flags); hlist_del_init_rcu(&napi->napi_hash_node); spin_unlock_irqrestore(&napi_hash_lock, flags); } static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) { struct napi_struct *napi; napi = container_of(timer, struct napi_struct, timer); /* Note : we use a relaxed variant of napi_schedule_prep() not setting * NAPI_STATE_MISSED, since we do not react to a device IRQ. */ if (!napi_disable_pending(napi) && !test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) { clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state); __napi_schedule_irqoff(napi); } return HRTIMER_NORESTART; } static void init_gro_hash(struct napi_struct *napi) { int i; for (i = 0; i < GRO_HASH_BUCKETS; i++) { INIT_LIST_HEAD(&napi->gro_hash[i].list); napi->gro_hash[i].count = 0; } napi->gro_bitmask = 0; } int dev_set_threaded(struct net_device *dev, bool threaded) { struct napi_struct *napi; int err = 0; if (dev->threaded == threaded) return 0; if (threaded) { list_for_each_entry(napi, &dev->napi_list, dev_list) { if (!napi->thread) { err = napi_kthread_create(napi); if (err) { threaded = false; break; } } } } WRITE_ONCE(dev->threaded, threaded); /* Make sure kthread is created before THREADED bit * is set. */ smp_mb__before_atomic(); /* Setting/unsetting threaded mode on a napi might not immediately * take effect, if the current napi instance is actively being * polled. In this case, the switch between threaded mode and * softirq mode will happen in the next round of napi_schedule(). * This should not cause hiccups/stalls to the live traffic. */ list_for_each_entry(napi, &dev->napi_list, dev_list) assign_bit(NAPI_STATE_THREADED, &napi->state, threaded); return err; } EXPORT_SYMBOL(dev_set_threaded); /** * netif_queue_set_napi - Associate queue with the napi * @dev: device to which NAPI and queue belong * @queue_index: Index of queue * @type: queue type as RX or TX * @napi: NAPI context, pass NULL to clear previously set NAPI * * Set queue with its corresponding napi context. This should be done after * registering the NAPI handler for the queue-vector and the queues have been * mapped to the corresponding interrupt vector. */ void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index, enum netdev_queue_type type, struct napi_struct *napi) { struct netdev_rx_queue *rxq; struct netdev_queue *txq; if (WARN_ON_ONCE(napi && !napi->dev)) return; if (dev->reg_state >= NETREG_REGISTERED) ASSERT_RTNL(); switch (type) { case NETDEV_QUEUE_TYPE_RX: rxq = __netif_get_rx_queue(dev, queue_index); rxq->napi = napi; return; case NETDEV_QUEUE_TYPE_TX: txq = netdev_get_tx_queue(dev, queue_index); txq->napi = napi; return; default: return; } } EXPORT_SYMBOL(netif_queue_set_napi); static void napi_restore_config(struct napi_struct *n) { n->defer_hard_irqs = n->config->defer_hard_irqs; n->gro_flush_timeout = n->config->gro_flush_timeout; n->irq_suspend_timeout = n->config->irq_suspend_timeout; /* a NAPI ID might be stored in the config, if so use it. if not, use * napi_hash_add to generate one for us. It will be saved to the config * in napi_disable. */ if (n->config->napi_id) napi_hash_add_with_id(n, n->config->napi_id); else napi_hash_add(n); } static void napi_save_config(struct napi_struct *n) { n->config->defer_hard_irqs = n->defer_hard_irqs; n->config->gro_flush_timeout = n->gro_flush_timeout; n->config->irq_suspend_timeout = n->irq_suspend_timeout; n->config->napi_id = n->napi_id; napi_hash_del(n); } void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) { if (WARN_ON(test_and_set_bit(NAPI_STATE_LISTED, &napi->state))) return; INIT_LIST_HEAD(&napi->poll_list); INIT_HLIST_NODE(&napi->napi_hash_node); hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); napi->timer.function = napi_watchdog; init_gro_hash(napi); napi->skb = NULL; INIT_LIST_HEAD(&napi->rx_list); napi->rx_count = 0; napi->poll = poll; if (weight > NAPI_POLL_WEIGHT) netdev_err_once(dev, "%s() called with weight %d\n", __func__, weight); napi->weight = weight; napi->dev = dev; #ifdef CONFIG_NETPOLL napi->poll_owner = -1; #endif napi->list_owner = -1; set_bit(NAPI_STATE_SCHED, &napi->state); set_bit(NAPI_STATE_NPSVC, &napi->state); list_add_rcu(&napi->dev_list, &dev->napi_list); /* default settings from sysfs are applied to all NAPIs. any per-NAPI * configuration will be loaded in napi_enable */ napi_set_defer_hard_irqs(napi, READ_ONCE(dev->napi_defer_hard_irqs)); napi_set_gro_flush_timeout(napi, READ_ONCE(dev->gro_flush_timeout)); napi_get_frags_check(napi); /* Create kthread for this napi if dev->threaded is set. * Clear dev->threaded if kthread creation failed so that * threaded mode will not be enabled in napi_enable(). */ if (dev->threaded && napi_kthread_create(napi)) dev->threaded = false; netif_napi_set_irq(napi, -1); } EXPORT_SYMBOL(netif_napi_add_weight); void napi_disable(struct napi_struct *n) { unsigned long val, new; might_sleep(); set_bit(NAPI_STATE_DISABLE, &n->state); val = READ_ONCE(n->state); do { while (val & (NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC)) { usleep_range(20, 200); val = READ_ONCE(n->state); } new = val | NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC; new &= ~(NAPIF_STATE_THREADED | NAPIF_STATE_PREFER_BUSY_POLL); } while (!try_cmpxchg(&n->state, &val, new)); hrtimer_cancel(&n->timer); if (n->config) napi_save_config(n); else napi_hash_del(n); clear_bit(NAPI_STATE_DISABLE, &n->state); } EXPORT_SYMBOL(napi_disable); /** * napi_enable - enable NAPI scheduling * @n: NAPI context * * Resume NAPI from being scheduled on this context. * Must be paired with napi_disable. */ void napi_enable(struct napi_struct *n) { unsigned long new, val = READ_ONCE(n->state); if (n->config) napi_restore_config(n); else napi_hash_add(n); do { BUG_ON(!test_bit(NAPI_STATE_SCHED, &val)); new = val & ~(NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC); if (n->dev->threaded && n->thread) new |= NAPIF_STATE_THREADED; } while (!try_cmpxchg(&n->state, &val, new)); } EXPORT_SYMBOL(napi_enable); static void flush_gro_hash(struct napi_struct *napi) { int i; for (i = 0; i < GRO_HASH_BUCKETS; i++) { struct sk_buff *skb, *n; list_for_each_entry_safe(skb, n, &napi->gro_hash[i].list, list) kfree_skb(skb); napi->gro_hash[i].count = 0; } } /* Must be called in process context */ void __netif_napi_del(struct napi_struct *napi) { if (!test_and_clear_bit(NAPI_STATE_LISTED, &napi->state)) return; if (napi->config) { napi->index = -1; napi->config = NULL; } list_del_rcu(&napi->dev_list); napi_free_frags(napi); flush_gro_hash(napi); napi->gro_bitmask = 0; if (napi->thread) { kthread_stop(napi->thread); napi->thread = NULL; } } EXPORT_SYMBOL(__netif_napi_del); static int __napi_poll(struct napi_struct *n, bool *repoll) { int work, weight; weight = n->weight; /* This NAPI_STATE_SCHED test is for avoiding a race * with netpoll's poll_napi(). Only the entity which * obtains the lock and sees NAPI_STATE_SCHED set will * actually make the ->poll() call. Therefore we avoid * accidentally calling ->poll() when NAPI is not scheduled. */ work = 0; if (napi_is_scheduled(n)) { work = n->poll(n, weight); trace_napi_poll(n, work, weight); xdp_do_check_flushed(n); } if (unlikely(work > weight)) netdev_err_once(n->dev, "NAPI poll function %pS returned %d, exceeding its budget of %d.\n", n->poll, work, weight); if (likely(work < weight)) return work; /* Drivers must not modify the NAPI state if they * consume the entire weight. In such cases this code * still "owns" the NAPI instance and therefore can * move the instance around on the list at-will. */ if (unlikely(napi_disable_pending(n))) { napi_complete(n); return work; } /* The NAPI context has more processing work, but busy-polling * is preferred. Exit early. */ if (napi_prefer_busy_poll(n)) { if (napi_complete_done(n, work)) { /* If timeout is not set, we need to make sure * that the NAPI is re-scheduled. */ napi_schedule(n); } return work; } if (n->gro_bitmask) { /* flush too old packets * If HZ < 1000, flush all packets. */ napi_gro_flush(n, HZ >= 1000); } gro_normal_list(n); /* Some drivers may have called napi_schedule * prior to exhausting their budget. */ if (unlikely(!list_empty(&n->poll_list))) { pr_warn_once("%s: Budget exhausted after napi rescheduled\n", n->dev ? n->dev->name : "backlog"); return work; } *repoll = true; return work; } static int napi_poll(struct napi_struct *n, struct list_head *repoll) { bool do_repoll = false; void *have; int work; list_del_init(&n->poll_list); have = netpoll_poll_lock(n); work = __napi_poll(n, &do_repoll); if (do_repoll) list_add_tail(&n->poll_list, repoll); netpoll_poll_unlock(have); return work; } static int napi_thread_wait(struct napi_struct *napi) { set_current_state(TASK_INTERRUPTIBLE); while (!kthread_should_stop()) { /* Testing SCHED_THREADED bit here to make sure the current * kthread owns this napi and could poll on this napi. * Testing SCHED bit is not enough because SCHED bit might be * set by some other busy poll thread or by napi_disable(). */ if (test_bit(NAPI_STATE_SCHED_THREADED, &napi->state)) { WARN_ON(!list_empty(&napi->poll_list)); __set_current_state(TASK_RUNNING); return 0; } schedule(); set_current_state(TASK_INTERRUPTIBLE); } __set_current_state(TASK_RUNNING); return -1; } static void napi_threaded_poll_loop(struct napi_struct *napi) { struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; struct softnet_data *sd; unsigned long last_qs = jiffies; for (;;) { bool repoll = false; void *have; local_bh_disable(); bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); sd = this_cpu_ptr(&softnet_data); sd->in_napi_threaded_poll = true; have = netpoll_poll_lock(napi); __napi_poll(napi, &repoll); netpoll_poll_unlock(have); sd->in_napi_threaded_poll = false; barrier(); if (sd_has_rps_ipi_waiting(sd)) { local_irq_disable(); net_rps_action_and_irq_enable(sd); } skb_defer_free_flush(sd); bpf_net_ctx_clear(bpf_net_ctx); local_bh_enable(); if (!repoll) break; rcu_softirq_qs_periodic(last_qs); cond_resched(); } } static int napi_threaded_poll(void *data) { struct napi_struct *napi = data; while (!napi_thread_wait(napi)) napi_threaded_poll_loop(napi); return 0; } static __latent_entropy void net_rx_action(void) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); unsigned long time_limit = jiffies + usecs_to_jiffies(READ_ONCE(net_hotdata.netdev_budget_usecs)); struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; int budget = READ_ONCE(net_hotdata.netdev_budget); LIST_HEAD(list); LIST_HEAD(repoll); bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); start: sd->in_net_rx_action = true; local_irq_disable(); list_splice_init(&sd->poll_list, &list); local_irq_enable(); for (;;) { struct napi_struct *n; skb_defer_free_flush(sd); if (list_empty(&list)) { if (list_empty(&repoll)) { sd->in_net_rx_action = false; barrier(); /* We need to check if ____napi_schedule() * had refilled poll_list while * sd->in_net_rx_action was true. */ if (!list_empty(&sd->poll_list)) goto start; if (!sd_has_rps_ipi_waiting(sd)) goto end; } break; } n = list_first_entry(&list, struct napi_struct, poll_list); budget -= napi_poll(n, &repoll); /* If softirq window is exhausted then punt. * Allow this to run for 2 jiffies since which will allow * an average latency of 1.5/HZ. */ if (unlikely(budget <= 0 || time_after_eq(jiffies, time_limit))) { sd->time_squeeze++; break; } } local_irq_disable(); list_splice_tail_init(&sd->poll_list, &list); list_splice_tail(&repoll, &list); list_splice(&list, &sd->poll_list); if (!list_empty(&sd->poll_list)) __raise_softirq_irqoff(NET_RX_SOFTIRQ); else sd->in_net_rx_action = false; net_rps_action_and_irq_enable(sd); end: bpf_net_ctx_clear(bpf_net_ctx); } struct netdev_adjacent { struct net_device *dev; netdevice_tracker dev_tracker; /* upper master flag, there can only be one master device per list */ bool master; /* lookup ignore flag */ bool ignore; /* counter for the number of times this device was added to us */ u16 ref_nr; /* private field for the users */ void *private; struct list_head list; struct rcu_head rcu; }; static struct netdev_adjacent *__netdev_find_adj(struct net_device *adj_dev, struct list_head *adj_list) { struct netdev_adjacent *adj; list_for_each_entry(adj, adj_list, list) { if (adj->dev == adj_dev) return adj; } return NULL; } static int ____netdev_has_upper_dev(struct net_device *upper_dev, struct netdev_nested_priv *priv) { struct net_device *dev = (struct net_device *)priv->data; return upper_dev == dev; } /** * netdev_has_upper_dev - Check if device is linked to an upper device * @dev: device * @upper_dev: upper device to check * * Find out if a device is linked to specified upper device and return true * in case it is. Note that this checks only immediate upper device, * not through a complete stack of devices. The caller must hold the RTNL lock. */ bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev) { struct netdev_nested_priv priv = { .data = (void *)upper_dev, }; ASSERT_RTNL(); return netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev, &priv); } EXPORT_SYMBOL(netdev_has_upper_dev); /** * netdev_has_upper_dev_all_rcu - Check if device is linked to an upper device * @dev: device * @upper_dev: upper device to check * * Find out if a device is linked to specified upper device and return true * in case it is. Note that this checks the entire upper device chain. * The caller must hold rcu lock. */ bool netdev_has_upper_dev_all_rcu(struct net_device *dev, struct net_device *upper_dev) { struct netdev_nested_priv priv = { .data = (void *)upper_dev, }; return !!netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev, &priv); } EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu); /** * netdev_has_any_upper_dev - Check if device is linked to some device * @dev: device * * Find out if a device is linked to an upper device and return true in case * it is. The caller must hold the RTNL lock. */ bool netdev_has_any_upper_dev(struct net_device *dev) { ASSERT_RTNL(); return !list_empty(&dev->adj_list.upper); } EXPORT_SYMBOL(netdev_has_any_upper_dev); /** * netdev_master_upper_dev_get - Get master upper device * @dev: device * * Find a master upper device and return pointer to it or NULL in case * it's not there. The caller must hold the RTNL lock. */ struct net_device *netdev_master_upper_dev_get(struct net_device *dev) { struct netdev_adjacent *upper; ASSERT_RTNL(); if (list_empty(&dev->adj_list.upper)) return NULL; upper = list_first_entry(&dev->adj_list.upper, struct netdev_adjacent, list); if (likely(upper->master)) return upper->dev; return NULL; } EXPORT_SYMBOL(netdev_master_upper_dev_get); static struct net_device *__netdev_master_upper_dev_get(struct net_device *dev) { struct netdev_adjacent *upper; ASSERT_RTNL(); if (list_empty(&dev->adj_list.upper)) return NULL; upper = list_first_entry(&dev->adj_list.upper, struct netdev_adjacent, list); if (likely(upper->master) && !upper->ignore) return upper->dev; return NULL; } /** * netdev_has_any_lower_dev - Check if device is linked to some device * @dev: device * * Find out if a device is linked to a lower device and return true in case * it is. The caller must hold the RTNL lock. */ static bool netdev_has_any_lower_dev(struct net_device *dev) { ASSERT_RTNL(); return !list_empty(&dev->adj_list.lower); } void *netdev_adjacent_get_private(struct list_head *adj_list) { struct netdev_adjacent *adj; adj = list_entry(adj_list, struct netdev_adjacent, list); return adj->private; } EXPORT_SYMBOL(netdev_adjacent_get_private); /** * netdev_upper_get_next_dev_rcu - Get the next dev from upper list * @dev: device * @iter: list_head ** of the current position * * Gets the next device from the dev's upper list, starting from iter * position. The caller must hold RCU read lock. */ struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *upper; WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held()); upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); if (&upper->list == &dev->adj_list.upper) return NULL; *iter = &upper->list; return upper->dev; } EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu); static struct net_device *__netdev_next_upper_dev(struct net_device *dev, struct list_head **iter, bool *ignore) { struct netdev_adjacent *upper; upper = list_entry((*iter)->next, struct netdev_adjacent, list); if (&upper->list == &dev->adj_list.upper) return NULL; *iter = &upper->list; *ignore = upper->ignore; return upper->dev; } static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *upper; WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held()); upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); if (&upper->list == &dev->adj_list.upper) return NULL; *iter = &upper->list; return upper->dev; } static int __netdev_walk_all_upper_dev(struct net_device *dev, int (*fn)(struct net_device *dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv) { struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; bool ignore; now = dev; iter = &dev->adj_list.upper; while (1) { if (now != dev) { ret = fn(now, priv); if (ret) return ret; } next = NULL; while (1) { udev = __netdev_next_upper_dev(now, &iter, &ignore); if (!udev) break; if (ignore) continue; next = udev; niter = &udev->adj_list.upper; dev_stack[cur] = now; iter_stack[cur++] = iter; break; } if (!next) { if (!cur) return 0; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return 0; } int netdev_walk_all_upper_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv) { struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; now = dev; iter = &dev->adj_list.upper; while (1) { if (now != dev) { ret = fn(now, priv); if (ret) return ret; } next = NULL; while (1) { udev = netdev_next_upper_dev_rcu(now, &iter); if (!udev) break; next = udev; niter = &udev->adj_list.upper; dev_stack[cur] = now; iter_stack[cur++] = iter; break; } if (!next) { if (!cur) return 0; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return 0; } EXPORT_SYMBOL_GPL(netdev_walk_all_upper_dev_rcu); static bool __netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev) { struct netdev_nested_priv priv = { .flags = 0, .data = (void *)upper_dev, }; ASSERT_RTNL(); return __netdev_walk_all_upper_dev(dev, ____netdev_has_upper_dev, &priv); } /** * netdev_lower_get_next_private - Get the next ->private from the * lower neighbour list * @dev: device * @iter: list_head ** of the current position * * Gets the next netdev_adjacent->private from the dev's lower neighbour * list, starting from iter position. The caller must hold either hold the * RTNL lock or its own locking that guarantees that the neighbour lower * list will remain unchanged. */ void *netdev_lower_get_next_private(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; lower = list_entry(*iter, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = lower->list.next; return lower->private; } EXPORT_SYMBOL(netdev_lower_get_next_private); /** * netdev_lower_get_next_private_rcu - Get the next ->private from the * lower neighbour list, RCU * variant * @dev: device * @iter: list_head ** of the current position * * Gets the next netdev_adjacent->private from the dev's lower neighbour * list, starting from iter position. The caller must hold RCU read lock. */ void *netdev_lower_get_next_private_rcu(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = &lower->list; return lower->private; } EXPORT_SYMBOL(netdev_lower_get_next_private_rcu); /** * netdev_lower_get_next - Get the next device from the lower neighbour * list * @dev: device * @iter: list_head ** of the current position * * Gets the next netdev_adjacent from the dev's lower neighbour * list, starting from iter position. The caller must hold RTNL lock or * its own locking that guarantees that the neighbour lower * list will remain unchanged. */ void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; lower = list_entry(*iter, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = lower->list.next; return lower->dev; } EXPORT_SYMBOL(netdev_lower_get_next); static struct net_device *netdev_next_lower_dev(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; lower = list_entry((*iter)->next, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = &lower->list; return lower->dev; } static struct net_device *__netdev_next_lower_dev(struct net_device *dev, struct list_head **iter, bool *ignore) { struct netdev_adjacent *lower; lower = list_entry((*iter)->next, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = &lower->list; *ignore = lower->ignore; return lower->dev; } int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; now = dev; iter = &dev->adj_list.lower; while (1) { if (now != dev) { ret = fn(now, priv); if (ret) return ret; } next = NULL; while (1) { ldev = netdev_next_lower_dev(now, &iter); if (!ldev) break; next = ldev; niter = &ldev->adj_list.lower; dev_stack[cur] = now; iter_stack[cur++] = iter; break; } if (!next) { if (!cur) return 0; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return 0; } EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev); static int __netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; bool ignore; now = dev; iter = &dev->adj_list.lower; while (1) { if (now != dev) { ret = fn(now, priv); if (ret) return ret; } next = NULL; while (1) { ldev = __netdev_next_lower_dev(now, &iter, &ignore); if (!ldev) break; if (ignore) continue; next = ldev; niter = &ldev->adj_list.lower; dev_stack[cur] = now; iter_stack[cur++] = iter; break; } if (!next) { if (!cur) return 0; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return 0; } struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = &lower->list; return lower->dev; } EXPORT_SYMBOL(netdev_next_lower_dev_rcu); static u8 __netdev_upper_depth(struct net_device *dev) { struct net_device *udev; struct list_head *iter; u8 max_depth = 0; bool ignore; for (iter = &dev->adj_list.upper, udev = __netdev_next_upper_dev(dev, &iter, &ignore); udev; udev = __netdev_next_upper_dev(dev, &iter, &ignore)) { if (ignore) continue; if (max_depth < udev->upper_level) max_depth = udev->upper_level; } return max_depth; } static u8 __netdev_lower_depth(struct net_device *dev) { struct net_device *ldev; struct list_head *iter; u8 max_depth = 0; bool ignore; for (iter = &dev->adj_list.lower, ldev = __netdev_next_lower_dev(dev, &iter, &ignore); ldev; ldev = __netdev_next_lower_dev(dev, &iter, &ignore)) { if (ignore) continue; if (max_depth < ldev->lower_level) max_depth = ldev->lower_level; } return max_depth; } static int __netdev_update_upper_level(struct net_device *dev, struct netdev_nested_priv *__unused) { dev->upper_level = __netdev_upper_depth(dev) + 1; return 0; } #ifdef CONFIG_LOCKDEP static LIST_HEAD(net_unlink_list); static void net_unlink_todo(struct net_device *dev) { if (list_empty(&dev->unlink_list)) list_add_tail(&dev->unlink_list, &net_unlink_list); } #endif static int __netdev_update_lower_level(struct net_device *dev, struct netdev_nested_priv *priv) { dev->lower_level = __netdev_lower_depth(dev) + 1; #ifdef CONFIG_LOCKDEP if (!priv) return 0; if (priv->flags & NESTED_SYNC_IMM) dev->nested_level = dev->lower_level - 1; if (priv->flags & NESTED_SYNC_TODO) net_unlink_todo(dev); #endif return 0; } int netdev_walk_all_lower_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; now = dev; iter = &dev->adj_list.lower; while (1) { if (now != dev) { ret = fn(now, priv); if (ret) return ret; } next = NULL; while (1) { ldev = netdev_next_lower_dev_rcu(now, &iter); if (!ldev) break; next = ldev; niter = &ldev->adj_list.lower; dev_stack[cur] = now; iter_stack[cur++] = iter; break; } if (!next) { if (!cur) return 0; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return 0; } EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev_rcu); /** * netdev_lower_get_first_private_rcu - Get the first ->private from the * lower neighbour list, RCU * variant * @dev: device * * Gets the first netdev_adjacent->private from the dev's lower neighbour * list. The caller must hold RCU read lock. */ void *netdev_lower_get_first_private_rcu(struct net_device *dev) { struct netdev_adjacent *lower; lower = list_first_or_null_rcu(&dev->adj_list.lower, struct netdev_adjacent, list); if (lower) return lower->private; return NULL; } EXPORT_SYMBOL(netdev_lower_get_first_private_rcu); /** * netdev_master_upper_dev_get_rcu - Get master upper device * @dev: device * * Find a master upper device and return pointer to it or NULL in case * it's not there. The caller must hold the RCU read lock. */ struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev) { struct netdev_adjacent *upper; upper = list_first_or_null_rcu(&dev->adj_list.upper, struct netdev_adjacent, list); if (upper && likely(upper->master)) return upper->dev; return NULL; } EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu); static int netdev_adjacent_sysfs_add(struct net_device *dev, struct net_device *adj_dev, struct list_head *dev_list) { char linkname[IFNAMSIZ+7]; sprintf(linkname, dev_list == &dev->adj_list.upper ? "upper_%s" : "lower_%s", adj_dev->name); return sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj), linkname); } static void netdev_adjacent_sysfs_del(struct net_device *dev, char *name, struct list_head *dev_list) { char linkname[IFNAMSIZ+7]; sprintf(linkname, dev_list == &dev->adj_list.upper ? "upper_%s" : "lower_%s", name); sysfs_remove_link(&(dev->dev.kobj), linkname); } static inline bool netdev_adjacent_is_neigh_list(struct net_device *dev, struct net_device *adj_dev, struct list_head *dev_list) { return (dev_list == &dev->adj_list.upper || dev_list == &dev->adj_list.lower) && net_eq(dev_net(dev), dev_net(adj_dev)); } static int __netdev_adjacent_dev_insert(struct net_device *dev, struct net_device *adj_dev, struct list_head *dev_list, void *private, bool master) { struct netdev_adjacent *adj; int ret; adj = __netdev_find_adj(adj_dev, dev_list); if (adj) { adj->ref_nr += 1; pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d\n", dev->name, adj_dev->name, adj->ref_nr); return 0; } adj = kmalloc(sizeof(*adj), GFP_KERNEL); if (!adj) return -ENOMEM; adj->dev = adj_dev; adj->master = master; adj->ref_nr = 1; adj->private = private; adj->ignore = false; netdev_hold(adj_dev, &adj->dev_tracker, GFP_KERNEL); pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d; dev_hold on %s\n", dev->name, adj_dev->name, adj->ref_nr, adj_dev->name); if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) { ret = netdev_adjacent_sysfs_add(dev, adj_dev, dev_list); if (ret) goto free_adj; } /* Ensure that master link is always the first item in list. */ if (master) { ret = sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj), "master"); if (ret) goto remove_symlinks; list_add_rcu(&adj->list, dev_list); } else { list_add_tail_rcu(&adj->list, dev_list); } return 0; remove_symlinks: if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); free_adj: netdev_put(adj_dev, &adj->dev_tracker); kfree(adj); return ret; } static void __netdev_adjacent_dev_remove(struct net_device *dev, struct net_device *adj_dev, u16 ref_nr, struct list_head *dev_list) { struct netdev_adjacent *adj; pr_debug("Remove adjacency: dev %s adj_dev %s ref_nr %d\n", dev->name, adj_dev->name, ref_nr); adj = __netdev_find_adj(adj_dev, dev_list); if (!adj) { pr_err("Adjacency does not exist for device %s from %s\n", dev->name, adj_dev->name); WARN_ON(1); return; } if (adj->ref_nr > ref_nr) { pr_debug("adjacency: %s to %s ref_nr - %d = %d\n", dev->name, adj_dev->name, ref_nr, adj->ref_nr - ref_nr); adj->ref_nr -= ref_nr; return; } if (adj->master) sysfs_remove_link(&(dev->dev.kobj), "master"); if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); list_del_rcu(&adj->list); pr_debug("adjacency: dev_put for %s, because link removed from %s to %s\n", adj_dev->name, dev->name, adj_dev->name); netdev_put(adj_dev, &adj->dev_tracker); kfree_rcu(adj, rcu); } static int __netdev_adjacent_dev_link_lists(struct net_device *dev, struct net_device *upper_dev, struct list_head *up_list, struct list_head *down_list, void *private, bool master) { int ret; ret = __netdev_adjacent_dev_insert(dev, upper_dev, up_list, private, master); if (ret) return ret; ret = __netdev_adjacent_dev_insert(upper_dev, dev, down_list, private, false); if (ret) { __netdev_adjacent_dev_remove(dev, upper_dev, 1, up_list); return ret; } return 0; } static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev, struct net_device *upper_dev, u16 ref_nr, struct list_head *up_list, struct list_head *down_list) { __netdev_adjacent_dev_remove(dev, upper_dev, ref_nr, up_list); __netdev_adjacent_dev_remove(upper_dev, dev, ref_nr, down_list); } static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev, struct net_device *upper_dev, void *private, bool master) { return __netdev_adjacent_dev_link_lists(dev, upper_dev, &dev->adj_list.upper, &upper_dev->adj_list.lower, private, master); } static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev, struct net_device *upper_dev) { __netdev_adjacent_dev_unlink_lists(dev, upper_dev, 1, &dev->adj_list.upper, &upper_dev->adj_list.lower); } static int __netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, bool master, void *upper_priv, void *upper_info, struct netdev_nested_priv *priv, struct netlink_ext_ack *extack) { struct netdev_notifier_changeupper_info changeupper_info = { .info = { .dev = dev, .extack = extack, }, .upper_dev = upper_dev, .master = master, .linking = true, .upper_info = upper_info, }; struct net_device *master_dev; int ret = 0; ASSERT_RTNL(); if (dev == upper_dev) return -EBUSY; /* To prevent loops, check if dev is not upper device to upper_dev. */ if (__netdev_has_upper_dev(upper_dev, dev)) return -EBUSY; if ((dev->lower_level + upper_dev->upper_level) > MAX_NEST_DEV) return -EMLINK; if (!master) { if (__netdev_has_upper_dev(dev, upper_dev)) return -EEXIST; } else { master_dev = __netdev_master_upper_dev_get(dev); if (master_dev) return master_dev == upper_dev ? -EEXIST : -EBUSY; } ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, &changeupper_info.info); ret = notifier_to_errno(ret); if (ret) return ret; ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, upper_priv, master); if (ret) return ret; ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, &changeupper_info.info); ret = notifier_to_errno(ret); if (ret) goto rollback; __netdev_update_upper_level(dev, NULL); __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); __netdev_update_lower_level(upper_dev, priv); __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, priv); return 0; rollback: __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); return ret; } /** * netdev_upper_dev_link - Add a link to the upper device * @dev: device * @upper_dev: new upper device * @extack: netlink extended ack * * Adds a link to device which is upper to this one. The caller must hold * the RTNL lock. On a failure a negative errno code is returned. * On success the reference counts are adjusted and the function * returns zero. */ int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, struct netlink_ext_ack *extack) { struct netdev_nested_priv priv = { .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO, .data = NULL, }; return __netdev_upper_dev_link(dev, upper_dev, false, NULL, NULL, &priv, extack); } EXPORT_SYMBOL(netdev_upper_dev_link); /** * netdev_master_upper_dev_link - Add a master link to the upper device * @dev: device * @upper_dev: new upper device * @upper_priv: upper device private * @upper_info: upper info to be passed down via notifier * @extack: netlink extended ack * * Adds a link to device which is upper to this one. In this case, only * one master upper device can be linked, although other non-master devices * might be linked as well. The caller must hold the RTNL lock. * On a failure a negative errno code is returned. On success the reference * counts are adjusted and the function returns zero. */ int netdev_master_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, void *upper_priv, void *upper_info, struct netlink_ext_ack *extack) { struct netdev_nested_priv priv = { .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO, .data = NULL, }; return __netdev_upper_dev_link(dev, upper_dev, true, upper_priv, upper_info, &priv, extack); } EXPORT_SYMBOL(netdev_master_upper_dev_link); static void __netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev, struct netdev_nested_priv *priv) { struct netdev_notifier_changeupper_info changeupper_info = { .info = { .dev = dev, }, .upper_dev = upper_dev, .linking = false, }; ASSERT_RTNL(); changeupper_info.master = netdev_master_upper_dev_get(dev) == upper_dev; call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, &changeupper_info.info); __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, &changeupper_info.info); __netdev_update_upper_level(dev, NULL); __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); __netdev_update_lower_level(upper_dev, priv); __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, priv); } /** * netdev_upper_dev_unlink - Removes a link to upper device * @dev: device * @upper_dev: new upper device * * Removes a link to device which is upper to this one. The caller must hold * the RTNL lock. */ void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev) { struct netdev_nested_priv priv = { .flags = NESTED_SYNC_TODO, .data = NULL, }; __netdev_upper_dev_unlink(dev, upper_dev, &priv); } EXPORT_SYMBOL(netdev_upper_dev_unlink); static void __netdev_adjacent_dev_set(struct net_device *upper_dev, struct net_device *lower_dev, bool val) { struct netdev_adjacent *adj; adj = __netdev_find_adj(lower_dev, &upper_dev->adj_list.lower); if (adj) adj->ignore = val; adj = __netdev_find_adj(upper_dev, &lower_dev->adj_list.upper); if (adj) adj->ignore = val; } static void netdev_adjacent_dev_disable(struct net_device *upper_dev, struct net_device *lower_dev) { __netdev_adjacent_dev_set(upper_dev, lower_dev, true); } static void netdev_adjacent_dev_enable(struct net_device *upper_dev, struct net_device *lower_dev) { __netdev_adjacent_dev_set(upper_dev, lower_dev, false); } int netdev_adjacent_change_prepare(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev, struct netlink_ext_ack *extack) { struct netdev_nested_priv priv = { .flags = 0, .data = NULL, }; int err; if (!new_dev) return 0; if (old_dev && new_dev != old_dev) netdev_adjacent_dev_disable(dev, old_dev); err = __netdev_upper_dev_link(new_dev, dev, false, NULL, NULL, &priv, extack); if (err) { if (old_dev && new_dev != old_dev) netdev_adjacent_dev_enable(dev, old_dev); return err; } return 0; } EXPORT_SYMBOL(netdev_adjacent_change_prepare); void netdev_adjacent_change_commit(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev) { struct netdev_nested_priv priv = { .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO, .data = NULL, }; if (!new_dev || !old_dev) return; if (new_dev == old_dev) return; netdev_adjacent_dev_enable(dev, old_dev); __netdev_upper_dev_unlink(old_dev, dev, &priv); } EXPORT_SYMBOL(netdev_adjacent_change_commit); void netdev_adjacent_change_abort(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev) { struct netdev_nested_priv priv = { .flags = 0, .data = NULL, }; if (!new_dev) return; if (old_dev && new_dev != old_dev) netdev_adjacent_dev_enable(dev, old_dev); __netdev_upper_dev_unlink(new_dev, dev, &priv); } EXPORT_SYMBOL(netdev_adjacent_change_abort); /** * netdev_bonding_info_change - Dispatch event about slave change * @dev: device * @bonding_info: info to dispatch * * Send NETDEV_BONDING_INFO to netdev notifiers with info. * The caller must hold the RTNL lock. */ void netdev_bonding_info_change(struct net_device *dev, struct netdev_bonding_info *bonding_info) { struct netdev_notifier_bonding_info info = { .info.dev = dev, }; memcpy(&info.bonding_info, bonding_info, sizeof(struct netdev_bonding_info)); call_netdevice_notifiers_info(NETDEV_BONDING_INFO, &info.info); } EXPORT_SYMBOL(netdev_bonding_info_change); static int netdev_offload_xstats_enable_l3(struct net_device *dev, struct netlink_ext_ack *extack) { struct netdev_notifier_offload_xstats_info info = { .info.dev = dev, .info.extack = extack, .type = NETDEV_OFFLOAD_XSTATS_TYPE_L3, }; int err; int rc; dev->offload_xstats_l3 = kzalloc(sizeof(*dev->offload_xstats_l3), GFP_KERNEL); if (!dev->offload_xstats_l3) return -ENOMEM; rc = call_netdevice_notifiers_info_robust(NETDEV_OFFLOAD_XSTATS_ENABLE, NETDEV_OFFLOAD_XSTATS_DISABLE, &info.info); err = notifier_to_errno(rc); if (err) goto free_stats; return 0; free_stats: kfree(dev->offload_xstats_l3); dev->offload_xstats_l3 = NULL; return err; } int netdev_offload_xstats_enable(struct net_device *dev, enum netdev_offload_xstats_type type, struct netlink_ext_ack *extack) { ASSERT_RTNL(); if (netdev_offload_xstats_enabled(dev, type)) return -EALREADY; switch (type) { case NETDEV_OFFLOAD_XSTATS_TYPE_L3: return netdev_offload_xstats_enable_l3(dev, extack); } WARN_ON(1); return -EINVAL; } EXPORT_SYMBOL(netdev_offload_xstats_enable); static void netdev_offload_xstats_disable_l3(struct net_device *dev) { struct netdev_notifier_offload_xstats_info info = { .info.dev = dev, .type = NETDEV_OFFLOAD_XSTATS_TYPE_L3, }; call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_DISABLE, &info.info); kfree(dev->offload_xstats_l3); dev->offload_xstats_l3 = NULL; } int netdev_offload_xstats_disable(struct net_device *dev, enum netdev_offload_xstats_type type) { ASSERT_RTNL(); if (!netdev_offload_xstats_enabled(dev, type)) return -EALREADY; switch (type) { case NETDEV_OFFLOAD_XSTATS_TYPE_L3: netdev_offload_xstats_disable_l3(dev); return 0; } WARN_ON(1); return -EINVAL; } EXPORT_SYMBOL(netdev_offload_xstats_disable); static void netdev_offload_xstats_disable_all(struct net_device *dev) { netdev_offload_xstats_disable(dev, NETDEV_OFFLOAD_XSTATS_TYPE_L3); } static struct rtnl_hw_stats64 * netdev_offload_xstats_get_ptr(const struct net_device *dev, enum netdev_offload_xstats_type type) { switch (type) { case NETDEV_OFFLOAD_XSTATS_TYPE_L3: return dev->offload_xstats_l3; } WARN_ON(1); return NULL; } bool netdev_offload_xstats_enabled(const struct net_device *dev, enum netdev_offload_xstats_type type) { ASSERT_RTNL(); return netdev_offload_xstats_get_ptr(dev, type); } EXPORT_SYMBOL(netdev_offload_xstats_enabled); struct netdev_notifier_offload_xstats_ru { bool used; }; struct netdev_notifier_offload_xstats_rd { struct rtnl_hw_stats64 stats; bool used; }; static void netdev_hw_stats64_add(struct rtnl_hw_stats64 *dest, const struct rtnl_hw_stats64 *src) { dest->rx_packets += src->rx_packets; dest->tx_packets += src->tx_packets; dest->rx_bytes += src->rx_bytes; dest->tx_bytes += src->tx_bytes; dest->rx_errors += src->rx_errors; dest->tx_errors += src->tx_errors; dest->rx_dropped += src->rx_dropped; dest->tx_dropped += src->tx_dropped; dest->multicast += src->multicast; } static int netdev_offload_xstats_get_used(struct net_device *dev, enum netdev_offload_xstats_type type, bool *p_used, struct netlink_ext_ack *extack) { struct netdev_notifier_offload_xstats_ru report_used = {}; struct netdev_notifier_offload_xstats_info info = { .info.dev = dev, .info.extack = extack, .type = type, .report_used = &report_used, }; int rc; WARN_ON(!netdev_offload_xstats_enabled(dev, type)); rc = call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_REPORT_USED, &info.info); *p_used = report_used.used; return notifier_to_errno(rc); } static int netdev_offload_xstats_get_stats(struct net_device *dev, enum netdev_offload_xstats_type type, struct rtnl_hw_stats64 *p_stats, bool *p_used, struct netlink_ext_ack *extack) { struct netdev_notifier_offload_xstats_rd report_delta = {}; struct netdev_notifier_offload_xstats_info info = { .info.dev = dev, .info.extack = extack, .type = type, .report_delta = &report_delta, }; struct rtnl_hw_stats64 *stats; int rc; stats = netdev_offload_xstats_get_ptr(dev, type); if (WARN_ON(!stats)) return -EINVAL; rc = call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_REPORT_DELTA, &info.info); /* Cache whatever we got, even if there was an error, otherwise the * successful stats retrievals would get lost. */ netdev_hw_stats64_add(stats, &report_delta.stats); if (p_stats) *p_stats = *stats; *p_used = report_delta.used; return notifier_to_errno(rc); } int netdev_offload_xstats_get(struct net_device *dev, enum netdev_offload_xstats_type type, struct rtnl_hw_stats64 *p_stats, bool *p_used, struct netlink_ext_ack *extack) { ASSERT_RTNL(); if (p_stats) return netdev_offload_xstats_get_stats(dev, type, p_stats, p_used, extack); else return netdev_offload_xstats_get_used(dev, type, p_used, extack); } EXPORT_SYMBOL(netdev_offload_xstats_get); void netdev_offload_xstats_report_delta(struct netdev_notifier_offload_xstats_rd *report_delta, const struct rtnl_hw_stats64 *stats) { report_delta->used = true; netdev_hw_stats64_add(&report_delta->stats, stats); } EXPORT_SYMBOL(netdev_offload_xstats_report_delta); void netdev_offload_xstats_report_used(struct netdev_notifier_offload_xstats_ru *report_used) { report_used->used = true; } EXPORT_SYMBOL(netdev_offload_xstats_report_used); void netdev_offload_xstats_push_delta(struct net_device *dev, enum netdev_offload_xstats_type type, const struct rtnl_hw_stats64 *p_stats) { struct rtnl_hw_stats64 *stats; ASSERT_RTNL(); stats = netdev_offload_xstats_get_ptr(dev, type); if (WARN_ON(!stats)) return; netdev_hw_stats64_add(stats, p_stats); } EXPORT_SYMBOL(netdev_offload_xstats_push_delta); /** * netdev_get_xmit_slave - Get the xmit slave of master device * @dev: device * @skb: The packet * @all_slaves: assume all the slaves are active * * The reference counters are not incremented so the caller must be * careful with locks. The caller must hold RCU lock. * %NULL is returned if no slave is found. */ struct net_device *netdev_get_xmit_slave(struct net_device *dev, struct sk_buff *skb, bool all_slaves) { const struct net_device_ops *ops = dev->netdev_ops; if (!ops->ndo_get_xmit_slave) return NULL; return ops->ndo_get_xmit_slave(dev, skb, all_slaves); } EXPORT_SYMBOL(netdev_get_xmit_slave); static struct net_device *netdev_sk_get_lower_dev(struct net_device *dev, struct sock *sk) { const struct net_device_ops *ops = dev->netdev_ops; if (!ops->ndo_sk_get_lower_dev) return NULL; return ops->ndo_sk_get_lower_dev(dev, sk); } /** * netdev_sk_get_lowest_dev - Get the lowest device in chain given device and socket * @dev: device * @sk: the socket * * %NULL is returned if no lower device is found. */ struct net_device *netdev_sk_get_lowest_dev(struct net_device *dev, struct sock *sk) { struct net_device *lower; lower = netdev_sk_get_lower_dev(dev, sk); while (lower) { dev = lower; lower = netdev_sk_get_lower_dev(dev, sk); } return dev; } EXPORT_SYMBOL(netdev_sk_get_lowest_dev); static void netdev_adjacent_add_links(struct net_device *dev) { struct netdev_adjacent *iter; struct net *net = dev_net(dev); list_for_each_entry(iter, &dev->adj_list.upper, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_add(iter->dev, dev, &iter->dev->adj_list.lower); netdev_adjacent_sysfs_add(dev, iter->dev, &dev->adj_list.upper); } list_for_each_entry(iter, &dev->adj_list.lower, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_add(iter->dev, dev, &iter->dev->adj_list.upper); netdev_adjacent_sysfs_add(dev, iter->dev, &dev->adj_list.lower); } } static void netdev_adjacent_del_links(struct net_device *dev) { struct netdev_adjacent *iter; struct net *net = dev_net(dev); list_for_each_entry(iter, &dev->adj_list.upper, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_del(iter->dev, dev->name, &iter->dev->adj_list.lower); netdev_adjacent_sysfs_del(dev, iter->dev->name, &dev->adj_list.upper); } list_for_each_entry(iter, &dev->adj_list.lower, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_del(iter->dev, dev->name, &iter->dev->adj_list.upper); netdev_adjacent_sysfs_del(dev, iter->dev->name, &dev->adj_list.lower); } } void netdev_adjacent_rename_links(struct net_device *dev, char *oldname) { struct netdev_adjacent *iter; struct net *net = dev_net(dev); list_for_each_entry(iter, &dev->adj_list.upper, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_del(iter->dev, oldname, &iter->dev->adj_list.lower); netdev_adjacent_sysfs_add(iter->dev, dev, &iter->dev->adj_list.lower); } list_for_each_entry(iter, &dev->adj_list.lower, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_del(iter->dev, oldname, &iter->dev->adj_list.upper); netdev_adjacent_sysfs_add(iter->dev, dev, &iter->dev->adj_list.upper); } } void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev) { struct netdev_adjacent *lower; if (!lower_dev) return NULL; lower = __netdev_find_adj(lower_dev, &dev->adj_list.lower); if (!lower) return NULL; return lower->private; } EXPORT_SYMBOL(netdev_lower_dev_get_private); /** * netdev_lower_state_changed - Dispatch event about lower device state change * @lower_dev: device * @lower_state_info: state to dispatch * * Send NETDEV_CHANGELOWERSTATE to netdev notifiers with info. * The caller must hold the RTNL lock. */ void netdev_lower_state_changed(struct net_device *lower_dev, void *lower_state_info) { struct netdev_notifier_changelowerstate_info changelowerstate_info = { .info.dev = lower_dev, }; ASSERT_RTNL(); changelowerstate_info.lower_state_info = lower_state_info; call_netdevice_notifiers_info(NETDEV_CHANGELOWERSTATE, &changelowerstate_info.info); } EXPORT_SYMBOL(netdev_lower_state_changed); static void dev_change_rx_flags(struct net_device *dev, int flags) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_change_rx_flags) ops->ndo_change_rx_flags(dev, flags); } static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify) { unsigned int old_flags = dev->flags; unsigned int promiscuity, flags; kuid_t uid; kgid_t gid; ASSERT_RTNL(); promiscuity = dev->promiscuity + inc; if (promiscuity == 0) { /* * Avoid overflow. * If inc causes overflow, untouch promisc and return error. */ if (unlikely(inc > 0)) { netdev_warn(dev, "promiscuity touches roof, set promiscuity failed. promiscuity feature of device might be broken.\n"); return -EOVERFLOW; } flags = old_flags & ~IFF_PROMISC; } else { flags = old_flags | IFF_PROMISC; } WRITE_ONCE(dev->promiscuity, promiscuity); if (flags != old_flags) { WRITE_ONCE(dev->flags, flags); netdev_info(dev, "%s promiscuous mode\n", dev->flags & IFF_PROMISC ? "entered" : "left"); if (audit_enabled) { current_uid_gid(&uid, &gid); audit_log(audit_context(), GFP_ATOMIC, AUDIT_ANOM_PROMISCUOUS, "dev=%s prom=%d old_prom=%d auid=%u uid=%u gid=%u ses=%u", dev->name, (dev->flags & IFF_PROMISC), (old_flags & IFF_PROMISC), from_kuid(&init_user_ns, audit_get_loginuid(current)), from_kuid(&init_user_ns, uid), from_kgid(&init_user_ns, gid), audit_get_sessionid(current)); } dev_change_rx_flags(dev, IFF_PROMISC); } if (notify) __dev_notify_flags(dev, old_flags, IFF_PROMISC, 0, NULL); return 0; } /** * dev_set_promiscuity - update promiscuity count on a device * @dev: device * @inc: modifier * * Add or remove promiscuity from a device. While the count in the device * remains above zero the interface remains promiscuous. Once it hits zero * the device reverts back to normal filtering operation. A negative inc * value is used to drop promiscuity on the device. * Return 0 if successful or a negative errno code on error. */ int dev_set_promiscuity(struct net_device *dev, int inc) { unsigned int old_flags = dev->flags; int err; err = __dev_set_promiscuity(dev, inc, true); if (err < 0) return err; if (dev->flags != old_flags) dev_set_rx_mode(dev); return err; } EXPORT_SYMBOL(dev_set_promiscuity); static int __dev_set_allmulti(struct net_device *dev, int inc, bool notify) { unsigned int old_flags = dev->flags, old_gflags = dev->gflags; unsigned int allmulti, flags; ASSERT_RTNL(); allmulti = dev->allmulti + inc; if (allmulti == 0) { /* * Avoid overflow. * If inc causes overflow, untouch allmulti and return error. */ if (unlikely(inc > 0)) { netdev_warn(dev, "allmulti touches roof, set allmulti failed. allmulti feature of device might be broken.\n"); return -EOVERFLOW; } flags = old_flags & ~IFF_ALLMULTI; } else { flags = old_flags | IFF_ALLMULTI; } WRITE_ONCE(dev->allmulti, allmulti); if (flags != old_flags) { WRITE_ONCE(dev->flags, flags); netdev_info(dev, "%s allmulticast mode\n", dev->flags & IFF_ALLMULTI ? "entered" : "left"); dev_change_rx_flags(dev, IFF_ALLMULTI); dev_set_rx_mode(dev); if (notify) __dev_notify_flags(dev, old_flags, dev->gflags ^ old_gflags, 0, NULL); } return 0; } /** * dev_set_allmulti - update allmulti count on a device * @dev: device * @inc: modifier * * Add or remove reception of all multicast frames to a device. While the * count in the device remains above zero the interface remains listening * to all interfaces. Once it hits zero the device reverts back to normal * filtering operation. A negative @inc value is used to drop the counter * when releasing a resource needing all multicasts. * Return 0 if successful or a negative errno code on error. */ int dev_set_allmulti(struct net_device *dev, int inc) { return __dev_set_allmulti(dev, inc, true); } EXPORT_SYMBOL(dev_set_allmulti); /* * Upload unicast and multicast address lists to device and * configure RX filtering. When the device doesn't support unicast * filtering it is put in promiscuous mode while unicast addresses * are present. */ void __dev_set_rx_mode(struct net_device *dev) { const struct net_device_ops *ops = dev->netdev_ops; /* dev_open will call this function so the list will stay sane. */ if (!(dev->flags&IFF_UP)) return; if (!netif_device_present(dev)) return; if (!(dev->priv_flags & IFF_UNICAST_FLT)) { /* Unicast addresses changes may only happen under the rtnl, * therefore calling __dev_set_promiscuity here is safe. */ if (!netdev_uc_empty(dev) && !dev->uc_promisc) { __dev_set_promiscuity(dev, 1, false); dev->uc_promisc = true; } else if (netdev_uc_empty(dev) && dev->uc_promisc) { __dev_set_promiscuity(dev, -1, false); dev->uc_promisc = false; } } if (ops->ndo_set_rx_mode) ops->ndo_set_rx_mode(dev); } void dev_set_rx_mode(struct net_device *dev) { netif_addr_lock_bh(dev); __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); } /** * dev_get_flags - get flags reported to userspace * @dev: device * * Get the combination of flag bits exported through APIs to userspace. */ unsigned int dev_get_flags(const struct net_device *dev) { unsigned int flags; flags = (READ_ONCE(dev->flags) & ~(IFF_PROMISC | IFF_ALLMULTI | IFF_RUNNING | IFF_LOWER_UP | IFF_DORMANT)) | (READ_ONCE(dev->gflags) & (IFF_PROMISC | IFF_ALLMULTI)); if (netif_running(dev)) { if (netif_oper_up(dev)) flags |= IFF_RUNNING; if (netif_carrier_ok(dev)) flags |= IFF_LOWER_UP; if (netif_dormant(dev)) flags |= IFF_DORMANT; } return flags; } EXPORT_SYMBOL(dev_get_flags); int __dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack) { unsigned int old_flags = dev->flags; int ret; ASSERT_RTNL(); /* * Set the flags on our device. */ dev->flags = (flags & (IFF_DEBUG | IFF_NOTRAILERS | IFF_NOARP | IFF_DYNAMIC | IFF_MULTICAST | IFF_PORTSEL | IFF_AUTOMEDIA)) | (dev->flags & (IFF_UP | IFF_VOLATILE | IFF_PROMISC | IFF_ALLMULTI)); /* * Load in the correct multicast list now the flags have changed. */ if ((old_flags ^ flags) & IFF_MULTICAST) dev_change_rx_flags(dev, IFF_MULTICAST); dev_set_rx_mode(dev); /* * Have we downed the interface. We handle IFF_UP ourselves * according to user attempts to set it, rather than blindly * setting it. */ ret = 0; if ((old_flags ^ flags) & IFF_UP) { if (old_flags & IFF_UP) __dev_close(dev); else ret = __dev_open(dev, extack); } if ((flags ^ dev->gflags) & IFF_PROMISC) { int inc = (flags & IFF_PROMISC) ? 1 : -1; unsigned int old_flags = dev->flags; dev->gflags ^= IFF_PROMISC; if (__dev_set_promiscuity(dev, inc, false) >= 0) if (dev->flags != old_flags) dev_set_rx_mode(dev); } /* NOTE: order of synchronization of IFF_PROMISC and IFF_ALLMULTI * is important. Some (broken) drivers set IFF_PROMISC, when * IFF_ALLMULTI is requested not asking us and not reporting. */ if ((flags ^ dev->gflags) & IFF_ALLMULTI) { int inc = (flags & IFF_ALLMULTI) ? 1 : -1; dev->gflags ^= IFF_ALLMULTI; __dev_set_allmulti(dev, inc, false); } return ret; } void __dev_notify_flags(struct net_device *dev, unsigned int old_flags, unsigned int gchanges, u32 portid, const struct nlmsghdr *nlh) { unsigned int changes = dev->flags ^ old_flags; if (gchanges) rtmsg_ifinfo(RTM_NEWLINK, dev, gchanges, GFP_ATOMIC, portid, nlh); if (changes & IFF_UP) { if (dev->flags & IFF_UP) call_netdevice_notifiers(NETDEV_UP, dev); else call_netdevice_notifiers(NETDEV_DOWN, dev); } if (dev->flags & IFF_UP && (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) { struct netdev_notifier_change_info change_info = { .info = { .dev = dev, }, .flags_changed = changes, }; call_netdevice_notifiers_info(NETDEV_CHANGE, &change_info.info); } } /** * dev_change_flags - change device settings * @dev: device * @flags: device state flags * @extack: netlink extended ack * * Change settings on device based state flags. The flags are * in the userspace exported format. */ int dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack) { int ret; unsigned int changes, old_flags = dev->flags, old_gflags = dev->gflags; ret = __dev_change_flags(dev, flags, extack); if (ret < 0) return ret; changes = (old_flags ^ dev->flags) | (old_gflags ^ dev->gflags); __dev_notify_flags(dev, old_flags, changes, 0, NULL); return ret; } EXPORT_SYMBOL(dev_change_flags); int __dev_set_mtu(struct net_device *dev, int new_mtu) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_change_mtu) return ops->ndo_change_mtu(dev, new_mtu); /* Pairs with all the lockless reads of dev->mtu in the stack */ WRITE_ONCE(dev->mtu, new_mtu); return 0; } EXPORT_SYMBOL(__dev_set_mtu); int dev_validate_mtu(struct net_device *dev, int new_mtu, struct netlink_ext_ack *extack) { /* MTU must be positive, and in range */ if (new_mtu < 0 || new_mtu < dev->min_mtu) { NL_SET_ERR_MSG(extack, "mtu less than device minimum"); return -EINVAL; } if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) { NL_SET_ERR_MSG(extack, "mtu greater than device maximum"); return -EINVAL; } return 0; } /** * dev_set_mtu_ext - Change maximum transfer unit * @dev: device * @new_mtu: new transfer unit * @extack: netlink extended ack * * Change the maximum transfer size of the network device. */ int dev_set_mtu_ext(struct net_device *dev, int new_mtu, struct netlink_ext_ack *extack) { int err, orig_mtu; if (new_mtu == dev->mtu) return 0; err = dev_validate_mtu(dev, new_mtu, extack); if (err) return err; if (!netif_device_present(dev)) return -ENODEV; err = call_netdevice_notifiers(NETDEV_PRECHANGEMTU, dev); err = notifier_to_errno(err); if (err) return err; orig_mtu = dev->mtu; err = __dev_set_mtu(dev, new_mtu); if (!err) { err = call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev, orig_mtu); err = notifier_to_errno(err); if (err) { /* setting mtu back and notifying everyone again, * so that they have a chance to revert changes. */ __dev_set_mtu(dev, orig_mtu); call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev, new_mtu); } } return err; } int dev_set_mtu(struct net_device *dev, int new_mtu) { struct netlink_ext_ack extack; int err; memset(&extack, 0, sizeof(extack)); err = dev_set_mtu_ext(dev, new_mtu, &extack); if (err && extack._msg) net_err_ratelimited("%s: %s\n", dev->name, extack._msg); return err; } EXPORT_SYMBOL(dev_set_mtu); /** * dev_change_tx_queue_len - Change TX queue length of a netdevice * @dev: device * @new_len: new tx queue length */ int dev_change_tx_queue_len(struct net_device *dev, unsigned long new_len) { unsigned int orig_len = dev->tx_queue_len; int res; if (new_len != (unsigned int)new_len) return -ERANGE; if (new_len != orig_len) { WRITE_ONCE(dev->tx_queue_len, new_len); res = call_netdevice_notifiers(NETDEV_CHANGE_TX_QUEUE_LEN, dev); res = notifier_to_errno(res); if (res) goto err_rollback; res = dev_qdisc_change_tx_queue_len(dev); if (res) goto err_rollback; } return 0; err_rollback: netdev_err(dev, "refused to change device tx_queue_len\n"); WRITE_ONCE(dev->tx_queue_len, orig_len); return res; } /** * dev_set_group - Change group this device belongs to * @dev: device * @new_group: group this device should belong to */ void dev_set_group(struct net_device *dev, int new_group) { dev->group = new_group; } /** * dev_pre_changeaddr_notify - Call NETDEV_PRE_CHANGEADDR. * @dev: device * @addr: new address * @extack: netlink extended ack */ int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr, struct netlink_ext_ack *extack) { struct netdev_notifier_pre_changeaddr_info info = { .info.dev = dev, .info.extack = extack, .dev_addr = addr, }; int rc; rc = call_netdevice_notifiers_info(NETDEV_PRE_CHANGEADDR, &info.info); return notifier_to_errno(rc); } EXPORT_SYMBOL(dev_pre_changeaddr_notify); /** * dev_set_mac_address - Change Media Access Control Address * @dev: device * @sa: new address * @extack: netlink extended ack * * Change the hardware (MAC) address of the device */ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa, struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; int err; if (!ops->ndo_set_mac_address) return -EOPNOTSUPP; if (sa->sa_family != dev->type) return -EINVAL; if (!netif_device_present(dev)) return -ENODEV; err = dev_pre_changeaddr_notify(dev, sa->sa_data, extack); if (err) return err; if (memcmp(dev->dev_addr, sa->sa_data, dev->addr_len)) { err = ops->ndo_set_mac_address(dev, sa); if (err) return err; } dev->addr_assign_type = NET_ADDR_SET; call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); add_device_randomness(dev->dev_addr, dev->addr_len); return 0; } EXPORT_SYMBOL(dev_set_mac_address); DECLARE_RWSEM(dev_addr_sem); int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa, struct netlink_ext_ack *extack) { int ret; down_write(&dev_addr_sem); ret = dev_set_mac_address(dev, sa, extack); up_write(&dev_addr_sem); return ret; } EXPORT_SYMBOL(dev_set_mac_address_user); int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name) { size_t size = sizeof(sa->sa_data_min); struct net_device *dev; int ret = 0; down_read(&dev_addr_sem); rcu_read_lock(); dev = dev_get_by_name_rcu(net, dev_name); if (!dev) { ret = -ENODEV; goto unlock; } if (!dev->addr_len) memset(sa->sa_data, 0, size); else memcpy(sa->sa_data, dev->dev_addr, min_t(size_t, size, dev->addr_len)); sa->sa_family = dev->type; unlock: rcu_read_unlock(); up_read(&dev_addr_sem); return ret; } EXPORT_SYMBOL(dev_get_mac_address); /** * dev_change_carrier - Change device carrier * @dev: device * @new_carrier: new value * * Change device carrier */ int dev_change_carrier(struct net_device *dev, bool new_carrier) { const struct net_device_ops *ops = dev->netdev_ops; if (!ops->ndo_change_carrier) return -EOPNOTSUPP; if (!netif_device_present(dev)) return -ENODEV; return ops->ndo_change_carrier(dev, new_carrier); } /** * dev_get_phys_port_id - Get device physical port ID * @dev: device * @ppid: port ID * * Get device physical port ID */ int dev_get_phys_port_id(struct net_device *dev, struct netdev_phys_item_id *ppid) { const struct net_device_ops *ops = dev->netdev_ops; if (!ops->ndo_get_phys_port_id) return -EOPNOTSUPP; return ops->ndo_get_phys_port_id(dev, ppid); } /** * dev_get_phys_port_name - Get device physical port name * @dev: device * @name: port name * @len: limit of bytes to copy to name * * Get device physical port name */ int dev_get_phys_port_name(struct net_device *dev, char *name, size_t len) { const struct net_device_ops *ops = dev->netdev_ops; int err; if (ops->ndo_get_phys_port_name) { err = ops->ndo_get_phys_port_name(dev, name, len); if (err != -EOPNOTSUPP) return err; } return devlink_compat_phys_port_name_get(dev, name, len); } /** * dev_get_port_parent_id - Get the device's port parent identifier * @dev: network device * @ppid: pointer to a storage for the port's parent identifier * @recurse: allow/disallow recursion to lower devices * * Get the devices's port parent identifier */ int dev_get_port_parent_id(struct net_device *dev, struct netdev_phys_item_id *ppid, bool recurse) { const struct net_device_ops *ops = dev->netdev_ops; struct netdev_phys_item_id first = { }; struct net_device *lower_dev; struct list_head *iter; int err; if (ops->ndo_get_port_parent_id) { err = ops->ndo_get_port_parent_id(dev, ppid); if (err != -EOPNOTSUPP) return err; } err = devlink_compat_switch_id_get(dev, ppid); if (!recurse || err != -EOPNOTSUPP) return err; netdev_for_each_lower_dev(dev, lower_dev, iter) { err = dev_get_port_parent_id(lower_dev, ppid, true); if (err) break; if (!first.id_len) first = *ppid; else if (memcmp(&first, ppid, sizeof(*ppid))) return -EOPNOTSUPP; } return err; } EXPORT_SYMBOL(dev_get_port_parent_id); /** * netdev_port_same_parent_id - Indicate if two network devices have * the same port parent identifier * @a: first network device * @b: second network device */ bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b) { struct netdev_phys_item_id a_id = { }; struct netdev_phys_item_id b_id = { }; if (dev_get_port_parent_id(a, &a_id, true) || dev_get_port_parent_id(b, &b_id, true)) return false; return netdev_phys_item_id_same(&a_id, &b_id); } EXPORT_SYMBOL(netdev_port_same_parent_id); /** * dev_change_proto_down - set carrier according to proto_down. * * @dev: device * @proto_down: new value */ int dev_change_proto_down(struct net_device *dev, bool proto_down) { if (!dev->change_proto_down) return -EOPNOTSUPP; if (!netif_device_present(dev)) return -ENODEV; if (proto_down) netif_carrier_off(dev); else netif_carrier_on(dev); WRITE_ONCE(dev->proto_down, proto_down); return 0; } /** * dev_change_proto_down_reason - proto down reason * * @dev: device * @mask: proto down mask * @value: proto down value */ void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask, u32 value) { u32 proto_down_reason; int b; if (!mask) { proto_down_reason = value; } else { proto_down_reason = dev->proto_down_reason; for_each_set_bit(b, &mask, 32) { if (value & (1 << b)) proto_down_reason |= BIT(b); else proto_down_reason &= ~BIT(b); } } WRITE_ONCE(dev->proto_down_reason, proto_down_reason); } struct bpf_xdp_link { struct bpf_link link; struct net_device *dev; /* protected by rtnl_lock, no refcnt held */ int flags; }; static enum bpf_xdp_mode dev_xdp_mode(struct net_device *dev, u32 flags) { if (flags & XDP_FLAGS_HW_MODE) return XDP_MODE_HW; if (flags & XDP_FLAGS_DRV_MODE) return XDP_MODE_DRV; if (flags & XDP_FLAGS_SKB_MODE) return XDP_MODE_SKB; return dev->netdev_ops->ndo_bpf ? XDP_MODE_DRV : XDP_MODE_SKB; } static bpf_op_t dev_xdp_bpf_op(struct net_device *dev, enum bpf_xdp_mode mode) { switch (mode) { case XDP_MODE_SKB: return generic_xdp_install; case XDP_MODE_DRV: case XDP_MODE_HW: return dev->netdev_ops->ndo_bpf; default: return NULL; } } static struct bpf_xdp_link *dev_xdp_link(struct net_device *dev, enum bpf_xdp_mode mode) { return dev->xdp_state[mode].link; } static struct bpf_prog *dev_xdp_prog(struct net_device *dev, enum bpf_xdp_mode mode) { struct bpf_xdp_link *link = dev_xdp_link(dev, mode); if (link) return link->link.prog; return dev->xdp_state[mode].prog; } u8 dev_xdp_prog_count(struct net_device *dev) { u8 count = 0; int i; for (i = 0; i < __MAX_XDP_MODE; i++) if (dev->xdp_state[i].prog || dev->xdp_state[i].link) count++; return count; } EXPORT_SYMBOL_GPL(dev_xdp_prog_count); int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf) { if (!dev->netdev_ops->ndo_bpf) return -EOPNOTSUPP; if (dev_get_min_mp_channel_count(dev)) { NL_SET_ERR_MSG(bpf->extack, "unable to propagate XDP to device using memory provider"); return -EBUSY; } return dev->netdev_ops->ndo_bpf(dev, bpf); } EXPORT_SYMBOL_GPL(dev_xdp_propagate); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode) { struct bpf_prog *prog = dev_xdp_prog(dev, mode); return prog ? prog->aux->id : 0; } static void dev_xdp_set_link(struct net_device *dev, enum bpf_xdp_mode mode, struct bpf_xdp_link *link) { dev->xdp_state[mode].link = link; dev->xdp_state[mode].prog = NULL; } static void dev_xdp_set_prog(struct net_device *dev, enum bpf_xdp_mode mode, struct bpf_prog *prog) { dev->xdp_state[mode].link = NULL; dev->xdp_state[mode].prog = prog; } static int dev_xdp_install(struct net_device *dev, enum bpf_xdp_mode mode, bpf_op_t bpf_op, struct netlink_ext_ack *extack, u32 flags, struct bpf_prog *prog) { struct netdev_bpf xdp; int err; if (dev_get_min_mp_channel_count(dev)) { NL_SET_ERR_MSG(extack, "unable to install XDP to device using memory provider"); return -EBUSY; } memset(&xdp, 0, sizeof(xdp)); xdp.command = mode == XDP_MODE_HW ? XDP_SETUP_PROG_HW : XDP_SETUP_PROG; xdp.extack = extack; xdp.flags = flags; xdp.prog = prog; /* Drivers assume refcnt is already incremented (i.e, prog pointer is * "moved" into driver), so they don't increment it on their own, but * they do decrement refcnt when program is detached or replaced. * Given net_device also owns link/prog, we need to bump refcnt here * to prevent drivers from underflowing it. */ if (prog) bpf_prog_inc(prog); err = bpf_op(dev, &xdp); if (err) { if (prog) bpf_prog_put(prog); return err; } if (mode != XDP_MODE_HW) bpf_prog_change_xdp(dev_xdp_prog(dev, mode), prog); return 0; } static void dev_xdp_uninstall(struct net_device *dev) { struct bpf_xdp_link *link; struct bpf_prog *prog; enum bpf_xdp_mode mode; bpf_op_t bpf_op; ASSERT_RTNL(); for (mode = XDP_MODE_SKB; mode < __MAX_XDP_MODE; mode++) { prog = dev_xdp_prog(dev, mode); if (!prog) continue; bpf_op = dev_xdp_bpf_op(dev, mode); if (!bpf_op) continue; WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL)); /* auto-detach link from net device */ link = dev_xdp_link(dev, mode); if (link) link->dev = NULL; else bpf_prog_put(prog); dev_xdp_set_link(dev, mode, NULL); } } static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack, struct bpf_xdp_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog, u32 flags) { unsigned int num_modes = hweight32(flags & XDP_FLAGS_MODES); struct bpf_prog *cur_prog; struct net_device *upper; struct list_head *iter; enum bpf_xdp_mode mode; bpf_op_t bpf_op; int err; ASSERT_RTNL(); /* either link or prog attachment, never both */ if (link && (new_prog || old_prog)) return -EINVAL; /* link supports only XDP mode flags */ if (link && (flags & ~XDP_FLAGS_MODES)) { NL_SET_ERR_MSG(extack, "Invalid XDP flags for BPF link attachment"); return -EINVAL; } /* just one XDP mode bit should be set, zero defaults to drv/skb mode */ if (num_modes > 1) { NL_SET_ERR_MSG(extack, "Only one XDP mode flag can be set"); return -EINVAL; } /* avoid ambiguity if offload + drv/skb mode progs are both loaded */ if (!num_modes && dev_xdp_prog_count(dev) > 1) { NL_SET_ERR_MSG(extack, "More than one program loaded, unset mode is ambiguous"); return -EINVAL; } /* old_prog != NULL implies XDP_FLAGS_REPLACE is set */ if (old_prog && !(flags & XDP_FLAGS_REPLACE)) { NL_SET_ERR_MSG(extack, "XDP_FLAGS_REPLACE is not specified"); return -EINVAL; } mode = dev_xdp_mode(dev, flags); /* can't replace attached link */ if (dev_xdp_link(dev, mode)) { NL_SET_ERR_MSG(extack, "Can't replace active BPF XDP link"); return -EBUSY; } /* don't allow if an upper device already has a program */ netdev_for_each_upper_dev_rcu(dev, upper, iter) { if (dev_xdp_prog_count(upper) > 0) { NL_SET_ERR_MSG(extack, "Cannot attach when an upper device already has a program"); return -EEXIST; } } cur_prog = dev_xdp_prog(dev, mode); /* can't replace attached prog with link */ if (link && cur_prog) { NL_SET_ERR_MSG(extack, "Can't replace active XDP program with BPF link"); return -EBUSY; } if ((flags & XDP_FLAGS_REPLACE) && cur_prog != old_prog) { NL_SET_ERR_MSG(extack, "Active program does not match expected"); return -EEXIST; } /* put effective new program into new_prog */ if (link) new_prog = link->link.prog; if (new_prog) { bool offload = mode == XDP_MODE_HW; enum bpf_xdp_mode other_mode = mode == XDP_MODE_SKB ? XDP_MODE_DRV : XDP_MODE_SKB; if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && cur_prog) { NL_SET_ERR_MSG(extack, "XDP program already attached"); return -EBUSY; } if (!offload && dev_xdp_prog(dev, other_mode)) { NL_SET_ERR_MSG(extack, "Native and generic XDP can't be active at the same time"); return -EEXIST; } if (!offload && bpf_prog_is_offloaded(new_prog->aux)) { NL_SET_ERR_MSG(extack, "Using offloaded program without HW_MODE flag is not supported"); return -EINVAL; } if (bpf_prog_is_dev_bound(new_prog->aux) && !bpf_offload_dev_match(new_prog, dev)) { NL_SET_ERR_MSG(extack, "Program bound to different device"); return -EINVAL; } if (new_prog->expected_attach_type == BPF_XDP_DEVMAP) { NL_SET_ERR_MSG(extack, "BPF_XDP_DEVMAP programs can not be attached to a device"); return -EINVAL; } if (new_prog->expected_attach_type == BPF_XDP_CPUMAP) { NL_SET_ERR_MSG(extack, "BPF_XDP_CPUMAP programs can not be attached to a device"); return -EINVAL; } } /* don't call drivers if the effective program didn't change */ if (new_prog != cur_prog) { bpf_op = dev_xdp_bpf_op(dev, mode); if (!bpf_op) { NL_SET_ERR_MSG(extack, "Underlying driver does not support XDP in native mode"); return -EOPNOTSUPP; } err = dev_xdp_install(dev, mode, bpf_op, extack, flags, new_prog); if (err) return err; } if (link) dev_xdp_set_link(dev, mode, link); else dev_xdp_set_prog(dev, mode, new_prog); if (cur_prog) bpf_prog_put(cur_prog); return 0; } static int dev_xdp_attach_link(struct net_device *dev, struct netlink_ext_ack *extack, struct bpf_xdp_link *link) { return dev_xdp_attach(dev, extack, link, NULL, NULL, link->flags); } static int dev_xdp_detach_link(struct net_device *dev, struct netlink_ext_ack *extack, struct bpf_xdp_link *link) { enum bpf_xdp_mode mode; bpf_op_t bpf_op; ASSERT_RTNL(); mode = dev_xdp_mode(dev, link->flags); if (dev_xdp_link(dev, mode) != link) return -EINVAL; bpf_op = dev_xdp_bpf_op(dev, mode); WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL)); dev_xdp_set_link(dev, mode, NULL); return 0; } static void bpf_xdp_link_release(struct bpf_link *link) { struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); rtnl_lock(); /* if racing with net_device's tear down, xdp_link->dev might be * already NULL, in which case link was already auto-detached */ if (xdp_link->dev) { WARN_ON(dev_xdp_detach_link(xdp_link->dev, NULL, xdp_link)); xdp_link->dev = NULL; } rtnl_unlock(); } static int bpf_xdp_link_detach(struct bpf_link *link) { bpf_xdp_link_release(link); return 0; } static void bpf_xdp_link_dealloc(struct bpf_link *link) { struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); kfree(xdp_link); } static void bpf_xdp_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); u32 ifindex = 0; rtnl_lock(); if (xdp_link->dev) ifindex = xdp_link->dev->ifindex; rtnl_unlock(); seq_printf(seq, "ifindex:\t%u\n", ifindex); } static int bpf_xdp_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); u32 ifindex = 0; rtnl_lock(); if (xdp_link->dev) ifindex = xdp_link->dev->ifindex; rtnl_unlock(); info->xdp.ifindex = ifindex; return 0; } static int bpf_xdp_link_update(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog) { struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); enum bpf_xdp_mode mode; bpf_op_t bpf_op; int err = 0; rtnl_lock(); /* link might have been auto-released already, so fail */ if (!xdp_link->dev) { err = -ENOLINK; goto out_unlock; } if (old_prog && link->prog != old_prog) { err = -EPERM; goto out_unlock; } old_prog = link->prog; if (old_prog->type != new_prog->type || old_prog->expected_attach_type != new_prog->expected_attach_type) { err = -EINVAL; goto out_unlock; } if (old_prog == new_prog) { /* no-op, don't disturb drivers */ bpf_prog_put(new_prog); goto out_unlock; } mode = dev_xdp_mode(xdp_link->dev, xdp_link->flags); bpf_op = dev_xdp_bpf_op(xdp_link->dev, mode); err = dev_xdp_install(xdp_link->dev, mode, bpf_op, NULL, xdp_link->flags, new_prog); if (err) goto out_unlock; old_prog = xchg(&link->prog, new_prog); bpf_prog_put(old_prog); out_unlock: rtnl_unlock(); return err; } static const struct bpf_link_ops bpf_xdp_link_lops = { .release = bpf_xdp_link_release, .dealloc = bpf_xdp_link_dealloc, .detach = bpf_xdp_link_detach, .show_fdinfo = bpf_xdp_link_show_fdinfo, .fill_link_info = bpf_xdp_link_fill_link_info, .update_prog = bpf_xdp_link_update, }; int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct net *net = current->nsproxy->net_ns; struct bpf_link_primer link_primer; struct netlink_ext_ack extack = {}; struct bpf_xdp_link *link; struct net_device *dev; int err, fd; rtnl_lock(); dev = dev_get_by_index(net, attr->link_create.target_ifindex); if (!dev) { rtnl_unlock(); return -EINVAL; } link = kzalloc(sizeof(*link), GFP_USER); if (!link) { err = -ENOMEM; goto unlock; } bpf_link_init(&link->link, BPF_LINK_TYPE_XDP, &bpf_xdp_link_lops, prog); link->dev = dev; link->flags = attr->link_create.flags; err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); goto unlock; } err = dev_xdp_attach_link(dev, &extack, link); rtnl_unlock(); if (err) { link->dev = NULL; bpf_link_cleanup(&link_primer); trace_bpf_xdp_link_attach_failed(extack._msg); goto out_put_dev; } fd = bpf_link_settle(&link_primer); /* link itself doesn't hold dev's refcnt to not complicate shutdown */ dev_put(dev); return fd; unlock: rtnl_unlock(); out_put_dev: dev_put(dev); return err; } /** * dev_change_xdp_fd - set or clear a bpf program for a device rx path * @dev: device * @extack: netlink extended ack * @fd: new program fd or negative value to clear * @expected_fd: old program fd that userspace expects to replace or clear * @flags: xdp-related flags * * Set or clear a bpf program for a device */ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, int expected_fd, u32 flags) { enum bpf_xdp_mode mode = dev_xdp_mode(dev, flags); struct bpf_prog *new_prog = NULL, *old_prog = NULL; int err; ASSERT_RTNL(); if (fd >= 0) { new_prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP, mode != XDP_MODE_SKB); if (IS_ERR(new_prog)) return PTR_ERR(new_prog); } if (expected_fd >= 0) { old_prog = bpf_prog_get_type_dev(expected_fd, BPF_PROG_TYPE_XDP, mode != XDP_MODE_SKB); if (IS_ERR(old_prog)) { err = PTR_ERR(old_prog); old_prog = NULL; goto err_out; } } err = dev_xdp_attach(dev, extack, NULL, new_prog, old_prog, flags); err_out: if (err && new_prog) bpf_prog_put(new_prog); if (old_prog) bpf_prog_put(old_prog); return err; } u32 dev_get_min_mp_channel_count(const struct net_device *dev) { int i; ASSERT_RTNL(); for (i = dev->real_num_rx_queues - 1; i >= 0; i--) if (dev->_rx[i].mp_params.mp_priv) /* The channel count is the idx plus 1. */ return i + 1; return 0; } /** * dev_index_reserve() - allocate an ifindex in a namespace * @net: the applicable net namespace * @ifindex: requested ifindex, pass %0 to get one allocated * * Allocate a ifindex for a new device. Caller must either use the ifindex * to store the device (via list_netdevice()) or call dev_index_release() * to give the index up. * * Return: a suitable unique value for a new device interface number or -errno. */ static int dev_index_reserve(struct net *net, u32 ifindex) { int err; if (ifindex > INT_MAX) { DEBUG_NET_WARN_ON_ONCE(1); return -EINVAL; } if (!ifindex) err = xa_alloc_cyclic(&net->dev_by_index, &ifindex, NULL, xa_limit_31b, &net->ifindex, GFP_KERNEL); else err = xa_insert(&net->dev_by_index, ifindex, NULL, GFP_KERNEL); if (err < 0) return err; return ifindex; } static void dev_index_release(struct net *net, int ifindex) { /* Expect only unused indexes, unlist_netdevice() removes the used */ WARN_ON(xa_erase(&net->dev_by_index, ifindex)); } /* Delayed registration/unregisteration */ LIST_HEAD(net_todo_list); DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); atomic_t dev_unreg_count = ATOMIC_INIT(0); static void net_set_todo(struct net_device *dev) { list_add_tail(&dev->todo_list, &net_todo_list); } static netdev_features_t netdev_sync_upper_features(struct net_device *lower, struct net_device *upper, netdev_features_t features) { netdev_features_t upper_disables = NETIF_F_UPPER_DISABLES; netdev_features_t feature; int feature_bit; for_each_netdev_feature(upper_disables, feature_bit) { feature = __NETIF_F_BIT(feature_bit); if (!(upper->wanted_features & feature) && (features & feature)) { netdev_dbg(lower, "Dropping feature %pNF, upper dev %s has it off.\n", &feature, upper->name); features &= ~feature; } } return features; } static void netdev_sync_lower_features(struct net_device *upper, struct net_device *lower, netdev_features_t features) { netdev_features_t upper_disables = NETIF_F_UPPER_DISABLES; netdev_features_t feature; int feature_bit; for_each_netdev_feature(upper_disables, feature_bit) { feature = __NETIF_F_BIT(feature_bit); if (!(features & feature) && (lower->features & feature)) { netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n", &feature, lower->name); lower->wanted_features &= ~feature; __netdev_update_features(lower); if (unlikely(lower->features & feature)) netdev_WARN(upper, "failed to disable %pNF on %s!\n", &feature, lower->name); else netdev_features_change(lower); } } } static bool netdev_has_ip_or_hw_csum(netdev_features_t features) { netdev_features_t ip_csum_mask = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; bool ip_csum = (features & ip_csum_mask) == ip_csum_mask; bool hw_csum = features & NETIF_F_HW_CSUM; return ip_csum || hw_csum; } static netdev_features_t netdev_fix_features(struct net_device *dev, netdev_features_t features) { /* Fix illegal checksum combinations */ if ((features & NETIF_F_HW_CSUM) && (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { netdev_warn(dev, "mixed HW and IP checksum settings.\n"); features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); } /* TSO requires that SG is present as well. */ if ((features & NETIF_F_ALL_TSO) && !(features & NETIF_F_SG)) { netdev_dbg(dev, "Dropping TSO features since no SG feature.\n"); features &= ~NETIF_F_ALL_TSO; } if ((features & NETIF_F_TSO) && !(features & NETIF_F_HW_CSUM) && !(features & NETIF_F_IP_CSUM)) { netdev_dbg(dev, "Dropping TSO features since no CSUM feature.\n"); features &= ~NETIF_F_TSO; features &= ~NETIF_F_TSO_ECN; } if ((features & NETIF_F_TSO6) && !(features & NETIF_F_HW_CSUM) && !(features & NETIF_F_IPV6_CSUM)) { netdev_dbg(dev, "Dropping TSO6 features since no CSUM feature.\n"); features &= ~NETIF_F_TSO6; } /* TSO with IPv4 ID mangling requires IPv4 TSO be enabled */ if ((features & NETIF_F_TSO_MANGLEID) && !(features & NETIF_F_TSO)) features &= ~NETIF_F_TSO_MANGLEID; /* TSO ECN requires that TSO is present as well. */ if ((features & NETIF_F_ALL_TSO) == NETIF_F_TSO_ECN) features &= ~NETIF_F_TSO_ECN; /* Software GSO depends on SG. */ if ((features & NETIF_F_GSO) && !(features & NETIF_F_SG)) { netdev_dbg(dev, "Dropping NETIF_F_GSO since no SG feature.\n"); features &= ~NETIF_F_GSO; } /* GSO partial features require GSO partial be set */ if ((features & dev->gso_partial_features) && !(features & NETIF_F_GSO_PARTIAL)) { netdev_dbg(dev, "Dropping partially supported GSO features since no GSO partial.\n"); features &= ~dev->gso_partial_features; } if (!(features & NETIF_F_RXCSUM)) { /* NETIF_F_GRO_HW implies doing RXCSUM since every packet * successfully merged by hardware must also have the * checksum verified by hardware. If the user does not * want to enable RXCSUM, logically, we should disable GRO_HW. */ if (features & NETIF_F_GRO_HW) { netdev_dbg(dev, "Dropping NETIF_F_GRO_HW since no RXCSUM feature.\n"); features &= ~NETIF_F_GRO_HW; } } /* LRO/HW-GRO features cannot be combined with RX-FCS */ if (features & NETIF_F_RXFCS) { if (features & NETIF_F_LRO) { netdev_dbg(dev, "Dropping LRO feature since RX-FCS is requested.\n"); features &= ~NETIF_F_LRO; } if (features & NETIF_F_GRO_HW) { netdev_dbg(dev, "Dropping HW-GRO feature since RX-FCS is requested.\n"); features &= ~NETIF_F_GRO_HW; } } if ((features & NETIF_F_GRO_HW) && (features & NETIF_F_LRO)) { netdev_dbg(dev, "Dropping LRO feature since HW-GRO is requested.\n"); features &= ~NETIF_F_LRO; } if ((features & NETIF_F_HW_TLS_TX) && !netdev_has_ip_or_hw_csum(features)) { netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n"); features &= ~NETIF_F_HW_TLS_TX; } if ((features & NETIF_F_HW_TLS_RX) && !(features & NETIF_F_RXCSUM)) { netdev_dbg(dev, "Dropping TLS RX HW offload feature since no RXCSUM feature.\n"); features &= ~NETIF_F_HW_TLS_RX; } if ((features & NETIF_F_GSO_UDP_L4) && !netdev_has_ip_or_hw_csum(features)) { netdev_dbg(dev, "Dropping USO feature since no CSUM feature.\n"); features &= ~NETIF_F_GSO_UDP_L4; } return features; } int __netdev_update_features(struct net_device *dev) { struct net_device *upper, *lower; netdev_features_t features; struct list_head *iter; int err = -1; ASSERT_RTNL(); features = netdev_get_wanted_features(dev); if (dev->netdev_ops->ndo_fix_features) features = dev->netdev_ops->ndo_fix_features(dev, features); /* driver might be less strict about feature dependencies */ features = netdev_fix_features(dev, features); /* some features can't be enabled if they're off on an upper device */ netdev_for_each_upper_dev_rcu(dev, upper, iter) features = netdev_sync_upper_features(dev, upper, features); if (dev->features == features) goto sync_lower; netdev_dbg(dev, "Features changed: %pNF -> %pNF\n", &dev->features, &features); if (dev->netdev_ops->ndo_set_features) err = dev->netdev_ops->ndo_set_features(dev, features); else err = 0; if (unlikely(err < 0)) { netdev_err(dev, "set_features() failed (%d); wanted %pNF, left %pNF\n", err, &features, &dev->features); /* return non-0 since some features might have changed and * it's better to fire a spurious notification than miss it */ return -1; } sync_lower: /* some features must be disabled on lower devices when disabled * on an upper device (think: bonding master or bridge) */ netdev_for_each_lower_dev(dev, lower, iter) netdev_sync_lower_features(dev, lower, features); if (!err) { netdev_features_t diff = features ^ dev->features; if (diff & NETIF_F_RX_UDP_TUNNEL_PORT) { /* udp_tunnel_{get,drop}_rx_info both need * NETIF_F_RX_UDP_TUNNEL_PORT enabled on the * device, or they won't do anything. * Thus we need to update dev->features * *before* calling udp_tunnel_get_rx_info, * but *after* calling udp_tunnel_drop_rx_info. */ if (features & NETIF_F_RX_UDP_TUNNEL_PORT) { dev->features = features; udp_tunnel_get_rx_info(dev); } else { udp_tunnel_drop_rx_info(dev); } } if (diff & NETIF_F_HW_VLAN_CTAG_FILTER) { if (features & NETIF_F_HW_VLAN_CTAG_FILTER) { dev->features = features; err |= vlan_get_rx_ctag_filter_info(dev); } else { vlan_drop_rx_ctag_filter_info(dev); } } if (diff & NETIF_F_HW_VLAN_STAG_FILTER) { if (features & NETIF_F_HW_VLAN_STAG_FILTER) { dev->features = features; err |= vlan_get_rx_stag_filter_info(dev); } else { vlan_drop_rx_stag_filter_info(dev); } } dev->features = features; } return err < 0 ? 0 : 1; } /** * netdev_update_features - recalculate device features * @dev: the device to check * * Recalculate dev->features set and send notifications if it * has changed. Should be called after driver or hardware dependent * conditions might have changed that influence the features. */ void netdev_update_features(struct net_device *dev) { if (__netdev_update_features(dev)) netdev_features_change(dev); } EXPORT_SYMBOL(netdev_update_features); /** * netdev_change_features - recalculate device features * @dev: the device to check * * Recalculate dev->features set and send notifications even * if they have not changed. Should be called instead of * netdev_update_features() if also dev->vlan_features might * have changed to allow the changes to be propagated to stacked * VLAN devices. */ void netdev_change_features(struct net_device *dev) { __netdev_update_features(dev); netdev_features_change(dev); } EXPORT_SYMBOL(netdev_change_features); /** * netif_stacked_transfer_operstate - transfer operstate * @rootdev: the root or lower level device to transfer state from * @dev: the device to transfer operstate to * * Transfer operational state from root to device. This is normally * called when a stacking relationship exists between the root * device and the device(a leaf device). */ void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev) { if (rootdev->operstate == IF_OPER_DORMANT) netif_dormant_on(dev); else netif_dormant_off(dev); if (rootdev->operstate == IF_OPER_TESTING) netif_testing_on(dev); else netif_testing_off(dev); if (netif_carrier_ok(rootdev)) netif_carrier_on(dev); else netif_carrier_off(dev); } EXPORT_SYMBOL(netif_stacked_transfer_operstate); static int netif_alloc_rx_queues(struct net_device *dev) { unsigned int i, count = dev->num_rx_queues; struct netdev_rx_queue *rx; size_t sz = count * sizeof(*rx); int err = 0; BUG_ON(count < 1); rx = kvzalloc(sz, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!rx) return -ENOMEM; dev->_rx = rx; for (i = 0; i < count; i++) { rx[i].dev = dev; /* XDP RX-queue setup */ err = xdp_rxq_info_reg(&rx[i].xdp_rxq, dev, i, 0); if (err < 0) goto err_rxq_info; } return 0; err_rxq_info: /* Rollback successful reg's and free other resources */ while (i--) xdp_rxq_info_unreg(&rx[i].xdp_rxq); kvfree(dev->_rx); dev->_rx = NULL; return err; } static void netif_free_rx_queues(struct net_device *dev) { unsigned int i, count = dev->num_rx_queues; /* netif_alloc_rx_queues alloc failed, resources have been unreg'ed */ if (!dev->_rx) return; for (i = 0; i < count; i++) xdp_rxq_info_unreg(&dev->_rx[i].xdp_rxq); kvfree(dev->_rx); } static void netdev_init_one_queue(struct net_device *dev, struct netdev_queue *queue, void *_unused) { /* Initialize queue lock */ spin_lock_init(&queue->_xmit_lock); netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type); queue->xmit_lock_owner = -1; netdev_queue_numa_node_write(queue, NUMA_NO_NODE); queue->dev = dev; #ifdef CONFIG_BQL dql_init(&queue->dql, HZ); #endif } static void netif_free_tx_queues(struct net_device *dev) { kvfree(dev->_tx); } static int netif_alloc_netdev_queues(struct net_device *dev) { unsigned int count = dev->num_tx_queues; struct netdev_queue *tx; size_t sz = count * sizeof(*tx); if (count < 1 || count > 0xffff) return -EINVAL; tx = kvzalloc(sz, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!tx) return -ENOMEM; dev->_tx = tx; netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL); spin_lock_init(&dev->tx_global_lock); return 0; } void netif_tx_stop_all_queues(struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); netif_tx_stop_queue(txq); } } EXPORT_SYMBOL(netif_tx_stop_all_queues); static int netdev_do_alloc_pcpu_stats(struct net_device *dev) { void __percpu *v; /* Drivers implementing ndo_get_peer_dev must support tstat * accounting, so that skb_do_redirect() can bump the dev's * RX stats upon network namespace switch. */ if (dev->netdev_ops->ndo_get_peer_dev && dev->pcpu_stat_type != NETDEV_PCPU_STAT_TSTATS) return -EOPNOTSUPP; switch (dev->pcpu_stat_type) { case NETDEV_PCPU_STAT_NONE: return 0; case NETDEV_PCPU_STAT_LSTATS: v = dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats); break; case NETDEV_PCPU_STAT_TSTATS: v = dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); break; case NETDEV_PCPU_STAT_DSTATS: v = dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats); break; default: return -EINVAL; } return v ? 0 : -ENOMEM; } static void netdev_do_free_pcpu_stats(struct net_device *dev) { switch (dev->pcpu_stat_type) { case NETDEV_PCPU_STAT_NONE: return; case NETDEV_PCPU_STAT_LSTATS: free_percpu(dev->lstats); break; case NETDEV_PCPU_STAT_TSTATS: free_percpu(dev->tstats); break; case NETDEV_PCPU_STAT_DSTATS: free_percpu(dev->dstats); break; } } static void netdev_free_phy_link_topology(struct net_device *dev) { struct phy_link_topology *topo = dev->link_topo; if (IS_ENABLED(CONFIG_PHYLIB) && topo) { xa_destroy(&topo->phys); kfree(topo); dev->link_topo = NULL; } } /** * register_netdevice() - register a network device * @dev: device to register * * Take a prepared network device structure and make it externally accessible. * A %NETDEV_REGISTER message is sent to the netdev notifier chain. * Callers must hold the rtnl lock - you may want register_netdev() * instead of this. */ int register_netdevice(struct net_device *dev) { int ret; struct net *net = dev_net(dev); BUILD_BUG_ON(sizeof(netdev_features_t) * BITS_PER_BYTE < NETDEV_FEATURE_COUNT); BUG_ON(dev_boot_phase); ASSERT_RTNL(); might_sleep(); /* When net_device's are persistent, this will be fatal. */ BUG_ON(dev->reg_state != NETREG_UNINITIALIZED); BUG_ON(!net); ret = ethtool_check_ops(dev->ethtool_ops); if (ret) return ret; /* rss ctx ID 0 is reserved for the default context, start from 1 */ xa_init_flags(&dev->ethtool->rss_ctx, XA_FLAGS_ALLOC1); mutex_init(&dev->ethtool->rss_lock); spin_lock_init(&dev->addr_list_lock); netdev_set_addr_lockdep_class(dev); ret = dev_get_valid_name(net, dev, dev->name); if (ret < 0) goto out; ret = -ENOMEM; dev->name_node = netdev_name_node_head_alloc(dev); if (!dev->name_node) goto out; /* Init, if this function is available */ if (dev->netdev_ops->ndo_init) { ret = dev->netdev_ops->ndo_init(dev); if (ret) { if (ret > 0) ret = -EIO; goto err_free_name; } } if (((dev->hw_features | dev->features) & NETIF_F_HW_VLAN_CTAG_FILTER) && (!dev->netdev_ops->ndo_vlan_rx_add_vid || !dev->netdev_ops->ndo_vlan_rx_kill_vid)) { netdev_WARN(dev, "Buggy VLAN acceleration in driver!\n"); ret = -EINVAL; goto err_uninit; } ret = netdev_do_alloc_pcpu_stats(dev); if (ret) goto err_uninit; ret = dev_index_reserve(net, dev->ifindex); if (ret < 0) goto err_free_pcpu; dev->ifindex = ret; /* Transfer changeable features to wanted_features and enable * software offloads (GSO and GRO). */ dev->hw_features |= (NETIF_F_SOFT_FEATURES | NETIF_F_SOFT_FEATURES_OFF); dev->features |= NETIF_F_SOFT_FEATURES; if (dev->udp_tunnel_nic_info) { dev->features |= NETIF_F_RX_UDP_TUNNEL_PORT; dev->hw_features |= NETIF_F_RX_UDP_TUNNEL_PORT; } dev->wanted_features = dev->features & dev->hw_features; if (!(dev->flags & IFF_LOOPBACK)) dev->hw_features |= NETIF_F_NOCACHE_COPY; /* If IPv4 TCP segmentation offload is supported we should also * allow the device to enable segmenting the frame with the option * of ignoring a static IP ID value. This doesn't enable the * feature itself but allows the user to enable it later. */ if (dev->hw_features & NETIF_F_TSO) dev->hw_features |= NETIF_F_TSO_MANGLEID; if (dev->vlan_features & NETIF_F_TSO) dev->vlan_features |= NETIF_F_TSO_MANGLEID; if (dev->mpls_features & NETIF_F_TSO) dev->mpls_features |= NETIF_F_TSO_MANGLEID; if (dev->hw_enc_features & NETIF_F_TSO) dev->hw_enc_features |= NETIF_F_TSO_MANGLEID; /* Make NETIF_F_HIGHDMA inheritable to VLAN devices. */ dev->vlan_features |= NETIF_F_HIGHDMA; /* Make NETIF_F_SG inheritable to tunnel devices. */ dev->hw_enc_features |= NETIF_F_SG | NETIF_F_GSO_PARTIAL; /* Make NETIF_F_SG inheritable to MPLS. */ dev->mpls_features |= NETIF_F_SG; ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev); ret = notifier_to_errno(ret); if (ret) goto err_ifindex_release; ret = netdev_register_kobject(dev); WRITE_ONCE(dev->reg_state, ret ? NETREG_UNREGISTERED : NETREG_REGISTERED); if (ret) goto err_uninit_notify; __netdev_update_features(dev); /* * Default initial state at registry is that the * device is present. */ set_bit(__LINK_STATE_PRESENT, &dev->state); linkwatch_init_dev(dev); dev_init_scheduler(dev); netdev_hold(dev, &dev->dev_registered_tracker, GFP_KERNEL); list_netdevice(dev); add_device_randomness(dev->dev_addr, dev->addr_len); /* If the device has permanent device address, driver should * set dev_addr and also addr_assign_type should be set to * NET_ADDR_PERM (default value). */ if (dev->addr_assign_type == NET_ADDR_PERM) memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len); /* Notify protocols, that a new device appeared. */ ret = call_netdevice_notifiers(NETDEV_REGISTER, dev); ret = notifier_to_errno(ret); if (ret) { /* Expect explicit free_netdev() on failure */ dev->needs_free_netdev = false; unregister_netdevice_queue(dev, NULL); goto out; } /* * Prevent userspace races by waiting until the network * device is fully setup before sending notifications. */ if (!dev->rtnl_link_ops || dev->rtnl_link_state == RTNL_LINK_INITIALIZED) rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL, 0, NULL); out: return ret; err_uninit_notify: call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev); err_ifindex_release: dev_index_release(net, dev->ifindex); err_free_pcpu: netdev_do_free_pcpu_stats(dev); err_uninit: if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); if (dev->priv_destructor) dev->priv_destructor(dev); err_free_name: netdev_name_node_free(dev->name_node); goto out; } EXPORT_SYMBOL(register_netdevice); /* Initialize the core of a dummy net device. * This is useful if you are calling this function after alloc_netdev(), * since it does not memset the net_device fields. */ static void init_dummy_netdev_core(struct net_device *dev) { /* make sure we BUG if trying to hit standard * register/unregister code path */ dev->reg_state = NETREG_DUMMY; /* NAPI wants this */ INIT_LIST_HEAD(&dev->napi_list); /* a dummy interface is started by default */ set_bit(__LINK_STATE_PRESENT, &dev->state); set_bit(__LINK_STATE_START, &dev->state); /* napi_busy_loop stats accounting wants this */ dev_net_set(dev, &init_net); /* Note : We dont allocate pcpu_refcnt for dummy devices, * because users of this 'device' dont need to change * its refcount. */ } /** * init_dummy_netdev - init a dummy network device for NAPI * @dev: device to init * * This takes a network device structure and initializes the minimum * amount of fields so it can be used to schedule NAPI polls without * registering a full blown interface. This is to be used by drivers * that need to tie several hardware interfaces to a single NAPI * poll scheduler due to HW limitations. */ void init_dummy_netdev(struct net_device *dev) { /* Clear everything. Note we don't initialize spinlocks * as they aren't supposed to be taken by any of the * NAPI code and this dummy netdev is supposed to be * only ever used for NAPI polls */ memset(dev, 0, sizeof(struct net_device)); init_dummy_netdev_core(dev); } EXPORT_SYMBOL_GPL(init_dummy_netdev); /** * register_netdev - register a network device * @dev: device to register * * Take a completed network device structure and add it to the kernel * interfaces. A %NETDEV_REGISTER message is sent to the netdev notifier * chain. 0 is returned on success. A negative errno code is returned * on a failure to set up the device, or if the name is a duplicate. * * This is a wrapper around register_netdevice that takes the rtnl semaphore * and expands the device name if you passed a format string to * alloc_netdev. */ int register_netdev(struct net_device *dev) { int err; if (rtnl_lock_killable()) return -EINTR; err = register_netdevice(dev); rtnl_unlock(); return err; } EXPORT_SYMBOL(register_netdev); int netdev_refcnt_read(const struct net_device *dev) { #ifdef CONFIG_PCPU_DEV_REFCNT int i, refcnt = 0; for_each_possible_cpu(i) refcnt += *per_cpu_ptr(dev->pcpu_refcnt, i); return refcnt; #else return refcount_read(&dev->dev_refcnt); #endif } EXPORT_SYMBOL(netdev_refcnt_read); int netdev_unregister_timeout_secs __read_mostly = 10; #define WAIT_REFS_MIN_MSECS 1 #define WAIT_REFS_MAX_MSECS 250 /** * netdev_wait_allrefs_any - wait until all references are gone. * @list: list of net_devices to wait on * * This is called when unregistering network devices. * * Any protocol or device that holds a reference should register * for netdevice notification, and cleanup and put back the * reference if they receive an UNREGISTER event. * We can get stuck here if buggy protocols don't correctly * call dev_put. */ static struct net_device *netdev_wait_allrefs_any(struct list_head *list) { unsigned long rebroadcast_time, warning_time; struct net_device *dev; int wait = 0; rebroadcast_time = warning_time = jiffies; list_for_each_entry(dev, list, todo_list) if (netdev_refcnt_read(dev) == 1) return dev; while (true) { if (time_after(jiffies, rebroadcast_time + 1 * HZ)) { rtnl_lock(); /* Rebroadcast unregister notification */ list_for_each_entry(dev, list, todo_list) call_netdevice_notifiers(NETDEV_UNREGISTER, dev); __rtnl_unlock(); rcu_barrier(); rtnl_lock(); list_for_each_entry(dev, list, todo_list) if (test_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state)) { /* We must not have linkwatch events * pending on unregister. If this * happens, we simply run the queue * unscheduled, resulting in a noop * for this device. */ linkwatch_run_queue(); break; } __rtnl_unlock(); rebroadcast_time = jiffies; } rcu_barrier(); if (!wait) { wait = WAIT_REFS_MIN_MSECS; } else { msleep(wait); wait = min(wait << 1, WAIT_REFS_MAX_MSECS); } list_for_each_entry(dev, list, todo_list) if (netdev_refcnt_read(dev) == 1) return dev; if (time_after(jiffies, warning_time + READ_ONCE(netdev_unregister_timeout_secs) * HZ)) { list_for_each_entry(dev, list, todo_list) { pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n", dev->name, netdev_refcnt_read(dev)); ref_tracker_dir_print(&dev->refcnt_tracker, 10); } warning_time = jiffies; } } } /* The sequence is: * * rtnl_lock(); * ... * register_netdevice(x1); * register_netdevice(x2); * ... * unregister_netdevice(y1); * unregister_netdevice(y2); * ... * rtnl_unlock(); * free_netdev(y1); * free_netdev(y2); * * We are invoked by rtnl_unlock(). * This allows us to deal with problems: * 1) We can delete sysfs objects which invoke hotplug * without deadlocking with linkwatch via keventd. * 2) Since we run with the RTNL semaphore not held, we can sleep * safely in order to wait for the netdev refcnt to drop to zero. * * We must not return until all unregister events added during * the interval the lock was held have been completed. */ void netdev_run_todo(void) { struct net_device *dev, *tmp; struct list_head list; int cnt; #ifdef CONFIG_LOCKDEP struct list_head unlink_list; list_replace_init(&net_unlink_list, &unlink_list); while (!list_empty(&unlink_list)) { struct net_device *dev = list_first_entry(&unlink_list, struct net_device, unlink_list); list_del_init(&dev->unlink_list); dev->nested_level = dev->lower_level - 1; } #endif /* Snapshot list, allow later requests */ list_replace_init(&net_todo_list, &list); __rtnl_unlock(); /* Wait for rcu callbacks to finish before next phase */ if (!list_empty(&list)) rcu_barrier(); list_for_each_entry_safe(dev, tmp, &list, todo_list) { if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) { netdev_WARN(dev, "run_todo but not unregistering\n"); list_del(&dev->todo_list); continue; } WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERED); linkwatch_sync_dev(dev); } cnt = 0; while (!list_empty(&list)) { dev = netdev_wait_allrefs_any(&list); list_del(&dev->todo_list); /* paranoia */ BUG_ON(netdev_refcnt_read(dev) != 1); BUG_ON(!list_empty(&dev->ptype_all)); BUG_ON(!list_empty(&dev->ptype_specific)); WARN_ON(rcu_access_pointer(dev->ip_ptr)); WARN_ON(rcu_access_pointer(dev->ip6_ptr)); netdev_do_free_pcpu_stats(dev); if (dev->priv_destructor) dev->priv_destructor(dev); if (dev->needs_free_netdev) free_netdev(dev); cnt++; /* Free network device */ kobject_put(&dev->dev.kobj); } if (cnt && atomic_sub_and_test(cnt, &dev_unreg_count)) wake_up(&netdev_unregistering_wq); } /* Collate per-cpu network dstats statistics * * Read per-cpu network statistics from dev->dstats and populate the related * fields in @s. */ static void dev_fetch_dstats(struct rtnl_link_stats64 *s, const struct pcpu_dstats __percpu *dstats) { int cpu; for_each_possible_cpu(cpu) { u64 rx_packets, rx_bytes, rx_drops; u64 tx_packets, tx_bytes, tx_drops; const struct pcpu_dstats *stats; unsigned int start; stats = per_cpu_ptr(dstats, cpu); do { start = u64_stats_fetch_begin(&stats->syncp); rx_packets = u64_stats_read(&stats->rx_packets); rx_bytes = u64_stats_read(&stats->rx_bytes); rx_drops = u64_stats_read(&stats->rx_drops); tx_packets = u64_stats_read(&stats->tx_packets); tx_bytes = u64_stats_read(&stats->tx_bytes); tx_drops = u64_stats_read(&stats->tx_drops); } while (u64_stats_fetch_retry(&stats->syncp, start)); s->rx_packets += rx_packets; s->rx_bytes += rx_bytes; s->rx_dropped += rx_drops; s->tx_packets += tx_packets; s->tx_bytes += tx_bytes; s->tx_dropped += tx_drops; } } /* ndo_get_stats64 implementation for dtstats-based accounting. * * Populate @s from dev->stats and dev->dstats. This is used internally by the * core for NETDEV_PCPU_STAT_DSTAT-type stats collection. */ static void dev_get_dstats64(const struct net_device *dev, struct rtnl_link_stats64 *s) { netdev_stats_to_stats64(s, &dev->stats); dev_fetch_dstats(s, dev->dstats); } /* Convert net_device_stats to rtnl_link_stats64. rtnl_link_stats64 has * all the same fields in the same order as net_device_stats, with only * the type differing, but rtnl_link_stats64 may have additional fields * at the end for newer counters. */ void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, const struct net_device_stats *netdev_stats) { size_t i, n = sizeof(*netdev_stats) / sizeof(atomic_long_t); const atomic_long_t *src = (atomic_long_t *)netdev_stats; u64 *dst = (u64 *)stats64; BUILD_BUG_ON(n > sizeof(*stats64) / sizeof(u64)); for (i = 0; i < n; i++) dst[i] = (unsigned long)atomic_long_read(&src[i]); /* zero out counters that only exist in rtnl_link_stats64 */ memset((char *)stats64 + n * sizeof(u64), 0, sizeof(*stats64) - n * sizeof(u64)); } EXPORT_SYMBOL(netdev_stats_to_stats64); static __cold struct net_device_core_stats __percpu *netdev_core_stats_alloc( struct net_device *dev) { struct net_device_core_stats __percpu *p; p = alloc_percpu_gfp(struct net_device_core_stats, GFP_ATOMIC | __GFP_NOWARN); if (p && cmpxchg(&dev->core_stats, NULL, p)) free_percpu(p); /* This READ_ONCE() pairs with the cmpxchg() above */ return READ_ONCE(dev->core_stats); } noinline void netdev_core_stats_inc(struct net_device *dev, u32 offset) { /* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */ struct net_device_core_stats __percpu *p = READ_ONCE(dev->core_stats); unsigned long __percpu *field; if (unlikely(!p)) { p = netdev_core_stats_alloc(dev); if (!p) return; } field = (unsigned long __percpu *)((void __percpu *)p + offset); this_cpu_inc(*field); } EXPORT_SYMBOL_GPL(netdev_core_stats_inc); /** * dev_get_stats - get network device statistics * @dev: device to get statistics from * @storage: place to store stats * * Get network statistics from device. Return @storage. * The device driver may provide its own method by setting * dev->netdev_ops->get_stats64 or dev->netdev_ops->get_stats; * otherwise the internal statistics structure is used. */ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, struct rtnl_link_stats64 *storage) { const struct net_device_ops *ops = dev->netdev_ops; const struct net_device_core_stats __percpu *p; if (ops->ndo_get_stats64) { memset(storage, 0, sizeof(*storage)); ops->ndo_get_stats64(dev, storage); } else if (ops->ndo_get_stats) { netdev_stats_to_stats64(storage, ops->ndo_get_stats(dev)); } else if (dev->pcpu_stat_type == NETDEV_PCPU_STAT_TSTATS) { dev_get_tstats64(dev, storage); } else if (dev->pcpu_stat_type == NETDEV_PCPU_STAT_DSTATS) { dev_get_dstats64(dev, storage); } else { netdev_stats_to_stats64(storage, &dev->stats); } /* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */ p = READ_ONCE(dev->core_stats); if (p) { const struct net_device_core_stats *core_stats; int i; for_each_possible_cpu(i) { core_stats = per_cpu_ptr(p, i); storage->rx_dropped += READ_ONCE(core_stats->rx_dropped); storage->tx_dropped += READ_ONCE(core_stats->tx_dropped); storage->rx_nohandler += READ_ONCE(core_stats->rx_nohandler); storage->rx_otherhost_dropped += READ_ONCE(core_stats->rx_otherhost_dropped); } } return storage; } EXPORT_SYMBOL(dev_get_stats); /** * dev_fetch_sw_netstats - get per-cpu network device statistics * @s: place to store stats * @netstats: per-cpu network stats to read from * * Read per-cpu network statistics and populate the related fields in @s. */ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, const struct pcpu_sw_netstats __percpu *netstats) { int cpu; for_each_possible_cpu(cpu) { u64 rx_packets, rx_bytes, tx_packets, tx_bytes; const struct pcpu_sw_netstats *stats; unsigned int start; stats = per_cpu_ptr(netstats, cpu); do { start = u64_stats_fetch_begin(&stats->syncp); rx_packets = u64_stats_read(&stats->rx_packets); rx_bytes = u64_stats_read(&stats->rx_bytes); tx_packets = u64_stats_read(&stats->tx_packets); tx_bytes = u64_stats_read(&stats->tx_bytes); } while (u64_stats_fetch_retry(&stats->syncp, start)); s->rx_packets += rx_packets; s->rx_bytes += rx_bytes; s->tx_packets += tx_packets; s->tx_bytes += tx_bytes; } } EXPORT_SYMBOL_GPL(dev_fetch_sw_netstats); /** * dev_get_tstats64 - ndo_get_stats64 implementation * @dev: device to get statistics from * @s: place to store stats * * Populate @s from dev->stats and dev->tstats. Can be used as * ndo_get_stats64() callback. */ void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s) { netdev_stats_to_stats64(s, &dev->stats); dev_fetch_sw_netstats(s, dev->tstats); } EXPORT_SYMBOL_GPL(dev_get_tstats64); struct netdev_queue *dev_ingress_queue_create(struct net_device *dev) { struct netdev_queue *queue = dev_ingress_queue(dev); #ifdef CONFIG_NET_CLS_ACT if (queue) return queue; queue = kzalloc(sizeof(*queue), GFP_KERNEL); if (!queue) return NULL; netdev_init_one_queue(dev, queue, NULL); RCU_INIT_POINTER(queue->qdisc, &noop_qdisc); RCU_INIT_POINTER(queue->qdisc_sleeping, &noop_qdisc); rcu_assign_pointer(dev->ingress_queue, queue); #endif return queue; } static const struct ethtool_ops default_ethtool_ops; void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops) { if (dev->ethtool_ops == &default_ethtool_ops) dev->ethtool_ops = ops; } EXPORT_SYMBOL_GPL(netdev_set_default_ethtool_ops); /** * netdev_sw_irq_coalesce_default_on() - enable SW IRQ coalescing by default * @dev: netdev to enable the IRQ coalescing on * * Sets a conservative default for SW IRQ coalescing. Users can use * sysfs attributes to override the default values. */ void netdev_sw_irq_coalesce_default_on(struct net_device *dev) { WARN_ON(dev->reg_state == NETREG_REGISTERED); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { netdev_set_gro_flush_timeout(dev, 20000); netdev_set_defer_hard_irqs(dev, 1); } } EXPORT_SYMBOL_GPL(netdev_sw_irq_coalesce_default_on); /** * alloc_netdev_mqs - allocate network device * @sizeof_priv: size of private data to allocate space for * @name: device name format string * @name_assign_type: origin of device name * @setup: callback to initialize device * @txqs: the number of TX subqueues to allocate * @rxqs: the number of RX subqueues to allocate * * Allocates a struct net_device with private data area for driver use * and performs basic initialization. Also allocates subqueue structs * for each queue on the device. */ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *), unsigned int txqs, unsigned int rxqs) { struct net_device *dev; size_t napi_config_sz; unsigned int maxqs; BUG_ON(strlen(name) >= sizeof(dev->name)); if (txqs < 1) { pr_err("alloc_netdev: Unable to allocate device with zero queues\n"); return NULL; } if (rxqs < 1) { pr_err("alloc_netdev: Unable to allocate device with zero RX queues\n"); return NULL; } maxqs = max(txqs, rxqs); dev = kvzalloc(struct_size(dev, priv, sizeof_priv), GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!dev) return NULL; dev->priv_len = sizeof_priv; ref_tracker_dir_init(&dev->refcnt_tracker, 128, name); #ifdef CONFIG_PCPU_DEV_REFCNT dev->pcpu_refcnt = alloc_percpu(int); if (!dev->pcpu_refcnt) goto free_dev; __dev_hold(dev); #else refcount_set(&dev->dev_refcnt, 1); #endif if (dev_addr_init(dev)) goto free_pcpu; dev_mc_init(dev); dev_uc_init(dev); dev_net_set(dev, &init_net); dev->gso_max_size = GSO_LEGACY_MAX_SIZE; dev->xdp_zc_max_segs = 1; dev->gso_max_segs = GSO_MAX_SEGS; dev->gro_max_size = GRO_LEGACY_MAX_SIZE; dev->gso_ipv4_max_size = GSO_LEGACY_MAX_SIZE; dev->gro_ipv4_max_size = GRO_LEGACY_MAX_SIZE; dev->tso_max_size = TSO_LEGACY_MAX_SIZE; dev->tso_max_segs = TSO_MAX_SEGS; dev->upper_level = 1; dev->lower_level = 1; #ifdef CONFIG_LOCKDEP dev->nested_level = 0; INIT_LIST_HEAD(&dev->unlink_list); #endif INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); INIT_LIST_HEAD(&dev->close_list); INIT_LIST_HEAD(&dev->link_watch_list); INIT_LIST_HEAD(&dev->adj_list.upper); INIT_LIST_HEAD(&dev->adj_list.lower); INIT_LIST_HEAD(&dev->ptype_all); INIT_LIST_HEAD(&dev->ptype_specific); INIT_LIST_HEAD(&dev->net_notifier_list); #ifdef CONFIG_NET_SCHED hash_init(dev->qdisc_hash); #endif mutex_init(&dev->lock); dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; setup(dev); if (!dev->tx_queue_len) { dev->priv_flags |= IFF_NO_QUEUE; dev->tx_queue_len = DEFAULT_TX_QUEUE_LEN; } dev->num_tx_queues = txqs; dev->real_num_tx_queues = txqs; if (netif_alloc_netdev_queues(dev)) goto free_all; dev->num_rx_queues = rxqs; dev->real_num_rx_queues = rxqs; if (netif_alloc_rx_queues(dev)) goto free_all; dev->ethtool = kzalloc(sizeof(*dev->ethtool), GFP_KERNEL_ACCOUNT); if (!dev->ethtool) goto free_all; napi_config_sz = array_size(maxqs, sizeof(*dev->napi_config)); dev->napi_config = kvzalloc(napi_config_sz, GFP_KERNEL_ACCOUNT); if (!dev->napi_config) goto free_all; strscpy(dev->name, name); dev->name_assign_type = name_assign_type; dev->group = INIT_NETDEV_GROUP; if (!dev->ethtool_ops) dev->ethtool_ops = &default_ethtool_ops; nf_hook_netdev_init(dev); return dev; free_all: free_netdev(dev); return NULL; free_pcpu: #ifdef CONFIG_PCPU_DEV_REFCNT free_percpu(dev->pcpu_refcnt); free_dev: #endif kvfree(dev); return NULL; } EXPORT_SYMBOL(alloc_netdev_mqs); /** * free_netdev - free network device * @dev: device * * This function does the last stage of destroying an allocated device * interface. The reference to the device object is released. If this * is the last reference then it will be freed.Must be called in process * context. */ void free_netdev(struct net_device *dev) { struct napi_struct *p, *n; might_sleep(); /* When called immediately after register_netdevice() failed the unwind * handling may still be dismantling the device. Handle that case by * deferring the free. */ if (dev->reg_state == NETREG_UNREGISTERING) { ASSERT_RTNL(); dev->needs_free_netdev = true; return; } mutex_destroy(&dev->lock); kfree(dev->ethtool); netif_free_tx_queues(dev); netif_free_rx_queues(dev); kfree(rcu_dereference_protected(dev->ingress_queue, 1)); /* Flush device addresses */ dev_addr_flush(dev); list_for_each_entry_safe(p, n, &dev->napi_list, dev_list) netif_napi_del(p); kvfree(dev->napi_config); ref_tracker_dir_exit(&dev->refcnt_tracker); #ifdef CONFIG_PCPU_DEV_REFCNT free_percpu(dev->pcpu_refcnt); dev->pcpu_refcnt = NULL; #endif free_percpu(dev->core_stats); dev->core_stats = NULL; free_percpu(dev->xdp_bulkq); dev->xdp_bulkq = NULL; netdev_free_phy_link_topology(dev); /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED || dev->reg_state == NETREG_DUMMY) { kvfree(dev); return; } BUG_ON(dev->reg_state != NETREG_UNREGISTERED); WRITE_ONCE(dev->reg_state, NETREG_RELEASED); /* will free via device release */ put_device(&dev->dev); } EXPORT_SYMBOL(free_netdev); /** * alloc_netdev_dummy - Allocate and initialize a dummy net device. * @sizeof_priv: size of private data to allocate space for * * Return: the allocated net_device on success, NULL otherwise */ struct net_device *alloc_netdev_dummy(int sizeof_priv) { return alloc_netdev(sizeof_priv, "dummy#", NET_NAME_UNKNOWN, init_dummy_netdev_core); } EXPORT_SYMBOL_GPL(alloc_netdev_dummy); /** * synchronize_net - Synchronize with packet receive processing * * Wait for packets currently being received to be done. * Does not block later packets from starting. */ void synchronize_net(void) { might_sleep(); if (rtnl_is_locked()) synchronize_rcu_expedited(); else synchronize_rcu(); } EXPORT_SYMBOL(synchronize_net); static void netdev_rss_contexts_free(struct net_device *dev) { struct ethtool_rxfh_context *ctx; unsigned long context; mutex_lock(&dev->ethtool->rss_lock); xa_for_each(&dev->ethtool->rss_ctx, context, ctx) { struct ethtool_rxfh_param rxfh; rxfh.indir = ethtool_rxfh_context_indir(ctx); rxfh.key = ethtool_rxfh_context_key(ctx); rxfh.hfunc = ctx->hfunc; rxfh.input_xfrm = ctx->input_xfrm; rxfh.rss_context = context; rxfh.rss_delete = true; xa_erase(&dev->ethtool->rss_ctx, context); if (dev->ethtool_ops->create_rxfh_context) dev->ethtool_ops->remove_rxfh_context(dev, ctx, context, NULL); else dev->ethtool_ops->set_rxfh(dev, &rxfh, NULL); kfree(ctx); } xa_destroy(&dev->ethtool->rss_ctx); mutex_unlock(&dev->ethtool->rss_lock); } /** * unregister_netdevice_queue - remove device from the kernel * @dev: device * @head: list * * This function shuts down a device interface and removes it * from the kernel tables. * If head not NULL, device is queued to be unregistered later. * * Callers must hold the rtnl semaphore. You may want * unregister_netdev() instead of this. */ void unregister_netdevice_queue(struct net_device *dev, struct list_head *head) { ASSERT_RTNL(); if (head) { list_move_tail(&dev->unreg_list, head); } else { LIST_HEAD(single); list_add(&dev->unreg_list, &single); unregister_netdevice_many(&single); } } EXPORT_SYMBOL(unregister_netdevice_queue); void unregister_netdevice_many_notify(struct list_head *head, u32 portid, const struct nlmsghdr *nlh) { struct net_device *dev, *tmp; LIST_HEAD(close_head); int cnt = 0; BUG_ON(dev_boot_phase); ASSERT_RTNL(); if (list_empty(head)) return; list_for_each_entry_safe(dev, tmp, head, unreg_list) { /* Some devices call without registering * for initialization unwind. Remove those * devices and proceed with the remaining. */ if (dev->reg_state == NETREG_UNINITIALIZED) { pr_debug("unregister_netdevice: device %s/%p never was registered\n", dev->name, dev); WARN_ON(1); list_del(&dev->unreg_list); continue; } dev->dismantle = true; BUG_ON(dev->reg_state != NETREG_REGISTERED); } /* If device is running, close it first. */ list_for_each_entry(dev, head, unreg_list) list_add_tail(&dev->close_list, &close_head); dev_close_many(&close_head, true); list_for_each_entry(dev, head, unreg_list) { /* And unlink it from device chain. */ unlist_netdevice(dev); WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERING); } flush_all_backlogs(); synchronize_net(); list_for_each_entry(dev, head, unreg_list) { struct sk_buff *skb = NULL; /* Shutdown queueing discipline. */ dev_shutdown(dev); dev_tcx_uninstall(dev); dev_xdp_uninstall(dev); bpf_dev_bound_netdev_unregister(dev); dev_dmabuf_uninstall(dev); netdev_offload_xstats_disable_all(dev); /* Notify protocols, that we are about to destroy * this device. They should clean all the things. */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); if (!dev->rtnl_link_ops || dev->rtnl_link_state == RTNL_LINK_INITIALIZED) skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, GFP_KERNEL, NULL, 0, portid, nlh); /* * Flush the unicast and multicast chains */ dev_uc_flush(dev); dev_mc_flush(dev); netdev_name_node_alt_flush(dev); netdev_name_node_free(dev->name_node); netdev_rss_contexts_free(dev); call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev); if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); mutex_destroy(&dev->ethtool->rss_lock); net_shaper_flush_netdev(dev); if (skb) rtmsg_ifinfo_send(skb, dev, GFP_KERNEL, portid, nlh); /* Notifier chain MUST detach us all upper devices. */ WARN_ON(netdev_has_any_upper_dev(dev)); WARN_ON(netdev_has_any_lower_dev(dev)); /* Remove entries from kobject tree */ netdev_unregister_kobject(dev); #ifdef CONFIG_XPS /* Remove XPS queueing entries */ netif_reset_xps_queues_gt(dev, 0); #endif } synchronize_net(); list_for_each_entry(dev, head, unreg_list) { netdev_put(dev, &dev->dev_registered_tracker); net_set_todo(dev); cnt++; } atomic_add(cnt, &dev_unreg_count); list_del(head); } /** * unregister_netdevice_many - unregister many devices * @head: list of devices * * Note: As most callers use a stack allocated list_head, * we force a list_del() to make sure stack won't be corrupted later. */ void unregister_netdevice_many(struct list_head *head) { unregister_netdevice_many_notify(head, 0, NULL); } EXPORT_SYMBOL(unregister_netdevice_many); /** * unregister_netdev - remove device from the kernel * @dev: device * * This function shuts down a device interface and removes it * from the kernel tables. * * This is just a wrapper for unregister_netdevice that takes * the rtnl semaphore. In general you want to use this and not * unregister_netdevice. */ void unregister_netdev(struct net_device *dev) { rtnl_lock(); unregister_netdevice(dev); rtnl_unlock(); } EXPORT_SYMBOL(unregister_netdev); /** * __dev_change_net_namespace - move device to different nethost namespace * @dev: device * @net: network namespace * @pat: If not NULL name pattern to try if the current device name * is already taken in the destination network namespace. * @new_ifindex: If not zero, specifies device index in the target * namespace. * * This function shuts down a device interface and moves it * to a new network namespace. On success 0 is returned, on * a failure a netagive errno code is returned. * * Callers must hold the rtnl semaphore. */ int __dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat, int new_ifindex) { struct netdev_name_node *name_node; struct net *net_old = dev_net(dev); char new_name[IFNAMSIZ] = {}; int err, new_nsid; ASSERT_RTNL(); /* Don't allow namespace local devices to be moved. */ err = -EINVAL; if (dev->netns_local) goto out; /* Ensure the device has been registered */ if (dev->reg_state != NETREG_REGISTERED) goto out; /* Get out if there is nothing todo */ err = 0; if (net_eq(net_old, net)) goto out; /* Pick the destination device name, and ensure * we can use it in the destination network namespace. */ err = -EEXIST; if (netdev_name_in_use(net, dev->name)) { /* We get here if we can't use the current device name */ if (!pat) goto out; err = dev_prep_valid_name(net, dev, pat, new_name, EEXIST); if (err < 0) goto out; } /* Check that none of the altnames conflicts. */ err = -EEXIST; netdev_for_each_altname(dev, name_node) if (netdev_name_in_use(net, name_node->name)) goto out; /* Check that new_ifindex isn't used yet. */ if (new_ifindex) { err = dev_index_reserve(net, new_ifindex); if (err < 0) goto out; } else { /* If there is an ifindex conflict assign a new one */ err = dev_index_reserve(net, dev->ifindex); if (err == -EBUSY) err = dev_index_reserve(net, 0); if (err < 0) goto out; new_ifindex = err; } /* * And now a mini version of register_netdevice unregister_netdevice. */ /* If device is running close it first. */ dev_close(dev); /* And unlink it from device chain */ unlist_netdevice(dev); synchronize_net(); /* Shutdown queueing discipline. */ dev_shutdown(dev); /* Notify protocols, that we are about to destroy * this device. They should clean all the things. * * Note that dev->reg_state stays at NETREG_REGISTERED. * This is wanted because this way 8021q and macvlan know * the device is just moving and can keep their slaves up. */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); rcu_barrier(); new_nsid = peernet2id_alloc(dev_net(dev), net, GFP_KERNEL); rtmsg_ifinfo_newnet(RTM_DELLINK, dev, ~0U, GFP_KERNEL, &new_nsid, new_ifindex); /* * Flush the unicast and multicast chains */ dev_uc_flush(dev); dev_mc_flush(dev); /* Send a netdev-removed uevent to the old namespace */ kobject_uevent(&dev->dev.kobj, KOBJ_REMOVE); netdev_adjacent_del_links(dev); /* Move per-net netdevice notifiers that are following the netdevice */ move_netdevice_notifiers_dev_net(dev, net); /* Actually switch the network namespace */ dev_net_set(dev, net); dev->ifindex = new_ifindex; if (new_name[0]) { /* Rename the netdev to prepared name */ write_seqlock_bh(&netdev_rename_lock); strscpy(dev->name, new_name, IFNAMSIZ); write_sequnlock_bh(&netdev_rename_lock); } /* Fixup kobjects */ dev_set_uevent_suppress(&dev->dev, 1); err = device_rename(&dev->dev, dev->name); dev_set_uevent_suppress(&dev->dev, 0); WARN_ON(err); /* Send a netdev-add uevent to the new namespace */ kobject_uevent(&dev->dev.kobj, KOBJ_ADD); netdev_adjacent_add_links(dev); /* Adapt owner in case owning user namespace of target network * namespace is different from the original one. */ err = netdev_change_owner(dev, net_old, net); WARN_ON(err); /* Add the device back in the hashes */ list_netdevice(dev); /* Notify protocols, that a new device appeared. */ call_netdevice_notifiers(NETDEV_REGISTER, dev); /* * Prevent userspace races by waiting until the network * device is fully setup before sending notifications. */ rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL, 0, NULL); synchronize_net(); err = 0; out: return err; } EXPORT_SYMBOL_GPL(__dev_change_net_namespace); static int dev_cpu_dead(unsigned int oldcpu) { struct sk_buff **list_skb; struct sk_buff *skb; unsigned int cpu; struct softnet_data *sd, *oldsd, *remsd = NULL; local_irq_disable(); cpu = smp_processor_id(); sd = &per_cpu(softnet_data, cpu); oldsd = &per_cpu(softnet_data, oldcpu); /* Find end of our completion_queue. */ list_skb = &sd->completion_queue; while (*list_skb) list_skb = &(*list_skb)->next; /* Append completion queue from offline CPU. */ *list_skb = oldsd->completion_queue; oldsd->completion_queue = NULL; /* Append output queue from offline CPU. */ if (oldsd->output_queue) { *sd->output_queue_tailp = oldsd->output_queue; sd->output_queue_tailp = oldsd->output_queue_tailp; oldsd->output_queue = NULL; oldsd->output_queue_tailp = &oldsd->output_queue; } /* Append NAPI poll list from offline CPU, with one exception : * process_backlog() must be called by cpu owning percpu backlog. * We properly handle process_queue & input_pkt_queue later. */ while (!list_empty(&oldsd->poll_list)) { struct napi_struct *napi = list_first_entry(&oldsd->poll_list, struct napi_struct, poll_list); list_del_init(&napi->poll_list); if (napi->poll == process_backlog) napi->state &= NAPIF_STATE_THREADED; else ____napi_schedule(sd, napi); } raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_enable(); if (!use_backlog_threads()) { #ifdef CONFIG_RPS remsd = oldsd->rps_ipi_list; oldsd->rps_ipi_list = NULL; #endif /* send out pending IPI's on offline CPU */ net_rps_send_ipi(remsd); } /* Process offline CPU's input_pkt_queue */ while ((skb = __skb_dequeue(&oldsd->process_queue))) { netif_rx(skb); rps_input_queue_head_incr(oldsd); } while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) { netif_rx(skb); rps_input_queue_head_incr(oldsd); } return 0; } /** * netdev_increment_features - increment feature set by one * @all: current feature set * @one: new feature set * @mask: mask feature set * * Computes a new feature set after adding a device with feature set * @one to the master device with current feature set @all. Will not * enable anything that is off in @mask. Returns the new feature set. */ netdev_features_t netdev_increment_features(netdev_features_t all, netdev_features_t one, netdev_features_t mask) { if (mask & NETIF_F_HW_CSUM) mask |= NETIF_F_CSUM_MASK; mask |= NETIF_F_VLAN_CHALLENGED; all |= one & (NETIF_F_ONE_FOR_ALL | NETIF_F_CSUM_MASK) & mask; all &= one | ~NETIF_F_ALL_FOR_ALL; /* If one device supports hw checksumming, set for all. */ if (all & NETIF_F_HW_CSUM) all &= ~(NETIF_F_CSUM_MASK & ~NETIF_F_HW_CSUM); return all; } EXPORT_SYMBOL(netdev_increment_features); static struct hlist_head * __net_init netdev_create_hash(void) { int i; struct hlist_head *hash; hash = kmalloc_array(NETDEV_HASHENTRIES, sizeof(*hash), GFP_KERNEL); if (hash != NULL) for (i = 0; i < NETDEV_HASHENTRIES; i++) INIT_HLIST_HEAD(&hash[i]); return hash; } /* Initialize per network namespace state */ static int __net_init netdev_init(struct net *net) { BUILD_BUG_ON(GRO_HASH_BUCKETS > 8 * sizeof_field(struct napi_struct, gro_bitmask)); INIT_LIST_HEAD(&net->dev_base_head); net->dev_name_head = netdev_create_hash(); if (net->dev_name_head == NULL) goto err_name; net->dev_index_head = netdev_create_hash(); if (net->dev_index_head == NULL) goto err_idx; xa_init_flags(&net->dev_by_index, XA_FLAGS_ALLOC1); RAW_INIT_NOTIFIER_HEAD(&net->netdev_chain); return 0; err_idx: kfree(net->dev_name_head); err_name: return -ENOMEM; } /** * netdev_drivername - network driver for the device * @dev: network device * * Determine network driver for device. */ const char *netdev_drivername(const struct net_device *dev) { const struct device_driver *driver; const struct device *parent; const char *empty = ""; parent = dev->dev.parent; if (!parent) return empty; driver = parent->driver; if (driver && driver->name) return driver->name; return empty; } static void __netdev_printk(const char *level, const struct net_device *dev, struct va_format *vaf) { if (dev && dev->dev.parent) { dev_printk_emit(level[1] - '0', dev->dev.parent, "%s %s %s%s: %pV", dev_driver_string(dev->dev.parent), dev_name(dev->dev.parent), netdev_name(dev), netdev_reg_state(dev), vaf); } else if (dev) { printk("%s%s%s: %pV", level, netdev_name(dev), netdev_reg_state(dev), vaf); } else { printk("%s(NULL net_device): %pV", level, vaf); } } void netdev_printk(const char *level, const struct net_device *dev, const char *format, ...) { struct va_format vaf; va_list args; va_start(args, format); vaf.fmt = format; vaf.va = &args; __netdev_printk(level, dev, &vaf); va_end(args); } EXPORT_SYMBOL(netdev_printk); #define define_netdev_printk_level(func, level) \ void func(const struct net_device *dev, const char *fmt, ...) \ { \ struct va_format vaf; \ va_list args; \ \ va_start(args, fmt); \ \ vaf.fmt = fmt; \ vaf.va = &args; \ \ __netdev_printk(level, dev, &vaf); \ \ va_end(args); \ } \ EXPORT_SYMBOL(func); define_netdev_printk_level(netdev_emerg, KERN_EMERG); define_netdev_printk_level(netdev_alert, KERN_ALERT); define_netdev_printk_level(netdev_crit, KERN_CRIT); define_netdev_printk_level(netdev_err, KERN_ERR); define_netdev_printk_level(netdev_warn, KERN_WARNING); define_netdev_printk_level(netdev_notice, KERN_NOTICE); define_netdev_printk_level(netdev_info, KERN_INFO); static void __net_exit netdev_exit(struct net *net) { kfree(net->dev_name_head); kfree(net->dev_index_head); xa_destroy(&net->dev_by_index); if (net != &init_net) WARN_ON_ONCE(!list_empty(&net->dev_base_head)); } static struct pernet_operations __net_initdata netdev_net_ops = { .init = netdev_init, .exit = netdev_exit, }; static void __net_exit default_device_exit_net(struct net *net) { struct netdev_name_node *name_node, *tmp; struct net_device *dev, *aux; /* * Push all migratable network devices back to the * initial network namespace */ ASSERT_RTNL(); for_each_netdev_safe(net, dev, aux) { int err; char fb_name[IFNAMSIZ]; /* Ignore unmoveable devices (i.e. loopback) */ if (dev->netns_local) continue; /* Leave virtual devices for the generic cleanup */ if (dev->rtnl_link_ops && !dev->rtnl_link_ops->netns_refund) continue; /* Push remaining network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); if (netdev_name_in_use(&init_net, fb_name)) snprintf(fb_name, IFNAMSIZ, "dev%%d"); netdev_for_each_altname_safe(dev, name_node, tmp) if (netdev_name_in_use(&init_net, name_node->name)) __netdev_name_node_alt_destroy(name_node); err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { pr_emerg("%s: failed to move %s to init_net: %d\n", __func__, dev->name, err); BUG(); } } } static void __net_exit default_device_exit_batch(struct list_head *net_list) { /* At exit all network devices most be removed from a network * namespace. Do this in the reverse order of registration. * Do this across as many network namespaces as possible to * improve batching efficiency. */ struct net_device *dev; struct net *net; LIST_HEAD(dev_kill_list); rtnl_lock(); list_for_each_entry(net, net_list, exit_list) { default_device_exit_net(net); cond_resched(); } list_for_each_entry(net, net_list, exit_list) { for_each_netdev_reverse(net, dev) { if (dev->rtnl_link_ops && dev->rtnl_link_ops->dellink) dev->rtnl_link_ops->dellink(dev, &dev_kill_list); else unregister_netdevice_queue(dev, &dev_kill_list); } } unregister_netdevice_many(&dev_kill_list); rtnl_unlock(); } static struct pernet_operations __net_initdata default_device_ops = { .exit_batch = default_device_exit_batch, }; static void __init net_dev_struct_check(void) { /* TX read-mostly hotpath */ CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, priv_flags_fast); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, netdev_ops); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, header_ops); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, _tx); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, real_num_tx_queues); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_max_size); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_ipv4_max_size); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_max_segs); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_partial_features); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, num_tc); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, mtu); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, needed_headroom); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, tc_to_txq); #ifdef CONFIG_XPS CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, xps_maps); #endif #ifdef CONFIG_NETFILTER_EGRESS CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, nf_hooks_egress); #endif #ifdef CONFIG_NET_XGRESS CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, tcx_egress); #endif CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_tx, 160); /* TXRX read-mostly hotpath */ CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, lstats); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, state); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, flags); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, hard_header_len); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, features); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, ip6_ptr); CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 46); /* RX read-mostly hotpath */ CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ptype_specific); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ifindex); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, real_num_rx_queues); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, _rx); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_max_size); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_ipv4_max_size); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, rx_handler); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, rx_handler_data); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, nd_net); #ifdef CONFIG_NETPOLL CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, npinfo); #endif #ifdef CONFIG_NET_XGRESS CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, tcx_ingress); #endif CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_rx, 92); } /* * Initialize the DEV module. At boot time this walks the device list and * unhooks any devices that fail to initialise (normally hardware not * present) and leaves us with a valid list of present and active devices. * */ /* We allocate 256 pages for each CPU if PAGE_SHIFT is 12 */ #define SYSTEM_PERCPU_PAGE_POOL_SIZE ((1 << 20) / PAGE_SIZE) static int net_page_pool_create(int cpuid) { #if IS_ENABLED(CONFIG_PAGE_POOL) struct page_pool_params page_pool_params = { .pool_size = SYSTEM_PERCPU_PAGE_POOL_SIZE, .flags = PP_FLAG_SYSTEM_POOL, .nid = cpu_to_mem(cpuid), }; struct page_pool *pp_ptr; pp_ptr = page_pool_create_percpu(&page_pool_params, cpuid); if (IS_ERR(pp_ptr)) return -ENOMEM; per_cpu(system_page_pool, cpuid) = pp_ptr; #endif return 0; } static int backlog_napi_should_run(unsigned int cpu) { struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu); struct napi_struct *napi = &sd->backlog; return test_bit(NAPI_STATE_SCHED_THREADED, &napi->state); } static void run_backlog_napi(unsigned int cpu) { struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu); napi_threaded_poll_loop(&sd->backlog); } static void backlog_napi_setup(unsigned int cpu) { struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu); struct napi_struct *napi = &sd->backlog; napi->thread = this_cpu_read(backlog_napi); set_bit(NAPI_STATE_THREADED, &napi->state); } static struct smp_hotplug_thread backlog_threads = { .store = &backlog_napi, .thread_should_run = backlog_napi_should_run, .thread_fn = run_backlog_napi, .thread_comm = "backlog_napi/%u", .setup = backlog_napi_setup, }; /* * This is called single threaded during boot, so no need * to take the rtnl semaphore. */ static int __init net_dev_init(void) { int i, rc = -ENOMEM; BUG_ON(!dev_boot_phase); net_dev_struct_check(); if (dev_proc_init()) goto out; if (netdev_kobject_init()) goto out; for (i = 0; i < PTYPE_HASH_SIZE; i++) INIT_LIST_HEAD(&ptype_base[i]); if (register_pernet_subsys(&netdev_net_ops)) goto out; /* * Initialise the packet receive queues. */ for_each_possible_cpu(i) { struct work_struct *flush = per_cpu_ptr(&flush_works, i); struct softnet_data *sd = &per_cpu(softnet_data, i); INIT_WORK(flush, flush_backlog); skb_queue_head_init(&sd->input_pkt_queue); skb_queue_head_init(&sd->process_queue); #ifdef CONFIG_XFRM_OFFLOAD skb_queue_head_init(&sd->xfrm_backlog); #endif INIT_LIST_HEAD(&sd->poll_list); sd->output_queue_tailp = &sd->output_queue; #ifdef CONFIG_RPS INIT_CSD(&sd->csd, rps_trigger_softirq, sd); sd->cpu = i; #endif INIT_CSD(&sd->defer_csd, trigger_rx_softirq, sd); spin_lock_init(&sd->defer_lock); init_gro_hash(&sd->backlog); sd->backlog.poll = process_backlog; sd->backlog.weight = weight_p; INIT_LIST_HEAD(&sd->backlog.poll_list); if (net_page_pool_create(i)) goto out; } if (use_backlog_threads()) smpboot_register_percpu_thread(&backlog_threads); dev_boot_phase = 0; /* The loopback device is special if any other network devices * is present in a network namespace the loopback device must * be present. Since we now dynamically allocate and free the * loopback device ensure this invariant is maintained by * keeping the loopback device as the first device on the * list of network devices. Ensuring the loopback devices * is the first device that appears and the last network device * that disappears. */ if (register_pernet_device(&loopback_net_ops)) goto out; if (register_pernet_device(&default_device_ops)) goto out; open_softirq(NET_TX_SOFTIRQ, net_tx_action); open_softirq(NET_RX_SOFTIRQ, net_rx_action); rc = cpuhp_setup_state_nocalls(CPUHP_NET_DEV_DEAD, "net/dev:dead", NULL, dev_cpu_dead); WARN_ON(rc < 0); rc = 0; /* avoid static key IPIs to isolated CPUs */ if (housekeeping_enabled(HK_TYPE_MISC)) net_enable_timestamp(); out: if (rc < 0) { for_each_possible_cpu(i) { struct page_pool *pp_ptr; pp_ptr = per_cpu(system_page_pool, i); if (!pp_ptr) continue; page_pool_destroy(pp_ptr); per_cpu(system_page_pool, i) = NULL; } } return rc; } subsys_initcall(net_dev_init); |
| 125 125 125 124 125 125 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ /* * fsnotify inode mark locking/lifetime/and refcnting * * REFCNT: * The group->recnt and mark->refcnt tell how many "things" in the kernel * currently are referencing the objects. Both kind of objects typically will * live inside the kernel with a refcnt of 2, one for its creation and one for * the reference a group and a mark hold to each other. * If you are holding the appropriate locks, you can take a reference and the * object itself is guaranteed to survive until the reference is dropped. * * LOCKING: * There are 3 locks involved with fsnotify inode marks and they MUST be taken * in order as follows: * * group->mark_mutex * mark->lock * mark->connector->lock * * group->mark_mutex protects the marks_list anchored inside a given group and * each mark is hooked via the g_list. It also protects the groups private * data (i.e group limits). * mark->lock protects the marks attributes like its masks and flags. * Furthermore it protects the access to a reference of the group that the mark * is assigned to as well as the access to a reference of the inode/vfsmount * that is being watched by the mark. * * mark->connector->lock protects the list of marks anchored inside an * inode / vfsmount and each mark is hooked via the i_list. * * A list of notification marks relating to inode / mnt is contained in * fsnotify_mark_connector. That structure is alive as long as there are any * marks in the list and is also protected by fsnotify_mark_srcu. A mark gets * detached from fsnotify_mark_connector when last reference to the mark is * dropped. Thus having mark reference is enough to protect mark->connector * pointer and to make sure fsnotify_mark_connector cannot disappear. Also * because we remove mark from g_list before dropping mark reference associated * with that, any mark found through g_list is guaranteed to have * mark->connector set until we drop group->mark_mutex. * * LIFETIME: * Inode marks survive between when they are added to an inode and when their * refcnt==0. Marks are also protected by fsnotify_mark_srcu. * * The inode mark can be cleared for a number of different reasons including: * - The inode is unlinked for the last time. (fsnotify_inode_remove) * - The inode is being evicted from cache. (fsnotify_inode_delete) * - The fs the inode is on is unmounted. (fsnotify_inode_delete/fsnotify_unmount_inodes) * - Something explicitly requests that it be removed. (fsnotify_destroy_mark) * - The fsnotify_group associated with the mark is going away and all such marks * need to be cleaned up. (fsnotify_clear_marks_by_group) * * This has the very interesting property of being able to run concurrently with * any (or all) other directions. */ #include <linux/fs.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kthread.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/srcu.h> #include <linux/ratelimit.h> #include <linux/atomic.h> #include <linux/fsnotify_backend.h> #include "fsnotify.h" #define FSNOTIFY_REAPER_DELAY (1) /* 1 jiffy */ struct srcu_struct fsnotify_mark_srcu; struct kmem_cache *fsnotify_mark_connector_cachep; static DEFINE_SPINLOCK(destroy_lock); static LIST_HEAD(destroy_list); static struct fsnotify_mark_connector *connector_destroy_list; static void fsnotify_mark_destroy_workfn(struct work_struct *work); static DECLARE_DELAYED_WORK(reaper_work, fsnotify_mark_destroy_workfn); static void fsnotify_connector_destroy_workfn(struct work_struct *work); static DECLARE_WORK(connector_reaper_work, fsnotify_connector_destroy_workfn); void fsnotify_get_mark(struct fsnotify_mark *mark) { WARN_ON_ONCE(!refcount_read(&mark->refcnt)); refcount_inc(&mark->refcnt); } static fsnotify_connp_t *fsnotify_object_connp(void *obj, enum fsnotify_obj_type obj_type) { switch (obj_type) { case FSNOTIFY_OBJ_TYPE_INODE: return &((struct inode *)obj)->i_fsnotify_marks; case FSNOTIFY_OBJ_TYPE_VFSMOUNT: return &real_mount(obj)->mnt_fsnotify_marks; case FSNOTIFY_OBJ_TYPE_SB: return fsnotify_sb_marks(obj); default: return NULL; } } static __u32 *fsnotify_conn_mask_p(struct fsnotify_mark_connector *conn) { if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) return &fsnotify_conn_inode(conn)->i_fsnotify_mask; else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) return &fsnotify_conn_mount(conn)->mnt_fsnotify_mask; else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) return &fsnotify_conn_sb(conn)->s_fsnotify_mask; return NULL; } __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn) { if (WARN_ON(!fsnotify_valid_obj_type(conn->type))) return 0; return READ_ONCE(*fsnotify_conn_mask_p(conn)); } static void fsnotify_get_sb_watched_objects(struct super_block *sb) { atomic_long_inc(fsnotify_sb_watched_objects(sb)); } static void fsnotify_put_sb_watched_objects(struct super_block *sb) { atomic_long_t *watched_objects = fsnotify_sb_watched_objects(sb); /* the superblock can go away after this decrement */ if (atomic_long_dec_and_test(watched_objects)) wake_up_var(watched_objects); } static void fsnotify_get_inode_ref(struct inode *inode) { ihold(inode); fsnotify_get_sb_watched_objects(inode->i_sb); } static void fsnotify_put_inode_ref(struct inode *inode) { /* read ->i_sb before the inode can go away */ struct super_block *sb = inode->i_sb; iput(inode); fsnotify_put_sb_watched_objects(sb); } /* * Grab or drop watched objects reference depending on whether the connector * is attached and has any marks attached. */ static void fsnotify_update_sb_watchers(struct super_block *sb, struct fsnotify_mark_connector *conn) { struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb); bool is_watched = conn->flags & FSNOTIFY_CONN_FLAG_IS_WATCHED; struct fsnotify_mark *first_mark = NULL; unsigned int highest_prio = 0; if (conn->obj) first_mark = hlist_entry_safe(conn->list.first, struct fsnotify_mark, obj_list); if (first_mark) highest_prio = first_mark->group->priority; if (WARN_ON(highest_prio >= __FSNOTIFY_PRIO_NUM)) highest_prio = 0; /* * If the highest priority of group watching this object is prio, * then watched object has a reference on counters [0..prio]. * Update priority >= 1 watched objects counters. */ for (unsigned int p = conn->prio + 1; p <= highest_prio; p++) atomic_long_inc(&sbinfo->watched_objects[p]); for (unsigned int p = conn->prio; p > highest_prio; p--) atomic_long_dec(&sbinfo->watched_objects[p]); conn->prio = highest_prio; /* Update priority >= 0 (a.k.a total) watched objects counter */ BUILD_BUG_ON(FSNOTIFY_PRIO_NORMAL != 0); if (first_mark && !is_watched) { conn->flags |= FSNOTIFY_CONN_FLAG_IS_WATCHED; fsnotify_get_sb_watched_objects(sb); } else if (!first_mark && is_watched) { conn->flags &= ~FSNOTIFY_CONN_FLAG_IS_WATCHED; fsnotify_put_sb_watched_objects(sb); } } /* * Grab or drop inode reference for the connector if needed. * * When it's time to drop the reference, we only clear the HAS_IREF flag and * return the inode object. fsnotify_drop_object() will be resonsible for doing * iput() outside of spinlocks. This happens when last mark that wanted iref is * detached. */ static struct inode *fsnotify_update_iref(struct fsnotify_mark_connector *conn, bool want_iref) { bool has_iref = conn->flags & FSNOTIFY_CONN_FLAG_HAS_IREF; struct inode *inode = NULL; if (conn->type != FSNOTIFY_OBJ_TYPE_INODE || want_iref == has_iref) return NULL; if (want_iref) { /* Pin inode if any mark wants inode refcount held */ fsnotify_get_inode_ref(fsnotify_conn_inode(conn)); conn->flags |= FSNOTIFY_CONN_FLAG_HAS_IREF; } else { /* Unpin inode after detach of last mark that wanted iref */ inode = fsnotify_conn_inode(conn); conn->flags &= ~FSNOTIFY_CONN_FLAG_HAS_IREF; } return inode; } static void *__fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) { u32 new_mask = 0; bool want_iref = false; struct fsnotify_mark *mark; assert_spin_locked(&conn->lock); /* We can get detached connector here when inode is getting unlinked. */ if (!fsnotify_valid_obj_type(conn->type)) return NULL; hlist_for_each_entry(mark, &conn->list, obj_list) { if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) continue; new_mask |= fsnotify_calc_mask(mark); if (conn->type == FSNOTIFY_OBJ_TYPE_INODE && !(mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF)) want_iref = true; } /* * We use WRITE_ONCE() to prevent silly compiler optimizations from * confusing readers not holding conn->lock with partial updates. */ WRITE_ONCE(*fsnotify_conn_mask_p(conn), new_mask); return fsnotify_update_iref(conn, want_iref); } static bool fsnotify_conn_watches_children( struct fsnotify_mark_connector *conn) { if (conn->type != FSNOTIFY_OBJ_TYPE_INODE) return false; return fsnotify_inode_watches_children(fsnotify_conn_inode(conn)); } static void fsnotify_conn_set_children_dentry_flags( struct fsnotify_mark_connector *conn) { if (conn->type != FSNOTIFY_OBJ_TYPE_INODE) return; fsnotify_set_children_dentry_flags(fsnotify_conn_inode(conn)); } /* * Calculate mask of events for a list of marks. The caller must make sure * connector and connector->obj cannot disappear under us. Callers achieve * this by holding a mark->lock or mark->group->mark_mutex for a mark on this * list. */ void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) { bool update_children; if (!conn) return; spin_lock(&conn->lock); update_children = !fsnotify_conn_watches_children(conn); __fsnotify_recalc_mask(conn); update_children &= fsnotify_conn_watches_children(conn); spin_unlock(&conn->lock); /* * Set children's PARENT_WATCHED flags only if parent started watching. * When parent stops watching, we clear false positive PARENT_WATCHED * flags lazily in __fsnotify_parent(). */ if (update_children) fsnotify_conn_set_children_dentry_flags(conn); } /* Free all connectors queued for freeing once SRCU period ends */ static void fsnotify_connector_destroy_workfn(struct work_struct *work) { struct fsnotify_mark_connector *conn, *free; spin_lock(&destroy_lock); conn = connector_destroy_list; connector_destroy_list = NULL; spin_unlock(&destroy_lock); synchronize_srcu(&fsnotify_mark_srcu); while (conn) { free = conn; conn = conn->destroy_next; kmem_cache_free(fsnotify_mark_connector_cachep, free); } } static void *fsnotify_detach_connector_from_object( struct fsnotify_mark_connector *conn, unsigned int *type) { fsnotify_connp_t *connp = fsnotify_object_connp(conn->obj, conn->type); struct super_block *sb = fsnotify_connector_sb(conn); struct inode *inode = NULL; *type = conn->type; if (conn->type == FSNOTIFY_OBJ_TYPE_DETACHED) return NULL; if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) { inode = fsnotify_conn_inode(conn); inode->i_fsnotify_mask = 0; /* Unpin inode when detaching from connector */ if (!(conn->flags & FSNOTIFY_CONN_FLAG_HAS_IREF)) inode = NULL; } else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) { fsnotify_conn_mount(conn)->mnt_fsnotify_mask = 0; } else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) { fsnotify_conn_sb(conn)->s_fsnotify_mask = 0; } rcu_assign_pointer(*connp, NULL); conn->obj = NULL; conn->type = FSNOTIFY_OBJ_TYPE_DETACHED; fsnotify_update_sb_watchers(sb, conn); return inode; } static void fsnotify_final_mark_destroy(struct fsnotify_mark *mark) { struct fsnotify_group *group = mark->group; if (WARN_ON_ONCE(!group)) return; group->ops->free_mark(mark); fsnotify_put_group(group); } /* Drop object reference originally held by a connector */ static void fsnotify_drop_object(unsigned int type, void *objp) { if (!objp) return; /* Currently only inode references are passed to be dropped */ if (WARN_ON_ONCE(type != FSNOTIFY_OBJ_TYPE_INODE)) return; fsnotify_put_inode_ref(objp); } void fsnotify_put_mark(struct fsnotify_mark *mark) { struct fsnotify_mark_connector *conn = READ_ONCE(mark->connector); void *objp = NULL; unsigned int type = FSNOTIFY_OBJ_TYPE_DETACHED; bool free_conn = false; /* Catch marks that were actually never attached to object */ if (!conn) { if (refcount_dec_and_test(&mark->refcnt)) fsnotify_final_mark_destroy(mark); return; } /* * We have to be careful so that traversals of obj_list under lock can * safely grab mark reference. */ if (!refcount_dec_and_lock(&mark->refcnt, &conn->lock)) return; hlist_del_init_rcu(&mark->obj_list); if (hlist_empty(&conn->list)) { objp = fsnotify_detach_connector_from_object(conn, &type); free_conn = true; } else { struct super_block *sb = fsnotify_connector_sb(conn); /* Update watched objects after detaching mark */ if (sb) fsnotify_update_sb_watchers(sb, conn); objp = __fsnotify_recalc_mask(conn); type = conn->type; } WRITE_ONCE(mark->connector, NULL); spin_unlock(&conn->lock); fsnotify_drop_object(type, objp); if (free_conn) { spin_lock(&destroy_lock); conn->destroy_next = connector_destroy_list; connector_destroy_list = conn; spin_unlock(&destroy_lock); queue_work(system_unbound_wq, &connector_reaper_work); } /* * Note that we didn't update flags telling whether inode cares about * what's happening with children. We update these flags from * __fsnotify_parent() lazily when next event happens on one of our * children. */ spin_lock(&destroy_lock); list_add(&mark->g_list, &destroy_list); spin_unlock(&destroy_lock); queue_delayed_work(system_unbound_wq, &reaper_work, FSNOTIFY_REAPER_DELAY); } EXPORT_SYMBOL_GPL(fsnotify_put_mark); /* * Get mark reference when we found the mark via lockless traversal of object * list. Mark can be already removed from the list by now and on its way to be * destroyed once SRCU period ends. * * Also pin the group so it doesn't disappear under us. */ static bool fsnotify_get_mark_safe(struct fsnotify_mark *mark) { if (!mark) return true; if (refcount_inc_not_zero(&mark->refcnt)) { spin_lock(&mark->lock); if (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) { /* mark is attached, group is still alive then */ atomic_inc(&mark->group->user_waits); spin_unlock(&mark->lock); return true; } spin_unlock(&mark->lock); fsnotify_put_mark(mark); } return false; } /* * Puts marks and wakes up group destruction if necessary. * * Pairs with fsnotify_get_mark_safe() */ static void fsnotify_put_mark_wake(struct fsnotify_mark *mark) { if (mark) { struct fsnotify_group *group = mark->group; fsnotify_put_mark(mark); /* * We abuse notification_waitq on group shutdown for waiting for * all marks pinned when waiting for userspace. */ if (atomic_dec_and_test(&group->user_waits) && group->shutdown) wake_up(&group->notification_waitq); } } bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info) __releases(&fsnotify_mark_srcu) { int type; fsnotify_foreach_iter_type(type) { /* This can fail if mark is being removed */ if (!fsnotify_get_mark_safe(iter_info->marks[type])) { __release(&fsnotify_mark_srcu); goto fail; } } /* * Now that both marks are pinned by refcount in the inode / vfsmount * lists, we can drop SRCU lock, and safely resume the list iteration * once userspace returns. */ srcu_read_unlock(&fsnotify_mark_srcu, iter_info->srcu_idx); return true; fail: for (type--; type >= 0; type--) fsnotify_put_mark_wake(iter_info->marks[type]); return false; } void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info) __acquires(&fsnotify_mark_srcu) { int type; iter_info->srcu_idx = srcu_read_lock(&fsnotify_mark_srcu); fsnotify_foreach_iter_type(type) fsnotify_put_mark_wake(iter_info->marks[type]); } /* * Mark mark as detached, remove it from group list. Mark still stays in object * list until its last reference is dropped. Note that we rely on mark being * removed from group list before corresponding reference to it is dropped. In * particular we rely on mark->connector being valid while we hold * group->mark_mutex if we found the mark through g_list. * * Must be called with group->mark_mutex held. The caller must either hold * reference to the mark or be protected by fsnotify_mark_srcu. */ void fsnotify_detach_mark(struct fsnotify_mark *mark) { fsnotify_group_assert_locked(mark->group); WARN_ON_ONCE(!srcu_read_lock_held(&fsnotify_mark_srcu) && refcount_read(&mark->refcnt) < 1 + !!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)); spin_lock(&mark->lock); /* something else already called this function on this mark */ if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) { spin_unlock(&mark->lock); return; } mark->flags &= ~FSNOTIFY_MARK_FLAG_ATTACHED; list_del_init(&mark->g_list); spin_unlock(&mark->lock); /* Drop mark reference acquired in fsnotify_add_mark_locked() */ fsnotify_put_mark(mark); } /* * Free fsnotify mark. The mark is actually only marked as being freed. The * freeing is actually happening only once last reference to the mark is * dropped from a workqueue which first waits for srcu period end. * * Caller must have a reference to the mark or be protected by * fsnotify_mark_srcu. */ void fsnotify_free_mark(struct fsnotify_mark *mark) { struct fsnotify_group *group = mark->group; spin_lock(&mark->lock); /* something else already called this function on this mark */ if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE)) { spin_unlock(&mark->lock); return; } mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE; spin_unlock(&mark->lock); /* * Some groups like to know that marks are being freed. This is a * callback to the group function to let it know that this mark * is being freed. */ if (group->ops->freeing_mark) group->ops->freeing_mark(mark, group); } void fsnotify_destroy_mark(struct fsnotify_mark *mark, struct fsnotify_group *group) { fsnotify_group_lock(group); fsnotify_detach_mark(mark); fsnotify_group_unlock(group); fsnotify_free_mark(mark); } EXPORT_SYMBOL_GPL(fsnotify_destroy_mark); /* * Sorting function for lists of fsnotify marks. * * Fanotify supports different notification classes (reflected as priority of * notification group). Events shall be passed to notification groups in * decreasing priority order. To achieve this marks in notification lists for * inodes and vfsmounts are sorted so that priorities of corresponding groups * are descending. * * Furthermore correct handling of the ignore mask requires processing inode * and vfsmount marks of each group together. Using the group address as * further sort criterion provides a unique sorting order and thus we can * merge inode and vfsmount lists of marks in linear time and find groups * present in both lists. * * A return value of 1 signifies that b has priority over a. * A return value of 0 signifies that the two marks have to be handled together. * A return value of -1 signifies that a has priority over b. */ int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b) { if (a == b) return 0; if (!a) return 1; if (!b) return -1; if (a->priority < b->priority) return 1; if (a->priority > b->priority) return -1; if (a < b) return 1; return -1; } static int fsnotify_attach_info_to_sb(struct super_block *sb) { struct fsnotify_sb_info *sbinfo; /* sb info is freed on fsnotify_sb_delete() */ sbinfo = kzalloc(sizeof(*sbinfo), GFP_KERNEL); if (!sbinfo) return -ENOMEM; /* * cmpxchg() provides the barrier so that callers of fsnotify_sb_info() * will observe an initialized structure */ if (cmpxchg(&sb->s_fsnotify_info, NULL, sbinfo)) { /* Someone else created sbinfo for us */ kfree(sbinfo); } return 0; } static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp, void *obj, unsigned int obj_type) { struct fsnotify_mark_connector *conn; conn = kmem_cache_alloc(fsnotify_mark_connector_cachep, GFP_KERNEL); if (!conn) return -ENOMEM; spin_lock_init(&conn->lock); INIT_HLIST_HEAD(&conn->list); conn->flags = 0; conn->prio = 0; conn->type = obj_type; conn->obj = obj; /* * cmpxchg() provides the barrier so that readers of *connp can see * only initialized structure */ if (cmpxchg(connp, NULL, conn)) { /* Someone else created list structure for us */ kmem_cache_free(fsnotify_mark_connector_cachep, conn); } return 0; } /* * Get mark connector, make sure it is alive and return with its lock held. * This is for users that get connector pointer from inode or mount. Users that * hold reference to a mark on the list may directly lock connector->lock as * they are sure list cannot go away under them. */ static struct fsnotify_mark_connector *fsnotify_grab_connector( fsnotify_connp_t *connp) { struct fsnotify_mark_connector *conn; int idx; idx = srcu_read_lock(&fsnotify_mark_srcu); conn = srcu_dereference(*connp, &fsnotify_mark_srcu); if (!conn) goto out; spin_lock(&conn->lock); if (conn->type == FSNOTIFY_OBJ_TYPE_DETACHED) { spin_unlock(&conn->lock); srcu_read_unlock(&fsnotify_mark_srcu, idx); return NULL; } out: srcu_read_unlock(&fsnotify_mark_srcu, idx); return conn; } /* * Add mark into proper place in given list of marks. These marks may be used * for the fsnotify backend to determine which event types should be delivered * to which group and for which inodes. These marks are ordered according to * priority, highest number first, and then by the group's location in memory. */ static int fsnotify_add_mark_list(struct fsnotify_mark *mark, void *obj, unsigned int obj_type, int add_flags) { struct super_block *sb = fsnotify_object_sb(obj, obj_type); struct fsnotify_mark *lmark, *last = NULL; struct fsnotify_mark_connector *conn; fsnotify_connp_t *connp; int cmp; int err = 0; if (WARN_ON(!fsnotify_valid_obj_type(obj_type))) return -EINVAL; /* * Attach the sb info before attaching a connector to any object on sb. * The sb info will remain attached as long as sb lives. */ if (!fsnotify_sb_info(sb)) { err = fsnotify_attach_info_to_sb(sb); if (err) return err; } connp = fsnotify_object_connp(obj, obj_type); restart: spin_lock(&mark->lock); conn = fsnotify_grab_connector(connp); if (!conn) { spin_unlock(&mark->lock); err = fsnotify_attach_connector_to_object(connp, obj, obj_type); if (err) return err; goto restart; } /* is mark the first mark? */ if (hlist_empty(&conn->list)) { hlist_add_head_rcu(&mark->obj_list, &conn->list); goto added; } /* should mark be in the middle of the current list? */ hlist_for_each_entry(lmark, &conn->list, obj_list) { last = lmark; if ((lmark->group == mark->group) && (lmark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) && !(mark->group->flags & FSNOTIFY_GROUP_DUPS)) { err = -EEXIST; goto out_err; } cmp = fsnotify_compare_groups(lmark->group, mark->group); if (cmp >= 0) { hlist_add_before_rcu(&mark->obj_list, &lmark->obj_list); goto added; } } BUG_ON(last == NULL); /* mark should be the last entry. last is the current last entry */ hlist_add_behind_rcu(&mark->obj_list, &last->obj_list); added: fsnotify_update_sb_watchers(sb, conn); /* * Since connector is attached to object using cmpxchg() we are * guaranteed that connector initialization is fully visible by anyone * seeing mark->connector set. */ WRITE_ONCE(mark->connector, conn); out_err: spin_unlock(&conn->lock); spin_unlock(&mark->lock); return err; } /* * Attach an initialized mark to a given group and fs object. * These marks may be used for the fsnotify backend to determine which * event types should be delivered to which group. */ int fsnotify_add_mark_locked(struct fsnotify_mark *mark, void *obj, unsigned int obj_type, int add_flags) { struct fsnotify_group *group = mark->group; int ret = 0; fsnotify_group_assert_locked(group); /* * LOCKING ORDER!!!! * group->mark_mutex * mark->lock * mark->connector->lock */ spin_lock(&mark->lock); mark->flags |= FSNOTIFY_MARK_FLAG_ALIVE | FSNOTIFY_MARK_FLAG_ATTACHED; list_add(&mark->g_list, &group->marks_list); fsnotify_get_mark(mark); /* for g_list */ spin_unlock(&mark->lock); ret = fsnotify_add_mark_list(mark, obj, obj_type, add_flags); if (ret) goto err; fsnotify_recalc_mask(mark->connector); return ret; err: spin_lock(&mark->lock); mark->flags &= ~(FSNOTIFY_MARK_FLAG_ALIVE | FSNOTIFY_MARK_FLAG_ATTACHED); list_del_init(&mark->g_list); spin_unlock(&mark->lock); fsnotify_put_mark(mark); return ret; } int fsnotify_add_mark(struct fsnotify_mark *mark, void *obj, unsigned int obj_type, int add_flags) { int ret; struct fsnotify_group *group = mark->group; fsnotify_group_lock(group); ret = fsnotify_add_mark_locked(mark, obj, obj_type, add_flags); fsnotify_group_unlock(group); return ret; } EXPORT_SYMBOL_GPL(fsnotify_add_mark); /* * Given a list of marks, find the mark associated with given group. If found * take a reference to that mark and return it, else return NULL. */ struct fsnotify_mark *fsnotify_find_mark(void *obj, unsigned int obj_type, struct fsnotify_group *group) { fsnotify_connp_t *connp = fsnotify_object_connp(obj, obj_type); struct fsnotify_mark_connector *conn; struct fsnotify_mark *mark; if (!connp) return NULL; conn = fsnotify_grab_connector(connp); if (!conn) return NULL; hlist_for_each_entry(mark, &conn->list, obj_list) { if (mark->group == group && (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) { fsnotify_get_mark(mark); spin_unlock(&conn->lock); return mark; } } spin_unlock(&conn->lock); return NULL; } EXPORT_SYMBOL_GPL(fsnotify_find_mark); /* Clear any marks in a group with given type mask */ void fsnotify_clear_marks_by_group(struct fsnotify_group *group, unsigned int obj_type) { struct fsnotify_mark *lmark, *mark; LIST_HEAD(to_free); struct list_head *head = &to_free; /* Skip selection step if we want to clear all marks. */ if (obj_type == FSNOTIFY_OBJ_TYPE_ANY) { head = &group->marks_list; goto clear; } /* * We have to be really careful here. Anytime we drop mark_mutex, e.g. * fsnotify_clear_marks_by_inode() can come and free marks. Even in our * to_free list so we have to use mark_mutex even when accessing that * list. And freeing mark requires us to drop mark_mutex. So we can * reliably free only the first mark in the list. That's why we first * move marks to free to to_free list in one go and then free marks in * to_free list one by one. */ fsnotify_group_lock(group); list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) { if (mark->connector->type == obj_type) list_move(&mark->g_list, &to_free); } fsnotify_group_unlock(group); clear: while (1) { fsnotify_group_lock(group); if (list_empty(head)) { fsnotify_group_unlock(group); break; } mark = list_first_entry(head, struct fsnotify_mark, g_list); fsnotify_get_mark(mark); fsnotify_detach_mark(mark); fsnotify_group_unlock(group); fsnotify_free_mark(mark); fsnotify_put_mark(mark); } } /* Destroy all marks attached to an object via connector */ void fsnotify_destroy_marks(fsnotify_connp_t *connp) { struct fsnotify_mark_connector *conn; struct fsnotify_mark *mark, *old_mark = NULL; void *objp; unsigned int type; conn = fsnotify_grab_connector(connp); if (!conn) return; /* * We have to be careful since we can race with e.g. * fsnotify_clear_marks_by_group() and once we drop the conn->lock, the * list can get modified. However we are holding mark reference and * thus our mark cannot be removed from obj_list so we can continue * iteration after regaining conn->lock. */ hlist_for_each_entry(mark, &conn->list, obj_list) { fsnotify_get_mark(mark); spin_unlock(&conn->lock); if (old_mark) fsnotify_put_mark(old_mark); old_mark = mark; fsnotify_destroy_mark(mark, mark->group); spin_lock(&conn->lock); } /* * Detach list from object now so that we don't pin inode until all * mark references get dropped. It would lead to strange results such * as delaying inode deletion or blocking unmount. */ objp = fsnotify_detach_connector_from_object(conn, &type); spin_unlock(&conn->lock); if (old_mark) fsnotify_put_mark(old_mark); fsnotify_drop_object(type, objp); } /* * Nothing fancy, just initialize lists and locks and counters. */ void fsnotify_init_mark(struct fsnotify_mark *mark, struct fsnotify_group *group) { memset(mark, 0, sizeof(*mark)); spin_lock_init(&mark->lock); refcount_set(&mark->refcnt, 1); fsnotify_get_group(group); mark->group = group; WRITE_ONCE(mark->connector, NULL); } EXPORT_SYMBOL_GPL(fsnotify_init_mark); /* * Destroy all marks in destroy_list, waits for SRCU period to finish before * actually freeing marks. */ static void fsnotify_mark_destroy_workfn(struct work_struct *work) { struct fsnotify_mark *mark, *next; struct list_head private_destroy_list; spin_lock(&destroy_lock); /* exchange the list head */ list_replace_init(&destroy_list, &private_destroy_list); spin_unlock(&destroy_lock); synchronize_srcu(&fsnotify_mark_srcu); list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) { list_del_init(&mark->g_list); fsnotify_final_mark_destroy(mark); } } /* Wait for all marks queued for destruction to be actually destroyed */ void fsnotify_wait_marks_destroyed(void) { flush_delayed_work(&reaper_work); } EXPORT_SYMBOL_GPL(fsnotify_wait_marks_destroyed); |
| 1 1 139 139 139 4 41 41 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_GENERIC_PGALLOC_H #define __ASM_GENERIC_PGALLOC_H #ifdef CONFIG_MMU #define GFP_PGTABLE_KERNEL (GFP_KERNEL | __GFP_ZERO) #define GFP_PGTABLE_USER (GFP_PGTABLE_KERNEL | __GFP_ACCOUNT) /** * __pte_alloc_one_kernel - allocate memory for a PTE-level kernel page table * @mm: the mm_struct of the current context * * This function is intended for architectures that need * anything beyond simple page allocation. * * Return: pointer to the allocated memory or %NULL on error */ static inline pte_t *__pte_alloc_one_kernel_noprof(struct mm_struct *mm) { struct ptdesc *ptdesc = pagetable_alloc_noprof(GFP_PGTABLE_KERNEL & ~__GFP_HIGHMEM, 0); if (!ptdesc) return NULL; return ptdesc_address(ptdesc); } #define __pte_alloc_one_kernel(...) alloc_hooks(__pte_alloc_one_kernel_noprof(__VA_ARGS__)) #ifndef __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL /** * pte_alloc_one_kernel - allocate memory for a PTE-level kernel page table * @mm: the mm_struct of the current context * * Return: pointer to the allocated memory or %NULL on error */ static inline pte_t *pte_alloc_one_kernel_noprof(struct mm_struct *mm) { return __pte_alloc_one_kernel_noprof(mm); } #define pte_alloc_one_kernel(...) alloc_hooks(pte_alloc_one_kernel_noprof(__VA_ARGS__)) #endif /** * pte_free_kernel - free PTE-level kernel page table memory * @mm: the mm_struct of the current context * @pte: pointer to the memory containing the page table */ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { pagetable_free(virt_to_ptdesc(pte)); } /** * __pte_alloc_one - allocate memory for a PTE-level user page table * @mm: the mm_struct of the current context * @gfp: GFP flags to use for the allocation * * Allocate memory for a page table and ptdesc and runs pagetable_pte_ctor(). * * This function is intended for architectures that need * anything beyond simple page allocation or must have custom GFP flags. * * Return: `struct page` referencing the ptdesc or %NULL on error */ static inline pgtable_t __pte_alloc_one_noprof(struct mm_struct *mm, gfp_t gfp) { struct ptdesc *ptdesc; ptdesc = pagetable_alloc_noprof(gfp, 0); if (!ptdesc) return NULL; if (!pagetable_pte_ctor(ptdesc)) { pagetable_free(ptdesc); return NULL; } return ptdesc_page(ptdesc); } #define __pte_alloc_one(...) alloc_hooks(__pte_alloc_one_noprof(__VA_ARGS__)) #ifndef __HAVE_ARCH_PTE_ALLOC_ONE /** * pte_alloc_one - allocate a page for PTE-level user page table * @mm: the mm_struct of the current context * * Allocate memory for a page table and ptdesc and runs pagetable_pte_ctor(). * * Return: `struct page` referencing the ptdesc or %NULL on error */ static inline pgtable_t pte_alloc_one_noprof(struct mm_struct *mm) { return __pte_alloc_one_noprof(mm, GFP_PGTABLE_USER); } #define pte_alloc_one(...) alloc_hooks(pte_alloc_one_noprof(__VA_ARGS__)) #endif /* * Should really implement gc for free page table pages. This could be * done with a reference count in struct page. */ /** * pte_free - free PTE-level user page table memory * @mm: the mm_struct of the current context * @pte_page: the `struct page` referencing the ptdesc */ static inline void pte_free(struct mm_struct *mm, struct page *pte_page) { struct ptdesc *ptdesc = page_ptdesc(pte_page); pagetable_pte_dtor(ptdesc); pagetable_free(ptdesc); } #if CONFIG_PGTABLE_LEVELS > 2 #ifndef __HAVE_ARCH_PMD_ALLOC_ONE /** * pmd_alloc_one - allocate memory for a PMD-level page table * @mm: the mm_struct of the current context * * Allocate memory for a page table and ptdesc and runs pagetable_pmd_ctor(). * * Allocations use %GFP_PGTABLE_USER in user context and * %GFP_PGTABLE_KERNEL in kernel context. * * Return: pointer to the allocated memory or %NULL on error */ static inline pmd_t *pmd_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) { struct ptdesc *ptdesc; gfp_t gfp = GFP_PGTABLE_USER; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; ptdesc = pagetable_alloc_noprof(gfp, 0); if (!ptdesc) return NULL; if (!pagetable_pmd_ctor(ptdesc)) { pagetable_free(ptdesc); return NULL; } return ptdesc_address(ptdesc); } #define pmd_alloc_one(...) alloc_hooks(pmd_alloc_one_noprof(__VA_ARGS__)) #endif #ifndef __HAVE_ARCH_PMD_FREE static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { struct ptdesc *ptdesc = virt_to_ptdesc(pmd); BUG_ON((unsigned long)pmd & (PAGE_SIZE-1)); pagetable_pmd_dtor(ptdesc); pagetable_free(ptdesc); } #endif #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #if CONFIG_PGTABLE_LEVELS > 3 static inline pud_t *__pud_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) { gfp_t gfp = GFP_PGTABLE_USER; struct ptdesc *ptdesc; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; gfp &= ~__GFP_HIGHMEM; ptdesc = pagetable_alloc_noprof(gfp, 0); if (!ptdesc) return NULL; pagetable_pud_ctor(ptdesc); return ptdesc_address(ptdesc); } #define __pud_alloc_one(...) alloc_hooks(__pud_alloc_one_noprof(__VA_ARGS__)) #ifndef __HAVE_ARCH_PUD_ALLOC_ONE /** * pud_alloc_one - allocate memory for a PUD-level page table * @mm: the mm_struct of the current context * * Allocate memory for a page table using %GFP_PGTABLE_USER for user context * and %GFP_PGTABLE_KERNEL for kernel context. * * Return: pointer to the allocated memory or %NULL on error */ static inline pud_t *pud_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) { return __pud_alloc_one_noprof(mm, addr); } #define pud_alloc_one(...) alloc_hooks(pud_alloc_one_noprof(__VA_ARGS__)) #endif static inline void __pud_free(struct mm_struct *mm, pud_t *pud) { struct ptdesc *ptdesc = virt_to_ptdesc(pud); BUG_ON((unsigned long)pud & (PAGE_SIZE-1)); pagetable_pud_dtor(ptdesc); pagetable_free(ptdesc); } #ifndef __HAVE_ARCH_PUD_FREE static inline void pud_free(struct mm_struct *mm, pud_t *pud) { __pud_free(mm, pud); } #endif #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #ifndef __HAVE_ARCH_PGD_FREE static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) { pagetable_free(virt_to_ptdesc(pgd)); } #endif #endif /* CONFIG_MMU */ #endif /* __ASM_GENERIC_PGALLOC_H */ |
| 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io */ /* Devmaps primary use is as a backend map for XDP BPF helper call * bpf_redirect_map(). Because XDP is mostly concerned with performance we * spent some effort to ensure the datapath with redirect maps does not use * any locking. This is a quick note on the details. * * We have three possible paths to get into the devmap control plane bpf * syscalls, bpf programs, and driver side xmit/flush operations. A bpf syscall * will invoke an update, delete, or lookup operation. To ensure updates and * deletes appear atomic from the datapath side xchg() is used to modify the * netdev_map array. Then because the datapath does a lookup into the netdev_map * array (read-only) from an RCU critical section we use call_rcu() to wait for * an rcu grace period before free'ing the old data structures. This ensures the * datapath always has a valid copy. However, the datapath does a "flush" * operation that pushes any pending packets in the driver outside the RCU * critical section. Each bpf_dtab_netdev tracks these pending operations using * a per-cpu flush list. The bpf_dtab_netdev object will not be destroyed until * this list is empty, indicating outstanding flush operations have completed. * * BPF syscalls may race with BPF program calls on any of the update, delete * or lookup operations. As noted above the xchg() operation also keep the * netdev_map consistent in this case. From the devmap side BPF programs * calling into these operations are the same as multiple user space threads * making system calls. * * Finally, any of the above may race with a netdev_unregister notifier. The * unregister notifier must search for net devices in the map structure that * contain a reference to the net device and remove them. This is a two step * process (a) dereference the bpf_dtab_netdev object in netdev_map and (b) * check to see if the ifindex is the same as the net_device being removed. * When removing the dev a cmpxchg() is used to ensure the correct dev is * removed, in the case of a concurrent update or delete operation it is * possible that the initially referenced dev is no longer in the map. As the * notifier hook walks the map we know that new dev references can not be * added by the user because core infrastructure ensures dev_get_by_index() * calls will fail at this point. * * The devmap_hash type is a map type which interprets keys as ifindexes and * indexes these using a hashmap. This allows maps that use ifindex as key to be * densely packed instead of having holes in the lookup array for unused * ifindexes. The setup and packet enqueue/send code is shared between the two * types of devmap; only the lookup and insertion is different. */ #include <linux/bpf.h> #include <net/xdp.h> #include <linux/filter.h> #include <trace/events/xdp.h> #include <linux/btf_ids.h> #define DEV_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) struct xdp_dev_bulk_queue { struct xdp_frame *q[DEV_MAP_BULK_SIZE]; struct list_head flush_node; struct net_device *dev; struct net_device *dev_rx; struct bpf_prog *xdp_prog; unsigned int count; }; struct bpf_dtab_netdev { struct net_device *dev; /* must be first member, due to tracepoint */ struct hlist_node index_hlist; struct bpf_prog *xdp_prog; struct rcu_head rcu; unsigned int idx; struct bpf_devmap_val val; }; struct bpf_dtab { struct bpf_map map; struct bpf_dtab_netdev __rcu **netdev_map; /* DEVMAP type only */ struct list_head list; /* these are only used for DEVMAP_HASH type maps */ struct hlist_head *dev_index_head; spinlock_t index_lock; unsigned int items; u32 n_buckets; }; static DEFINE_SPINLOCK(dev_map_lock); static LIST_HEAD(dev_map_list); static struct hlist_head *dev_map_create_hash(unsigned int entries, int numa_node) { int i; struct hlist_head *hash; hash = bpf_map_area_alloc((u64) entries * sizeof(*hash), numa_node); if (hash != NULL) for (i = 0; i < entries; i++) INIT_HLIST_HEAD(&hash[i]); return hash; } static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab, int idx) { return &dtab->dev_index_head[idx & (dtab->n_buckets - 1)]; } static int dev_map_alloc_check(union bpf_attr *attr) { u32 valsize = attr->value_size; /* check sanity of attributes. 2 value sizes supported: * 4 bytes: ifindex * 8 bytes: ifindex + prog fd */ if (attr->max_entries == 0 || attr->key_size != 4 || (valsize != offsetofend(struct bpf_devmap_val, ifindex) && valsize != offsetofend(struct bpf_devmap_val, bpf_prog.fd)) || attr->map_flags & ~DEV_CREATE_FLAG_MASK) return -EINVAL; if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { /* Hash table size must be power of 2; roundup_pow_of_two() * can overflow into UB on 32-bit arches */ if (attr->max_entries > 1UL << 31) return -EINVAL; } return 0; } static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) { /* Lookup returns a pointer straight to dev->ifindex, so make sure the * verifier prevents writes from the BPF side */ attr->map_flags |= BPF_F_RDONLY_PROG; bpf_map_init_from_attr(&dtab->map, attr); if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { /* Hash table size must be power of 2 */ dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries); dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets, dtab->map.numa_node); if (!dtab->dev_index_head) return -ENOMEM; spin_lock_init(&dtab->index_lock); } else { dtab->netdev_map = bpf_map_area_alloc((u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *), dtab->map.numa_node); if (!dtab->netdev_map) return -ENOMEM; } return 0; } static struct bpf_map *dev_map_alloc(union bpf_attr *attr) { struct bpf_dtab *dtab; int err; dtab = bpf_map_area_alloc(sizeof(*dtab), NUMA_NO_NODE); if (!dtab) return ERR_PTR(-ENOMEM); err = dev_map_init_map(dtab, attr); if (err) { bpf_map_area_free(dtab); return ERR_PTR(err); } spin_lock(&dev_map_lock); list_add_tail_rcu(&dtab->list, &dev_map_list); spin_unlock(&dev_map_lock); return &dtab->map; } static void dev_map_free(struct bpf_map *map) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); u32 i; /* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, * so the programs (can be more than one that used this map) were * disconnected from events. The following synchronize_rcu() guarantees * both rcu read critical sections complete and waits for * preempt-disable regions (NAPI being the relevant context here) so we * are certain there will be no further reads against the netdev_map and * all flush operations are complete. Flush operations can only be done * from NAPI context for this reason. */ spin_lock(&dev_map_lock); list_del_rcu(&dtab->list); spin_unlock(&dev_map_lock); /* bpf_redirect_info->map is assigned in __bpf_xdp_redirect_map() * during NAPI callback and cleared after the XDP redirect. There is no * explicit RCU read section which protects bpf_redirect_info->map but * local_bh_disable() also marks the beginning an RCU section. This * makes the complete softirq callback RCU protected. Thus after * following synchronize_rcu() there no bpf_redirect_info->map == map * assignment. */ synchronize_rcu(); /* Make sure prior __dev_map_entry_free() have completed. */ rcu_barrier(); if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) { for (i = 0; i < dtab->n_buckets; i++) { struct bpf_dtab_netdev *dev; struct hlist_head *head; struct hlist_node *next; head = dev_map_index_hash(dtab, i); hlist_for_each_entry_safe(dev, next, head, index_hlist) { hlist_del_rcu(&dev->index_hlist); if (dev->xdp_prog) bpf_prog_put(dev->xdp_prog); dev_put(dev->dev); kfree(dev); } } bpf_map_area_free(dtab->dev_index_head); } else { for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev; dev = rcu_dereference_raw(dtab->netdev_map[i]); if (!dev) continue; if (dev->xdp_prog) bpf_prog_put(dev->xdp_prog); dev_put(dev->dev); kfree(dev); } bpf_map_area_free(dtab->netdev_map); } bpf_map_area_free(dtab); } static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); u32 index = key ? *(u32 *)key : U32_MAX; u32 *next = next_key; if (index >= dtab->map.max_entries) { *next = 0; return 0; } if (index == dtab->map.max_entries - 1) return -ENOENT; *next = index + 1; return 0; } /* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or * by local_bh_disable() (from XDP calls inside NAPI). The * rcu_read_lock_bh_held() below makes lockdep accept both. */ static void *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct hlist_head *head = dev_map_index_hash(dtab, key); struct bpf_dtab_netdev *dev; hlist_for_each_entry_rcu(dev, head, index_hlist, lockdep_is_held(&dtab->index_lock)) if (dev->idx == key) return dev; return NULL; } static int dev_map_hash_get_next_key(struct bpf_map *map, void *key, void *next_key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); u32 idx, *next = next_key; struct bpf_dtab_netdev *dev, *next_dev; struct hlist_head *head; int i = 0; if (!key) goto find_first; idx = *(u32 *)key; dev = __dev_map_hash_lookup_elem(map, idx); if (!dev) goto find_first; next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&dev->index_hlist)), struct bpf_dtab_netdev, index_hlist); if (next_dev) { *next = next_dev->idx; return 0; } i = idx & (dtab->n_buckets - 1); i++; find_first: for (; i < dtab->n_buckets; i++) { head = dev_map_index_hash(dtab, i); next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)), struct bpf_dtab_netdev, index_hlist); if (next_dev) { *next = next_dev->idx; return 0; } } return -ENOENT; } static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog, struct xdp_frame **frames, int n, struct net_device *tx_dev, struct net_device *rx_dev) { struct xdp_txq_info txq = { .dev = tx_dev }; struct xdp_rxq_info rxq = { .dev = rx_dev }; struct xdp_buff xdp; int i, nframes = 0; for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; u32 act; int err; xdp_convert_frame_to_buff(xdpf, &xdp); xdp.txq = &txq; xdp.rxq = &rxq; act = bpf_prog_run_xdp(xdp_prog, &xdp); switch (act) { case XDP_PASS: err = xdp_update_frame_from_buff(&xdp, xdpf); if (unlikely(err < 0)) xdp_return_frame_rx_napi(xdpf); else frames[nframes++] = xdpf; break; default: bpf_warn_invalid_xdp_action(NULL, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(tx_dev, xdp_prog, act); fallthrough; case XDP_DROP: xdp_return_frame_rx_napi(xdpf); break; } } return nframes; /* sent frames count */ } static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags) { struct net_device *dev = bq->dev; unsigned int cnt = bq->count; int sent = 0, err = 0; int to_send = cnt; int i; if (unlikely(!cnt)) return; for (i = 0; i < cnt; i++) { struct xdp_frame *xdpf = bq->q[i]; prefetch(xdpf); } if (bq->xdp_prog) { to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev, bq->dev_rx); if (!to_send) goto out; } sent = dev->netdev_ops->ndo_xdp_xmit(dev, to_send, bq->q, flags); if (sent < 0) { /* If ndo_xdp_xmit fails with an errno, no frames have * been xmit'ed. */ err = sent; sent = 0; } /* If not all frames have been transmitted, it is our * responsibility to free them */ for (i = sent; unlikely(i < to_send); i++) xdp_return_frame_rx_napi(bq->q[i]); out: bq->count = 0; trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, cnt - sent, err); } /* __dev_flush is called from xdp_do_flush() which _must_ be signalled from the * driver before returning from its napi->poll() routine. See the comment above * xdp_do_flush() in filter.c. */ void __dev_flush(struct list_head *flush_list) { struct xdp_dev_bulk_queue *bq, *tmp; list_for_each_entry_safe(bq, tmp, flush_list, flush_node) { bq_xmit_all(bq, XDP_XMIT_FLUSH); bq->dev_rx = NULL; bq->xdp_prog = NULL; __list_del_clearprev(&bq->flush_node); } } /* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or * by local_bh_disable() (from XDP calls inside NAPI). The * rcu_read_lock_bh_held() below makes lockdep accept both. */ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *obj; if (key >= map->max_entries) return NULL; obj = rcu_dereference_check(dtab->netdev_map[key], rcu_read_lock_bh_held()); return obj; } /* Runs in NAPI, i.e., softirq under local_bh_disable(). Thus, safe percpu * variable access, and map elements stick around. See comment above * xdp_do_flush() in filter.c. */ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_prog *xdp_prog) { struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq); if (unlikely(bq->count == DEV_MAP_BULK_SIZE)) bq_xmit_all(bq, 0); /* Ingress dev_rx will be the same for all xdp_frame's in * bulk_queue, because bq stored per-CPU and must be flushed * from net_device drivers NAPI func end. * * Do the same with xdp_prog and flush_list since these fields * are only ever modified together. */ if (!bq->dev_rx) { struct list_head *flush_list = bpf_net_ctx_get_dev_flush_list(); bq->dev_rx = dev_rx; bq->xdp_prog = xdp_prog; list_add(&bq->flush_node, flush_list); } bq->q[bq->count++] = xdpf; } static inline int __xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_prog *xdp_prog) { int err; if (!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT)) return -EOPNOTSUPP; if (unlikely(!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) && xdp_frame_has_frags(xdpf))) return -EOPNOTSUPP; err = xdp_ok_fwd_dev(dev, xdp_get_frame_len(xdpf)); if (unlikely(err)) return err; bq_enqueue(dev, xdpf, dev_rx, xdp_prog); return 0; } static u32 dev_map_bpf_prog_run_skb(struct sk_buff *skb, struct bpf_dtab_netdev *dst) { struct xdp_txq_info txq = { .dev = dst->dev }; struct xdp_buff xdp; u32 act; if (!dst->xdp_prog) return XDP_PASS; __skb_pull(skb, skb->mac_len); xdp.txq = &txq; act = bpf_prog_run_generic_xdp(skb, &xdp, dst->xdp_prog); switch (act) { case XDP_PASS: __skb_push(skb, skb->mac_len); break; default: bpf_warn_invalid_xdp_action(NULL, dst->xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(dst->dev, dst->xdp_prog, act); fallthrough; case XDP_DROP: kfree_skb(skb); break; } return act; } int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx) { return __xdp_enqueue(dev, xdpf, dev_rx, NULL); } int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx) { struct net_device *dev = dst->dev; return __xdp_enqueue(dev, xdpf, dev_rx, dst->xdp_prog); } static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf) { if (!obj) return false; if (!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT)) return false; if (unlikely(!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) && xdp_frame_has_frags(xdpf))) return false; if (xdp_ok_fwd_dev(obj->dev, xdp_get_frame_len(xdpf))) return false; return true; } static int dev_map_enqueue_clone(struct bpf_dtab_netdev *obj, struct net_device *dev_rx, struct xdp_frame *xdpf) { struct xdp_frame *nxdpf; nxdpf = xdpf_clone(xdpf); if (!nxdpf) return -ENOMEM; bq_enqueue(obj->dev, nxdpf, dev_rx, obj->xdp_prog); return 0; } static inline bool is_ifindex_excluded(int *excluded, int num_excluded, int ifindex) { while (num_excluded--) { if (ifindex == excluded[num_excluded]) return true; } return false; } /* Get ifindex of each upper device. 'indexes' must be able to hold at * least MAX_NEST_DEV elements. * Returns the number of ifindexes added. */ static int get_upper_ifindexes(struct net_device *dev, int *indexes) { struct net_device *upper; struct list_head *iter; int n = 0; netdev_for_each_upper_dev_rcu(dev, upper, iter) { indexes[n++] = upper->ifindex; } return n; } int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dst, *last_dst = NULL; int excluded_devices[1+MAX_NEST_DEV]; struct hlist_head *head; int num_excluded = 0; unsigned int i; int err; if (exclude_ingress) { num_excluded = get_upper_ifindexes(dev_rx, excluded_devices); excluded_devices[num_excluded++] = dev_rx->ifindex; } if (map->map_type == BPF_MAP_TYPE_DEVMAP) { for (i = 0; i < map->max_entries; i++) { dst = rcu_dereference_check(dtab->netdev_map[i], rcu_read_lock_bh_held()); if (!is_valid_dst(dst, xdpf)) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf); if (err) return err; last_dst = dst; } } else { /* BPF_MAP_TYPE_DEVMAP_HASH */ for (i = 0; i < dtab->n_buckets; i++) { head = dev_map_index_hash(dtab, i); hlist_for_each_entry_rcu(dst, head, index_hlist, lockdep_is_held(&dtab->index_lock)) { if (!is_valid_dst(dst, xdpf)) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf); if (err) return err; last_dst = dst; } } } /* consume the last copy of the frame */ if (last_dst) bq_enqueue(last_dst->dev, xdpf, dev_rx, last_dst->xdp_prog); else xdp_return_frame_rx_napi(xdpf); /* dtab is empty */ return 0; } int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog) { int err; err = xdp_ok_fwd_dev(dst->dev, skb->len); if (unlikely(err)) return err; /* Redirect has already succeeded semantically at this point, so we just * return 0 even if packet is dropped. Helper below takes care of * freeing skb. */ if (dev_map_bpf_prog_run_skb(skb, dst) != XDP_PASS) return 0; skb->dev = dst->dev; generic_xdp_tx(skb, xdp_prog); return 0; } static int dev_map_redirect_clone(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog) { struct sk_buff *nskb; int err; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return -ENOMEM; err = dev_map_generic_redirect(dst, nskb, xdp_prog); if (unlikely(err)) { consume_skb(nskb); return err; } return 0; } int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, struct bpf_prog *xdp_prog, struct bpf_map *map, bool exclude_ingress) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dst, *last_dst = NULL; int excluded_devices[1+MAX_NEST_DEV]; struct hlist_head *head; struct hlist_node *next; int num_excluded = 0; unsigned int i; int err; if (exclude_ingress) { num_excluded = get_upper_ifindexes(dev, excluded_devices); excluded_devices[num_excluded++] = dev->ifindex; } if (map->map_type == BPF_MAP_TYPE_DEVMAP) { for (i = 0; i < map->max_entries; i++) { dst = rcu_dereference_check(dtab->netdev_map[i], rcu_read_lock_bh_held()); if (!dst) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_redirect_clone(last_dst, skb, xdp_prog); if (err) return err; last_dst = dst; } } else { /* BPF_MAP_TYPE_DEVMAP_HASH */ for (i = 0; i < dtab->n_buckets; i++) { head = dev_map_index_hash(dtab, i); hlist_for_each_entry_safe(dst, next, head, index_hlist) { if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_redirect_clone(last_dst, skb, xdp_prog); if (err) return err; last_dst = dst; } } } /* consume the first skb and return */ if (last_dst) return dev_map_generic_redirect(last_dst, skb, xdp_prog); /* dtab is empty */ consume_skb(skb); return 0; } static void *dev_map_lookup_elem(struct bpf_map *map, void *key) { struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key); return obj ? &obj->val : NULL; } static void *dev_map_hash_lookup_elem(struct bpf_map *map, void *key) { struct bpf_dtab_netdev *obj = __dev_map_hash_lookup_elem(map, *(u32 *)key); return obj ? &obj->val : NULL; } static void __dev_map_entry_free(struct rcu_head *rcu) { struct bpf_dtab_netdev *dev; dev = container_of(rcu, struct bpf_dtab_netdev, rcu); if (dev->xdp_prog) bpf_prog_put(dev->xdp_prog); dev_put(dev->dev); kfree(dev); } static long dev_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *old_dev; u32 k = *(u32 *)key; if (k >= map->max_entries) return -EINVAL; old_dev = unrcu_pointer(xchg(&dtab->netdev_map[k], NULL)); if (old_dev) { call_rcu(&old_dev->rcu, __dev_map_entry_free); atomic_dec((atomic_t *)&dtab->items); } return 0; } static long dev_map_hash_delete_elem(struct bpf_map *map, void *key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *old_dev; u32 k = *(u32 *)key; unsigned long flags; int ret = -ENOENT; spin_lock_irqsave(&dtab->index_lock, flags); old_dev = __dev_map_hash_lookup_elem(map, k); if (old_dev) { dtab->items--; hlist_del_init_rcu(&old_dev->index_hlist); call_rcu(&old_dev->rcu, __dev_map_entry_free); ret = 0; } spin_unlock_irqrestore(&dtab->index_lock, flags); return ret; } static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, struct bpf_dtab *dtab, struct bpf_devmap_val *val, unsigned int idx) { struct bpf_prog *prog = NULL; struct bpf_dtab_netdev *dev; dev = bpf_map_kmalloc_node(&dtab->map, sizeof(*dev), GFP_NOWAIT | __GFP_NOWARN, dtab->map.numa_node); if (!dev) return ERR_PTR(-ENOMEM); dev->dev = dev_get_by_index(net, val->ifindex); if (!dev->dev) goto err_out; if (val->bpf_prog.fd > 0) { prog = bpf_prog_get_type_dev(val->bpf_prog.fd, BPF_PROG_TYPE_XDP, false); if (IS_ERR(prog)) goto err_put_dev; if (prog->expected_attach_type != BPF_XDP_DEVMAP || !bpf_prog_map_compatible(&dtab->map, prog)) goto err_put_prog; } dev->idx = idx; if (prog) { dev->xdp_prog = prog; dev->val.bpf_prog.id = prog->aux->id; } else { dev->xdp_prog = NULL; dev->val.bpf_prog.id = 0; } dev->val.ifindex = val->ifindex; return dev; err_put_prog: bpf_prog_put(prog); err_put_dev: dev_put(dev->dev); err_out: kfree(dev); return ERR_PTR(-EINVAL); } static long __dev_map_update_elem(struct net *net, struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dev, *old_dev; struct bpf_devmap_val val = {}; u32 i = *(u32 *)key; if (unlikely(map_flags > BPF_EXIST)) return -EINVAL; if (unlikely(i >= dtab->map.max_entries)) return -E2BIG; if (unlikely(map_flags == BPF_NOEXIST)) return -EEXIST; /* already verified value_size <= sizeof val */ memcpy(&val, value, map->value_size); if (!val.ifindex) { dev = NULL; /* can not specify fd if ifindex is 0 */ if (val.bpf_prog.fd > 0) return -EINVAL; } else { dev = __dev_map_alloc_node(net, dtab, &val, i); if (IS_ERR(dev)) return PTR_ERR(dev); } /* Use call_rcu() here to ensure rcu critical sections have completed * Remembering the driver side flush operation will happen before the * net device is removed. */ old_dev = unrcu_pointer(xchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev))); if (old_dev) call_rcu(&old_dev->rcu, __dev_map_entry_free); else atomic_inc((atomic_t *)&dtab->items); return 0; } static long dev_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { return __dev_map_update_elem(current->nsproxy->net_ns, map, key, value, map_flags); } static long __dev_map_hash_update_elem(struct net *net, struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dev, *old_dev; struct bpf_devmap_val val = {}; u32 idx = *(u32 *)key; unsigned long flags; int err = -EEXIST; /* already verified value_size <= sizeof val */ memcpy(&val, value, map->value_size); if (unlikely(map_flags > BPF_EXIST || !val.ifindex)) return -EINVAL; spin_lock_irqsave(&dtab->index_lock, flags); old_dev = __dev_map_hash_lookup_elem(map, idx); if (old_dev && (map_flags & BPF_NOEXIST)) goto out_err; dev = __dev_map_alloc_node(net, dtab, &val, idx); if (IS_ERR(dev)) { err = PTR_ERR(dev); goto out_err; } if (old_dev) { hlist_del_rcu(&old_dev->index_hlist); } else { if (dtab->items >= dtab->map.max_entries) { spin_unlock_irqrestore(&dtab->index_lock, flags); call_rcu(&dev->rcu, __dev_map_entry_free); return -E2BIG; } dtab->items++; } hlist_add_head_rcu(&dev->index_hlist, dev_map_index_hash(dtab, idx)); spin_unlock_irqrestore(&dtab->index_lock, flags); if (old_dev) call_rcu(&old_dev->rcu, __dev_map_entry_free); return 0; out_err: spin_unlock_irqrestore(&dtab->index_lock, flags); return err; } static long dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { return __dev_map_hash_update_elem(current->nsproxy->net_ns, map, key, value, map_flags); } static long dev_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags) { return __bpf_xdp_redirect_map(map, ifindex, flags, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, __dev_map_lookup_elem); } static long dev_hash_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags) { return __bpf_xdp_redirect_map(map, ifindex, flags, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, __dev_map_hash_lookup_elem); } static u64 dev_map_mem_usage(const struct bpf_map *map) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); u64 usage = sizeof(struct bpf_dtab); if (map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) usage += (u64)dtab->n_buckets * sizeof(struct hlist_head); else usage += (u64)map->max_entries * sizeof(struct bpf_dtab_netdev *); usage += atomic_read((atomic_t *)&dtab->items) * (u64)sizeof(struct bpf_dtab_netdev); return usage; } BTF_ID_LIST_SINGLE(dev_map_btf_ids, struct, bpf_dtab) const struct bpf_map_ops dev_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = dev_map_alloc_check, .map_alloc = dev_map_alloc, .map_free = dev_map_free, .map_get_next_key = dev_map_get_next_key, .map_lookup_elem = dev_map_lookup_elem, .map_update_elem = dev_map_update_elem, .map_delete_elem = dev_map_delete_elem, .map_check_btf = map_check_no_btf, .map_mem_usage = dev_map_mem_usage, .map_btf_id = &dev_map_btf_ids[0], .map_redirect = dev_map_redirect, }; const struct bpf_map_ops dev_map_hash_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = dev_map_alloc_check, .map_alloc = dev_map_alloc, .map_free = dev_map_free, .map_get_next_key = dev_map_hash_get_next_key, .map_lookup_elem = dev_map_hash_lookup_elem, .map_update_elem = dev_map_hash_update_elem, .map_delete_elem = dev_map_hash_delete_elem, .map_check_btf = map_check_no_btf, .map_mem_usage = dev_map_mem_usage, .map_btf_id = &dev_map_btf_ids[0], .map_redirect = dev_hash_map_redirect, }; static void dev_map_hash_remove_netdev(struct bpf_dtab *dtab, struct net_device *netdev) { unsigned long flags; u32 i; spin_lock_irqsave(&dtab->index_lock, flags); for (i = 0; i < dtab->n_buckets; i++) { struct bpf_dtab_netdev *dev; struct hlist_head *head; struct hlist_node *next; head = dev_map_index_hash(dtab, i); hlist_for_each_entry_safe(dev, next, head, index_hlist) { if (netdev != dev->dev) continue; dtab->items--; hlist_del_rcu(&dev->index_hlist); call_rcu(&dev->rcu, __dev_map_entry_free); } } spin_unlock_irqrestore(&dtab->index_lock, flags); } static int dev_map_notification(struct notifier_block *notifier, ulong event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); struct bpf_dtab *dtab; int i, cpu; switch (event) { case NETDEV_REGISTER: if (!netdev->netdev_ops->ndo_xdp_xmit || netdev->xdp_bulkq) break; /* will be freed in free_netdev() */ netdev->xdp_bulkq = alloc_percpu(struct xdp_dev_bulk_queue); if (!netdev->xdp_bulkq) return NOTIFY_BAD; for_each_possible_cpu(cpu) per_cpu_ptr(netdev->xdp_bulkq, cpu)->dev = netdev; break; case NETDEV_UNREGISTER: /* This rcu_read_lock/unlock pair is needed because * dev_map_list is an RCU list AND to ensure a delete * operation does not free a netdev_map entry while we * are comparing it against the netdev being unregistered. */ rcu_read_lock(); list_for_each_entry_rcu(dtab, &dev_map_list, list) { if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) { dev_map_hash_remove_netdev(dtab, netdev); continue; } for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev, *odev; dev = rcu_dereference(dtab->netdev_map[i]); if (!dev || netdev != dev->dev) continue; odev = unrcu_pointer(cmpxchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev), NULL)); if (dev == odev) { call_rcu(&dev->rcu, __dev_map_entry_free); atomic_dec((atomic_t *)&dtab->items); } } } rcu_read_unlock(); break; default: break; } return NOTIFY_OK; } static struct notifier_block dev_map_notifier = { .notifier_call = dev_map_notification, }; static int __init dev_map_init(void) { /* Assure tracepoint shadow struct _bpf_dtab_netdev is in sync */ BUILD_BUG_ON(offsetof(struct bpf_dtab_netdev, dev) != offsetof(struct _bpf_dtab_netdev, dev)); register_netdevice_notifier(&dev_map_notifier); return 0; } subsys_initcall(dev_map_init); |
| 44 347 27 170 1 47 357 357 357 356 127 228 233 22 85 20 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* internal.h: mm/ internal definitions * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef __MM_INTERNAL_H #define __MM_INTERNAL_H #include <linux/fs.h> #include <linux/khugepaged.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/pagemap.h> #include <linux/pagewalk.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/swap_cgroup.h> #include <linux/tracepoint-defs.h> /* Internal core VMA manipulation functions. */ #include "vma.h" struct folio_batch; /* * The set of flags that only affect watermark checking and reclaim * behaviour. This is used by the MM to obey the caller constraints * about IO, FS and watermark checking while ignoring placement * hints such as HIGHMEM usage. */ #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\ __GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\ __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\ __GFP_NOLOCKDEP) /* The GFP flags allowed during early boot */ #define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS)) /* Control allocation cpuset and node placement constraints */ #define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE) /* Do not use these with a slab allocator */ #define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK) /* * Different from WARN_ON_ONCE(), no warning will be issued * when we specify __GFP_NOWARN. */ #define WARN_ON_ONCE_GFP(cond, gfp) ({ \ static bool __section(".data..once") __warned; \ int __ret_warn_once = !!(cond); \ \ if (unlikely(!(gfp & __GFP_NOWARN) && __ret_warn_once && !__warned)) { \ __warned = true; \ WARN_ON(1); \ } \ unlikely(__ret_warn_once); \ }) void page_writeback_init(void); /* * If a 16GB hugetlb folio were mapped by PTEs of all of its 4kB pages, * its nr_pages_mapped would be 0x400000: choose the ENTIRELY_MAPPED bit * above that range, instead of 2*(PMD_SIZE/PAGE_SIZE). Hugetlb currently * leaves nr_pages_mapped at 0, but avoid surprise if it participates later. */ #define ENTIRELY_MAPPED 0x800000 #define FOLIO_PAGES_MAPPED (ENTIRELY_MAPPED - 1) /* * Flags passed to __show_mem() and show_free_areas() to suppress output in * various contexts. */ #define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */ /* * How many individual pages have an elevated _mapcount. Excludes * the folio's entire_mapcount. * * Don't use this function outside of debugging code. */ static inline int folio_nr_pages_mapped(const struct folio *folio) { return atomic_read(&folio->_nr_pages_mapped) & FOLIO_PAGES_MAPPED; } /* * Retrieve the first entry of a folio based on a provided entry within the * folio. We cannot rely on folio->swap as there is no guarantee that it has * been initialized. Used for calling arch_swap_restore() */ static inline swp_entry_t folio_swap(swp_entry_t entry, const struct folio *folio) { swp_entry_t swap = { .val = ALIGN_DOWN(entry.val, folio_nr_pages(folio)), }; return swap; } static inline void *folio_raw_mapping(const struct folio *folio) { unsigned long mapping = (unsigned long)folio->mapping; return (void *)(mapping & ~PAGE_MAPPING_FLAGS); } /* * This is a file-backed mapping, and is about to be memory mapped - invoke its * mmap hook and safely handle error conditions. On error, VMA hooks will be * mutated. * * @file: File which backs the mapping. * @vma: VMA which we are mapping. * * Returns: 0 if success, error otherwise. */ static inline int mmap_file(struct file *file, struct vm_area_struct *vma) { int err = call_mmap(file, vma); if (likely(!err)) return 0; /* * OK, we tried to call the file hook for mmap(), but an error * arose. The mapping is in an inconsistent state and we most not invoke * any further hooks on it. */ vma->vm_ops = &vma_dummy_vm_ops; return err; } /* * If the VMA has a close hook then close it, and since closing it might leave * it in an inconsistent state which makes the use of any hooks suspect, clear * them down by installing dummy empty hooks. */ static inline void vma_close(struct vm_area_struct *vma) { if (vma->vm_ops && vma->vm_ops->close) { vma->vm_ops->close(vma); /* * The mapping is in an inconsistent state, and no further hooks * may be invoked upon it. */ vma->vm_ops = &vma_dummy_vm_ops; } } #ifdef CONFIG_MMU /* Flags for folio_pte_batch(). */ typedef int __bitwise fpb_t; /* Compare PTEs after pte_mkclean(), ignoring the dirty bit. */ #define FPB_IGNORE_DIRTY ((__force fpb_t)BIT(0)) /* Compare PTEs after pte_clear_soft_dirty(), ignoring the soft-dirty bit. */ #define FPB_IGNORE_SOFT_DIRTY ((__force fpb_t)BIT(1)) static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags) { if (flags & FPB_IGNORE_DIRTY) pte = pte_mkclean(pte); if (likely(flags & FPB_IGNORE_SOFT_DIRTY)) pte = pte_clear_soft_dirty(pte); return pte_wrprotect(pte_mkold(pte)); } /** * folio_pte_batch - detect a PTE batch for a large folio * @folio: The large folio to detect a PTE batch for. * @addr: The user virtual address the first page is mapped at. * @start_ptep: Page table pointer for the first entry. * @pte: Page table entry for the first page. * @max_nr: The maximum number of table entries to consider. * @flags: Flags to modify the PTE batch semantics. * @any_writable: Optional pointer to indicate whether any entry except the * first one is writable. * @any_young: Optional pointer to indicate whether any entry except the * first one is young. * @any_dirty: Optional pointer to indicate whether any entry except the * first one is dirty. * * Detect a PTE batch: consecutive (present) PTEs that map consecutive * pages of the same large folio. * * All PTEs inside a PTE batch have the same PTE bits set, excluding the PFN, * the accessed bit, writable bit, dirty bit (with FPB_IGNORE_DIRTY) and * soft-dirty bit (with FPB_IGNORE_SOFT_DIRTY). * * start_ptep must map any page of the folio. max_nr must be at least one and * must be limited by the caller so scanning cannot exceed a single page table. * * Return: the number of table entries in the batch. */ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags, bool *any_writable, bool *any_young, bool *any_dirty) { unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio); const pte_t *end_ptep = start_ptep + max_nr; pte_t expected_pte, *ptep; bool writable, young, dirty; int nr; if (any_writable) *any_writable = false; if (any_young) *any_young = false; if (any_dirty) *any_dirty = false; VM_WARN_ON_FOLIO(!pte_present(pte), folio); VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio); VM_WARN_ON_FOLIO(page_folio(pfn_to_page(pte_pfn(pte))) != folio, folio); nr = pte_batch_hint(start_ptep, pte); expected_pte = __pte_batch_clear_ignored(pte_advance_pfn(pte, nr), flags); ptep = start_ptep + nr; while (ptep < end_ptep) { pte = ptep_get(ptep); if (any_writable) writable = !!pte_write(pte); if (any_young) young = !!pte_young(pte); if (any_dirty) dirty = !!pte_dirty(pte); pte = __pte_batch_clear_ignored(pte, flags); if (!pte_same(pte, expected_pte)) break; /* * Stop immediately once we reached the end of the folio. In * corner cases the next PFN might fall into a different * folio. */ if (pte_pfn(pte) >= folio_end_pfn) break; if (any_writable) *any_writable |= writable; if (any_young) *any_young |= young; if (any_dirty) *any_dirty |= dirty; nr = pte_batch_hint(ptep, pte); expected_pte = pte_advance_pfn(expected_pte, nr); ptep += nr; } return min(ptep - start_ptep, max_nr); } /** * pte_move_swp_offset - Move the swap entry offset field of a swap pte * forward or backward by delta * @pte: The initial pte state; is_swap_pte(pte) must be true and * non_swap_entry() must be false. * @delta: The direction and the offset we are moving; forward if delta * is positive; backward if delta is negative * * Moves the swap offset, while maintaining all other fields, including * swap type, and any swp pte bits. The resulting pte is returned. */ static inline pte_t pte_move_swp_offset(pte_t pte, long delta) { swp_entry_t entry = pte_to_swp_entry(pte); pte_t new = __swp_entry_to_pte(__swp_entry(swp_type(entry), (swp_offset(entry) + delta))); if (pte_swp_soft_dirty(pte)) new = pte_swp_mksoft_dirty(new); if (pte_swp_exclusive(pte)) new = pte_swp_mkexclusive(new); if (pte_swp_uffd_wp(pte)) new = pte_swp_mkuffd_wp(new); return new; } /** * pte_next_swp_offset - Increment the swap entry offset field of a swap pte. * @pte: The initial pte state; is_swap_pte(pte) must be true and * non_swap_entry() must be false. * * Increments the swap offset, while maintaining all other fields, including * swap type, and any swp pte bits. The resulting pte is returned. */ static inline pte_t pte_next_swp_offset(pte_t pte) { return pte_move_swp_offset(pte, 1); } /** * swap_pte_batch - detect a PTE batch for a set of contiguous swap entries * @start_ptep: Page table pointer for the first entry. * @max_nr: The maximum number of table entries to consider. * @pte: Page table entry for the first entry. * * Detect a batch of contiguous swap entries: consecutive (non-present) PTEs * containing swap entries all with consecutive offsets and targeting the same * swap type, all with matching swp pte bits. * * max_nr must be at least one and must be limited by the caller so scanning * cannot exceed a single page table. * * Return: the number of table entries in the batch. */ static inline int swap_pte_batch(pte_t *start_ptep, int max_nr, pte_t pte) { pte_t expected_pte = pte_next_swp_offset(pte); const pte_t *end_ptep = start_ptep + max_nr; swp_entry_t entry = pte_to_swp_entry(pte); pte_t *ptep = start_ptep + 1; unsigned short cgroup_id; VM_WARN_ON(max_nr < 1); VM_WARN_ON(!is_swap_pte(pte)); VM_WARN_ON(non_swap_entry(entry)); cgroup_id = lookup_swap_cgroup_id(entry); while (ptep < end_ptep) { pte = ptep_get(ptep); if (!pte_same(pte, expected_pte)) break; if (lookup_swap_cgroup_id(pte_to_swp_entry(pte)) != cgroup_id) break; expected_pte = pte_next_swp_offset(expected_pte); ptep++; } return ptep - start_ptep; } #endif /* CONFIG_MMU */ void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio, int nr_throttled); static inline void acct_reclaim_writeback(struct folio *folio) { pg_data_t *pgdat = folio_pgdat(folio); int nr_throttled = atomic_read(&pgdat->nr_writeback_throttled); if (nr_throttled) __acct_reclaim_writeback(pgdat, folio, nr_throttled); } static inline void wake_throttle_isolated(pg_data_t *pgdat) { wait_queue_head_t *wqh; wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_ISOLATED]; if (waitqueue_active(wqh)) wake_up(wqh); } vm_fault_t __vmf_anon_prepare(struct vm_fault *vmf); static inline vm_fault_t vmf_anon_prepare(struct vm_fault *vmf) { vm_fault_t ret = __vmf_anon_prepare(vmf); if (unlikely(ret & VM_FAULT_RETRY)) vma_end_read(vmf->vma); return ret; } vm_fault_t do_swap_page(struct vm_fault *vmf); void folio_rotate_reclaimable(struct folio *folio); bool __folio_end_writeback(struct folio *folio); void deactivate_file_folio(struct folio *folio); void folio_activate(struct folio *folio); void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling, bool mm_wr_locked); void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte); struct zap_details; void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, struct zap_details *details); void page_cache_ra_order(struct readahead_control *, struct file_ra_state *, unsigned int order); void force_page_cache_ra(struct readahead_control *, unsigned long nr); static inline void force_page_cache_readahead(struct address_space *mapping, struct file *file, pgoff_t index, unsigned long nr_to_read) { DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, index); force_page_cache_ra(&ractl, nr_to_read); } unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices); unsigned find_get_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices); void filemap_free_folio(struct address_space *mapping, struct folio *folio); int truncate_inode_folio(struct address_space *mapping, struct folio *folio); bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end); long mapping_evict_folio(struct address_space *mapping, struct folio *folio); unsigned long mapping_try_invalidate(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_failed); /** * folio_evictable - Test whether a folio is evictable. * @folio: The folio to test. * * Test whether @folio is evictable -- i.e., should be placed on * active/inactive lists vs unevictable list. * * Reasons folio might not be evictable: * 1. folio's mapping marked unevictable * 2. One of the pages in the folio is part of an mlocked VMA */ static inline bool folio_evictable(struct folio *folio) { bool ret; /* Prevent address_space of inode and swap cache from being freed */ rcu_read_lock(); ret = !mapping_unevictable(folio_mapping(folio)) && !folio_test_mlocked(folio); rcu_read_unlock(); return ret; } /* * Turn a non-refcounted page (->_refcount == 0) into refcounted with * a count of one. */ static inline void set_page_refcounted(struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(page_ref_count(page), page); set_page_count(page, 1); } /* * Return true if a folio needs ->release_folio() calling upon it. */ static inline bool folio_needs_release(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); return folio_has_private(folio) || (mapping && mapping_release_always(mapping)); } extern unsigned long highest_memmap_pfn; /* * Maximum number of reclaim retries without progress before the OOM * killer is consider the only way forward. */ #define MAX_RECLAIM_RETRIES 16 /* * in mm/vmscan.c: */ bool folio_isolate_lru(struct folio *folio); void folio_putback_lru(struct folio *folio); extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason); /* * in mm/rmap.c: */ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address); /* * in mm/page_alloc.c */ #define K(x) ((x) << (PAGE_SHIFT-10)) extern char * const zone_names[MAX_NR_ZONES]; /* perform sanity checks on struct pages being allocated or freed */ DECLARE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled); extern int min_free_kbytes; void setup_per_zone_wmarks(void); void calculate_min_free_kbytes(void); int __meminit init_per_zone_wmark_min(void); void page_alloc_sysctl_init(void); /* * Structure for holding the mostly immutable allocation parameters passed * between functions involved in allocations, including the alloc_pages* * family of functions. * * nodemask, migratetype and highest_zoneidx are initialized only once in * __alloc_pages() and then never change. * * zonelist, preferred_zone and highest_zoneidx are set first in * __alloc_pages() for the fast path, and might be later changed * in __alloc_pages_slowpath(). All other functions pass the whole structure * by a const pointer. */ struct alloc_context { struct zonelist *zonelist; nodemask_t *nodemask; struct zoneref *preferred_zoneref; int migratetype; /* * highest_zoneidx represents highest usable zone index of * the allocation request. Due to the nature of the zone, * memory on lower zone than the highest_zoneidx will be * protected by lowmem_reserve[highest_zoneidx]. * * highest_zoneidx is also used by reclaim/compaction to limit * the target zone since higher zone than this index cannot be * usable for this allocation request. */ enum zone_type highest_zoneidx; bool spread_dirty_pages; }; /* * This function returns the order of a free page in the buddy system. In * general, page_zone(page)->lock must be held by the caller to prevent the * page from being allocated in parallel and returning garbage as the order. * If a caller does not hold page_zone(page)->lock, it must guarantee that the * page cannot be allocated or merged in parallel. Alternatively, it must * handle invalid values gracefully, and use buddy_order_unsafe() below. */ static inline unsigned int buddy_order(struct page *page) { /* PageBuddy() must be checked by the caller */ return page_private(page); } /* * Like buddy_order(), but for callers who cannot afford to hold the zone lock. * PageBuddy() should be checked first by the caller to minimize race window, * and invalid values must be handled gracefully. * * READ_ONCE is used so that if the caller assigns the result into a local * variable and e.g. tests it for valid range before using, the compiler cannot * decide to remove the variable and inline the page_private(page) multiple * times, potentially observing different values in the tests and the actual * use of the result. */ #define buddy_order_unsafe(page) READ_ONCE(page_private(page)) /* * This function checks whether a page is free && is the buddy * we can coalesce a page and its buddy if * (a) the buddy is not in a hole (check before calling!) && * (b) the buddy is in the buddy system && * (c) a page and its buddy have the same order && * (d) a page and its buddy are in the same zone. * * For recording whether a page is in the buddy system, we set PageBuddy. * Setting, clearing, and testing PageBuddy is serialized by zone->lock. * * For recording page's order, we use page_private(page). */ static inline bool page_is_buddy(struct page *page, struct page *buddy, unsigned int order) { if (!page_is_guard(buddy) && !PageBuddy(buddy)) return false; if (buddy_order(buddy) != order) return false; /* * zone check is done late to avoid uselessly calculating * zone/node ids for pages that could never merge. */ if (page_zone_id(page) != page_zone_id(buddy)) return false; VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); return true; } /* * Locate the struct page for both the matching buddy in our * pair (buddy1) and the combined O(n+1) page they form (page). * * 1) Any buddy B1 will have an order O twin B2 which satisfies * the following equation: * B2 = B1 ^ (1 << O) * For example, if the starting buddy (buddy2) is #8 its order * 1 buddy is #10: * B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10 * * 2) Any buddy B will have an order O+1 parent P which * satisfies the following equation: * P = B & ~(1 << O) * * Assumption: *_mem_map is contiguous at least up to MAX_PAGE_ORDER */ static inline unsigned long __find_buddy_pfn(unsigned long page_pfn, unsigned int order) { return page_pfn ^ (1 << order); } /* * Find the buddy of @page and validate it. * @page: The input page * @pfn: The pfn of the page, it saves a call to page_to_pfn() when the * function is used in the performance-critical __free_one_page(). * @order: The order of the page * @buddy_pfn: The output pointer to the buddy pfn, it also saves a call to * page_to_pfn(). * * The found buddy can be a non PageBuddy, out of @page's zone, or its order is * not the same as @page. The validation is necessary before use it. * * Return: the found buddy page or NULL if not found. */ static inline struct page *find_buddy_page_pfn(struct page *page, unsigned long pfn, unsigned int order, unsigned long *buddy_pfn) { unsigned long __buddy_pfn = __find_buddy_pfn(pfn, order); struct page *buddy; buddy = page + (__buddy_pfn - pfn); if (buddy_pfn) *buddy_pfn = __buddy_pfn; if (page_is_buddy(page, buddy, order)) return buddy; return NULL; } extern struct page *__pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone); static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone) { if (zone->contiguous) return pfn_to_page(start_pfn); return __pageblock_pfn_to_page(start_pfn, end_pfn, zone); } void set_zone_contiguous(struct zone *zone); static inline void clear_zone_contiguous(struct zone *zone) { zone->contiguous = false; } extern int __isolate_free_page(struct page *page, unsigned int order); extern void __putback_isolated_page(struct page *page, unsigned int order, int mt); extern void memblock_free_pages(struct page *page, unsigned long pfn, unsigned int order); extern void __free_pages_core(struct page *page, unsigned int order, enum meminit_context context); /* * This will have no effect, other than possibly generating a warning, if the * caller passes in a non-large folio. */ static inline void folio_set_order(struct folio *folio, unsigned int order) { if (WARN_ON_ONCE(!order || !folio_test_large(folio))) return; folio->_flags_1 = (folio->_flags_1 & ~0xffUL) | order; #ifdef CONFIG_64BIT folio->_folio_nr_pages = 1U << order; #endif } bool __folio_unqueue_deferred_split(struct folio *folio); static inline bool folio_unqueue_deferred_split(struct folio *folio) { if (folio_order(folio) <= 1 || !folio_test_large_rmappable(folio)) return false; /* * At this point, there is no one trying to add the folio to * deferred_list. If folio is not in deferred_list, it's safe * to check without acquiring the split_queue_lock. */ if (data_race(list_empty(&folio->_deferred_list))) return false; return __folio_unqueue_deferred_split(folio); } static inline struct folio *page_rmappable_folio(struct page *page) { struct folio *folio = (struct folio *)page; if (folio && folio_test_large(folio)) folio_set_large_rmappable(folio); return folio; } static inline void prep_compound_head(struct page *page, unsigned int order) { struct folio *folio = (struct folio *)page; folio_set_order(folio, order); atomic_set(&folio->_large_mapcount, -1); atomic_set(&folio->_entire_mapcount, -1); atomic_set(&folio->_nr_pages_mapped, 0); atomic_set(&folio->_pincount, 0); if (order > 1) INIT_LIST_HEAD(&folio->_deferred_list); } static inline void prep_compound_tail(struct page *head, int tail_idx) { struct page *p = head + tail_idx; p->mapping = TAIL_MAPPING; set_compound_head(p, head); set_page_private(p, 0); } extern void prep_compound_page(struct page *page, unsigned int order); extern void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags); extern bool free_pages_prepare(struct page *page, unsigned int order); extern int user_min_free_kbytes; void free_unref_page(struct page *page, unsigned int order); void free_unref_folios(struct folio_batch *fbatch); extern void zone_pcp_reset(struct zone *zone); extern void zone_pcp_disable(struct zone *zone); extern void zone_pcp_enable(struct zone *zone); extern void zone_pcp_init(struct zone *zone); extern void *memmap_alloc(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, int nid, bool exact_nid); void memmap_init_range(unsigned long, int, unsigned long, unsigned long, unsigned long, enum meminit_context, struct vmem_altmap *, int); #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* * in mm/compaction.c */ /* * compact_control is used to track pages being migrated and the free pages * they are being migrated to during memory compaction. The free_pfn starts * at the end of a zone and migrate_pfn begins at the start. Movable pages * are moved to the end of a zone during a compaction run and the run * completes when free_pfn <= migrate_pfn */ struct compact_control { struct list_head freepages[NR_PAGE_ORDERS]; /* List of free pages to migrate to */ struct list_head migratepages; /* List of pages being migrated */ unsigned int nr_freepages; /* Number of isolated free pages */ unsigned int nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ /* * Acts as an in/out parameter to page isolation for migration. * isolate_migratepages uses it as a search base. * isolate_migratepages_block will update the value to the next pfn * after the last isolated one. */ unsigned long migrate_pfn; unsigned long fast_start_pfn; /* a pfn to start linear scan from */ struct zone *zone; unsigned long total_migrate_scanned; unsigned long total_free_scanned; unsigned short fast_search_fail;/* failures to use free list searches */ short search_order; /* order to start a fast search at */ const gfp_t gfp_mask; /* gfp mask of a direct compactor */ int order; /* order a direct compactor needs */ int migratetype; /* migratetype of direct compactor */ const unsigned int alloc_flags; /* alloc flags of a direct compactor */ const int highest_zoneidx; /* zone index of a direct compactor */ enum migrate_mode mode; /* Async or sync migration mode */ bool ignore_skip_hint; /* Scan blocks even if marked skip */ bool no_set_skip_hint; /* Don't mark blocks for skipping */ bool ignore_block_suitable; /* Scan blocks considered unsuitable */ bool direct_compaction; /* False from kcompactd or /proc/... */ bool proactive_compaction; /* kcompactd proactive compaction */ bool whole_zone; /* Whole zone should/has been scanned */ bool contended; /* Signal lock contention */ bool finish_pageblock; /* Scan the remainder of a pageblock. Used * when there are potentially transient * isolation or migration failures to * ensure forward progress. */ bool alloc_contig; /* alloc_contig_range allocation */ }; /* * Used in direct compaction when a page should be taken from the freelists * immediately when one is created during the free path. */ struct capture_control { struct compact_control *cc; struct page *page; }; unsigned long isolate_freepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn); int isolate_migratepages_range(struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn); int __alloc_contig_migrate_range(struct compact_control *cc, unsigned long start, unsigned long end, int migratetype); /* Free whole pageblock and set its migration type to MIGRATE_CMA. */ void init_cma_reserved_pageblock(struct page *page); #endif /* CONFIG_COMPACTION || CONFIG_CMA */ int find_suitable_fallback(struct free_area *area, unsigned int order, int migratetype, bool only_stealable, bool *can_steal); static inline bool free_area_empty(struct free_area *area, int migratetype) { return list_empty(&area->free_list[migratetype]); } /* mm/util.c */ struct anon_vma *folio_anon_vma(const struct folio *folio); #ifdef CONFIG_MMU void unmap_mapping_folio(struct folio *folio); extern long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *locked); extern long faultin_page_range(struct mm_struct *mm, unsigned long start, unsigned long end, bool write, int *locked); extern bool mlock_future_ok(struct mm_struct *mm, unsigned long flags, unsigned long bytes); /* * NOTE: This function can't tell whether the folio is "fully mapped" in the * range. * "fully mapped" means all the pages of folio is associated with the page * table of range while this function just check whether the folio range is * within the range [start, end). Function caller needs to do page table * check if it cares about the page table association. * * Typical usage (like mlock or madvise) is: * Caller knows at least 1 page of folio is associated with page table of VMA * and the range [start, end) is intersect with the VMA range. Caller wants * to know whether the folio is fully associated with the range. It calls * this function to check whether the folio is in the range first. Then checks * the page table to know whether the folio is fully mapped to the range. */ static inline bool folio_within_range(struct folio *folio, struct vm_area_struct *vma, unsigned long start, unsigned long end) { pgoff_t pgoff, addr; unsigned long vma_pglen = vma_pages(vma); VM_WARN_ON_FOLIO(folio_test_ksm(folio), folio); if (start > end) return false; if (start < vma->vm_start) start = vma->vm_start; if (end > vma->vm_end) end = vma->vm_end; pgoff = folio_pgoff(folio); /* if folio start address is not in vma range */ if (!in_range(pgoff, vma->vm_pgoff, vma_pglen)) return false; addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); return !(addr < start || end - addr < folio_size(folio)); } static inline bool folio_within_vma(struct folio *folio, struct vm_area_struct *vma) { return folio_within_range(folio, vma, vma->vm_start, vma->vm_end); } /* * mlock_vma_folio() and munlock_vma_folio(): * should be called with vma's mmap_lock held for read or write, * under page table lock for the pte/pmd being added or removed. * * mlock is usually called at the end of folio_add_*_rmap_*(), munlock at * the end of folio_remove_rmap_*(); but new anon folios are managed by * folio_add_lru_vma() calling mlock_new_folio(). */ void mlock_folio(struct folio *folio); static inline void mlock_vma_folio(struct folio *folio, struct vm_area_struct *vma) { /* * The VM_SPECIAL check here serves two purposes. * 1) VM_IO check prevents migration from double-counting during mlock. * 2) Although mmap_region() and mlock_fixup() take care that VM_LOCKED * is never left set on a VM_SPECIAL vma, there is an interval while * file->f_op->mmap() is using vm_insert_page(s), when VM_LOCKED may * still be set while VM_SPECIAL bits are added: so ignore it then. */ if (unlikely((vma->vm_flags & (VM_LOCKED|VM_SPECIAL)) == VM_LOCKED)) mlock_folio(folio); } void munlock_folio(struct folio *folio); static inline void munlock_vma_folio(struct folio *folio, struct vm_area_struct *vma) { /* * munlock if the function is called. Ideally, we should only * do munlock if any page of folio is unmapped from VMA and * cause folio not fully mapped to VMA. * * But it's not easy to confirm that's the situation. So we * always munlock the folio and page reclaim will correct it * if it's wrong. */ if (unlikely(vma->vm_flags & VM_LOCKED)) munlock_folio(folio); } void mlock_new_folio(struct folio *folio); bool need_mlock_drain(int cpu); void mlock_drain_local(void); void mlock_drain_remote(int cpu); extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); /** * vma_address - Find the virtual address a page range is mapped at * @vma: The vma which maps this object. * @pgoff: The page offset within its object. * @nr_pages: The number of pages to consider. * * If any page in this range is mapped by this VMA, return the first address * where any of these pages appear. Otherwise, return -EFAULT. */ static inline unsigned long vma_address(const struct vm_area_struct *vma, pgoff_t pgoff, unsigned long nr_pages) { unsigned long address; if (pgoff >= vma->vm_pgoff) { address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); /* Check for address beyond vma (or wrapped through 0?) */ if (address < vma->vm_start || address >= vma->vm_end) address = -EFAULT; } else if (pgoff + nr_pages - 1 >= vma->vm_pgoff) { /* Test above avoids possibility of wrap to 0 on 32-bit */ address = vma->vm_start; } else { address = -EFAULT; } return address; } /* * Then at what user virtual address will none of the range be found in vma? * Assumes that vma_address() already returned a good starting address. */ static inline unsigned long vma_address_end(struct page_vma_mapped_walk *pvmw) { struct vm_area_struct *vma = pvmw->vma; pgoff_t pgoff; unsigned long address; /* Common case, plus ->pgoff is invalid for KSM */ if (pvmw->nr_pages == 1) return pvmw->address + PAGE_SIZE; pgoff = pvmw->pgoff + pvmw->nr_pages; address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); /* Check for address beyond vma (or wrapped through 0?) */ if (address < vma->vm_start || address > vma->vm_end) address = vma->vm_end; return address; } static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, struct file *fpin) { int flags = vmf->flags; if (fpin) return fpin; /* * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or * anything, so we only pin the file and drop the mmap_lock if only * FAULT_FLAG_ALLOW_RETRY is set, while this is the first attempt. */ if (fault_flag_allow_retry_first(flags) && !(flags & FAULT_FLAG_RETRY_NOWAIT)) { fpin = get_file(vmf->vma->vm_file); release_fault_lock(vmf); } return fpin; } #else /* !CONFIG_MMU */ static inline void unmap_mapping_folio(struct folio *folio) { } static inline void mlock_new_folio(struct folio *folio) { } static inline bool need_mlock_drain(int cpu) { return false; } static inline void mlock_drain_local(void) { } static inline void mlock_drain_remote(int cpu) { } static inline void vunmap_range_noflush(unsigned long start, unsigned long end) { } #endif /* !CONFIG_MMU */ /* Memory initialisation debug and verification */ #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT DECLARE_STATIC_KEY_TRUE(deferred_pages); bool __init deferred_grow_zone(struct zone *zone, unsigned int order); #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ enum mminit_level { MMINIT_WARNING, MMINIT_VERIFY, MMINIT_TRACE }; #ifdef CONFIG_DEBUG_MEMORY_INIT extern int mminit_loglevel; #define mminit_dprintk(level, prefix, fmt, arg...) \ do { \ if (level < mminit_loglevel) { \ if (level <= MMINIT_WARNING) \ pr_warn("mminit::" prefix " " fmt, ##arg); \ else \ printk(KERN_DEBUG "mminit::" prefix " " fmt, ##arg); \ } \ } while (0) extern void mminit_verify_pageflags_layout(void); extern void mminit_verify_zonelist(void); #else static inline void mminit_dprintk(enum mminit_level level, const char *prefix, const char *fmt, ...) { } static inline void mminit_verify_pageflags_layout(void) { } static inline void mminit_verify_zonelist(void) { } #endif /* CONFIG_DEBUG_MEMORY_INIT */ #define NODE_RECLAIM_NOSCAN -2 #define NODE_RECLAIM_FULL -1 #define NODE_RECLAIM_SOME 0 #define NODE_RECLAIM_SUCCESS 1 #ifdef CONFIG_NUMA extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int); extern int find_next_best_node(int node, nodemask_t *used_node_mask); #else static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask, unsigned int order) { return NODE_RECLAIM_NOSCAN; } static inline int find_next_best_node(int node, nodemask_t *used_node_mask) { return NUMA_NO_NODE; } #endif /* * mm/memory-failure.c */ #ifdef CONFIG_MEMORY_FAILURE void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu); void shake_folio(struct folio *folio); extern int hwpoison_filter(struct page *p); extern u32 hwpoison_filter_dev_major; extern u32 hwpoison_filter_dev_minor; extern u64 hwpoison_filter_flags_mask; extern u64 hwpoison_filter_flags_value; extern u64 hwpoison_filter_memcg; extern u32 hwpoison_filter_enable; #define MAGIC_HWPOISON 0x48575053U /* HWPS */ void SetPageHWPoisonTakenOff(struct page *page); void ClearPageHWPoisonTakenOff(struct page *page); bool take_page_off_buddy(struct page *page); bool put_page_back_buddy(struct page *page); struct task_struct *task_early_kill(struct task_struct *tsk, int force_early); void add_to_kill_ksm(struct task_struct *tsk, const struct page *p, struct vm_area_struct *vma, struct list_head *to_kill, unsigned long ksm_addr); unsigned long page_mapped_in_vma(const struct page *page, struct vm_area_struct *vma); #else static inline void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu) { } #endif extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); extern void set_pageblock_order(void); struct folio *alloc_migrate_folio(struct folio *src, unsigned long private); unsigned long reclaim_pages(struct list_head *folio_list); unsigned int reclaim_clean_pages_from_list(struct zone *zone, struct list_head *folio_list); /* The ALLOC_WMARK bits are used as an index to zone->watermark */ #define ALLOC_WMARK_MIN WMARK_MIN #define ALLOC_WMARK_LOW WMARK_LOW #define ALLOC_WMARK_HIGH WMARK_HIGH #define ALLOC_NO_WATERMARKS 0x04 /* don't check watermarks at all */ /* Mask to get the watermark bits */ #define ALLOC_WMARK_MASK (ALLOC_NO_WATERMARKS-1) /* * Only MMU archs have async oom victim reclaim - aka oom_reaper so we * cannot assume a reduced access to memory reserves is sufficient for * !MMU */ #ifdef CONFIG_MMU #define ALLOC_OOM 0x08 #else #define ALLOC_OOM ALLOC_NO_WATERMARKS #endif #define ALLOC_NON_BLOCK 0x10 /* Caller cannot block. Allow access * to 25% of the min watermark or * 62.5% if __GFP_HIGH is set. */ #define ALLOC_MIN_RESERVE 0x20 /* __GFP_HIGH set. Allow access to 50% * of the min watermark. */ #define ALLOC_CPUSET 0x40 /* check for correct cpuset */ #define ALLOC_CMA 0x80 /* allow allocations from CMA areas */ #ifdef CONFIG_ZONE_DMA32 #define ALLOC_NOFRAGMENT 0x100 /* avoid mixing pageblock types */ #else #define ALLOC_NOFRAGMENT 0x0 #endif #define ALLOC_HIGHATOMIC 0x200 /* Allows access to MIGRATE_HIGHATOMIC */ #define ALLOC_KSWAPD 0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */ /* Flags that allow allocations below the min watermark. */ #define ALLOC_RESERVES (ALLOC_NON_BLOCK|ALLOC_MIN_RESERVE|ALLOC_HIGHATOMIC|ALLOC_OOM) enum ttu_flags; struct tlbflush_unmap_batch; /* * only for MM internal work items which do not depend on * any allocations or locks which might depend on allocations */ extern struct workqueue_struct *mm_percpu_wq; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH void try_to_unmap_flush(void); void try_to_unmap_flush_dirty(void); void flush_tlb_batched_pending(struct mm_struct *mm); #else static inline void try_to_unmap_flush(void) { } static inline void try_to_unmap_flush_dirty(void) { } static inline void flush_tlb_batched_pending(struct mm_struct *mm) { } #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ extern const struct trace_print_flags pageflag_names[]; extern const struct trace_print_flags vmaflag_names[]; extern const struct trace_print_flags gfpflag_names[]; static inline bool is_migrate_highatomic(enum migratetype migratetype) { return migratetype == MIGRATE_HIGHATOMIC; } void setup_zone_pageset(struct zone *zone); struct migration_target_control { int nid; /* preferred node id */ nodemask_t *nmask; gfp_t gfp_mask; enum migrate_reason reason; }; /* * mm/filemap.c */ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, struct folio *folio, loff_t fpos, size_t size); /* * mm/vmalloc.c */ #ifdef CONFIG_MMU void __init vmalloc_init(void); int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift); unsigned int get_vm_area_page_order(struct vm_struct *vm); #else static inline void vmalloc_init(void) { } static inline int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift) { return -EINVAL; } #endif int __must_check __vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift); void vunmap_range_noflush(unsigned long start, unsigned long end); void __vunmap_range_noflush(unsigned long start, unsigned long end); int numa_migrate_check(struct folio *folio, struct vm_fault *vmf, unsigned long addr, int *flags, bool writable, int *last_cpupid); void free_zone_device_folio(struct folio *folio); int migrate_device_coherent_folio(struct folio *folio); struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long align, unsigned long shift, unsigned long flags, unsigned long start, unsigned long end, int node, gfp_t gfp_mask, const void *caller); /* * mm/gup.c */ int __must_check try_grab_folio(struct folio *folio, int refs, unsigned int flags); /* * mm/huge_memory.c */ void touch_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, bool write); void touch_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, bool write); static inline bool alloc_zeroed(void) { return static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, &init_on_alloc); } /* * Parses a string with mem suffixes into its order. Useful to parse kernel * parameters. */ static inline int get_order_from_str(const char *size_str, unsigned long valid_orders) { unsigned long size; char *endptr; int order; size = memparse(size_str, &endptr); if (!is_power_of_2(size)) return -EINVAL; order = get_order(size); if (BIT(order) & ~valid_orders) return -EINVAL; return order; } enum { /* mark page accessed */ FOLL_TOUCH = 1 << 16, /* a retry, previous pass started an IO */ FOLL_TRIED = 1 << 17, /* we are working on non-current tsk/mm */ FOLL_REMOTE = 1 << 18, /* pages must be released via unpin_user_page */ FOLL_PIN = 1 << 19, /* gup_fast: prevent fall-back to slow gup */ FOLL_FAST_ONLY = 1 << 20, /* allow unlocking the mmap lock */ FOLL_UNLOCKABLE = 1 << 21, /* VMA lookup+checks compatible with MADV_POPULATE_(READ|WRITE) */ FOLL_MADV_POPULATE = 1 << 22, }; #define INTERNAL_GUP_FLAGS (FOLL_TOUCH | FOLL_TRIED | FOLL_REMOTE | FOLL_PIN | \ FOLL_FAST_ONLY | FOLL_UNLOCKABLE | \ FOLL_MADV_POPULATE) /* * Indicates for which pages that are write-protected in the page table, * whether GUP has to trigger unsharing via FAULT_FLAG_UNSHARE such that the * GUP pin will remain consistent with the pages mapped into the page tables * of the MM. * * Temporary unmapping of PageAnonExclusive() pages or clearing of * PageAnonExclusive() has to protect against concurrent GUP: * * Ordinary GUP: Using the PT lock * * GUP-fast and fork(): mm->write_protect_seq * * GUP-fast and KSM or temporary unmapping (swap, migration): see * folio_try_share_anon_rmap_*() * * Must be called with the (sub)page that's actually referenced via the * page table entry, which might not necessarily be the head page for a * PTE-mapped THP. * * If the vma is NULL, we're coming from the GUP-fast path and might have * to fallback to the slow path just to lookup the vma. */ static inline bool gup_must_unshare(struct vm_area_struct *vma, unsigned int flags, struct page *page) { /* * FOLL_WRITE is implicitly handled correctly as the page table entry * has to be writable -- and if it references (part of) an anonymous * folio, that part is required to be marked exclusive. */ if ((flags & (FOLL_WRITE | FOLL_PIN)) != FOLL_PIN) return false; /* * Note: PageAnon(page) is stable until the page is actually getting * freed. */ if (!PageAnon(page)) { /* * We only care about R/O long-term pining: R/O short-term * pinning does not have the semantics to observe successive * changes through the process page tables. */ if (!(flags & FOLL_LONGTERM)) return false; /* We really need the vma ... */ if (!vma) return true; /* * ... because we only care about writable private ("COW") * mappings where we have to break COW early. */ return is_cow_mapping(vma->vm_flags); } /* Paired with a memory barrier in folio_try_share_anon_rmap_*(). */ if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_rmb(); /* * Note that KSM pages cannot be exclusive, and consequently, * cannot get pinned. */ return !PageAnonExclusive(page); } extern bool mirrored_kernelcore; extern bool memblock_has_mirror(void); static __always_inline void vma_set_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff) { vma->vm_start = start; vma->vm_end = end; vma->vm_pgoff = pgoff; } static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma) { /* * NOTE: we must check this before VM_SOFTDIRTY on soft-dirty * enablements, because when without soft-dirty being compiled in, * VM_SOFTDIRTY is defined as 0x0, then !(vm_flags & VM_SOFTDIRTY) * will be constantly true. */ if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY)) return false; /* * Soft-dirty is kind of special: its tracking is enabled when the * vma flags not set. */ return !(vma->vm_flags & VM_SOFTDIRTY); } static inline bool pmd_needs_soft_dirty_wp(struct vm_area_struct *vma, pmd_t pmd) { return vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd); } static inline bool pte_needs_soft_dirty_wp(struct vm_area_struct *vma, pte_t pte) { return vma_soft_dirty_enabled(vma) && !pte_soft_dirty(pte); } void __meminit __init_single_page(struct page *page, unsigned long pfn, unsigned long zone, int nid); /* shrinker related functions */ unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority); #ifdef CONFIG_64BIT static inline int can_do_mseal(unsigned long flags) { if (flags) return -EINVAL; return 0; } #else static inline int can_do_mseal(unsigned long flags) { return -EPERM; } #endif #ifdef CONFIG_SHRINKER_DEBUG static inline __printf(2, 0) int shrinker_debugfs_name_alloc( struct shrinker *shrinker, const char *fmt, va_list ap) { shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); return shrinker->name ? 0 : -ENOMEM; } static inline void shrinker_debugfs_name_free(struct shrinker *shrinker) { kfree_const(shrinker->name); shrinker->name = NULL; } extern int shrinker_debugfs_add(struct shrinker *shrinker); extern struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, int *debugfs_id); extern void shrinker_debugfs_remove(struct dentry *debugfs_entry, int debugfs_id); #else /* CONFIG_SHRINKER_DEBUG */ static inline int shrinker_debugfs_add(struct shrinker *shrinker) { return 0; } static inline int shrinker_debugfs_name_alloc(struct shrinker *shrinker, const char *fmt, va_list ap) { return 0; } static inline void shrinker_debugfs_name_free(struct shrinker *shrinker) { } static inline struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, int *debugfs_id) { *debugfs_id = -1; return NULL; } static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry, int debugfs_id) { } #endif /* CONFIG_SHRINKER_DEBUG */ /* Only track the nodes of mappings with shadow entries */ void workingset_update_node(struct xa_node *node); extern struct list_lru shadow_nodes; /* mremap.c */ unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long len, bool need_rmap_locks, bool for_stack); #ifdef CONFIG_UNACCEPTED_MEMORY void accept_page(struct page *page); #else /* CONFIG_UNACCEPTED_MEMORY */ static inline void accept_page(struct page *page) { } #endif /* CONFIG_UNACCEPTED_MEMORY */ /* pagewalk.c */ int walk_page_range_mm(struct mm_struct *mm, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, void *private); #endif /* __MM_INTERNAL_H */ |
| 400 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/mmu_context.h * * Copyright (C) 1996 Russell King. * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_MMU_CONTEXT_H #define __ASM_MMU_CONTEXT_H #ifndef __ASSEMBLY__ #include <linux/compiler.h> #include <linux/sched.h> #include <linux/sched/hotplug.h> #include <linux/mm_types.h> #include <linux/pgtable.h> #include <linux/pkeys.h> #include <asm/cacheflush.h> #include <asm/cpufeature.h> #include <asm/daifflags.h> #include <asm/gcs.h> #include <asm/proc-fns.h> #include <asm/cputype.h> #include <asm/sysreg.h> #include <asm/tlbflush.h> extern bool rodata_full; static inline void contextidr_thread_switch(struct task_struct *next) { if (!IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR)) return; write_sysreg(task_pid_nr(next), contextidr_el1); isb(); } /* * Set TTBR0 to reserved_pg_dir. No translations will be possible via TTBR0. */ static inline void cpu_set_reserved_ttbr0_nosync(void) { unsigned long ttbr = phys_to_ttbr(__pa_symbol(reserved_pg_dir)); write_sysreg(ttbr, ttbr0_el1); } static inline void cpu_set_reserved_ttbr0(void) { cpu_set_reserved_ttbr0_nosync(); isb(); } void cpu_do_switch_mm(phys_addr_t pgd_phys, struct mm_struct *mm); static inline void cpu_switch_mm(pgd_t *pgd, struct mm_struct *mm) { BUG_ON(pgd == swapper_pg_dir); cpu_do_switch_mm(virt_to_phys(pgd),mm); } /* * TCR.T0SZ value to use when the ID map is active. */ #define idmap_t0sz TCR_T0SZ(IDMAP_VA_BITS) /* * Ensure TCR.T0SZ is set to the provided value. */ static inline void __cpu_set_tcr_t0sz(unsigned long t0sz) { unsigned long tcr = read_sysreg(tcr_el1); if ((tcr & TCR_T0SZ_MASK) == t0sz) return; tcr &= ~TCR_T0SZ_MASK; tcr |= t0sz; write_sysreg(tcr, tcr_el1); isb(); } #define cpu_set_default_tcr_t0sz() __cpu_set_tcr_t0sz(TCR_T0SZ(vabits_actual)) #define cpu_set_idmap_tcr_t0sz() __cpu_set_tcr_t0sz(idmap_t0sz) /* * Remove the idmap from TTBR0_EL1 and install the pgd of the active mm. * * The idmap lives in the same VA range as userspace, but uses global entries * and may use a different TCR_EL1.T0SZ. To avoid issues resulting from * speculative TLB fetches, we must temporarily install the reserved page * tables while we invalidate the TLBs and set up the correct TCR_EL1.T0SZ. * * If current is a not a user task, the mm covers the TTBR1_EL1 page tables, * which should not be installed in TTBR0_EL1. In this case we can leave the * reserved page tables in place. */ static inline void cpu_uninstall_idmap(void) { struct mm_struct *mm = current->active_mm; cpu_set_reserved_ttbr0(); local_flush_tlb_all(); cpu_set_default_tcr_t0sz(); if (mm != &init_mm && !system_uses_ttbr0_pan()) cpu_switch_mm(mm->pgd, mm); } static inline void cpu_install_idmap(void) { cpu_set_reserved_ttbr0(); local_flush_tlb_all(); cpu_set_idmap_tcr_t0sz(); cpu_switch_mm(lm_alias(idmap_pg_dir), &init_mm); } /* * Load our new page tables. A strict BBM approach requires that we ensure that * TLBs are free of any entries that may overlap with the global mappings we are * about to install. * * For a real hibernate/resume/kexec cycle TTBR0 currently points to a zero * page, but TLBs may contain stale ASID-tagged entries (e.g. for EFI runtime * services), while for a userspace-driven test_resume cycle it points to * userspace page tables (and we must point it at a zero page ourselves). * * We change T0SZ as part of installing the idmap. This is undone by * cpu_uninstall_idmap() in __cpu_suspend_exit(). */ static inline void cpu_install_ttbr0(phys_addr_t ttbr0, unsigned long t0sz) { cpu_set_reserved_ttbr0(); local_flush_tlb_all(); __cpu_set_tcr_t0sz(t0sz); /* avoid cpu_switch_mm() and its SW-PAN and CNP interactions */ write_sysreg(ttbr0, ttbr0_el1); isb(); } void __cpu_replace_ttbr1(pgd_t *pgdp, bool cnp); static inline void cpu_enable_swapper_cnp(void) { __cpu_replace_ttbr1(lm_alias(swapper_pg_dir), true); } static inline void cpu_replace_ttbr1(pgd_t *pgdp) { /* * Only for early TTBR1 replacement before cpucaps are finalized and * before we've decided whether to use CNP. */ WARN_ON(system_capabilities_finalized()); __cpu_replace_ttbr1(pgdp, false); } /* * It would be nice to return ASIDs back to the allocator, but unfortunately * that introduces a race with a generation rollover where we could erroneously * free an ASID allocated in a future generation. We could workaround this by * freeing the ASID from the context of the dying mm (e.g. in arch_exit_mmap), * but we'd then need to make sure that we didn't dirty any TLBs afterwards. * Setting a reserved TTBR0 or EPD0 would work, but it all gets ugly when you * take CPU migration into account. */ void check_and_switch_context(struct mm_struct *mm); #define init_new_context(tsk, mm) init_new_context(tsk, mm) static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { atomic64_set(&mm->context.id, 0); refcount_set(&mm->context.pinned, 0); /* pkey 0 is the default, so always reserve it. */ mm->context.pkey_allocation_map = BIT(0); return 0; } static inline void arch_dup_pkeys(struct mm_struct *oldmm, struct mm_struct *mm) { /* Duplicate the oldmm pkey state in mm: */ mm->context.pkey_allocation_map = oldmm->context.pkey_allocation_map; } static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { arch_dup_pkeys(oldmm, mm); return 0; } static inline void arch_exit_mmap(struct mm_struct *mm) { } static inline void arch_unmap(struct mm_struct *mm, unsigned long start, unsigned long end) { } #ifdef CONFIG_ARM64_SW_TTBR0_PAN static inline void update_saved_ttbr0(struct task_struct *tsk, struct mm_struct *mm) { u64 ttbr; if (!system_uses_ttbr0_pan()) return; if (mm == &init_mm) ttbr = phys_to_ttbr(__pa_symbol(reserved_pg_dir)); else ttbr = phys_to_ttbr(virt_to_phys(mm->pgd)) | ASID(mm) << 48; WRITE_ONCE(task_thread_info(tsk)->ttbr0, ttbr); } #else static inline void update_saved_ttbr0(struct task_struct *tsk, struct mm_struct *mm) { } #endif #define enter_lazy_tlb enter_lazy_tlb static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) { /* * We don't actually care about the ttbr0 mapping, so point it at the * zero page. */ update_saved_ttbr0(tsk, &init_mm); } static inline void __switch_mm(struct mm_struct *next) { /* * init_mm.pgd does not contain any user mappings and it is always * active for kernel addresses in TTBR1. Just set the reserved TTBR0. */ if (next == &init_mm) { cpu_set_reserved_ttbr0(); return; } check_and_switch_context(next); } static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { if (prev != next) __switch_mm(next); /* * Update the saved TTBR0_EL1 of the scheduled-in task as the previous * value may have not been initialised yet (activate_mm caller) or the * ASID has changed since the last run (following the context switch * of another thread of the same process). */ update_saved_ttbr0(tsk, next); } static inline const struct cpumask * task_cpu_possible_mask(struct task_struct *p) { if (!static_branch_unlikely(&arm64_mismatched_32bit_el0)) return cpu_possible_mask; if (!is_compat_thread(task_thread_info(p))) return cpu_possible_mask; return system_32bit_el0_cpumask(); } #define task_cpu_possible_mask task_cpu_possible_mask void verify_cpu_asid_bits(void); void post_ttbr_update_workaround(void); unsigned long arm64_mm_context_get(struct mm_struct *mm); void arm64_mm_context_put(struct mm_struct *mm); #define mm_untag_mask mm_untag_mask static inline unsigned long mm_untag_mask(struct mm_struct *mm) { return -1UL >> 8; } /* * Only enforce protection keys on the current process, because there is no * user context to access POR_EL0 for another address space. */ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write, bool execute, bool foreign) { if (!system_supports_poe()) return true; /* allow access if the VMA is not one from this process */ if (foreign || vma_is_foreign(vma)) return true; return por_el0_allows_pkey(vma_pkey(vma), write, execute); } #define deactivate_mm deactivate_mm static inline void deactivate_mm(struct task_struct *tsk, struct mm_struct *mm) { gcs_free(tsk); } #include <asm-generic/mmu_context.h> #endif /* !__ASSEMBLY__ */ #endif /* !__ASM_MMU_CONTEXT_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 | /* SPDX-License-Identifier: GPL-2.0 */ /* * descriptor table internals; you almost certainly want file.h instead. */ #ifndef __LINUX_FDTABLE_H #define __LINUX_FDTABLE_H #include <linux/posix_types.h> #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/nospec.h> #include <linux/types.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/atomic.h> /* * The default fd array needs to be at least BITS_PER_LONG, * as this is the granularity returned by copy_fdset(). */ #define NR_OPEN_DEFAULT BITS_PER_LONG struct fdtable { unsigned int max_fds; struct file __rcu **fd; /* current fd array */ unsigned long *close_on_exec; unsigned long *open_fds; unsigned long *full_fds_bits; struct rcu_head rcu; }; /* * Open file table structure */ struct files_struct { /* * read mostly part */ atomic_t count; bool resize_in_progress; wait_queue_head_t resize_wait; struct fdtable __rcu *fdt; struct fdtable fdtab; /* * written part on a separate cache line in SMP */ spinlock_t file_lock ____cacheline_aligned_in_smp; unsigned int next_fd; unsigned long close_on_exec_init[1]; unsigned long open_fds_init[1]; unsigned long full_fds_bits_init[1]; struct file __rcu * fd_array[NR_OPEN_DEFAULT]; }; struct file_operations; struct vfsmount; struct dentry; #define rcu_dereference_check_fdtable(files, fdtfd) \ rcu_dereference_check((fdtfd), lockdep_is_held(&(files)->file_lock)) #define files_fdtable(files) \ rcu_dereference_check_fdtable((files), (files)->fdt) /* * The caller must ensure that fd table isn't shared or hold rcu or file lock */ static inline struct file *files_lookup_fd_raw(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = rcu_dereference_raw(files->fdt); unsigned long mask = array_index_mask_nospec(fd, fdt->max_fds); struct file *needs_masking; /* * 'mask' is zero for an out-of-bounds fd, all ones for ok. * 'fd&mask' is 'fd' for ok, or 0 for out of bounds. * * Accessing fdt->fd[0] is ok, but needs masking of the result. */ needs_masking = rcu_dereference_raw(fdt->fd[fd&mask]); return (struct file *)(mask & (unsigned long)needs_masking); } static inline struct file *files_lookup_fd_locked(struct files_struct *files, unsigned int fd) { RCU_LOCKDEP_WARN(!lockdep_is_held(&files->file_lock), "suspicious rcu_dereference_check() usage"); return files_lookup_fd_raw(files, fd); } static inline bool close_on_exec(unsigned int fd, const struct files_struct *files) { return test_bit(fd, files_fdtable(files)->close_on_exec); } struct task_struct; void put_files_struct(struct files_struct *fs); int unshare_files(void); struct fd_range { unsigned int from, to; }; struct files_struct *dup_fd(struct files_struct *, struct fd_range *) __latent_entropy; void do_close_on_exec(struct files_struct *); int iterate_fd(struct files_struct *, unsigned, int (*)(const void *, struct file *, unsigned), const void *); extern int close_fd(unsigned int fd); extern struct file *file_close_fd(unsigned int fd); extern struct kmem_cache *files_cachep; #endif /* __LINUX_FDTABLE_H */ |
| 1011 1042 723 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_ALTERNATIVE_MACROS_H #define __ASM_ALTERNATIVE_MACROS_H #include <linux/const.h> #include <vdso/bits.h> #include <asm/cpucaps.h> #include <asm/insn-def.h> /* * Binutils 2.27.0 can't handle a 'UL' suffix on constants, so for the assembly * macros below we must use we must use `(1 << ARM64_CB_SHIFT)`. */ #define ARM64_CB_SHIFT 15 #define ARM64_CB_BIT BIT(ARM64_CB_SHIFT) #if ARM64_NCAPS >= ARM64_CB_BIT #error "cpucaps have overflown ARM64_CB_BIT" #endif #ifndef __ASSEMBLY__ #include <linux/stringify.h> #define ALTINSTR_ENTRY(cpucap) \ " .word 661b - .\n" /* label */ \ " .word 663f - .\n" /* new instruction */ \ " .hword " __stringify(cpucap) "\n" /* cpucap */ \ " .byte 662b-661b\n" /* source len */ \ " .byte 664f-663f\n" /* replacement len */ #define ALTINSTR_ENTRY_CB(cpucap, cb) \ " .word 661b - .\n" /* label */ \ " .word " __stringify(cb) "- .\n" /* callback */ \ " .hword " __stringify(cpucap) "\n" /* cpucap */ \ " .byte 662b-661b\n" /* source len */ \ " .byte 664f-663f\n" /* replacement len */ /* * alternative assembly primitive: * * If any of these .org directive fail, it means that insn1 and insn2 * don't have the same length. This used to be written as * * .if ((664b-663b) != (662b-661b)) * .error "Alternatives instruction length mismatch" * .endif * * but most assemblers die if insn1 or insn2 have a .inst. This should * be fixed in a binutils release posterior to 2.25.51.0.2 (anything * containing commit 4e4d08cf7399b606 or c1baaddf8861). * * Alternatives with callbacks do not generate replacement instructions. */ #define __ALTERNATIVE_CFG(oldinstr, newinstr, cpucap, cfg_enabled) \ ".if "__stringify(cfg_enabled)" == 1\n" \ "661:\n\t" \ oldinstr "\n" \ "662:\n" \ ".pushsection .altinstructions,\"a\"\n" \ ALTINSTR_ENTRY(cpucap) \ ".popsection\n" \ ".subsection 1\n" \ "663:\n\t" \ newinstr "\n" \ "664:\n\t" \ ".org . - (664b-663b) + (662b-661b)\n\t" \ ".org . - (662b-661b) + (664b-663b)\n\t" \ ".previous\n" \ ".endif\n" #define __ALTERNATIVE_CFG_CB(oldinstr, cpucap, cfg_enabled, cb) \ ".if "__stringify(cfg_enabled)" == 1\n" \ "661:\n\t" \ oldinstr "\n" \ "662:\n" \ ".pushsection .altinstructions,\"a\"\n" \ ALTINSTR_ENTRY_CB(cpucap, cb) \ ".popsection\n" \ "663:\n\t" \ "664:\n\t" \ ".endif\n" #define _ALTERNATIVE_CFG(oldinstr, newinstr, cpucap, cfg, ...) \ __ALTERNATIVE_CFG(oldinstr, newinstr, cpucap, IS_ENABLED(cfg)) #define ALTERNATIVE_CB(oldinstr, cpucap, cb) \ __ALTERNATIVE_CFG_CB(oldinstr, (1 << ARM64_CB_SHIFT) | (cpucap), 1, cb) #else #include <asm/assembler.h> .macro altinstruction_entry orig_offset alt_offset cpucap orig_len alt_len .word \orig_offset - . .word \alt_offset - . .hword (\cpucap) .byte \orig_len .byte \alt_len .endm .macro alternative_insn insn1, insn2, cap, enable = 1 .if \enable 661: \insn1 662: .pushsection .altinstructions, "a" altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f .popsection .subsection 1 663: \insn2 664: .org . - (664b-663b) + (662b-661b) .org . - (662b-661b) + (664b-663b) .previous .endif .endm /* * Alternative sequences * * The code for the case where the capability is not present will be * assembled and linked as normal. There are no restrictions on this * code. * * The code for the case where the capability is present will be * assembled into a special section to be used for dynamic patching. * Code for that case must: * * 1. Be exactly the same length (in bytes) as the default code * sequence. * * 2. Not contain a branch target that is used outside of the * alternative sequence it is defined in (branches into an * alternative sequence are not fixed up). */ /* * Begin an alternative code sequence. */ .macro alternative_if_not cap .set .Lasm_alt_mode, 0 .pushsection .altinstructions, "a" altinstruction_entry 661f, 663f, \cap, 662f-661f, 664f-663f .popsection 661: .endm .macro alternative_if cap .set .Lasm_alt_mode, 1 .pushsection .altinstructions, "a" altinstruction_entry 663f, 661f, \cap, 664f-663f, 662f-661f .popsection .subsection 1 .align 2 /* So GAS knows label 661 is suitably aligned */ 661: .endm .macro alternative_cb cap, cb .set .Lasm_alt_mode, 0 .pushsection .altinstructions, "a" altinstruction_entry 661f, \cb, (1 << ARM64_CB_SHIFT) | \cap, 662f-661f, 0 .popsection 661: .endm /* * Provide the other half of the alternative code sequence. */ .macro alternative_else 662: .if .Lasm_alt_mode==0 .subsection 1 .else .previous .endif 663: .endm /* * Complete an alternative code sequence. */ .macro alternative_endif 664: .org . - (664b-663b) + (662b-661b) .org . - (662b-661b) + (664b-663b) .if .Lasm_alt_mode==0 .previous .endif .endm /* * Callback-based alternative epilogue */ .macro alternative_cb_end 662: .endm /* * Provides a trivial alternative or default sequence consisting solely * of NOPs. The number of NOPs is chosen automatically to match the * previous case. */ .macro alternative_else_nop_endif alternative_else nops (662b-661b) / AARCH64_INSN_SIZE alternative_endif .endm #define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...) \ alternative_insn insn1, insn2, cap, IS_ENABLED(cfg) #endif /* __ASSEMBLY__ */ /* * Usage: asm(ALTERNATIVE(oldinstr, newinstr, cpucap)); * * Usage: asm(ALTERNATIVE(oldinstr, newinstr, cpucap, CONFIG_FOO)); * N.B. If CONFIG_FOO is specified, but not selected, the whole block * will be omitted, including oldinstr. */ #define ALTERNATIVE(oldinstr, newinstr, ...) \ _ALTERNATIVE_CFG(oldinstr, newinstr, __VA_ARGS__, 1) #ifndef __ASSEMBLY__ #include <linux/types.h> static __always_inline bool alternative_has_cap_likely(const unsigned long cpucap) { if (!cpucap_is_possible(cpucap)) return false; asm goto( #ifdef BUILD_VDSO ALTERNATIVE("b %l[l_no]", "nop", %[cpucap]) #else ALTERNATIVE_CB("b %l[l_no]", %[cpucap], alt_cb_patch_nops) #endif : : [cpucap] "i" (cpucap) : : l_no); return true; l_no: return false; } static __always_inline bool alternative_has_cap_unlikely(const unsigned long cpucap) { if (!cpucap_is_possible(cpucap)) return false; asm goto( ALTERNATIVE("nop", "b %l[l_yes]", %[cpucap]) : : [cpucap] "i" (cpucap) : : l_yes); return false; l_yes: return true; } #endif /* __ASSEMBLY__ */ #endif /* __ASM_ALTERNATIVE_MACROS_H */ |
| 1024 1023 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 | // SPDX-License-Identifier: GPL-2.0 /* * Generic sched_clock() support, to extend low level hardware time * counters to full 64-bit ns values. */ #include <linux/clocksource.h> #include <linux/init.h> #include <linux/jiffies.h> #include <linux/ktime.h> #include <linux/kernel.h> #include <linux/math.h> #include <linux/moduleparam.h> #include <linux/sched.h> #include <linux/sched/clock.h> #include <linux/syscore_ops.h> #include <linux/hrtimer.h> #include <linux/sched_clock.h> #include <linux/seqlock.h> #include <linux/bitops.h> #include "timekeeping.h" /** * struct clock_data - all data needed for sched_clock() (including * registration of a new clock source) * * @seq: Sequence counter for protecting updates. The lowest * bit is the index for @read_data. * @read_data: Data required to read from sched_clock. * @wrap_kt: Duration for which clock can run before wrapping. * @rate: Tick rate of the registered clock. * @actual_read_sched_clock: Registered hardware level clock read function. * * The ordering of this structure has been chosen to optimize cache * performance. In particular 'seq' and 'read_data[0]' (combined) should fit * into a single 64-byte cache line. */ struct clock_data { seqcount_latch_t seq; struct clock_read_data read_data[2]; ktime_t wrap_kt; unsigned long rate; u64 (*actual_read_sched_clock)(void); }; static struct hrtimer sched_clock_timer; static int irqtime = -1; core_param(irqtime, irqtime, int, 0400); static u64 notrace jiffy_sched_clock_read(void) { /* * We don't need to use get_jiffies_64 on 32-bit arches here * because we register with BITS_PER_LONG */ return (u64)(jiffies - INITIAL_JIFFIES); } static struct clock_data cd ____cacheline_aligned = { .read_data[0] = { .mult = NSEC_PER_SEC / HZ, .read_sched_clock = jiffy_sched_clock_read, }, .actual_read_sched_clock = jiffy_sched_clock_read, }; static __always_inline u64 cyc_to_ns(u64 cyc, u32 mult, u32 shift) { return (cyc * mult) >> shift; } notrace struct clock_read_data *sched_clock_read_begin(unsigned int *seq) { *seq = read_seqcount_latch(&cd.seq); return cd.read_data + (*seq & 1); } notrace int sched_clock_read_retry(unsigned int seq) { return read_seqcount_latch_retry(&cd.seq, seq); } static __always_inline unsigned long long __sched_clock(void) { struct clock_read_data *rd; unsigned int seq; u64 cyc, res; do { seq = raw_read_seqcount_latch(&cd.seq); rd = cd.read_data + (seq & 1); cyc = (rd->read_sched_clock() - rd->epoch_cyc) & rd->sched_clock_mask; res = rd->epoch_ns + cyc_to_ns(cyc, rd->mult, rd->shift); } while (raw_read_seqcount_latch_retry(&cd.seq, seq)); return res; } unsigned long long noinstr sched_clock_noinstr(void) { return __sched_clock(); } unsigned long long notrace sched_clock(void) { unsigned long long ns; preempt_disable_notrace(); /* * All of __sched_clock() is a seqcount_latch reader critical section, * but relies on the raw helpers which are uninstrumented. For KCSAN, * mark all accesses in __sched_clock() as atomic. */ kcsan_nestable_atomic_begin(); ns = __sched_clock(); kcsan_nestable_atomic_end(); preempt_enable_notrace(); return ns; } /* * Updating the data required to read the clock. * * sched_clock() will never observe mis-matched data even if called from * an NMI. We do this by maintaining an odd/even copy of the data and * steering sched_clock() to one or the other using a sequence counter. * In order to preserve the data cache profile of sched_clock() as much * as possible the system reverts back to the even copy when the update * completes; the odd copy is used *only* during an update. */ static void update_clock_read_data(struct clock_read_data *rd) { /* steer readers towards the odd copy */ write_seqcount_latch_begin(&cd.seq); /* now its safe for us to update the normal (even) copy */ cd.read_data[0] = *rd; /* switch readers back to the even copy */ write_seqcount_latch(&cd.seq); /* update the backup (odd) copy with the new data */ cd.read_data[1] = *rd; write_seqcount_latch_end(&cd.seq); } /* * Atomically update the sched_clock() epoch. */ static void update_sched_clock(void) { u64 cyc; u64 ns; struct clock_read_data rd; rd = cd.read_data[0]; cyc = cd.actual_read_sched_clock(); ns = rd.epoch_ns + cyc_to_ns((cyc - rd.epoch_cyc) & rd.sched_clock_mask, rd.mult, rd.shift); rd.epoch_ns = ns; rd.epoch_cyc = cyc; update_clock_read_data(&rd); } static enum hrtimer_restart sched_clock_poll(struct hrtimer *hrt) { update_sched_clock(); hrtimer_forward_now(hrt, cd.wrap_kt); return HRTIMER_RESTART; } void __init sched_clock_register(u64 (*read)(void), int bits, unsigned long rate) { u64 res, wrap, new_mask, new_epoch, cyc, ns; u32 new_mult, new_shift; unsigned long r, flags; char r_unit; struct clock_read_data rd; if (cd.rate > rate) return; /* Cannot register a sched_clock with interrupts on */ local_irq_save(flags); /* Calculate the mult/shift to convert counter ticks to ns. */ clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600); new_mask = CLOCKSOURCE_MASK(bits); cd.rate = rate; /* Calculate how many nanosecs until we risk wrapping */ wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask, NULL); cd.wrap_kt = ns_to_ktime(wrap); rd = cd.read_data[0]; /* Update epoch for new counter and update 'epoch_ns' from old counter*/ new_epoch = read(); cyc = cd.actual_read_sched_clock(); ns = rd.epoch_ns + cyc_to_ns((cyc - rd.epoch_cyc) & rd.sched_clock_mask, rd.mult, rd.shift); cd.actual_read_sched_clock = read; rd.read_sched_clock = read; rd.sched_clock_mask = new_mask; rd.mult = new_mult; rd.shift = new_shift; rd.epoch_cyc = new_epoch; rd.epoch_ns = ns; update_clock_read_data(&rd); if (sched_clock_timer.function != NULL) { /* update timeout for clock wrap */ hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL_HARD); } r = rate; if (r >= 4000000) { r = DIV_ROUND_CLOSEST(r, 1000000); r_unit = 'M'; } else if (r >= 4000) { r = DIV_ROUND_CLOSEST(r, 1000); r_unit = 'k'; } else { r_unit = ' '; } /* Calculate the ns resolution of this counter */ res = cyc_to_ns(1ULL, new_mult, new_shift); pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lluns\n", bits, r, r_unit, res, wrap); /* Enable IRQ time accounting if we have a fast enough sched_clock() */ if (irqtime > 0 || (irqtime == -1 && rate >= 1000000)) enable_sched_clock_irqtime(); local_irq_restore(flags); pr_debug("Registered %pS as sched_clock source\n", read); } void __init generic_sched_clock_init(void) { /* * If no sched_clock() function has been provided at that point, * make it the final one. */ if (cd.actual_read_sched_clock == jiffy_sched_clock_read) sched_clock_register(jiffy_sched_clock_read, BITS_PER_LONG, HZ); update_sched_clock(); /* * Start the timer to keep sched_clock() properly updated and * sets the initial epoch. */ hrtimer_init(&sched_clock_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); sched_clock_timer.function = sched_clock_poll; hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL_HARD); } /* * Clock read function for use when the clock is suspended. * * This function makes it appear to sched_clock() as if the clock * stopped counting at its last update. * * This function must only be called from the critical * section in sched_clock(). It relies on the read_seqcount_retry() * at the end of the critical section to be sure we observe the * correct copy of 'epoch_cyc'. */ static u64 notrace suspended_sched_clock_read(void) { unsigned int seq = read_seqcount_latch(&cd.seq); return cd.read_data[seq & 1].epoch_cyc; } int sched_clock_suspend(void) { struct clock_read_data *rd = &cd.read_data[0]; update_sched_clock(); hrtimer_cancel(&sched_clock_timer); rd->read_sched_clock = suspended_sched_clock_read; return 0; } void sched_clock_resume(void) { struct clock_read_data *rd = &cd.read_data[0]; rd->epoch_cyc = cd.actual_read_sched_clock(); hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL_HARD); rd->read_sched_clock = cd.actual_read_sched_clock; } static struct syscore_ops sched_clock_ops = { .suspend = sched_clock_suspend, .resume = sched_clock_resume, }; static int __init sched_clock_syscore_init(void) { register_syscore_ops(&sched_clock_ops); return 0; } device_initcall(sched_clock_syscore_init); |
| 13 13 13 4 3 1 5 1 4 10 3 7 2 2 3 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 | // SPDX-License-Identifier: GPL-2.0-only /* * Fault injection for both 32 and 64bit guests. * * Copyright (C) 2012,2013 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> * * Based on arch/arm/kvm/emulate.c * Copyright (C) 2012 - Virtual Open Systems and Columbia University * Author: Christoffer Dall <c.dall@virtualopensystems.com> */ #include <linux/kvm_host.h> #include <asm/kvm_emulate.h> #include <asm/kvm_nested.h> #include <asm/esr.h> static void pend_sync_exception(struct kvm_vcpu *vcpu) { /* If not nesting, EL1 is the only possible exception target */ if (likely(!vcpu_has_nv(vcpu))) { kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC); return; } /* * With NV, we need to pick between EL1 and EL2. Note that we * never deal with a nesting exception here, hence never * changing context, and the exception itself can be delayed * until the next entry. */ switch(*vcpu_cpsr(vcpu) & PSR_MODE_MASK) { case PSR_MODE_EL2h: case PSR_MODE_EL2t: kvm_pend_exception(vcpu, EXCEPT_AA64_EL2_SYNC); break; case PSR_MODE_EL1h: case PSR_MODE_EL1t: kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC); break; case PSR_MODE_EL0t: if (vcpu_el2_tge_is_set(vcpu)) kvm_pend_exception(vcpu, EXCEPT_AA64_EL2_SYNC); else kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC); break; default: BUG(); } } static bool match_target_el(struct kvm_vcpu *vcpu, unsigned long target) { return (vcpu_get_flag(vcpu, EXCEPT_MASK) == target); } static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr) { unsigned long cpsr = *vcpu_cpsr(vcpu); bool is_aarch32 = vcpu_mode_is_32bit(vcpu); u64 esr = 0; pend_sync_exception(vcpu); /* * Build an {i,d}abort, depending on the level and the * instruction set. Report an external synchronous abort. */ if (kvm_vcpu_trap_il_is32bit(vcpu)) esr |= ESR_ELx_IL; /* * Here, the guest runs in AArch64 mode when in EL1. If we get * an AArch32 fault, it means we managed to trap an EL0 fault. */ if (is_aarch32 || (cpsr & PSR_MODE_MASK) == PSR_MODE_EL0t) esr |= (ESR_ELx_EC_IABT_LOW << ESR_ELx_EC_SHIFT); else esr |= (ESR_ELx_EC_IABT_CUR << ESR_ELx_EC_SHIFT); if (!is_iabt) esr |= ESR_ELx_EC_DABT_LOW << ESR_ELx_EC_SHIFT; esr |= ESR_ELx_FSC_EXTABT; if (match_target_el(vcpu, unpack_vcpu_flag(EXCEPT_AA64_EL1_SYNC))) { vcpu_write_sys_reg(vcpu, addr, FAR_EL1); vcpu_write_sys_reg(vcpu, esr, ESR_EL1); } else { vcpu_write_sys_reg(vcpu, addr, FAR_EL2); vcpu_write_sys_reg(vcpu, esr, ESR_EL2); } } static void inject_undef64(struct kvm_vcpu *vcpu) { u64 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT); pend_sync_exception(vcpu); /* * Build an unknown exception, depending on the instruction * set. */ if (kvm_vcpu_trap_il_is32bit(vcpu)) esr |= ESR_ELx_IL; if (match_target_el(vcpu, unpack_vcpu_flag(EXCEPT_AA64_EL1_SYNC))) vcpu_write_sys_reg(vcpu, esr, ESR_EL1); else vcpu_write_sys_reg(vcpu, esr, ESR_EL2); } #define DFSR_FSC_EXTABT_LPAE 0x10 #define DFSR_FSC_EXTABT_nLPAE 0x08 #define DFSR_LPAE BIT(9) #define TTBCR_EAE BIT(31) static void inject_undef32(struct kvm_vcpu *vcpu) { kvm_pend_exception(vcpu, EXCEPT_AA32_UND); } /* * Modelled after TakeDataAbortException() and TakePrefetchAbortException * pseudocode. */ static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt, u32 addr) { u64 far; u32 fsr; /* Give the guest an IMPLEMENTATION DEFINED exception */ if (vcpu_read_sys_reg(vcpu, TCR_EL1) & TTBCR_EAE) { fsr = DFSR_LPAE | DFSR_FSC_EXTABT_LPAE; } else { /* no need to shuffle FS[4] into DFSR[10] as it's 0 */ fsr = DFSR_FSC_EXTABT_nLPAE; } far = vcpu_read_sys_reg(vcpu, FAR_EL1); if (is_pabt) { kvm_pend_exception(vcpu, EXCEPT_AA32_IABT); far &= GENMASK(31, 0); far |= (u64)addr << 32; vcpu_write_sys_reg(vcpu, fsr, IFSR32_EL2); } else { /* !iabt */ kvm_pend_exception(vcpu, EXCEPT_AA32_DABT); far &= GENMASK(63, 32); far |= addr; vcpu_write_sys_reg(vcpu, fsr, ESR_EL1); } vcpu_write_sys_reg(vcpu, far, FAR_EL1); } /** * kvm_inject_dabt - inject a data abort into the guest * @vcpu: The VCPU to receive the data abort * @addr: The address to report in the DFAR * * It is assumed that this code is called from the VCPU thread and that the * VCPU therefore is not currently executing guest code. */ void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr) { if (vcpu_el1_is_32bit(vcpu)) inject_abt32(vcpu, false, addr); else inject_abt64(vcpu, false, addr); } /** * kvm_inject_pabt - inject a prefetch abort into the guest * @vcpu: The VCPU to receive the prefetch abort * @addr: The address to report in the DFAR * * It is assumed that this code is called from the VCPU thread and that the * VCPU therefore is not currently executing guest code. */ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr) { if (vcpu_el1_is_32bit(vcpu)) inject_abt32(vcpu, true, addr); else inject_abt64(vcpu, true, addr); } void kvm_inject_size_fault(struct kvm_vcpu *vcpu) { unsigned long addr, esr; addr = kvm_vcpu_get_fault_ipa(vcpu); addr |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0); if (kvm_vcpu_trap_is_iabt(vcpu)) kvm_inject_pabt(vcpu, addr); else kvm_inject_dabt(vcpu, addr); /* * If AArch64 or LPAE, set FSC to 0 to indicate an Address * Size Fault at level 0, as if exceeding PARange. * * Non-LPAE guests will only get the external abort, as there * is no way to describe the ASF. */ if (vcpu_el1_is_32bit(vcpu) && !(vcpu_read_sys_reg(vcpu, TCR_EL1) & TTBCR_EAE)) return; esr = vcpu_read_sys_reg(vcpu, ESR_EL1); esr &= ~GENMASK_ULL(5, 0); vcpu_write_sys_reg(vcpu, esr, ESR_EL1); } /** * kvm_inject_undefined - inject an undefined instruction into the guest * @vcpu: The vCPU in which to inject the exception * * It is assumed that this code is called from the VCPU thread and that the * VCPU therefore is not currently executing guest code. */ void kvm_inject_undefined(struct kvm_vcpu *vcpu) { if (vcpu_el1_is_32bit(vcpu)) inject_undef32(vcpu); else inject_undef64(vcpu); } void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 esr) { vcpu_set_vsesr(vcpu, esr & ESR_ELx_ISS_MASK); *vcpu_hcr(vcpu) |= HCR_VSE; } /** * kvm_inject_vabt - inject an async abort / SError into the guest * @vcpu: The VCPU to receive the exception * * It is assumed that this code is called from the VCPU thread and that the * VCPU therefore is not currently executing guest code. * * Systems with the RAS Extensions specify an imp-def ESR (ISV/IDS = 1) with * the remaining ISS all-zeros so that this error is not interpreted as an * uncategorized RAS error. Without the RAS Extensions we can't specify an ESR * value, so the CPU generates an imp-def value. */ void kvm_inject_vabt(struct kvm_vcpu *vcpu) { kvm_set_sei_esr(vcpu, ESR_ELx_ISV); } |
| 77 545 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2021, Google LLC. * Pasha Tatashin <pasha.tatashin@soleen.com> */ #ifndef __LINUX_PAGE_TABLE_CHECK_H #define __LINUX_PAGE_TABLE_CHECK_H #ifdef CONFIG_PAGE_TABLE_CHECK #include <linux/jump_label.h> extern struct static_key_true page_table_check_disabled; extern struct page_ext_operations page_table_check_ops; void __page_table_check_zero(struct page *page, unsigned int order); void __page_table_check_pte_clear(struct mm_struct *mm, pte_t pte); void __page_table_check_pmd_clear(struct mm_struct *mm, pmd_t pmd); void __page_table_check_pud_clear(struct mm_struct *mm, pud_t pud); void __page_table_check_ptes_set(struct mm_struct *mm, pte_t *ptep, pte_t pte, unsigned int nr); void __page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd); void __page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp, pud_t pud); void __page_table_check_pte_clear_range(struct mm_struct *mm, unsigned long addr, pmd_t pmd); static inline void page_table_check_alloc(struct page *page, unsigned int order) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_zero(page, order); } static inline void page_table_check_free(struct page *page, unsigned int order) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_zero(page, order); } static inline void page_table_check_pte_clear(struct mm_struct *mm, pte_t pte) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_pte_clear(mm, pte); } static inline void page_table_check_pmd_clear(struct mm_struct *mm, pmd_t pmd) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_pmd_clear(mm, pmd); } static inline void page_table_check_pud_clear(struct mm_struct *mm, pud_t pud) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_pud_clear(mm, pud); } static inline void page_table_check_ptes_set(struct mm_struct *mm, pte_t *ptep, pte_t pte, unsigned int nr) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_ptes_set(mm, ptep, pte, nr); } static inline void page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_pmd_set(mm, pmdp, pmd); } static inline void page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp, pud_t pud) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_pud_set(mm, pudp, pud); } static inline void page_table_check_pte_clear_range(struct mm_struct *mm, unsigned long addr, pmd_t pmd) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_pte_clear_range(mm, addr, pmd); } #else static inline void page_table_check_alloc(struct page *page, unsigned int order) { } static inline void page_table_check_free(struct page *page, unsigned int order) { } static inline void page_table_check_pte_clear(struct mm_struct *mm, pte_t pte) { } static inline void page_table_check_pmd_clear(struct mm_struct *mm, pmd_t pmd) { } static inline void page_table_check_pud_clear(struct mm_struct *mm, pud_t pud) { } static inline void page_table_check_ptes_set(struct mm_struct *mm, pte_t *ptep, pte_t pte, unsigned int nr) { } static inline void page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd) { } static inline void page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp, pud_t pud) { } static inline void page_table_check_pte_clear_range(struct mm_struct *mm, unsigned long addr, pmd_t pmd) { } #endif /* CONFIG_PAGE_TABLE_CHECK */ #endif /* __LINUX_PAGE_TABLE_CHECK_H */ |
| 91 89 6 4 91 89 2 2 60 1 35 16 35 1 1 1 1 1 1 1 2 2 21 1 2 64 47 14 1 8 1 4 46 8 8 1 1 1 1 2 1 1 6 3 1 2 1 2 3 3 2 1 1 1 3 3 3 3 3 2 11 2 2 7 1 4 2 1 1 1 1 1 1 1 1 1 3 3 2 2 2 67 1 8 25 5 4 4 25 141 1 22 67 6 7 7 75 1 2 2 1 1 8 2 1 3 2 3 4 2 2 1 2 2 5 5 2 1 1 1 34 1 20 5 7 12 1 4 5 3 6 1 3 1 1 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012,2013 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> * * Derived from arch/arm/kvm/guest.c: * Copyright (C) 2012 - Virtual Open Systems and Columbia University * Author: Christoffer Dall <c.dall@virtualopensystems.com> */ #include <linux/bits.h> #include <linux/errno.h> #include <linux/err.h> #include <linux/nospec.h> #include <linux/kvm_host.h> #include <linux/module.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/vmalloc.h> #include <linux/fs.h> #include <kvm/arm_hypercalls.h> #include <asm/cputype.h> #include <linux/uaccess.h> #include <asm/fpsimd.h> #include <asm/kvm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_nested.h> #include <asm/sigcontext.h> #include "trace.h" const struct _kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS() }; const struct kvm_stats_header kvm_vm_stats_header = { .name_size = KVM_STATS_NAME_SIZE, .num_desc = ARRAY_SIZE(kvm_vm_stats_desc), .id_offset = sizeof(struct kvm_stats_header), .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + sizeof(kvm_vm_stats_desc), }; const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, hvc_exit_stat), STATS_DESC_COUNTER(VCPU, wfe_exit_stat), STATS_DESC_COUNTER(VCPU, wfi_exit_stat), STATS_DESC_COUNTER(VCPU, mmio_exit_user), STATS_DESC_COUNTER(VCPU, mmio_exit_kernel), STATS_DESC_COUNTER(VCPU, signal_exits), STATS_DESC_COUNTER(VCPU, exits) }; const struct kvm_stats_header kvm_vcpu_stats_header = { .name_size = KVM_STATS_NAME_SIZE, .num_desc = ARRAY_SIZE(kvm_vcpu_stats_desc), .id_offset = sizeof(struct kvm_stats_header), .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + sizeof(kvm_vcpu_stats_desc), }; static bool core_reg_offset_is_vreg(u64 off) { return off >= KVM_REG_ARM_CORE_REG(fp_regs.vregs) && off < KVM_REG_ARM_CORE_REG(fp_regs.fpsr); } static u64 core_reg_offset_from_id(u64 id) { return id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_CORE); } static int core_reg_size_from_offset(const struct kvm_vcpu *vcpu, u64 off) { int size; switch (off) { case KVM_REG_ARM_CORE_REG(regs.regs[0]) ... KVM_REG_ARM_CORE_REG(regs.regs[30]): case KVM_REG_ARM_CORE_REG(regs.sp): case KVM_REG_ARM_CORE_REG(regs.pc): case KVM_REG_ARM_CORE_REG(regs.pstate): case KVM_REG_ARM_CORE_REG(sp_el1): case KVM_REG_ARM_CORE_REG(elr_el1): case KVM_REG_ARM_CORE_REG(spsr[0]) ... KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]): size = sizeof(__u64); break; case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ... KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]): size = sizeof(__uint128_t); break; case KVM_REG_ARM_CORE_REG(fp_regs.fpsr): case KVM_REG_ARM_CORE_REG(fp_regs.fpcr): size = sizeof(__u32); break; default: return -EINVAL; } if (!IS_ALIGNED(off, size / sizeof(__u32))) return -EINVAL; /* * The KVM_REG_ARM64_SVE regs must be used instead of * KVM_REG_ARM_CORE for accessing the FPSIMD V-registers on * SVE-enabled vcpus: */ if (vcpu_has_sve(vcpu) && core_reg_offset_is_vreg(off)) return -EINVAL; return size; } static void *core_reg_addr(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { u64 off = core_reg_offset_from_id(reg->id); int size = core_reg_size_from_offset(vcpu, off); if (size < 0) return NULL; if (KVM_REG_SIZE(reg->id) != size) return NULL; switch (off) { case KVM_REG_ARM_CORE_REG(regs.regs[0]) ... KVM_REG_ARM_CORE_REG(regs.regs[30]): off -= KVM_REG_ARM_CORE_REG(regs.regs[0]); off /= 2; return &vcpu->arch.ctxt.regs.regs[off]; case KVM_REG_ARM_CORE_REG(regs.sp): return &vcpu->arch.ctxt.regs.sp; case KVM_REG_ARM_CORE_REG(regs.pc): return &vcpu->arch.ctxt.regs.pc; case KVM_REG_ARM_CORE_REG(regs.pstate): return &vcpu->arch.ctxt.regs.pstate; case KVM_REG_ARM_CORE_REG(sp_el1): return __ctxt_sys_reg(&vcpu->arch.ctxt, SP_EL1); case KVM_REG_ARM_CORE_REG(elr_el1): return __ctxt_sys_reg(&vcpu->arch.ctxt, ELR_EL1); case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_EL1]): return __ctxt_sys_reg(&vcpu->arch.ctxt, SPSR_EL1); case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_ABT]): return &vcpu->arch.ctxt.spsr_abt; case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_UND]): return &vcpu->arch.ctxt.spsr_und; case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_IRQ]): return &vcpu->arch.ctxt.spsr_irq; case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_FIQ]): return &vcpu->arch.ctxt.spsr_fiq; case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ... KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]): off -= KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]); off /= 4; return &vcpu->arch.ctxt.fp_regs.vregs[off]; case KVM_REG_ARM_CORE_REG(fp_regs.fpsr): return &vcpu->arch.ctxt.fp_regs.fpsr; case KVM_REG_ARM_CORE_REG(fp_regs.fpcr): return &vcpu->arch.ctxt.fp_regs.fpcr; default: return NULL; } } static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { /* * Because the kvm_regs structure is a mix of 32, 64 and * 128bit fields, we index it as if it was a 32bit * array. Hence below, nr_regs is the number of entries, and * off the index in the "array". */ __u32 __user *uaddr = (__u32 __user *)(unsigned long)reg->addr; int nr_regs = sizeof(struct kvm_regs) / sizeof(__u32); void *addr; u32 off; /* Our ID is an index into the kvm_regs struct. */ off = core_reg_offset_from_id(reg->id); if (off >= nr_regs || (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs) return -ENOENT; addr = core_reg_addr(vcpu, reg); if (!addr) return -EINVAL; if (copy_to_user(uaddr, addr, KVM_REG_SIZE(reg->id))) return -EFAULT; return 0; } static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { __u32 __user *uaddr = (__u32 __user *)(unsigned long)reg->addr; int nr_regs = sizeof(struct kvm_regs) / sizeof(__u32); __uint128_t tmp; void *valp = &tmp, *addr; u64 off; int err = 0; /* Our ID is an index into the kvm_regs struct. */ off = core_reg_offset_from_id(reg->id); if (off >= nr_regs || (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs) return -ENOENT; addr = core_reg_addr(vcpu, reg); if (!addr) return -EINVAL; if (KVM_REG_SIZE(reg->id) > sizeof(tmp)) return -EINVAL; if (copy_from_user(valp, uaddr, KVM_REG_SIZE(reg->id))) { err = -EFAULT; goto out; } if (off == KVM_REG_ARM_CORE_REG(regs.pstate)) { u64 mode = (*(u64 *)valp) & PSR_AA32_MODE_MASK; switch (mode) { case PSR_AA32_MODE_USR: if (!kvm_supports_32bit_el0()) return -EINVAL; break; case PSR_AA32_MODE_FIQ: case PSR_AA32_MODE_IRQ: case PSR_AA32_MODE_SVC: case PSR_AA32_MODE_ABT: case PSR_AA32_MODE_UND: case PSR_AA32_MODE_SYS: if (!vcpu_el1_is_32bit(vcpu)) return -EINVAL; break; case PSR_MODE_EL2h: case PSR_MODE_EL2t: if (!vcpu_has_nv(vcpu)) return -EINVAL; fallthrough; case PSR_MODE_EL0t: case PSR_MODE_EL1t: case PSR_MODE_EL1h: if (vcpu_el1_is_32bit(vcpu)) return -EINVAL; break; default: err = -EINVAL; goto out; } } memcpy(addr, valp, KVM_REG_SIZE(reg->id)); if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) { int i, nr_reg; switch (*vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK) { /* * Either we are dealing with user mode, and only the * first 15 registers (+ PC) must be narrowed to 32bit. * AArch32 r0-r14 conveniently map to AArch64 x0-x14. */ case PSR_AA32_MODE_USR: case PSR_AA32_MODE_SYS: nr_reg = 15; break; /* * Otherwise, this is a privileged mode, and *all* the * registers must be narrowed to 32bit. */ default: nr_reg = 31; break; } for (i = 0; i < nr_reg; i++) vcpu_set_reg(vcpu, i, (u32)vcpu_get_reg(vcpu, i)); *vcpu_pc(vcpu) = (u32)*vcpu_pc(vcpu); } out: return err; } #define vq_word(vq) (((vq) - SVE_VQ_MIN) / 64) #define vq_mask(vq) ((u64)1 << ((vq) - SVE_VQ_MIN) % 64) #define vq_present(vqs, vq) (!!((vqs)[vq_word(vq)] & vq_mask(vq))) static int get_sve_vls(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { unsigned int max_vq, vq; u64 vqs[KVM_ARM64_SVE_VLS_WORDS]; if (!vcpu_has_sve(vcpu)) return -ENOENT; if (WARN_ON(!sve_vl_valid(vcpu->arch.sve_max_vl))) return -EINVAL; memset(vqs, 0, sizeof(vqs)); max_vq = vcpu_sve_max_vq(vcpu); for (vq = SVE_VQ_MIN; vq <= max_vq; ++vq) if (sve_vq_available(vq)) vqs[vq_word(vq)] |= vq_mask(vq); if (copy_to_user((void __user *)reg->addr, vqs, sizeof(vqs))) return -EFAULT; return 0; } static int set_sve_vls(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { unsigned int max_vq, vq; u64 vqs[KVM_ARM64_SVE_VLS_WORDS]; if (!vcpu_has_sve(vcpu)) return -ENOENT; if (kvm_arm_vcpu_sve_finalized(vcpu)) return -EPERM; /* too late! */ if (WARN_ON(vcpu->arch.sve_state)) return -EINVAL; if (copy_from_user(vqs, (const void __user *)reg->addr, sizeof(vqs))) return -EFAULT; max_vq = 0; for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; ++vq) if (vq_present(vqs, vq)) max_vq = vq; if (max_vq > sve_vq_from_vl(kvm_sve_max_vl)) return -EINVAL; /* * Vector lengths supported by the host can't currently be * hidden from the guest individually: instead we can only set a * maximum via ZCR_EL2.LEN. So, make sure the available vector * lengths match the set requested exactly up to the requested * maximum: */ for (vq = SVE_VQ_MIN; vq <= max_vq; ++vq) if (vq_present(vqs, vq) != sve_vq_available(vq)) return -EINVAL; /* Can't run with no vector lengths at all: */ if (max_vq < SVE_VQ_MIN) return -EINVAL; /* vcpu->arch.sve_state will be alloc'd by kvm_vcpu_finalize_sve() */ vcpu->arch.sve_max_vl = sve_vl_from_vq(max_vq); return 0; } #define SVE_REG_SLICE_SHIFT 0 #define SVE_REG_SLICE_BITS 5 #define SVE_REG_ID_SHIFT (SVE_REG_SLICE_SHIFT + SVE_REG_SLICE_BITS) #define SVE_REG_ID_BITS 5 #define SVE_REG_SLICE_MASK \ GENMASK(SVE_REG_SLICE_SHIFT + SVE_REG_SLICE_BITS - 1, \ SVE_REG_SLICE_SHIFT) #define SVE_REG_ID_MASK \ GENMASK(SVE_REG_ID_SHIFT + SVE_REG_ID_BITS - 1, SVE_REG_ID_SHIFT) #define SVE_NUM_SLICES (1 << SVE_REG_SLICE_BITS) #define KVM_SVE_ZREG_SIZE KVM_REG_SIZE(KVM_REG_ARM64_SVE_ZREG(0, 0)) #define KVM_SVE_PREG_SIZE KVM_REG_SIZE(KVM_REG_ARM64_SVE_PREG(0, 0)) /* * Number of register slices required to cover each whole SVE register. * NOTE: Only the first slice every exists, for now. * If you are tempted to modify this, you must also rework sve_reg_to_region() * to match: */ #define vcpu_sve_slices(vcpu) 1 /* Bounds of a single SVE register slice within vcpu->arch.sve_state */ struct sve_state_reg_region { unsigned int koffset; /* offset into sve_state in kernel memory */ unsigned int klen; /* length in kernel memory */ unsigned int upad; /* extra trailing padding in user memory */ }; /* * Validate SVE register ID and get sanitised bounds for user/kernel SVE * register copy */ static int sve_reg_to_region(struct sve_state_reg_region *region, struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { /* reg ID ranges for Z- registers */ const u64 zreg_id_min = KVM_REG_ARM64_SVE_ZREG(0, 0); const u64 zreg_id_max = KVM_REG_ARM64_SVE_ZREG(SVE_NUM_ZREGS - 1, SVE_NUM_SLICES - 1); /* reg ID ranges for P- registers and FFR (which are contiguous) */ const u64 preg_id_min = KVM_REG_ARM64_SVE_PREG(0, 0); const u64 preg_id_max = KVM_REG_ARM64_SVE_FFR(SVE_NUM_SLICES - 1); unsigned int vq; unsigned int reg_num; unsigned int reqoffset, reqlen; /* User-requested offset and length */ unsigned int maxlen; /* Maximum permitted length */ size_t sve_state_size; const u64 last_preg_id = KVM_REG_ARM64_SVE_PREG(SVE_NUM_PREGS - 1, SVE_NUM_SLICES - 1); /* Verify that the P-regs and FFR really do have contiguous IDs: */ BUILD_BUG_ON(KVM_REG_ARM64_SVE_FFR(0) != last_preg_id + 1); /* Verify that we match the UAPI header: */ BUILD_BUG_ON(SVE_NUM_SLICES != KVM_ARM64_SVE_MAX_SLICES); reg_num = (reg->id & SVE_REG_ID_MASK) >> SVE_REG_ID_SHIFT; if (reg->id >= zreg_id_min && reg->id <= zreg_id_max) { if (!vcpu_has_sve(vcpu) || (reg->id & SVE_REG_SLICE_MASK) > 0) return -ENOENT; vq = vcpu_sve_max_vq(vcpu); reqoffset = SVE_SIG_ZREG_OFFSET(vq, reg_num) - SVE_SIG_REGS_OFFSET; reqlen = KVM_SVE_ZREG_SIZE; maxlen = SVE_SIG_ZREG_SIZE(vq); } else if (reg->id >= preg_id_min && reg->id <= preg_id_max) { if (!vcpu_has_sve(vcpu) || (reg->id & SVE_REG_SLICE_MASK) > 0) return -ENOENT; vq = vcpu_sve_max_vq(vcpu); reqoffset = SVE_SIG_PREG_OFFSET(vq, reg_num) - SVE_SIG_REGS_OFFSET; reqlen = KVM_SVE_PREG_SIZE; maxlen = SVE_SIG_PREG_SIZE(vq); } else { return -EINVAL; } sve_state_size = vcpu_sve_state_size(vcpu); if (WARN_ON(!sve_state_size)) return -EINVAL; region->koffset = array_index_nospec(reqoffset, sve_state_size); region->klen = min(maxlen, reqlen); region->upad = reqlen - region->klen; return 0; } static int get_sve_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { int ret; struct sve_state_reg_region region; char __user *uptr = (char __user *)reg->addr; /* Handle the KVM_REG_ARM64_SVE_VLS pseudo-reg as a special case: */ if (reg->id == KVM_REG_ARM64_SVE_VLS) return get_sve_vls(vcpu, reg); /* Try to interpret reg ID as an architectural SVE register... */ ret = sve_reg_to_region(®ion, vcpu, reg); if (ret) return ret; if (!kvm_arm_vcpu_sve_finalized(vcpu)) return -EPERM; if (copy_to_user(uptr, vcpu->arch.sve_state + region.koffset, region.klen) || clear_user(uptr + region.klen, region.upad)) return -EFAULT; return 0; } static int set_sve_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { int ret; struct sve_state_reg_region region; const char __user *uptr = (const char __user *)reg->addr; /* Handle the KVM_REG_ARM64_SVE_VLS pseudo-reg as a special case: */ if (reg->id == KVM_REG_ARM64_SVE_VLS) return set_sve_vls(vcpu, reg); /* Try to interpret reg ID as an architectural SVE register... */ ret = sve_reg_to_region(®ion, vcpu, reg); if (ret) return ret; if (!kvm_arm_vcpu_sve_finalized(vcpu)) return -EPERM; if (copy_from_user(vcpu->arch.sve_state + region.koffset, uptr, region.klen)) return -EFAULT; return 0; } int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { return -EINVAL; } int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { return -EINVAL; } static int copy_core_reg_indices(const struct kvm_vcpu *vcpu, u64 __user *uindices) { unsigned int i; int n = 0; for (i = 0; i < sizeof(struct kvm_regs) / sizeof(__u32); i++) { u64 reg = KVM_REG_ARM64 | KVM_REG_ARM_CORE | i; int size = core_reg_size_from_offset(vcpu, i); if (size < 0) continue; switch (size) { case sizeof(__u32): reg |= KVM_REG_SIZE_U32; break; case sizeof(__u64): reg |= KVM_REG_SIZE_U64; break; case sizeof(__uint128_t): reg |= KVM_REG_SIZE_U128; break; default: WARN_ON(1); continue; } if (uindices) { if (put_user(reg, uindices)) return -EFAULT; uindices++; } n++; } return n; } static unsigned long num_core_regs(const struct kvm_vcpu *vcpu) { return copy_core_reg_indices(vcpu, NULL); } static const u64 timer_reg_list[] = { KVM_REG_ARM_TIMER_CTL, KVM_REG_ARM_TIMER_CNT, KVM_REG_ARM_TIMER_CVAL, KVM_REG_ARM_PTIMER_CTL, KVM_REG_ARM_PTIMER_CNT, KVM_REG_ARM_PTIMER_CVAL, }; #define NUM_TIMER_REGS ARRAY_SIZE(timer_reg_list) static bool is_timer_reg(u64 index) { switch (index) { case KVM_REG_ARM_TIMER_CTL: case KVM_REG_ARM_TIMER_CNT: case KVM_REG_ARM_TIMER_CVAL: case KVM_REG_ARM_PTIMER_CTL: case KVM_REG_ARM_PTIMER_CNT: case KVM_REG_ARM_PTIMER_CVAL: return true; } return false; } static int copy_timer_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) { for (int i = 0; i < NUM_TIMER_REGS; i++) { if (put_user(timer_reg_list[i], uindices)) return -EFAULT; uindices++; } return 0; } static int set_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { void __user *uaddr = (void __user *)(long)reg->addr; u64 val; int ret; ret = copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id)); if (ret != 0) return -EFAULT; return kvm_arm_timer_set_reg(vcpu, reg->id, val); } static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { void __user *uaddr = (void __user *)(long)reg->addr; u64 val; val = kvm_arm_timer_get_reg(vcpu, reg->id); return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0; } static unsigned long num_sve_regs(const struct kvm_vcpu *vcpu) { const unsigned int slices = vcpu_sve_slices(vcpu); if (!vcpu_has_sve(vcpu)) return 0; /* Policed by KVM_GET_REG_LIST: */ WARN_ON(!kvm_arm_vcpu_sve_finalized(vcpu)); return slices * (SVE_NUM_PREGS + SVE_NUM_ZREGS + 1 /* FFR */) + 1; /* KVM_REG_ARM64_SVE_VLS */ } static int copy_sve_reg_indices(const struct kvm_vcpu *vcpu, u64 __user *uindices) { const unsigned int slices = vcpu_sve_slices(vcpu); u64 reg; unsigned int i, n; int num_regs = 0; if (!vcpu_has_sve(vcpu)) return 0; /* Policed by KVM_GET_REG_LIST: */ WARN_ON(!kvm_arm_vcpu_sve_finalized(vcpu)); /* * Enumerate this first, so that userspace can save/restore in * the order reported by KVM_GET_REG_LIST: */ reg = KVM_REG_ARM64_SVE_VLS; if (put_user(reg, uindices++)) return -EFAULT; ++num_regs; for (i = 0; i < slices; i++) { for (n = 0; n < SVE_NUM_ZREGS; n++) { reg = KVM_REG_ARM64_SVE_ZREG(n, i); if (put_user(reg, uindices++)) return -EFAULT; num_regs++; } for (n = 0; n < SVE_NUM_PREGS; n++) { reg = KVM_REG_ARM64_SVE_PREG(n, i); if (put_user(reg, uindices++)) return -EFAULT; num_regs++; } reg = KVM_REG_ARM64_SVE_FFR(i); if (put_user(reg, uindices++)) return -EFAULT; num_regs++; } return num_regs; } /** * kvm_arm_num_regs - how many registers do we present via KVM_GET_ONE_REG * @vcpu: the vCPU pointer * * This is for all registers. */ unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu) { unsigned long res = 0; res += num_core_regs(vcpu); res += num_sve_regs(vcpu); res += kvm_arm_num_sys_reg_descs(vcpu); res += kvm_arm_get_fw_num_regs(vcpu); res += NUM_TIMER_REGS; return res; } /** * kvm_arm_copy_reg_indices - get indices of all registers. * @vcpu: the vCPU pointer * @uindices: register list to copy * * We do core registers right here, then we append system regs. */ int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) { int ret; ret = copy_core_reg_indices(vcpu, uindices); if (ret < 0) return ret; uindices += ret; ret = copy_sve_reg_indices(vcpu, uindices); if (ret < 0) return ret; uindices += ret; ret = kvm_arm_copy_fw_reg_indices(vcpu, uindices); if (ret < 0) return ret; uindices += kvm_arm_get_fw_num_regs(vcpu); ret = copy_timer_indices(vcpu, uindices); if (ret < 0) return ret; uindices += NUM_TIMER_REGS; return kvm_arm_copy_sys_reg_indices(vcpu, uindices); } int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { /* We currently use nothing arch-specific in upper 32 bits */ if ((reg->id & ~KVM_REG_SIZE_MASK) >> 32 != KVM_REG_ARM64 >> 32) return -EINVAL; switch (reg->id & KVM_REG_ARM_COPROC_MASK) { case KVM_REG_ARM_CORE: return get_core_reg(vcpu, reg); case KVM_REG_ARM_FW: case KVM_REG_ARM_FW_FEAT_BMAP: return kvm_arm_get_fw_reg(vcpu, reg); case KVM_REG_ARM64_SVE: return get_sve_reg(vcpu, reg); } if (is_timer_reg(reg->id)) return get_timer_reg(vcpu, reg); return kvm_arm_sys_reg_get_reg(vcpu, reg); } int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { /* We currently use nothing arch-specific in upper 32 bits */ if ((reg->id & ~KVM_REG_SIZE_MASK) >> 32 != KVM_REG_ARM64 >> 32) return -EINVAL; switch (reg->id & KVM_REG_ARM_COPROC_MASK) { case KVM_REG_ARM_CORE: return set_core_reg(vcpu, reg); case KVM_REG_ARM_FW: case KVM_REG_ARM_FW_FEAT_BMAP: return kvm_arm_set_fw_reg(vcpu, reg); case KVM_REG_ARM64_SVE: return set_sve_reg(vcpu, reg); } if (is_timer_reg(reg->id)) return set_timer_reg(vcpu, reg); return kvm_arm_sys_reg_set_reg(vcpu, reg); } int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { return -EINVAL; } int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { return -EINVAL; } int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { events->exception.serror_pending = !!(vcpu->arch.hcr_el2 & HCR_VSE); events->exception.serror_has_esr = cpus_have_final_cap(ARM64_HAS_RAS_EXTN); if (events->exception.serror_pending && events->exception.serror_has_esr) events->exception.serror_esr = vcpu_get_vsesr(vcpu); /* * We never return a pending ext_dabt here because we deliver it to * the virtual CPU directly when setting the event and it's no longer * 'pending' at this point. */ return 0; } int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { bool serror_pending = events->exception.serror_pending; bool has_esr = events->exception.serror_has_esr; bool ext_dabt_pending = events->exception.ext_dabt_pending; if (serror_pending && has_esr) { if (!cpus_have_final_cap(ARM64_HAS_RAS_EXTN)) return -EINVAL; if (!((events->exception.serror_esr) & ~ESR_ELx_ISS_MASK)) kvm_set_sei_esr(vcpu, events->exception.serror_esr); else return -EINVAL; } else if (serror_pending) { kvm_inject_vabt(vcpu); } if (ext_dabt_pending) kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); return 0; } u32 __attribute_const__ kvm_target_cpu(void) { unsigned long implementor = read_cpuid_implementor(); unsigned long part_number = read_cpuid_part_number(); switch (implementor) { case ARM_CPU_IMP_ARM: switch (part_number) { case ARM_CPU_PART_AEM_V8: return KVM_ARM_TARGET_AEM_V8; case ARM_CPU_PART_FOUNDATION: return KVM_ARM_TARGET_FOUNDATION_V8; case ARM_CPU_PART_CORTEX_A53: return KVM_ARM_TARGET_CORTEX_A53; case ARM_CPU_PART_CORTEX_A57: return KVM_ARM_TARGET_CORTEX_A57; } break; case ARM_CPU_IMP_APM: switch (part_number) { case APM_CPU_PART_XGENE: return KVM_ARM_TARGET_XGENE_POTENZA; } break; } /* Return a default generic target */ return KVM_ARM_TARGET_GENERIC_V8; } int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { return -EINVAL; } int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { return -EINVAL; } int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, struct kvm_translation *tr) { return -EINVAL; } /** * kvm_arch_vcpu_ioctl_set_guest_debug - set up guest debugging * @vcpu: the vCPU pointer * @dbg: the ioctl data buffer * * This sets up and enables the VM for guest debugging. Userspace * passes in a control flag to enable different debug types and * potentially other architecture specific information in the rest of * the structure. */ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { trace_kvm_set_guest_debug(vcpu, dbg->control); if (dbg->control & ~KVM_GUESTDBG_VALID_MASK) return -EINVAL; if (!(dbg->control & KVM_GUESTDBG_ENABLE)) { vcpu->guest_debug = 0; vcpu_clear_flag(vcpu, HOST_SS_ACTIVE_PENDING); return 0; } vcpu->guest_debug = dbg->control; /* Hardware assisted Break and Watch points */ if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) vcpu->arch.external_debug_state = dbg->arch; return 0; } int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { int ret; switch (attr->group) { case KVM_ARM_VCPU_PMU_V3_CTRL: mutex_lock(&vcpu->kvm->arch.config_lock); ret = kvm_arm_pmu_v3_set_attr(vcpu, attr); mutex_unlock(&vcpu->kvm->arch.config_lock); break; case KVM_ARM_VCPU_TIMER_CTRL: ret = kvm_arm_timer_set_attr(vcpu, attr); break; case KVM_ARM_VCPU_PVTIME_CTRL: ret = kvm_arm_pvtime_set_attr(vcpu, attr); break; default: ret = -ENXIO; break; } return ret; } int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { int ret; switch (attr->group) { case KVM_ARM_VCPU_PMU_V3_CTRL: ret = kvm_arm_pmu_v3_get_attr(vcpu, attr); break; case KVM_ARM_VCPU_TIMER_CTRL: ret = kvm_arm_timer_get_attr(vcpu, attr); break; case KVM_ARM_VCPU_PVTIME_CTRL: ret = kvm_arm_pvtime_get_attr(vcpu, attr); break; default: ret = -ENXIO; break; } return ret; } int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { int ret; switch (attr->group) { case KVM_ARM_VCPU_PMU_V3_CTRL: ret = kvm_arm_pmu_v3_has_attr(vcpu, attr); break; case KVM_ARM_VCPU_TIMER_CTRL: ret = kvm_arm_timer_has_attr(vcpu, attr); break; case KVM_ARM_VCPU_PVTIME_CTRL: ret = kvm_arm_pvtime_has_attr(vcpu, attr); break; default: ret = -ENXIO; break; } return ret; } int kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm, struct kvm_arm_copy_mte_tags *copy_tags) { gpa_t guest_ipa = copy_tags->guest_ipa; size_t length = copy_tags->length; void __user *tags = copy_tags->addr; gpa_t gfn; bool write = !(copy_tags->flags & KVM_ARM_TAGS_FROM_GUEST); int ret = 0; if (!kvm_has_mte(kvm)) return -EINVAL; if (copy_tags->reserved[0] || copy_tags->reserved[1]) return -EINVAL; if (copy_tags->flags & ~KVM_ARM_TAGS_FROM_GUEST) return -EINVAL; if (length & ~PAGE_MASK || guest_ipa & ~PAGE_MASK) return -EINVAL; /* Lengths above INT_MAX cannot be represented in the return value */ if (length > INT_MAX) return -EINVAL; gfn = gpa_to_gfn(guest_ipa); mutex_lock(&kvm->slots_lock); if (write && atomic_read(&kvm->nr_memslots_dirty_logging)) { ret = -EBUSY; goto out; } while (length > 0) { struct page *page = __gfn_to_page(kvm, gfn, write); void *maddr; unsigned long num_tags; struct folio *folio; if (!page) { ret = -EFAULT; goto out; } if (!pfn_to_online_page(page_to_pfn(page))) { /* Reject ZONE_DEVICE memory */ kvm_release_page_unused(page); ret = -EFAULT; goto out; } folio = page_folio(page); maddr = page_address(page); if (!write) { if ((folio_test_hugetlb(folio) && folio_test_hugetlb_mte_tagged(folio)) || page_mte_tagged(page)) num_tags = mte_copy_tags_to_user(tags, maddr, MTE_GRANULES_PER_PAGE); else /* No tags in memory, so write zeros */ num_tags = MTE_GRANULES_PER_PAGE - clear_user(tags, MTE_GRANULES_PER_PAGE); kvm_release_page_clean(page); } else { /* * Only locking to serialise with a concurrent * __set_ptes() in the VMM but still overriding the * tags, hence ignoring the return value. */ if (folio_test_hugetlb(folio)) folio_try_hugetlb_mte_tagging(folio); else try_page_mte_tagging(page); num_tags = mte_copy_tags_from_user(maddr, tags, MTE_GRANULES_PER_PAGE); /* uaccess failed, don't leave stale tags */ if (num_tags != MTE_GRANULES_PER_PAGE) mte_clear_page_tags(maddr); if (folio_test_hugetlb(folio)) folio_set_hugetlb_mte_tagged(folio); else set_page_mte_tagged(page); kvm_release_page_dirty(page); } if (num_tags != MTE_GRANULES_PER_PAGE) { ret = -EFAULT; goto out; } gfn++; tags += num_tags; length -= PAGE_SIZE; } out: mutex_unlock(&kvm->slots_lock); /* If some data has been copied report the number of bytes copied */ if (length != copy_tags->length) return copy_tags->length - length; return ret; } |
| 3 2 3 3 3 3 3 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 | // SPDX-License-Identifier: GPL-2.0 /* * NETLINK Netlink attributes * * Authors: Thomas Graf <tgraf@suug.ch> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/jiffies.h> #include <linux/nospec.h> #include <linux/skbuff.h> #include <linux/string.h> #include <linux/types.h> #include <net/netlink.h> /* For these data types, attribute length should be exactly the given * size. However, to maintain compatibility with broken commands, if the * attribute length does not match the expected size a warning is emitted * to the user that the command is sending invalid data and needs to be fixed. */ static const u8 nla_attr_len[NLA_TYPE_MAX+1] = { [NLA_U8] = sizeof(u8), [NLA_U16] = sizeof(u16), [NLA_U32] = sizeof(u32), [NLA_U64] = sizeof(u64), [NLA_S8] = sizeof(s8), [NLA_S16] = sizeof(s16), [NLA_S32] = sizeof(s32), [NLA_S64] = sizeof(s64), [NLA_BE16] = sizeof(__be16), [NLA_BE32] = sizeof(__be32), }; static const u8 nla_attr_minlen[NLA_TYPE_MAX+1] = { [NLA_U8] = sizeof(u8), [NLA_U16] = sizeof(u16), [NLA_U32] = sizeof(u32), [NLA_U64] = sizeof(u64), [NLA_MSECS] = sizeof(u64), [NLA_NESTED] = NLA_HDRLEN, [NLA_S8] = sizeof(s8), [NLA_S16] = sizeof(s16), [NLA_S32] = sizeof(s32), [NLA_S64] = sizeof(s64), [NLA_BE16] = sizeof(__be16), [NLA_BE32] = sizeof(__be32), }; /* * Nested policies might refer back to the original * policy in some cases, and userspace could try to * abuse that and recurse by nesting in the right * ways. Limit recursion to avoid this problem. */ #define MAX_POLICY_RECURSION_DEPTH 10 static int __nla_validate_parse(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack, struct nlattr **tb, unsigned int depth); static int validate_nla_bitfield32(const struct nlattr *nla, const u32 valid_flags_mask) { const struct nla_bitfield32 *bf = nla_data(nla); if (!valid_flags_mask) return -EINVAL; /*disallow invalid bit selector */ if (bf->selector & ~valid_flags_mask) return -EINVAL; /*disallow invalid bit values */ if (bf->value & ~valid_flags_mask) return -EINVAL; /*disallow valid bit values that are not selected*/ if (bf->value & ~bf->selector) return -EINVAL; return 0; } static int nla_validate_array(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack, unsigned int validate, unsigned int depth) { const struct nlattr *entry; int rem; nla_for_each_attr(entry, head, len, rem) { int ret; if (nla_len(entry) == 0) continue; if (nla_len(entry) < NLA_HDRLEN) { NL_SET_ERR_MSG_ATTR_POL(extack, entry, policy, "Array element too short"); return -ERANGE; } ret = __nla_validate_parse(nla_data(entry), nla_len(entry), maxtype, policy, validate, extack, NULL, depth + 1); if (ret < 0) return ret; } return 0; } void nla_get_range_unsigned(const struct nla_policy *pt, struct netlink_range_validation *range) { WARN_ON_ONCE(pt->validation_type != NLA_VALIDATE_RANGE_PTR && (pt->min < 0 || pt->max < 0)); range->min = 0; switch (pt->type) { case NLA_U8: range->max = U8_MAX; break; case NLA_U16: case NLA_BE16: case NLA_BINARY: range->max = U16_MAX; break; case NLA_U32: case NLA_BE32: range->max = U32_MAX; break; case NLA_U64: case NLA_UINT: case NLA_MSECS: range->max = U64_MAX; break; default: WARN_ON_ONCE(1); return; } switch (pt->validation_type) { case NLA_VALIDATE_RANGE: case NLA_VALIDATE_RANGE_WARN_TOO_LONG: range->min = pt->min; range->max = pt->max; break; case NLA_VALIDATE_RANGE_PTR: *range = *pt->range; break; case NLA_VALIDATE_MIN: range->min = pt->min; break; case NLA_VALIDATE_MAX: range->max = pt->max; break; default: break; } } static int nla_validate_range_unsigned(const struct nla_policy *pt, const struct nlattr *nla, struct netlink_ext_ack *extack, unsigned int validate) { struct netlink_range_validation range; u64 value; switch (pt->type) { case NLA_U8: value = nla_get_u8(nla); break; case NLA_U16: value = nla_get_u16(nla); break; case NLA_U32: value = nla_get_u32(nla); break; case NLA_U64: value = nla_get_u64(nla); break; case NLA_UINT: value = nla_get_uint(nla); break; case NLA_MSECS: value = nla_get_u64(nla); break; case NLA_BINARY: value = nla_len(nla); break; case NLA_BE16: value = ntohs(nla_get_be16(nla)); break; case NLA_BE32: value = ntohl(nla_get_be32(nla)); break; default: return -EINVAL; } nla_get_range_unsigned(pt, &range); if (pt->validation_type == NLA_VALIDATE_RANGE_WARN_TOO_LONG && pt->type == NLA_BINARY && value > range.max) { pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n", current->comm, pt->type); if (validate & NL_VALIDATE_STRICT_ATTRS) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "invalid attribute length"); return -EINVAL; } /* this assumes min <= max (don't validate against min) */ return 0; } if (value < range.min || value > range.max) { bool binary = pt->type == NLA_BINARY; if (binary) NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "binary attribute size out of range"); else NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "integer out of range"); return -ERANGE; } return 0; } void nla_get_range_signed(const struct nla_policy *pt, struct netlink_range_validation_signed *range) { switch (pt->type) { case NLA_S8: range->min = S8_MIN; range->max = S8_MAX; break; case NLA_S16: range->min = S16_MIN; range->max = S16_MAX; break; case NLA_S32: range->min = S32_MIN; range->max = S32_MAX; break; case NLA_S64: case NLA_SINT: range->min = S64_MIN; range->max = S64_MAX; break; default: WARN_ON_ONCE(1); return; } switch (pt->validation_type) { case NLA_VALIDATE_RANGE: range->min = pt->min; range->max = pt->max; break; case NLA_VALIDATE_RANGE_PTR: *range = *pt->range_signed; break; case NLA_VALIDATE_MIN: range->min = pt->min; break; case NLA_VALIDATE_MAX: range->max = pt->max; break; default: break; } } static int nla_validate_int_range_signed(const struct nla_policy *pt, const struct nlattr *nla, struct netlink_ext_ack *extack) { struct netlink_range_validation_signed range; s64 value; switch (pt->type) { case NLA_S8: value = nla_get_s8(nla); break; case NLA_S16: value = nla_get_s16(nla); break; case NLA_S32: value = nla_get_s32(nla); break; case NLA_S64: value = nla_get_s64(nla); break; case NLA_SINT: value = nla_get_sint(nla); break; default: return -EINVAL; } nla_get_range_signed(pt, &range); if (value < range.min || value > range.max) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "integer out of range"); return -ERANGE; } return 0; } static int nla_validate_int_range(const struct nla_policy *pt, const struct nlattr *nla, struct netlink_ext_ack *extack, unsigned int validate) { switch (pt->type) { case NLA_U8: case NLA_U16: case NLA_U32: case NLA_U64: case NLA_UINT: case NLA_MSECS: case NLA_BINARY: case NLA_BE16: case NLA_BE32: return nla_validate_range_unsigned(pt, nla, extack, validate); case NLA_S8: case NLA_S16: case NLA_S32: case NLA_S64: case NLA_SINT: return nla_validate_int_range_signed(pt, nla, extack); default: WARN_ON(1); return -EINVAL; } } static int nla_validate_mask(const struct nla_policy *pt, const struct nlattr *nla, struct netlink_ext_ack *extack) { u64 value; switch (pt->type) { case NLA_U8: value = nla_get_u8(nla); break; case NLA_U16: value = nla_get_u16(nla); break; case NLA_U32: value = nla_get_u32(nla); break; case NLA_U64: value = nla_get_u64(nla); break; case NLA_UINT: value = nla_get_uint(nla); break; case NLA_BE16: value = ntohs(nla_get_be16(nla)); break; case NLA_BE32: value = ntohl(nla_get_be32(nla)); break; default: return -EINVAL; } if (value & ~(u64)pt->mask) { NL_SET_ERR_MSG_ATTR(extack, nla, "reserved bit set"); return -EINVAL; } return 0; } static int validate_nla(const struct nlattr *nla, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack, unsigned int depth) { u16 strict_start_type = policy[0].strict_start_type; const struct nla_policy *pt; int minlen = 0, attrlen = nla_len(nla), type = nla_type(nla); int err = -ERANGE; if (strict_start_type && type >= strict_start_type) validate |= NL_VALIDATE_STRICT; if (type <= 0 || type > maxtype) return 0; type = array_index_nospec(type, maxtype + 1); pt = &policy[type]; BUG_ON(pt->type > NLA_TYPE_MAX); if (nla_attr_len[pt->type] && attrlen != nla_attr_len[pt->type]) { pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n", current->comm, type); if (validate & NL_VALIDATE_STRICT_ATTRS) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "invalid attribute length"); return -EINVAL; } } if (validate & NL_VALIDATE_NESTED) { if ((pt->type == NLA_NESTED || pt->type == NLA_NESTED_ARRAY) && !(nla->nla_type & NLA_F_NESTED)) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "NLA_F_NESTED is missing"); return -EINVAL; } if (pt->type != NLA_NESTED && pt->type != NLA_NESTED_ARRAY && pt->type != NLA_UNSPEC && (nla->nla_type & NLA_F_NESTED)) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "NLA_F_NESTED not expected"); return -EINVAL; } } switch (pt->type) { case NLA_REJECT: if (extack && pt->reject_message) { NL_SET_BAD_ATTR(extack, nla); extack->_msg = pt->reject_message; return -EINVAL; } err = -EINVAL; goto out_err; case NLA_FLAG: if (attrlen > 0) goto out_err; break; case NLA_SINT: case NLA_UINT: if (attrlen != sizeof(u32) && attrlen != sizeof(u64)) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "invalid attribute length"); return -EINVAL; } break; case NLA_BITFIELD32: if (attrlen != sizeof(struct nla_bitfield32)) goto out_err; err = validate_nla_bitfield32(nla, pt->bitfield32_valid); if (err) goto out_err; break; case NLA_NUL_STRING: if (pt->len) minlen = min_t(int, attrlen, pt->len + 1); else minlen = attrlen; if (!minlen || memchr(nla_data(nla), '\0', minlen) == NULL) { err = -EINVAL; goto out_err; } fallthrough; case NLA_STRING: if (attrlen < 1) goto out_err; if (pt->len) { char *buf = nla_data(nla); if (buf[attrlen - 1] == '\0') attrlen--; if (attrlen > pt->len) goto out_err; } break; case NLA_BINARY: if (pt->len && attrlen > pt->len) goto out_err; break; case NLA_NESTED: /* a nested attributes is allowed to be empty; if its not, * it must have a size of at least NLA_HDRLEN. */ if (attrlen == 0) break; if (attrlen < NLA_HDRLEN) goto out_err; if (pt->nested_policy) { err = __nla_validate_parse(nla_data(nla), nla_len(nla), pt->len, pt->nested_policy, validate, extack, NULL, depth + 1); if (err < 0) { /* * return directly to preserve the inner * error message/attribute pointer */ return err; } } break; case NLA_NESTED_ARRAY: /* a nested array attribute is allowed to be empty; if its not, * it must have a size of at least NLA_HDRLEN. */ if (attrlen == 0) break; if (attrlen < NLA_HDRLEN) goto out_err; if (pt->nested_policy) { int err; err = nla_validate_array(nla_data(nla), nla_len(nla), pt->len, pt->nested_policy, extack, validate, depth); if (err < 0) { /* * return directly to preserve the inner * error message/attribute pointer */ return err; } } break; case NLA_UNSPEC: if (validate & NL_VALIDATE_UNSPEC) { NL_SET_ERR_MSG_ATTR(extack, nla, "Unsupported attribute"); return -EINVAL; } if (attrlen < pt->len) goto out_err; break; default: if (pt->len) minlen = pt->len; else minlen = nla_attr_minlen[pt->type]; if (attrlen < minlen) goto out_err; } /* further validation */ switch (pt->validation_type) { case NLA_VALIDATE_NONE: /* nothing to do */ break; case NLA_VALIDATE_RANGE_PTR: case NLA_VALIDATE_RANGE: case NLA_VALIDATE_RANGE_WARN_TOO_LONG: case NLA_VALIDATE_MIN: case NLA_VALIDATE_MAX: err = nla_validate_int_range(pt, nla, extack, validate); if (err) return err; break; case NLA_VALIDATE_MASK: err = nla_validate_mask(pt, nla, extack); if (err) return err; break; case NLA_VALIDATE_FUNCTION: if (pt->validate) { err = pt->validate(nla, extack); if (err) return err; } break; } return 0; out_err: NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "Attribute failed policy validation"); return err; } static int __nla_validate_parse(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack, struct nlattr **tb, unsigned int depth) { const struct nlattr *nla; int rem; if (depth >= MAX_POLICY_RECURSION_DEPTH) { NL_SET_ERR_MSG(extack, "allowed policy recursion depth exceeded"); return -EINVAL; } if (tb) memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1)); nla_for_each_attr(nla, head, len, rem) { u16 type = nla_type(nla); if (type == 0 || type > maxtype) { if (validate & NL_VALIDATE_MAXTYPE) { NL_SET_ERR_MSG_ATTR(extack, nla, "Unknown attribute type"); return -EINVAL; } continue; } type = array_index_nospec(type, maxtype + 1); if (policy) { int err = validate_nla(nla, maxtype, policy, validate, extack, depth); if (err < 0) return err; } if (tb) tb[type] = (struct nlattr *)nla; } if (unlikely(rem > 0)) { pr_warn_ratelimited("netlink: %d bytes leftover after parsing attributes in process `%s'.\n", rem, current->comm); NL_SET_ERR_MSG(extack, "bytes leftover after parsing attributes"); if (validate & NL_VALIDATE_TRAILING) return -EINVAL; } return 0; } /** * __nla_validate - Validate a stream of attributes * @head: head of attribute stream * @len: length of attribute stream * @maxtype: maximum attribute type to be expected * @policy: validation policy * @validate: validation strictness * @extack: extended ACK report struct * * Validates all attributes in the specified attribute stream against the * specified policy. Validation depends on the validate flags passed, see * &enum netlink_validation for more details on that. * See documentation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ int __nla_validate(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack) { return __nla_validate_parse(head, len, maxtype, policy, validate, extack, NULL, 0); } EXPORT_SYMBOL(__nla_validate); /** * nla_policy_len - Determine the max. length of a policy * @p: policy to use * @n: number of policies * * Determines the max. length of the policy. It is currently used * to allocated Netlink buffers roughly the size of the actual * message. * * Returns 0 on success or a negative error code. */ int nla_policy_len(const struct nla_policy *p, int n) { int i, len = 0; for (i = 0; i < n; i++, p++) { if (p->len) len += nla_total_size(p->len); else if (nla_attr_len[p->type]) len += nla_total_size(nla_attr_len[p->type]); else if (nla_attr_minlen[p->type]) len += nla_total_size(nla_attr_minlen[p->type]); } return len; } EXPORT_SYMBOL(nla_policy_len); /** * __nla_parse - Parse a stream of attributes into a tb buffer * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @head: head of attribute stream * @len: length of attribute stream * @policy: validation policy * @validate: validation strictness * @extack: extended ACK pointer * * Parses a stream of attributes and stores a pointer to each attribute in * the tb array accessible via the attribute type. * Validation is controlled by the @validate parameter. * * Returns 0 on success or a negative error code. */ int __nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head, int len, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack) { return __nla_validate_parse(head, len, maxtype, policy, validate, extack, tb, 0); } EXPORT_SYMBOL(__nla_parse); /** * nla_find - Find a specific attribute in a stream of attributes * @head: head of attribute stream * @len: length of attribute stream * @attrtype: type of attribute to look for * * Returns the first attribute in the stream matching the specified type. */ struct nlattr *nla_find(const struct nlattr *head, int len, int attrtype) { const struct nlattr *nla; int rem; nla_for_each_attr(nla, head, len, rem) if (nla_type(nla) == attrtype) return (struct nlattr *)nla; return NULL; } EXPORT_SYMBOL(nla_find); /** * nla_strscpy - Copy string attribute payload into a sized buffer * @dst: Where to copy the string to. * @nla: Attribute to copy the string from. * @dstsize: Size of destination buffer. * * Copies at most dstsize - 1 bytes into the destination buffer. * Unlike strscpy() the destination buffer is always padded out. * * Return: * * srclen - Returns @nla length (not including the trailing %NUL). * * -E2BIG - If @dstsize is 0 or greater than U16_MAX or @nla length greater * than @dstsize. */ ssize_t nla_strscpy(char *dst, const struct nlattr *nla, size_t dstsize) { size_t srclen = nla_len(nla); char *src = nla_data(nla); ssize_t ret; size_t len; if (dstsize == 0 || WARN_ON_ONCE(dstsize > U16_MAX)) return -E2BIG; if (srclen > 0 && src[srclen - 1] == '\0') srclen--; if (srclen >= dstsize) { len = dstsize - 1; ret = -E2BIG; } else { len = srclen; ret = len; } memcpy(dst, src, len); /* Zero pad end of dst. */ memset(dst + len, 0, dstsize - len); return ret; } EXPORT_SYMBOL(nla_strscpy); /** * nla_strdup - Copy string attribute payload into a newly allocated buffer * @nla: attribute to copy the string from * @flags: the type of memory to allocate (see kmalloc). * * Returns a pointer to the allocated buffer or NULL on error. */ char *nla_strdup(const struct nlattr *nla, gfp_t flags) { size_t srclen = nla_len(nla); char *src = nla_data(nla), *dst; if (srclen > 0 && src[srclen - 1] == '\0') srclen--; dst = kmalloc(srclen + 1, flags); if (dst != NULL) { memcpy(dst, src, srclen); dst[srclen] = '\0'; } return dst; } EXPORT_SYMBOL(nla_strdup); /** * nla_memcpy - Copy a netlink attribute into another memory area * @dest: where to copy to memcpy * @src: netlink attribute to copy from * @count: size of the destination area * * Note: The number of bytes copied is limited by the length of * attribute's payload. memcpy * * Returns the number of bytes copied. */ int nla_memcpy(void *dest, const struct nlattr *src, int count) { int minlen = min_t(int, count, nla_len(src)); memcpy(dest, nla_data(src), minlen); if (count > minlen) memset(dest + minlen, 0, count - minlen); return minlen; } EXPORT_SYMBOL(nla_memcpy); /** * nla_memcmp - Compare an attribute with sized memory area * @nla: netlink attribute * @data: memory area * @size: size of memory area */ int nla_memcmp(const struct nlattr *nla, const void *data, size_t size) { int d = nla_len(nla) - size; if (d == 0) d = memcmp(nla_data(nla), data, size); return d; } EXPORT_SYMBOL(nla_memcmp); /** * nla_strcmp - Compare a string attribute against a string * @nla: netlink string attribute * @str: another string */ int nla_strcmp(const struct nlattr *nla, const char *str) { int len = strlen(str); char *buf = nla_data(nla); int attrlen = nla_len(nla); int d; while (attrlen > 0 && buf[attrlen - 1] == '\0') attrlen--; d = attrlen - len; if (d == 0) d = memcmp(nla_data(nla), str, len); return d; } EXPORT_SYMBOL(nla_strcmp); #ifdef CONFIG_NET /** * __nla_reserve - reserve room for attribute on the skb * @skb: socket buffer to reserve room on * @attrtype: attribute type * @attrlen: length of attribute payload * * Adds a netlink attribute header to a socket buffer and reserves * room for the payload but does not copy it. * * The caller is responsible to ensure that the skb provides enough * tailroom for the attribute header and payload. */ struct nlattr *__nla_reserve(struct sk_buff *skb, int attrtype, int attrlen) { struct nlattr *nla; nla = skb_put(skb, nla_total_size(attrlen)); nla->nla_type = attrtype; nla->nla_len = nla_attr_size(attrlen); memset((unsigned char *) nla + nla->nla_len, 0, nla_padlen(attrlen)); return nla; } EXPORT_SYMBOL(__nla_reserve); /** * __nla_reserve_64bit - reserve room for attribute on the skb and align it * @skb: socket buffer to reserve room on * @attrtype: attribute type * @attrlen: length of attribute payload * @padattr: attribute type for the padding * * Adds a netlink attribute header to a socket buffer and reserves * room for the payload but does not copy it. It also ensure that this * attribute will have a 64-bit aligned nla_data() area. * * The caller is responsible to ensure that the skb provides enough * tailroom for the attribute header and payload. */ struct nlattr *__nla_reserve_64bit(struct sk_buff *skb, int attrtype, int attrlen, int padattr) { nla_align_64bit(skb, padattr); return __nla_reserve(skb, attrtype, attrlen); } EXPORT_SYMBOL(__nla_reserve_64bit); /** * __nla_reserve_nohdr - reserve room for attribute without header * @skb: socket buffer to reserve room on * @attrlen: length of attribute payload * * Reserves room for attribute payload without a header. * * The caller is responsible to ensure that the skb provides enough * tailroom for the payload. */ void *__nla_reserve_nohdr(struct sk_buff *skb, int attrlen) { return skb_put_zero(skb, NLA_ALIGN(attrlen)); } EXPORT_SYMBOL(__nla_reserve_nohdr); /** * nla_reserve - reserve room for attribute on the skb * @skb: socket buffer to reserve room on * @attrtype: attribute type * @attrlen: length of attribute payload * * Adds a netlink attribute header to a socket buffer and reserves * room for the payload but does not copy it. * * Returns NULL if the tailroom of the skb is insufficient to store * the attribute header and payload. */ struct nlattr *nla_reserve(struct sk_buff *skb, int attrtype, int attrlen) { if (unlikely(skb_tailroom(skb) < nla_total_size(attrlen))) return NULL; return __nla_reserve(skb, attrtype, attrlen); } EXPORT_SYMBOL(nla_reserve); /** * nla_reserve_64bit - reserve room for attribute on the skb and align it * @skb: socket buffer to reserve room on * @attrtype: attribute type * @attrlen: length of attribute payload * @padattr: attribute type for the padding * * Adds a netlink attribute header to a socket buffer and reserves * room for the payload but does not copy it. It also ensure that this * attribute will have a 64-bit aligned nla_data() area. * * Returns NULL if the tailroom of the skb is insufficient to store * the attribute header and payload. */ struct nlattr *nla_reserve_64bit(struct sk_buff *skb, int attrtype, int attrlen, int padattr) { size_t len; if (nla_need_padding_for_64bit(skb)) len = nla_total_size_64bit(attrlen); else len = nla_total_size(attrlen); if (unlikely(skb_tailroom(skb) < len)) return NULL; return __nla_reserve_64bit(skb, attrtype, attrlen, padattr); } EXPORT_SYMBOL(nla_reserve_64bit); /** * nla_reserve_nohdr - reserve room for attribute without header * @skb: socket buffer to reserve room on * @attrlen: length of attribute payload * * Reserves room for attribute payload without a header. * * Returns NULL if the tailroom of the skb is insufficient to store * the attribute payload. */ void *nla_reserve_nohdr(struct sk_buff *skb, int attrlen) { if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) return NULL; return __nla_reserve_nohdr(skb, attrlen); } EXPORT_SYMBOL(nla_reserve_nohdr); /** * __nla_put - Add a netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @attrlen: length of attribute payload * @data: head of attribute payload * * The caller is responsible to ensure that the skb provides enough * tailroom for the attribute header and payload. */ void __nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data) { struct nlattr *nla; nla = __nla_reserve(skb, attrtype, attrlen); memcpy(nla_data(nla), data, attrlen); } EXPORT_SYMBOL(__nla_put); /** * __nla_put_64bit - Add a netlink attribute to a socket buffer and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @attrlen: length of attribute payload * @data: head of attribute payload * @padattr: attribute type for the padding * * The caller is responsible to ensure that the skb provides enough * tailroom for the attribute header and payload. */ void __nla_put_64bit(struct sk_buff *skb, int attrtype, int attrlen, const void *data, int padattr) { struct nlattr *nla; nla = __nla_reserve_64bit(skb, attrtype, attrlen, padattr); memcpy(nla_data(nla), data, attrlen); } EXPORT_SYMBOL(__nla_put_64bit); /** * __nla_put_nohdr - Add a netlink attribute without header * @skb: socket buffer to add attribute to * @attrlen: length of attribute payload * @data: head of attribute payload * * The caller is responsible to ensure that the skb provides enough * tailroom for the attribute payload. */ void __nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) { void *start; start = __nla_reserve_nohdr(skb, attrlen); memcpy(start, data, attrlen); } EXPORT_SYMBOL(__nla_put_nohdr); /** * nla_put - Add a netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @attrlen: length of attribute payload * @data: head of attribute payload * * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute header and payload. */ int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data) { if (unlikely(skb_tailroom(skb) < nla_total_size(attrlen))) return -EMSGSIZE; __nla_put(skb, attrtype, attrlen, data); return 0; } EXPORT_SYMBOL(nla_put); /** * nla_put_64bit - Add a netlink attribute to a socket buffer and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @attrlen: length of attribute payload * @data: head of attribute payload * @padattr: attribute type for the padding * * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute header and payload. */ int nla_put_64bit(struct sk_buff *skb, int attrtype, int attrlen, const void *data, int padattr) { size_t len; if (nla_need_padding_for_64bit(skb)) len = nla_total_size_64bit(attrlen); else len = nla_total_size(attrlen); if (unlikely(skb_tailroom(skb) < len)) return -EMSGSIZE; __nla_put_64bit(skb, attrtype, attrlen, data, padattr); return 0; } EXPORT_SYMBOL(nla_put_64bit); /** * nla_put_nohdr - Add a netlink attribute without header * @skb: socket buffer to add attribute to * @attrlen: length of attribute payload * @data: head of attribute payload * * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute payload. */ int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) { if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) return -EMSGSIZE; __nla_put_nohdr(skb, attrlen, data); return 0; } EXPORT_SYMBOL(nla_put_nohdr); /** * nla_append - Add a netlink attribute without header or padding * @skb: socket buffer to add attribute to * @attrlen: length of attribute payload * @data: head of attribute payload * * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute payload. */ int nla_append(struct sk_buff *skb, int attrlen, const void *data) { if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) return -EMSGSIZE; skb_put_data(skb, data, attrlen); return 0; } EXPORT_SYMBOL(nla_append); #endif |
| 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 | // SPDX-License-Identifier: GPL-2.0 /* Copyright 2011-2014 Autronica Fire and Security AS * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * This file contains device methods for creating, using and destroying * virtual HSR or PRP devices. */ #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <linux/pkt_sched.h> #include "hsr_device.h" #include "hsr_slave.h" #include "hsr_framereg.h" #include "hsr_main.h" #include "hsr_forward.h" static bool is_admin_up(struct net_device *dev) { return dev && (dev->flags & IFF_UP); } static bool is_slave_up(struct net_device *dev) { return dev && is_admin_up(dev) && netif_oper_up(dev); } static void hsr_set_operstate(struct hsr_port *master, bool has_carrier) { struct net_device *dev = master->dev; if (!is_admin_up(dev)) { netdev_set_operstate(dev, IF_OPER_DOWN); return; } if (has_carrier) netdev_set_operstate(dev, IF_OPER_UP); else netdev_set_operstate(dev, IF_OPER_LOWERLAYERDOWN); } static bool hsr_check_carrier(struct hsr_port *master) { struct hsr_port *port; ASSERT_RTNL(); hsr_for_each_port(master->hsr, port) { if (port->type != HSR_PT_MASTER && is_slave_up(port->dev)) { netif_carrier_on(master->dev); return true; } } netif_carrier_off(master->dev); return false; } static void hsr_check_announce(struct net_device *hsr_dev) { struct hsr_priv *hsr; hsr = netdev_priv(hsr_dev); if (netif_running(hsr_dev) && netif_oper_up(hsr_dev)) { /* Enable announce timer and start sending supervisory frames */ if (!timer_pending(&hsr->announce_timer)) { hsr->announce_count = 0; mod_timer(&hsr->announce_timer, jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL)); } if (hsr->redbox && !timer_pending(&hsr->announce_proxy_timer)) mod_timer(&hsr->announce_proxy_timer, jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL) / 2); } else { /* Deactivate the announce timer */ timer_delete(&hsr->announce_timer); if (hsr->redbox) timer_delete(&hsr->announce_proxy_timer); } } void hsr_check_carrier_and_operstate(struct hsr_priv *hsr) { struct hsr_port *master; bool has_carrier; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); /* netif_stacked_transfer_operstate() cannot be used here since * it doesn't set IF_OPER_LOWERLAYERDOWN (?) */ has_carrier = hsr_check_carrier(master); hsr_set_operstate(master, has_carrier); hsr_check_announce(master->dev); } int hsr_get_max_mtu(struct hsr_priv *hsr) { unsigned int mtu_max; struct hsr_port *port; mtu_max = ETH_DATA_LEN; hsr_for_each_port(hsr, port) if (port->type != HSR_PT_MASTER) mtu_max = min(port->dev->mtu, mtu_max); if (mtu_max < HSR_HLEN) return 0; return mtu_max - HSR_HLEN; } static int hsr_dev_change_mtu(struct net_device *dev, int new_mtu) { struct hsr_priv *hsr; hsr = netdev_priv(dev); if (new_mtu > hsr_get_max_mtu(hsr)) { netdev_info(dev, "A HSR master's MTU cannot be greater than the smallest MTU of its slaves minus the HSR Tag length (%d octets).\n", HSR_HLEN); return -EINVAL; } WRITE_ONCE(dev->mtu, new_mtu); return 0; } static int hsr_dev_open(struct net_device *dev) { struct hsr_priv *hsr; struct hsr_port *port; const char *designation = NULL; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: designation = "Slave A"; break; case HSR_PT_SLAVE_B: designation = "Slave B"; break; case HSR_PT_INTERLINK: designation = "Interlink"; break; default: designation = "Unknown"; } if (!is_slave_up(port->dev)) netdev_warn(dev, "%s (%s) is not up; please bring it up to get a fully working HSR network\n", designation, port->dev->name); } if (!designation) netdev_warn(dev, "No slave devices configured\n"); return 0; } static int hsr_dev_close(struct net_device *dev) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: dev_uc_unsync(port->dev, dev); dev_mc_unsync(port->dev, dev); break; default: break; } } return 0; } static netdev_features_t hsr_features_recompute(struct hsr_priv *hsr, netdev_features_t features) { netdev_features_t mask; struct hsr_port *port; mask = features; /* Mask out all features that, if supported by one device, should be * enabled for all devices (see NETIF_F_ONE_FOR_ALL). * * Anything that's off in mask will not be enabled - so only things * that were in features originally, and also is in NETIF_F_ONE_FOR_ALL, * may become enabled. */ features &= ~NETIF_F_ONE_FOR_ALL; hsr_for_each_port(hsr, port) features = netdev_increment_features(features, port->dev->features, mask); return features; } static netdev_features_t hsr_fix_features(struct net_device *dev, netdev_features_t features) { struct hsr_priv *hsr = netdev_priv(dev); return hsr_features_recompute(hsr, features); } static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) { struct hsr_priv *hsr = netdev_priv(dev); struct hsr_port *master; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (master) { skb->dev = master->dev; skb_reset_mac_header(skb); skb_reset_mac_len(skb); spin_lock_bh(&hsr->seqnr_lock); hsr_forward_skb(skb, master); spin_unlock_bh(&hsr->seqnr_lock); } else { dev_core_stats_tx_dropped_inc(dev); dev_kfree_skb_any(skb); } return NETDEV_TX_OK; } static const struct header_ops hsr_header_ops = { .create = eth_header, .parse = eth_header_parse, }; static struct sk_buff *hsr_init_skb(struct hsr_port *master, int extra) { struct hsr_priv *hsr = master->hsr; struct sk_buff *skb; int hlen, tlen; int len; hlen = LL_RESERVED_SPACE(master->dev); tlen = master->dev->needed_tailroom; len = sizeof(struct hsr_sup_tag) + sizeof(struct hsr_sup_payload); /* skb size is same for PRP/HSR frames, only difference * being, for PRP it is a trailer and for HSR it is a * header. * RedBox might use @extra more bytes. */ skb = dev_alloc_skb(len + extra + hlen + tlen); if (!skb) return skb; skb_reserve(skb, hlen); skb->dev = master->dev; skb->priority = TC_PRIO_CONTROL; skb_reset_network_header(skb); skb_reset_transport_header(skb); if (dev_hard_header(skb, skb->dev, ETH_P_PRP, hsr->sup_multicast_addr, skb->dev->dev_addr, skb->len) <= 0) goto out; skb_reset_mac_header(skb); skb_reset_mac_len(skb); return skb; out: kfree_skb(skb); return NULL; } static void send_hsr_supervision_frame(struct hsr_port *port, unsigned long *interval, const unsigned char *addr) { struct hsr_priv *hsr = port->hsr; __u8 type = HSR_TLV_LIFE_CHECK; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tlv *hsr_stlv; struct hsr_sup_tag *hsr_stag; struct sk_buff *skb; int extra = 0; *interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); if (hsr->announce_count < 3 && hsr->prot_version == 0) { type = HSR_TLV_ANNOUNCE; *interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); hsr->announce_count++; } if (hsr->redbox) extra = sizeof(struct hsr_sup_tlv) + sizeof(struct hsr_sup_payload); skb = hsr_init_skb(port, extra); if (!skb) { netdev_warn_once(port->dev, "HSR: Could not send supervision frame\n"); return; } hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); set_hsr_stag_HSR_ver(hsr_stag, hsr->prot_version); /* From HSRv1 on we have separate supervision sequence numbers. */ spin_lock_bh(&hsr->seqnr_lock); if (hsr->prot_version > 0) { hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); hsr->sup_sequence_nr++; } else { hsr_stag->sequence_nr = htons(hsr->sequence_nr); hsr->sequence_nr++; } hsr_stag->tlv.HSR_TLV_type = type; /* TODO: Why 12 in HSRv0? */ hsr_stag->tlv.HSR_TLV_length = hsr->prot_version ? sizeof(struct hsr_sup_payload) : 12; /* Payload: MacAddressA / SAN MAC from ProxyNodeTable */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, addr); if (hsr->redbox && hsr_is_node_in_db(&hsr->proxy_node_db, addr)) { hsr_stlv = skb_put(skb, sizeof(struct hsr_sup_tlv)); hsr_stlv->HSR_TLV_type = PRP_TLV_REDBOX_MAC; hsr_stlv->HSR_TLV_length = sizeof(struct hsr_sup_payload); /* Payload: MacAddressRedBox */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, hsr->macaddress_redbox); } if (skb_put_padto(skb, ETH_ZLEN)) { spin_unlock_bh(&hsr->seqnr_lock); return; } hsr_forward_skb(skb, port); spin_unlock_bh(&hsr->seqnr_lock); return; } static void send_prp_supervision_frame(struct hsr_port *master, unsigned long *interval, const unsigned char *addr) { struct hsr_priv *hsr = master->hsr; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tag *hsr_stag; struct sk_buff *skb; skb = hsr_init_skb(master, 0); if (!skb) { netdev_warn_once(master->dev, "PRP: Could not send supervision frame\n"); return; } *interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); set_hsr_stag_HSR_ver(hsr_stag, (hsr->prot_version ? 1 : 0)); /* From HSRv1 on we have separate supervision sequence numbers. */ spin_lock_bh(&hsr->seqnr_lock); hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); hsr->sup_sequence_nr++; hsr_stag->tlv.HSR_TLV_type = PRP_TLV_LIFE_CHECK_DD; hsr_stag->tlv.HSR_TLV_length = sizeof(struct hsr_sup_payload); /* Payload: MacAddressA */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr); if (skb_put_padto(skb, ETH_ZLEN)) { spin_unlock_bh(&hsr->seqnr_lock); return; } hsr_forward_skb(skb, master); spin_unlock_bh(&hsr->seqnr_lock); } /* Announce (supervision frame) timer function */ static void hsr_announce(struct timer_list *t) { struct hsr_priv *hsr; struct hsr_port *master; unsigned long interval; hsr = from_timer(hsr, t, announce_timer); rcu_read_lock(); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); hsr->proto_ops->send_sv_frame(master, &interval, master->dev->dev_addr); if (is_admin_up(master->dev)) mod_timer(&hsr->announce_timer, jiffies + interval); rcu_read_unlock(); } /* Announce (supervision frame) timer function for RedBox */ static void hsr_proxy_announce(struct timer_list *t) { struct hsr_priv *hsr = from_timer(hsr, t, announce_proxy_timer); struct hsr_port *interlink; unsigned long interval = 0; struct hsr_node *node; rcu_read_lock(); /* RedBOX sends supervisory frames to HSR network with MAC addresses * of SAN nodes stored in ProxyNodeTable. */ interlink = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK); if (!interlink) goto done; list_for_each_entry_rcu(node, &hsr->proxy_node_db, mac_list) { if (hsr_addr_is_redbox(hsr, node->macaddress_A)) continue; hsr->proto_ops->send_sv_frame(interlink, &interval, node->macaddress_A); } if (is_admin_up(interlink->dev)) { if (!interval) interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); mod_timer(&hsr->announce_proxy_timer, jiffies + interval); } done: rcu_read_unlock(); } void hsr_del_ports(struct hsr_priv *hsr) { struct hsr_port *port; port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (port) hsr_del_port(port); } static void hsr_set_rx_mode(struct net_device *dev) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: dev_mc_sync_multiple(port->dev, dev); dev_uc_sync_multiple(port->dev, dev); break; default: break; } } } static void hsr_change_rx_flags(struct net_device *dev, int change) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: if (change & IFF_ALLMULTI) dev_set_allmulti(port->dev, dev->flags & IFF_ALLMULTI ? 1 : -1); break; default: break; } } } static int hsr_ndo_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { bool is_slave_a_added = false; bool is_slave_b_added = false; struct hsr_port *port; struct hsr_priv *hsr; int ret = 0; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER || port->type == HSR_PT_INTERLINK) continue; ret = vlan_vid_add(port->dev, proto, vid); switch (port->type) { case HSR_PT_SLAVE_A: if (ret) { /* clean up Slave-B */ netdev_err(dev, "add vid failed for Slave-A\n"); if (is_slave_b_added) vlan_vid_del(port->dev, proto, vid); return ret; } is_slave_a_added = true; break; case HSR_PT_SLAVE_B: if (ret) { /* clean up Slave-A */ netdev_err(dev, "add vid failed for Slave-B\n"); if (is_slave_a_added) vlan_vid_del(port->dev, proto, vid); return ret; } is_slave_b_added = true; break; default: break; } } return 0; } static int hsr_ndo_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: vlan_vid_del(port->dev, proto, vid); break; default: break; } } return 0; } static const struct net_device_ops hsr_device_ops = { .ndo_change_mtu = hsr_dev_change_mtu, .ndo_open = hsr_dev_open, .ndo_stop = hsr_dev_close, .ndo_start_xmit = hsr_dev_xmit, .ndo_change_rx_flags = hsr_change_rx_flags, .ndo_fix_features = hsr_fix_features, .ndo_set_rx_mode = hsr_set_rx_mode, .ndo_vlan_rx_add_vid = hsr_ndo_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = hsr_ndo_vlan_rx_kill_vid, }; static const struct device_type hsr_type = { .name = "hsr", }; static struct hsr_proto_ops hsr_ops = { .send_sv_frame = send_hsr_supervision_frame, .create_tagged_frame = hsr_create_tagged_frame, .get_untagged_frame = hsr_get_untagged_frame, .drop_frame = hsr_drop_frame, .fill_frame_info = hsr_fill_frame_info, .invalid_dan_ingress_frame = hsr_invalid_dan_ingress_frame, }; static struct hsr_proto_ops prp_ops = { .send_sv_frame = send_prp_supervision_frame, .create_tagged_frame = prp_create_tagged_frame, .get_untagged_frame = prp_get_untagged_frame, .drop_frame = prp_drop_frame, .fill_frame_info = prp_fill_frame_info, .handle_san_frame = prp_handle_san_frame, .update_san_info = prp_update_san_info, }; void hsr_dev_setup(struct net_device *dev) { eth_hw_addr_random(dev); ether_setup(dev); dev->min_mtu = 0; dev->header_ops = &hsr_header_ops; dev->netdev_ops = &hsr_device_ops; SET_NETDEV_DEVTYPE(dev, &hsr_type); dev->priv_flags |= IFF_NO_QUEUE | IFF_DISABLE_NETPOLL; /* Prevent recursive tx locking */ dev->lltx = true; /* Not sure about this. Taken from bridge code. netdevice.h says * it means "Does not change network namespaces". */ dev->netns_local = true; dev->needs_free_netdev = true; dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | NETIF_F_GSO_MASK | NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_FILTER; dev->features = dev->hw_features; } /* Return true if dev is a HSR master; return false otherwise. */ bool is_hsr_master(struct net_device *dev) { return (dev->netdev_ops->ndo_start_xmit == hsr_dev_xmit); } EXPORT_SYMBOL(is_hsr_master); /* Default multicast address for HSR Supervision frames */ static const unsigned char def_multicast_addr[ETH_ALEN] __aligned(2) = { 0x01, 0x15, 0x4e, 0x00, 0x01, 0x00 }; int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], struct net_device *interlink, unsigned char multicast_spec, u8 protocol_version, struct netlink_ext_ack *extack) { bool unregister = false; struct hsr_priv *hsr; int res; hsr = netdev_priv(hsr_dev); INIT_LIST_HEAD(&hsr->ports); INIT_LIST_HEAD(&hsr->node_db); INIT_LIST_HEAD(&hsr->proxy_node_db); spin_lock_init(&hsr->list_lock); eth_hw_addr_set(hsr_dev, slave[0]->dev_addr); /* initialize protocol specific functions */ if (protocol_version == PRP_V1) { /* For PRP, lan_id has most significant 3 bits holding * the net_id of PRP_LAN_ID */ hsr->net_id = PRP_LAN_ID << 1; hsr->proto_ops = &prp_ops; } else { hsr->proto_ops = &hsr_ops; } /* Make sure we recognize frames from ourselves in hsr_rcv() */ res = hsr_create_self_node(hsr, hsr_dev->dev_addr, slave[1]->dev_addr); if (res < 0) return res; spin_lock_init(&hsr->seqnr_lock); /* Overflow soon to find bugs easier: */ hsr->sequence_nr = HSR_SEQNR_START; hsr->sup_sequence_nr = HSR_SUP_SEQNR_START; timer_setup(&hsr->announce_timer, hsr_announce, 0); timer_setup(&hsr->prune_timer, hsr_prune_nodes, 0); timer_setup(&hsr->prune_proxy_timer, hsr_prune_proxy_nodes, 0); timer_setup(&hsr->announce_proxy_timer, hsr_proxy_announce, 0); ether_addr_copy(hsr->sup_multicast_addr, def_multicast_addr); hsr->sup_multicast_addr[ETH_ALEN - 1] = multicast_spec; hsr->prot_version = protocol_version; /* Make sure the 1st call to netif_carrier_on() gets through */ netif_carrier_off(hsr_dev); res = hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER, extack); if (res) goto err_add_master; /* HSR forwarding offload supported in lower device? */ if ((slave[0]->features & NETIF_F_HW_HSR_FWD) && (slave[1]->features & NETIF_F_HW_HSR_FWD)) hsr->fwd_offloaded = true; if ((slave[0]->features & NETIF_F_HW_VLAN_CTAG_FILTER) && (slave[1]->features & NETIF_F_HW_VLAN_CTAG_FILTER)) hsr_dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; res = register_netdevice(hsr_dev); if (res) goto err_unregister; unregister = true; res = hsr_add_port(hsr, slave[0], HSR_PT_SLAVE_A, extack); if (res) goto err_unregister; res = hsr_add_port(hsr, slave[1], HSR_PT_SLAVE_B, extack); if (res) goto err_unregister; if (interlink) { res = hsr_add_port(hsr, interlink, HSR_PT_INTERLINK, extack); if (res) goto err_unregister; hsr->redbox = true; ether_addr_copy(hsr->macaddress_redbox, interlink->dev_addr); mod_timer(&hsr->prune_proxy_timer, jiffies + msecs_to_jiffies(PRUNE_PROXY_PERIOD)); } hsr_debugfs_init(hsr, hsr_dev); mod_timer(&hsr->prune_timer, jiffies + msecs_to_jiffies(PRUNE_PERIOD)); return 0; err_unregister: hsr_del_ports(hsr); err_add_master: hsr_del_self_node(hsr); if (unregister) unregister_netdevice(hsr_dev); return res; } |
| 581 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 | // SPDX-License-Identifier: GPL-2.0 #include <linux/err.h> #include <linux/bug.h> #include <linux/atomic.h> #include <linux/errseq.h> #include <linux/log2.h> /* * An errseq_t is a way of recording errors in one place, and allowing any * number of "subscribers" to tell whether it has changed since a previous * point where it was sampled. * * It's implemented as an unsigned 32-bit value. The low order bits are * designated to hold an error code (between 0 and -MAX_ERRNO). The upper bits * are used as a counter. This is done with atomics instead of locking so that * these functions can be called from any context. * * The general idea is for consumers to sample an errseq_t value. That value * can later be used to tell whether any new errors have occurred since that * sampling was done. * * Note that there is a risk of collisions if new errors are being recorded * frequently, since we have so few bits to use as a counter. * * To mitigate this, one bit is used as a flag to tell whether the value has * been sampled since a new value was recorded. That allows us to avoid bumping * the counter if no one has sampled it since the last time an error was * recorded. * * A new errseq_t should always be zeroed out. A errseq_t value of all zeroes * is the special (but common) case where there has never been an error. An all * zero value thus serves as the "epoch" if one wishes to know whether there * has ever been an error set since it was first initialized. */ /* The low bits are designated for error code (max of MAX_ERRNO) */ #define ERRSEQ_SHIFT ilog2(MAX_ERRNO + 1) /* This bit is used as a flag to indicate whether the value has been seen */ #define ERRSEQ_SEEN (1 << ERRSEQ_SHIFT) /* The lowest bit of the counter */ #define ERRSEQ_CTR_INC (1 << (ERRSEQ_SHIFT + 1)) /** * errseq_set - set a errseq_t for later reporting * @eseq: errseq_t field that should be set * @err: error to set (must be between -1 and -MAX_ERRNO) * * This function sets the error in @eseq, and increments the sequence counter * if the last sequence was sampled at some point in the past. * * Any error set will always overwrite an existing error. * * Return: The previous value, primarily for debugging purposes. The * return value should not be used as a previously sampled value in later * calls as it will not have the SEEN flag set. */ errseq_t errseq_set(errseq_t *eseq, int err) { errseq_t cur, old; /* MAX_ERRNO must be able to serve as a mask */ BUILD_BUG_ON_NOT_POWER_OF_2(MAX_ERRNO + 1); /* * Ensure the error code actually fits where we want it to go. If it * doesn't then just throw a warning and don't record anything. We * also don't accept zero here as that would effectively clear a * previous error. */ old = READ_ONCE(*eseq); if (WARN(unlikely(err == 0 || (unsigned int)-err > MAX_ERRNO), "err = %d\n", err)) return old; for (;;) { errseq_t new; /* Clear out error bits and set new error */ new = (old & ~(MAX_ERRNO|ERRSEQ_SEEN)) | -err; /* Only increment if someone has looked at it */ if (old & ERRSEQ_SEEN) new += ERRSEQ_CTR_INC; /* If there would be no change, then call it done */ if (new == old) { cur = new; break; } /* Try to swap the new value into place */ cur = cmpxchg(eseq, old, new); /* * Call it success if we did the swap or someone else beat us * to it for the same value. */ if (likely(cur == old || cur == new)) break; /* Raced with an update, try again */ old = cur; } return cur; } EXPORT_SYMBOL(errseq_set); /** * errseq_sample() - Grab current errseq_t value. * @eseq: Pointer to errseq_t to be sampled. * * This function allows callers to initialise their errseq_t variable. * If the error has been "seen", new callers will not see an old error. * If there is an unseen error in @eseq, the caller of this function will * see it the next time it checks for an error. * * Context: Any context. * Return: The current errseq value. */ errseq_t errseq_sample(errseq_t *eseq) { errseq_t old = READ_ONCE(*eseq); /* If nobody has seen this error yet, then we can be the first. */ if (!(old & ERRSEQ_SEEN)) old = 0; return old; } EXPORT_SYMBOL(errseq_sample); /** * errseq_check() - Has an error occurred since a particular sample point? * @eseq: Pointer to errseq_t value to be checked. * @since: Previously-sampled errseq_t from which to check. * * Grab the value that eseq points to, and see if it has changed @since * the given value was sampled. The @since value is not advanced, so there * is no need to mark the value as seen. * * Return: The latest error set in the errseq_t or 0 if it hasn't changed. */ int errseq_check(errseq_t *eseq, errseq_t since) { errseq_t cur = READ_ONCE(*eseq); if (likely(cur == since)) return 0; return -(cur & MAX_ERRNO); } EXPORT_SYMBOL(errseq_check); /** * errseq_check_and_advance() - Check an errseq_t and advance to current value. * @eseq: Pointer to value being checked and reported. * @since: Pointer to previously-sampled errseq_t to check against and advance. * * Grab the eseq value, and see whether it matches the value that @since * points to. If it does, then just return 0. * * If it doesn't, then the value has changed. Set the "seen" flag, and try to * swap it into place as the new eseq value. Then, set that value as the new * "since" value, and return whatever the error portion is set to. * * Note that no locking is provided here for concurrent updates to the "since" * value. The caller must provide that if necessary. Because of this, callers * may want to do a lockless errseq_check before taking the lock and calling * this. * * Return: Negative errno if one has been stored, or 0 if no new error has * occurred. */ int errseq_check_and_advance(errseq_t *eseq, errseq_t *since) { int err = 0; errseq_t old, new; /* * Most callers will want to use the inline wrapper to check this, * so that the common case of no error is handled without needing * to take the lock that protects the "since" value. */ old = READ_ONCE(*eseq); if (old != *since) { /* * Set the flag and try to swap it into place if it has * changed. * * We don't care about the outcome of the swap here. If the * swap doesn't occur, then it has either been updated by a * writer who is altering the value in some way (updating * counter or resetting the error), or another reader who is * just setting the "seen" flag. Either outcome is OK, and we * can advance "since" and return an error based on what we * have. */ new = old | ERRSEQ_SEEN; if (new != old) cmpxchg(eseq, old, new); *since = new; err = -(new & MAX_ERRNO); } return err; } EXPORT_SYMBOL(errseq_check_and_advance); |
| 41 108 15 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_H #define _LINUX_SCHED_H /* * Define 'struct task_struct' and provide the main scheduler * APIs (schedule(), wakeup variants, etc.) */ #include <uapi/linux/sched.h> #include <asm/current.h> #include <asm/processor.h> #include <linux/thread_info.h> #include <linux/preempt.h> #include <linux/cpumask_types.h> #include <linux/cache.h> #include <linux/irqflags_types.h> #include <linux/smp_types.h> #include <linux/pid_types.h> #include <linux/sem_types.h> #include <linux/shm.h> #include <linux/kmsan_types.h> #include <linux/mutex_types.h> #include <linux/plist_types.h> #include <linux/hrtimer_types.h> #include <linux/timer_types.h> #include <linux/seccomp_types.h> #include <linux/nodemask_types.h> #include <linux/refcount_types.h> #include <linux/resource.h> #include <linux/latencytop.h> #include <linux/sched/prio.h> #include <linux/sched/types.h> #include <linux/signal_types.h> #include <linux/syscall_user_dispatch_types.h> #include <linux/mm_types_task.h> #include <linux/netdevice_xmit.h> #include <linux/task_io_accounting.h> #include <linux/posix-timers_types.h> #include <linux/restart_block.h> #include <uapi/linux/rseq.h> #include <linux/seqlock_types.h> #include <linux/kcsan.h> #include <linux/rv.h> #include <linux/livepatch_sched.h> #include <linux/uidgid_types.h> #include <asm/kmap_size.h> /* task_struct member predeclarations (sorted alphabetically): */ struct audit_context; struct bio_list; struct blk_plug; struct bpf_local_storage; struct bpf_run_ctx; struct bpf_net_context; struct capture_control; struct cfs_rq; struct fs_struct; struct futex_pi_state; struct io_context; struct io_uring_task; struct mempolicy; struct nameidata; struct nsproxy; struct perf_event_context; struct pid_namespace; struct pipe_inode_info; struct rcu_node; struct reclaim_state; struct robust_list_head; struct root_domain; struct rq; struct sched_attr; struct sched_dl_entity; struct seq_file; struct sighand_struct; struct signal_struct; struct task_delay_info; struct task_group; struct task_struct; struct user_event_mm; #include <linux/sched/ext.h> /* * Task state bitmask. NOTE! These bits are also * encoded in fs/proc/array.c: get_task_state(). * * We have two separate sets of flags: task->__state * is about runnability, while task->exit_state are * about the task exiting. Confusing, but this way * modifying one set can't modify the other one by * mistake. */ /* Used in tsk->__state: */ #define TASK_RUNNING 0x00000000 #define TASK_INTERRUPTIBLE 0x00000001 #define TASK_UNINTERRUPTIBLE 0x00000002 #define __TASK_STOPPED 0x00000004 #define __TASK_TRACED 0x00000008 /* Used in tsk->exit_state: */ #define EXIT_DEAD 0x00000010 #define EXIT_ZOMBIE 0x00000020 #define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD) /* Used in tsk->__state again: */ #define TASK_PARKED 0x00000040 #define TASK_DEAD 0x00000080 #define TASK_WAKEKILL 0x00000100 #define TASK_WAKING 0x00000200 #define TASK_NOLOAD 0x00000400 #define TASK_NEW 0x00000800 #define TASK_RTLOCK_WAIT 0x00001000 #define TASK_FREEZABLE 0x00002000 #define __TASK_FREEZABLE_UNSAFE (0x00004000 * IS_ENABLED(CONFIG_LOCKDEP)) #define TASK_FROZEN 0x00008000 #define TASK_STATE_MAX 0x00010000 #define TASK_ANY (TASK_STATE_MAX-1) /* * DO NOT ADD ANY NEW USERS ! */ #define TASK_FREEZABLE_UNSAFE (TASK_FREEZABLE | __TASK_FREEZABLE_UNSAFE) /* Convenience macros for the sake of set_current_state: */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) #define TASK_STOPPED (TASK_WAKEKILL | __TASK_STOPPED) #define TASK_TRACED __TASK_TRACED #define TASK_IDLE (TASK_UNINTERRUPTIBLE | TASK_NOLOAD) /* Convenience macros for the sake of wake_up(): */ #define TASK_NORMAL (TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE) /* get_task_state(): */ #define TASK_REPORT (TASK_RUNNING | TASK_INTERRUPTIBLE | \ TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \ __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \ TASK_PARKED) #define task_is_running(task) (READ_ONCE((task)->__state) == TASK_RUNNING) #define task_is_traced(task) ((READ_ONCE(task->jobctl) & JOBCTL_TRACED) != 0) #define task_is_stopped(task) ((READ_ONCE(task->jobctl) & JOBCTL_STOPPED) != 0) #define task_is_stopped_or_traced(task) ((READ_ONCE(task->jobctl) & (JOBCTL_STOPPED | JOBCTL_TRACED)) != 0) /* * Special states are those that do not use the normal wait-loop pattern. See * the comment with set_special_state(). */ #define is_special_task_state(state) \ ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | \ TASK_DEAD | TASK_FROZEN)) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP # define debug_normal_state_change(state_value) \ do { \ WARN_ON_ONCE(is_special_task_state(state_value)); \ current->task_state_change = _THIS_IP_; \ } while (0) # define debug_special_state_change(state_value) \ do { \ WARN_ON_ONCE(!is_special_task_state(state_value)); \ current->task_state_change = _THIS_IP_; \ } while (0) # define debug_rtlock_wait_set_state() \ do { \ current->saved_state_change = current->task_state_change;\ current->task_state_change = _THIS_IP_; \ } while (0) # define debug_rtlock_wait_restore_state() \ do { \ current->task_state_change = current->saved_state_change;\ } while (0) #else # define debug_normal_state_change(cond) do { } while (0) # define debug_special_state_change(cond) do { } while (0) # define debug_rtlock_wait_set_state() do { } while (0) # define debug_rtlock_wait_restore_state() do { } while (0) #endif /* * set_current_state() includes a barrier so that the write of current->__state * is correctly serialised wrt the caller's subsequent test of whether to * actually sleep: * * for (;;) { * set_current_state(TASK_UNINTERRUPTIBLE); * if (CONDITION) * break; * * schedule(); * } * __set_current_state(TASK_RUNNING); * * If the caller does not need such serialisation (because, for instance, the * CONDITION test and condition change and wakeup are under the same lock) then * use __set_current_state(). * * The above is typically ordered against the wakeup, which does: * * CONDITION = 1; * wake_up_state(p, TASK_UNINTERRUPTIBLE); * * where wake_up_state()/try_to_wake_up() executes a full memory barrier before * accessing p->__state. * * Wakeup will do: if (@state & p->__state) p->__state = TASK_RUNNING, that is, * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a * TASK_RUNNING store which can collide with __set_current_state(TASK_RUNNING). * * However, with slightly different timing the wakeup TASK_RUNNING store can * also collide with the TASK_UNINTERRUPTIBLE store. Losing that store is not * a problem either because that will result in one extra go around the loop * and our @cond test will save the day. * * Also see the comments of try_to_wake_up(). */ #define __set_current_state(state_value) \ do { \ debug_normal_state_change((state_value)); \ WRITE_ONCE(current->__state, (state_value)); \ } while (0) #define set_current_state(state_value) \ do { \ debug_normal_state_change((state_value)); \ smp_store_mb(current->__state, (state_value)); \ } while (0) /* * set_special_state() should be used for those states when the blocking task * can not use the regular condition based wait-loop. In that case we must * serialize against wakeups such that any possible in-flight TASK_RUNNING * stores will not collide with our state change. */ #define set_special_state(state_value) \ do { \ unsigned long flags; /* may shadow */ \ \ raw_spin_lock_irqsave(¤t->pi_lock, flags); \ debug_special_state_change((state_value)); \ WRITE_ONCE(current->__state, (state_value)); \ raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \ } while (0) /* * PREEMPT_RT specific variants for "sleeping" spin/rwlocks * * RT's spin/rwlock substitutions are state preserving. The state of the * task when blocking on the lock is saved in task_struct::saved_state and * restored after the lock has been acquired. These operations are * serialized by task_struct::pi_lock against try_to_wake_up(). Any non RT * lock related wakeups while the task is blocked on the lock are * redirected to operate on task_struct::saved_state to ensure that these * are not dropped. On restore task_struct::saved_state is set to * TASK_RUNNING so any wakeup attempt redirected to saved_state will fail. * * The lock operation looks like this: * * current_save_and_set_rtlock_wait_state(); * for (;;) { * if (try_lock()) * break; * raw_spin_unlock_irq(&lock->wait_lock); * schedule_rtlock(); * raw_spin_lock_irq(&lock->wait_lock); * set_current_state(TASK_RTLOCK_WAIT); * } * current_restore_rtlock_saved_state(); */ #define current_save_and_set_rtlock_wait_state() \ do { \ lockdep_assert_irqs_disabled(); \ raw_spin_lock(¤t->pi_lock); \ current->saved_state = current->__state; \ debug_rtlock_wait_set_state(); \ WRITE_ONCE(current->__state, TASK_RTLOCK_WAIT); \ raw_spin_unlock(¤t->pi_lock); \ } while (0); #define current_restore_rtlock_saved_state() \ do { \ lockdep_assert_irqs_disabled(); \ raw_spin_lock(¤t->pi_lock); \ debug_rtlock_wait_restore_state(); \ WRITE_ONCE(current->__state, current->saved_state); \ current->saved_state = TASK_RUNNING; \ raw_spin_unlock(¤t->pi_lock); \ } while (0); #define get_current_state() READ_ONCE(current->__state) /* * Define the task command name length as enum, then it can be visible to * BPF programs. */ enum { TASK_COMM_LEN = 16, }; extern void sched_tick(void); #define MAX_SCHEDULE_TIMEOUT LONG_MAX extern long schedule_timeout(long timeout); extern long schedule_timeout_interruptible(long timeout); extern long schedule_timeout_killable(long timeout); extern long schedule_timeout_uninterruptible(long timeout); extern long schedule_timeout_idle(long timeout); asmlinkage void schedule(void); extern void schedule_preempt_disabled(void); asmlinkage void preempt_schedule_irq(void); #ifdef CONFIG_PREEMPT_RT extern void schedule_rtlock(void); #endif extern int __must_check io_schedule_prepare(void); extern void io_schedule_finish(int token); extern long io_schedule_timeout(long timeout); extern void io_schedule(void); /** * struct prev_cputime - snapshot of system and user cputime * @utime: time spent in user mode * @stime: time spent in system mode * @lock: protects the above two fields * * Stores previous user/system time values such that we can guarantee * monotonicity. */ struct prev_cputime { #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE u64 utime; u64 stime; raw_spinlock_t lock; #endif }; enum vtime_state { /* Task is sleeping or running in a CPU with VTIME inactive: */ VTIME_INACTIVE = 0, /* Task is idle */ VTIME_IDLE, /* Task runs in kernelspace in a CPU with VTIME active: */ VTIME_SYS, /* Task runs in userspace in a CPU with VTIME active: */ VTIME_USER, /* Task runs as guests in a CPU with VTIME active: */ VTIME_GUEST, }; struct vtime { seqcount_t seqcount; unsigned long long starttime; enum vtime_state state; unsigned int cpu; u64 utime; u64 stime; u64 gtime; }; /* * Utilization clamp constraints. * @UCLAMP_MIN: Minimum utilization * @UCLAMP_MAX: Maximum utilization * @UCLAMP_CNT: Utilization clamp constraints count */ enum uclamp_id { UCLAMP_MIN = 0, UCLAMP_MAX, UCLAMP_CNT }; #ifdef CONFIG_SMP extern struct root_domain def_root_domain; extern struct mutex sched_domains_mutex; #endif struct sched_param { int sched_priority; }; struct sched_info { #ifdef CONFIG_SCHED_INFO /* Cumulative counters: */ /* # of times we have run on this CPU: */ unsigned long pcount; /* Time spent waiting on a runqueue: */ unsigned long long run_delay; /* Timestamps: */ /* When did we last run on a CPU? */ unsigned long long last_arrival; /* When were we last queued to run? */ unsigned long long last_queued; #endif /* CONFIG_SCHED_INFO */ }; /* * Integer metrics need fixed point arithmetic, e.g., sched/fair * has a few: load, load_avg, util_avg, freq, and capacity. * * We define a basic fixed point arithmetic range, and then formalize * all these metrics based on that basic range. */ # define SCHED_FIXEDPOINT_SHIFT 10 # define SCHED_FIXEDPOINT_SCALE (1L << SCHED_FIXEDPOINT_SHIFT) /* Increase resolution of cpu_capacity calculations */ # define SCHED_CAPACITY_SHIFT SCHED_FIXEDPOINT_SHIFT # define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT) struct load_weight { unsigned long weight; u32 inv_weight; }; /* * The load/runnable/util_avg accumulates an infinite geometric series * (see __update_load_avg_cfs_rq() in kernel/sched/pelt.c). * * [load_avg definition] * * load_avg = runnable% * scale_load_down(load) * * [runnable_avg definition] * * runnable_avg = runnable% * SCHED_CAPACITY_SCALE * * [util_avg definition] * * util_avg = running% * SCHED_CAPACITY_SCALE * * where runnable% is the time ratio that a sched_entity is runnable and * running% the time ratio that a sched_entity is running. * * For cfs_rq, they are the aggregated values of all runnable and blocked * sched_entities. * * The load/runnable/util_avg doesn't directly factor frequency scaling and CPU * capacity scaling. The scaling is done through the rq_clock_pelt that is used * for computing those signals (see update_rq_clock_pelt()) * * N.B., the above ratios (runnable% and running%) themselves are in the * range of [0, 1]. To do fixed point arithmetics, we therefore scale them * to as large a range as necessary. This is for example reflected by * util_avg's SCHED_CAPACITY_SCALE. * * [Overflow issue] * * The 64-bit load_sum can have 4353082796 (=2^64/47742/88761) entities * with the highest load (=88761), always runnable on a single cfs_rq, * and should not overflow as the number already hits PID_MAX_LIMIT. * * For all other cases (including 32-bit kernels), struct load_weight's * weight will overflow first before we do, because: * * Max(load_avg) <= Max(load.weight) * * Then it is the load_weight's responsibility to consider overflow * issues. */ struct sched_avg { u64 last_update_time; u64 load_sum; u64 runnable_sum; u32 util_sum; u32 period_contrib; unsigned long load_avg; unsigned long runnable_avg; unsigned long util_avg; unsigned int util_est; } ____cacheline_aligned; /* * The UTIL_AVG_UNCHANGED flag is used to synchronize util_est with util_avg * updates. When a task is dequeued, its util_est should not be updated if its * util_avg has not been updated in the meantime. * This information is mapped into the MSB bit of util_est at dequeue time. * Since max value of util_est for a task is 1024 (PELT util_avg for a task) * it is safe to use MSB. */ #define UTIL_EST_WEIGHT_SHIFT 2 #define UTIL_AVG_UNCHANGED 0x80000000 struct sched_statistics { #ifdef CONFIG_SCHEDSTATS u64 wait_start; u64 wait_max; u64 wait_count; u64 wait_sum; u64 iowait_count; u64 iowait_sum; u64 sleep_start; u64 sleep_max; s64 sum_sleep_runtime; u64 block_start; u64 block_max; s64 sum_block_runtime; s64 exec_max; u64 slice_max; u64 nr_migrations_cold; u64 nr_failed_migrations_affine; u64 nr_failed_migrations_running; u64 nr_failed_migrations_hot; u64 nr_forced_migrations; u64 nr_wakeups; u64 nr_wakeups_sync; u64 nr_wakeups_migrate; u64 nr_wakeups_local; u64 nr_wakeups_remote; u64 nr_wakeups_affine; u64 nr_wakeups_affine_attempts; u64 nr_wakeups_passive; u64 nr_wakeups_idle; #ifdef CONFIG_SCHED_CORE u64 core_forceidle_sum; #endif #endif /* CONFIG_SCHEDSTATS */ } ____cacheline_aligned; struct sched_entity { /* For load-balancing: */ struct load_weight load; struct rb_node run_node; u64 deadline; u64 min_vruntime; u64 min_slice; struct list_head group_node; unsigned char on_rq; unsigned char sched_delayed; unsigned char rel_deadline; unsigned char custom_slice; /* hole */ u64 exec_start; u64 sum_exec_runtime; u64 prev_sum_exec_runtime; u64 vruntime; s64 vlag; u64 slice; u64 nr_migrations; #ifdef CONFIG_FAIR_GROUP_SCHED int depth; struct sched_entity *parent; /* rq on which this entity is (to be) queued: */ struct cfs_rq *cfs_rq; /* rq "owned" by this entity/group: */ struct cfs_rq *my_q; /* cached value of my_q->h_nr_running */ unsigned long runnable_weight; #endif #ifdef CONFIG_SMP /* * Per entity load average tracking. * * Put into separate cache line so it does not * collide with read-mostly values above. */ struct sched_avg avg; #endif }; struct sched_rt_entity { struct list_head run_list; unsigned long timeout; unsigned long watchdog_stamp; unsigned int time_slice; unsigned short on_rq; unsigned short on_list; struct sched_rt_entity *back; #ifdef CONFIG_RT_GROUP_SCHED struct sched_rt_entity *parent; /* rq on which this entity is (to be) queued: */ struct rt_rq *rt_rq; /* rq "owned" by this entity/group: */ struct rt_rq *my_q; #endif } __randomize_layout; typedef bool (*dl_server_has_tasks_f)(struct sched_dl_entity *); typedef struct task_struct *(*dl_server_pick_f)(struct sched_dl_entity *); struct sched_dl_entity { struct rb_node rb_node; /* * Original scheduling parameters. Copied here from sched_attr * during sched_setattr(), they will remain the same until * the next sched_setattr(). */ u64 dl_runtime; /* Maximum runtime for each instance */ u64 dl_deadline; /* Relative deadline of each instance */ u64 dl_period; /* Separation of two instances (period) */ u64 dl_bw; /* dl_runtime / dl_period */ u64 dl_density; /* dl_runtime / dl_deadline */ /* * Actual scheduling parameters. Initialized with the values above, * they are continuously updated during task execution. Note that * the remaining runtime could be < 0 in case we are in overrun. */ s64 runtime; /* Remaining runtime for this instance */ u64 deadline; /* Absolute deadline for this instance */ unsigned int flags; /* Specifying the scheduler behaviour */ /* * Some bool flags: * * @dl_throttled tells if we exhausted the runtime. If so, the * task has to wait for a replenishment to be performed at the * next firing of dl_timer. * * @dl_yielded tells if task gave up the CPU before consuming * all its available runtime during the last job. * * @dl_non_contending tells if the task is inactive while still * contributing to the active utilization. In other words, it * indicates if the inactive timer has been armed and its handler * has not been executed yet. This flag is useful to avoid race * conditions between the inactive timer handler and the wakeup * code. * * @dl_overrun tells if the task asked to be informed about runtime * overruns. * * @dl_server tells if this is a server entity. * * @dl_defer tells if this is a deferred or regular server. For * now only defer server exists. * * @dl_defer_armed tells if the deferrable server is waiting * for the replenishment timer to activate it. * * @dl_server_active tells if the dlserver is active(started). * dlserver is started on first cfs enqueue on an idle runqueue * and is stopped when a dequeue results in 0 cfs tasks on the * runqueue. In other words, dlserver is active only when cpu's * runqueue has atleast one cfs task. * * @dl_defer_running tells if the deferrable server is actually * running, skipping the defer phase. */ unsigned int dl_throttled : 1; unsigned int dl_yielded : 1; unsigned int dl_non_contending : 1; unsigned int dl_overrun : 1; unsigned int dl_server : 1; unsigned int dl_server_active : 1; unsigned int dl_defer : 1; unsigned int dl_defer_armed : 1; unsigned int dl_defer_running : 1; /* * Bandwidth enforcement timer. Each -deadline task has its * own bandwidth to be enforced, thus we need one timer per task. */ struct hrtimer dl_timer; /* * Inactive timer, responsible for decreasing the active utilization * at the "0-lag time". When a -deadline task blocks, it contributes * to GRUB's active utilization until the "0-lag time", hence a * timer is needed to decrease the active utilization at the correct * time. */ struct hrtimer inactive_timer; /* * Bits for DL-server functionality. Also see the comment near * dl_server_update(). * * @rq the runqueue this server is for * * @server_has_tasks() returns true if @server_pick return a * runnable task. */ struct rq *rq; dl_server_has_tasks_f server_has_tasks; dl_server_pick_f server_pick_task; #ifdef CONFIG_RT_MUTEXES /* * Priority Inheritance. When a DEADLINE scheduling entity is boosted * pi_se points to the donor, otherwise points to the dl_se it belongs * to (the original one/itself). */ struct sched_dl_entity *pi_se; #endif }; #ifdef CONFIG_UCLAMP_TASK /* Number of utilization clamp buckets (shorter alias) */ #define UCLAMP_BUCKETS CONFIG_UCLAMP_BUCKETS_COUNT /* * Utilization clamp for a scheduling entity * @value: clamp value "assigned" to a se * @bucket_id: bucket index corresponding to the "assigned" value * @active: the se is currently refcounted in a rq's bucket * @user_defined: the requested clamp value comes from user-space * * The bucket_id is the index of the clamp bucket matching the clamp value * which is pre-computed and stored to avoid expensive integer divisions from * the fast path. * * The active bit is set whenever a task has got an "effective" value assigned, * which can be different from the clamp value "requested" from user-space. * This allows to know a task is refcounted in the rq's bucket corresponding * to the "effective" bucket_id. * * The user_defined bit is set whenever a task has got a task-specific clamp * value requested from userspace, i.e. the system defaults apply to this task * just as a restriction. This allows to relax default clamps when a less * restrictive task-specific value has been requested, thus allowing to * implement a "nice" semantic. For example, a task running with a 20% * default boost can still drop its own boosting to 0%. */ struct uclamp_se { unsigned int value : bits_per(SCHED_CAPACITY_SCALE); unsigned int bucket_id : bits_per(UCLAMP_BUCKETS); unsigned int active : 1; unsigned int user_defined : 1; }; #endif /* CONFIG_UCLAMP_TASK */ union rcu_special { struct { u8 blocked; u8 need_qs; u8 exp_hint; /* Hint for performance. */ u8 need_mb; /* Readers need smp_mb(). */ } b; /* Bits. */ u32 s; /* Set of bits. */ }; enum perf_event_task_context { perf_invalid_context = -1, perf_hw_context = 0, perf_sw_context, perf_nr_task_contexts, }; /* * Number of contexts where an event can trigger: * task, softirq, hardirq, nmi. */ #define PERF_NR_CONTEXTS 4 struct wake_q_node { struct wake_q_node *next; }; struct kmap_ctrl { #ifdef CONFIG_KMAP_LOCAL int idx; pte_t pteval[KM_MAX_IDX]; #endif }; struct task_struct { #ifdef CONFIG_THREAD_INFO_IN_TASK /* * For reasons of header soup (see current_thread_info()), this * must be the first element of task_struct. */ struct thread_info thread_info; #endif unsigned int __state; /* saved state for "spinlock sleepers" */ unsigned int saved_state; /* * This begins the randomizable portion of task_struct. Only * scheduling-critical items should be added above here. */ randomized_struct_fields_start void *stack; refcount_t usage; /* Per task flags (PF_*), defined further below: */ unsigned int flags; unsigned int ptrace; #ifdef CONFIG_MEM_ALLOC_PROFILING struct alloc_tag *alloc_tag; #endif #ifdef CONFIG_SMP int on_cpu; struct __call_single_node wake_entry; unsigned int wakee_flips; unsigned long wakee_flip_decay_ts; struct task_struct *last_wakee; /* * recent_used_cpu is initially set as the last CPU used by a task * that wakes affine another task. Waker/wakee relationships can * push tasks around a CPU where each wakeup moves to the next one. * Tracking a recently used CPU allows a quick search for a recently * used CPU that may be idle. */ int recent_used_cpu; int wake_cpu; #endif int on_rq; int prio; int static_prio; int normal_prio; unsigned int rt_priority; struct sched_entity se; struct sched_rt_entity rt; struct sched_dl_entity dl; struct sched_dl_entity *dl_server; #ifdef CONFIG_SCHED_CLASS_EXT struct sched_ext_entity scx; #endif const struct sched_class *sched_class; #ifdef CONFIG_SCHED_CORE struct rb_node core_node; unsigned long core_cookie; unsigned int core_occupation; #endif #ifdef CONFIG_CGROUP_SCHED struct task_group *sched_task_group; #endif #ifdef CONFIG_UCLAMP_TASK /* * Clamp values requested for a scheduling entity. * Must be updated with task_rq_lock() held. */ struct uclamp_se uclamp_req[UCLAMP_CNT]; /* * Effective clamp values used for a scheduling entity. * Must be updated with task_rq_lock() held. */ struct uclamp_se uclamp[UCLAMP_CNT]; #endif struct sched_statistics stats; #ifdef CONFIG_PREEMPT_NOTIFIERS /* List of struct preempt_notifier: */ struct hlist_head preempt_notifiers; #endif #ifdef CONFIG_BLK_DEV_IO_TRACE unsigned int btrace_seq; #endif unsigned int policy; unsigned long max_allowed_capacity; int nr_cpus_allowed; const cpumask_t *cpus_ptr; cpumask_t *user_cpus_ptr; cpumask_t cpus_mask; void *migration_pending; #ifdef CONFIG_SMP unsigned short migration_disabled; #endif unsigned short migration_flags; #ifdef CONFIG_PREEMPT_RCU int rcu_read_lock_nesting; union rcu_special rcu_read_unlock_special; struct list_head rcu_node_entry; struct rcu_node *rcu_blocked_node; #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TASKS_RCU unsigned long rcu_tasks_nvcsw; u8 rcu_tasks_holdout; u8 rcu_tasks_idx; int rcu_tasks_idle_cpu; struct list_head rcu_tasks_holdout_list; int rcu_tasks_exit_cpu; struct list_head rcu_tasks_exit_list; #endif /* #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_TRACE_RCU int trc_reader_nesting; int trc_ipi_to_cpu; union rcu_special trc_reader_special; struct list_head trc_holdout_list; struct list_head trc_blkd_node; int trc_blkd_cpu; #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ struct sched_info sched_info; struct list_head tasks; #ifdef CONFIG_SMP struct plist_node pushable_tasks; struct rb_node pushable_dl_tasks; #endif struct mm_struct *mm; struct mm_struct *active_mm; struct address_space *faults_disabled_mapping; int exit_state; int exit_code; int exit_signal; /* The signal sent when the parent dies: */ int pdeath_signal; /* JOBCTL_*, siglock protected: */ unsigned long jobctl; /* Used for emulating ABI behavior of previous Linux versions: */ unsigned int personality; /* Scheduler bits, serialized by scheduler locks: */ unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; /* Force alignment to the next boundary: */ unsigned :0; /* Unserialized, strictly 'current' */ /* * This field must not be in the scheduler word above due to wakelist * queueing no longer being serialized by p->on_cpu. However: * * p->XXX = X; ttwu() * schedule() if (p->on_rq && ..) // false * smp_mb__after_spinlock(); if (smp_load_acquire(&p->on_cpu) && //true * deactivate_task() ttwu_queue_wakelist()) * p->on_rq = 0; p->sched_remote_wakeup = Y; * * guarantees all stores of 'current' are visible before * ->sched_remote_wakeup gets used, so it can be in this word. */ unsigned sched_remote_wakeup:1; #ifdef CONFIG_RT_MUTEXES unsigned sched_rt_mutex:1; #endif /* Bit to tell TOMOYO we're in execve(): */ unsigned in_execve:1; unsigned in_iowait:1; #ifndef TIF_RESTORE_SIGMASK unsigned restore_sigmask:1; #endif #ifdef CONFIG_MEMCG_V1 unsigned in_user_fault:1; #endif #ifdef CONFIG_LRU_GEN /* whether the LRU algorithm may apply to this access */ unsigned in_lru_fault:1; #endif #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; #endif #ifdef CONFIG_CGROUPS /* disallow userland-initiated cgroup migration */ unsigned no_cgroup_migration:1; /* task is frozen/stopped (used by the cgroup freezer) */ unsigned frozen:1; #endif #ifdef CONFIG_BLK_CGROUP unsigned use_memdelay:1; #endif #ifdef CONFIG_PSI /* Stalled due to lack of memory */ unsigned in_memstall:1; #endif #ifdef CONFIG_PAGE_OWNER /* Used by page_owner=on to detect recursion in page tracking. */ unsigned in_page_owner:1; #endif #ifdef CONFIG_EVENTFD /* Recursion prevention for eventfd_signal() */ unsigned in_eventfd:1; #endif #ifdef CONFIG_ARCH_HAS_CPU_PASID unsigned pasid_activated:1; #endif #ifdef CONFIG_X86_BUS_LOCK_DETECT unsigned reported_split_lock:1; #endif #ifdef CONFIG_TASK_DELAY_ACCT /* delay due to memory thrashing */ unsigned in_thrashing:1; #endif #ifdef CONFIG_PREEMPT_RT struct netdev_xmit net_xmit; #endif unsigned long atomic_flags; /* Flags requiring atomic access. */ struct restart_block restart_block; pid_t pid; pid_t tgid; #ifdef CONFIG_STACKPROTECTOR /* Canary value for the -fstack-protector GCC feature: */ unsigned long stack_canary; #endif /* * Pointers to the (original) parent process, youngest child, younger sibling, * older sibling, respectively. (p->father can be replaced with * p->real_parent->pid) */ /* Real parent process: */ struct task_struct __rcu *real_parent; /* Recipient of SIGCHLD, wait4() reports: */ struct task_struct __rcu *parent; /* * Children/sibling form the list of natural children: */ struct list_head children; struct list_head sibling; struct task_struct *group_leader; /* * 'ptraced' is the list of tasks this task is using ptrace() on. * * This includes both natural children and PTRACE_ATTACH targets. * 'ptrace_entry' is this task's link on the p->parent->ptraced list. */ struct list_head ptraced; struct list_head ptrace_entry; /* PID/PID hash table linkage. */ struct pid *thread_pid; struct hlist_node pid_links[PIDTYPE_MAX]; struct list_head thread_node; struct completion *vfork_done; /* CLONE_CHILD_SETTID: */ int __user *set_child_tid; /* CLONE_CHILD_CLEARTID: */ int __user *clear_child_tid; /* PF_KTHREAD | PF_IO_WORKER */ void *worker_private; u64 utime; u64 stime; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME u64 utimescaled; u64 stimescaled; #endif u64 gtime; struct prev_cputime prev_cputime; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN struct vtime vtime; #endif #ifdef CONFIG_NO_HZ_FULL atomic_t tick_dep_mask; #endif /* Context switch counts: */ unsigned long nvcsw; unsigned long nivcsw; /* Monotonic time in nsecs: */ u64 start_time; /* Boot based time in nsecs: */ u64 start_boottime; /* MM fault and swap info: this can arguably be seen as either mm-specific or thread-specific: */ unsigned long min_flt; unsigned long maj_flt; /* Empty if CONFIG_POSIX_CPUTIMERS=n */ struct posix_cputimers posix_cputimers; #ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK struct posix_cputimers_work posix_cputimers_work; #endif /* Process credentials: */ /* Tracer's credentials at attach: */ const struct cred __rcu *ptracer_cred; /* Objective and real subjective task credentials (COW): */ const struct cred __rcu *real_cred; /* Effective (overridable) subjective task credentials (COW): */ const struct cred __rcu *cred; #ifdef CONFIG_KEYS /* Cached requested key. */ struct key *cached_requested_key; #endif /* * executable name, excluding path. * * - normally initialized begin_new_exec() * - set it with set_task_comm() * - strscpy_pad() to ensure it is always NUL-terminated and * zero-padded * - task_lock() to ensure the operation is atomic and the name is * fully updated. */ char comm[TASK_COMM_LEN]; struct nameidata *nameidata; #ifdef CONFIG_SYSVIPC struct sysv_sem sysvsem; struct sysv_shm sysvshm; #endif #ifdef CONFIG_DETECT_HUNG_TASK unsigned long last_switch_count; unsigned long last_switch_time; #endif /* Filesystem information: */ struct fs_struct *fs; /* Open file information: */ struct files_struct *files; #ifdef CONFIG_IO_URING struct io_uring_task *io_uring; #endif /* Namespaces: */ struct nsproxy *nsproxy; /* Signal handlers: */ struct signal_struct *signal; struct sighand_struct __rcu *sighand; sigset_t blocked; sigset_t real_blocked; /* Restored if set_restore_sigmask() was used: */ sigset_t saved_sigmask; struct sigpending pending; unsigned long sas_ss_sp; size_t sas_ss_size; unsigned int sas_ss_flags; struct callback_head *task_works; #ifdef CONFIG_AUDIT #ifdef CONFIG_AUDITSYSCALL struct audit_context *audit_context; #endif kuid_t loginuid; unsigned int sessionid; #endif struct seccomp seccomp; struct syscall_user_dispatch syscall_dispatch; /* Thread group tracking: */ u64 parent_exec_id; u64 self_exec_id; /* Protection against (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed, mempolicy: */ spinlock_t alloc_lock; /* Protection of the PI data structures: */ raw_spinlock_t pi_lock; struct wake_q_node wake_q; #ifdef CONFIG_RT_MUTEXES /* PI waiters blocked on a rt_mutex held by this task: */ struct rb_root_cached pi_waiters; /* Updated under owner's pi_lock and rq lock */ struct task_struct *pi_top_task; /* Deadlock detection and priority inheritance handling: */ struct rt_mutex_waiter *pi_blocked_on; #endif #ifdef CONFIG_DEBUG_MUTEXES /* Mutex deadlock detection: */ struct mutex_waiter *blocked_on; #endif #ifdef CONFIG_DEBUG_ATOMIC_SLEEP int non_block_count; #endif #ifdef CONFIG_TRACE_IRQFLAGS struct irqtrace_events irqtrace; unsigned int hardirq_threaded; u64 hardirq_chain_key; int softirqs_enabled; int softirq_context; int irq_config; #endif #ifdef CONFIG_PREEMPT_RT int softirq_disable_cnt; #endif #ifdef CONFIG_LOCKDEP # define MAX_LOCK_DEPTH 48UL u64 curr_chain_key; int lockdep_depth; unsigned int lockdep_recursion; struct held_lock held_locks[MAX_LOCK_DEPTH]; #endif #if defined(CONFIG_UBSAN) && !defined(CONFIG_UBSAN_TRAP) unsigned int in_ubsan; #endif /* Journalling filesystem info: */ void *journal_info; /* Stacked block device info: */ struct bio_list *bio_list; /* Stack plugging: */ struct blk_plug *plug; /* VM state: */ struct reclaim_state *reclaim_state; struct io_context *io_context; #ifdef CONFIG_COMPACTION struct capture_control *capture_control; #endif /* Ptrace state: */ unsigned long ptrace_message; kernel_siginfo_t *last_siginfo; struct task_io_accounting ioac; #ifdef CONFIG_PSI /* Pressure stall state */ unsigned int psi_flags; #endif #ifdef CONFIG_TASK_XACCT /* Accumulated RSS usage: */ u64 acct_rss_mem1; /* Accumulated virtual memory usage: */ u64 acct_vm_mem1; /* stime + utime since last update: */ u64 acct_timexpd; #endif #ifdef CONFIG_CPUSETS /* Protected by ->alloc_lock: */ nodemask_t mems_allowed; /* Sequence number to catch updates: */ seqcount_spinlock_t mems_allowed_seq; int cpuset_mem_spread_rotor; #endif #ifdef CONFIG_CGROUPS /* Control Group info protected by css_set_lock: */ struct css_set __rcu *cgroups; /* cg_list protected by css_set_lock and tsk->alloc_lock: */ struct list_head cg_list; #endif #ifdef CONFIG_X86_CPU_RESCTRL u32 closid; u32 rmid; #endif #ifdef CONFIG_FUTEX struct robust_list_head __user *robust_list; #ifdef CONFIG_COMPAT struct compat_robust_list_head __user *compat_robust_list; #endif struct list_head pi_state_list; struct futex_pi_state *pi_state_cache; struct mutex futex_exit_mutex; unsigned int futex_state; #endif #ifdef CONFIG_PERF_EVENTS u8 perf_recursion[PERF_NR_CONTEXTS]; struct perf_event_context *perf_event_ctxp; struct mutex perf_event_mutex; struct list_head perf_event_list; #endif #ifdef CONFIG_DEBUG_PREEMPT unsigned long preempt_disable_ip; #endif #ifdef CONFIG_NUMA /* Protected by alloc_lock: */ struct mempolicy *mempolicy; short il_prev; u8 il_weight; short pref_node_fork; #endif #ifdef CONFIG_NUMA_BALANCING int numa_scan_seq; unsigned int numa_scan_period; unsigned int numa_scan_period_max; int numa_preferred_nid; unsigned long numa_migrate_retry; /* Migration stamp: */ u64 node_stamp; u64 last_task_numa_placement; u64 last_sum_exec_runtime; struct callback_head numa_work; /* * This pointer is only modified for current in syscall and * pagefault context (and for tasks being destroyed), so it can be read * from any of the following contexts: * - RCU read-side critical section * - current->numa_group from everywhere * - task's runqueue locked, task not running */ struct numa_group __rcu *numa_group; /* * numa_faults is an array split into four regions: * faults_memory, faults_cpu, faults_memory_buffer, faults_cpu_buffer * in this precise order. * * faults_memory: Exponential decaying average of faults on a per-node * basis. Scheduling placement decisions are made based on these * counts. The values remain static for the duration of a PTE scan. * faults_cpu: Track the nodes the process was running on when a NUMA * hinting fault was incurred. * faults_memory_buffer and faults_cpu_buffer: Record faults per node * during the current scan window. When the scan completes, the counts * in faults_memory and faults_cpu decay and these values are copied. */ unsigned long *numa_faults; unsigned long total_numa_faults; /* * numa_faults_locality tracks if faults recorded during the last * scan window were remote/local or failed to migrate. The task scan * period is adapted based on the locality of the faults with different * weights depending on whether they were shared or private faults */ unsigned long numa_faults_locality[3]; unsigned long numa_pages_migrated; #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_RSEQ struct rseq __user *rseq; u32 rseq_len; u32 rseq_sig; /* * RmW on rseq_event_mask must be performed atomically * with respect to preemption. */ unsigned long rseq_event_mask; #endif #ifdef CONFIG_SCHED_MM_CID int mm_cid; /* Current cid in mm */ int last_mm_cid; /* Most recent cid in mm */ int migrate_from_cpu; int mm_cid_active; /* Whether cid bitmap is active */ struct callback_head cid_work; #endif struct tlbflush_unmap_batch tlb_ubc; /* Cache last used pipe for splice(): */ struct pipe_inode_info *splice_pipe; struct page_frag task_frag; #ifdef CONFIG_TASK_DELAY_ACCT struct task_delay_info *delays; #endif #ifdef CONFIG_FAULT_INJECTION int make_it_fail; unsigned int fail_nth; #endif /* * When (nr_dirtied >= nr_dirtied_pause), it's time to call * balance_dirty_pages() for a dirty throttling pause: */ int nr_dirtied; int nr_dirtied_pause; /* Start of a write-and-pause period: */ unsigned long dirty_paused_when; #ifdef CONFIG_LATENCYTOP int latency_record_count; struct latency_record latency_record[LT_SAVECOUNT]; #endif /* * Time slack values; these are used to round up poll() and * select() etc timeout values. These are in nanoseconds. */ u64 timer_slack_ns; u64 default_timer_slack_ns; #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) unsigned int kasan_depth; #endif #ifdef CONFIG_KCSAN struct kcsan_ctx kcsan_ctx; #ifdef CONFIG_TRACE_IRQFLAGS struct irqtrace_events kcsan_save_irqtrace; #endif #ifdef CONFIG_KCSAN_WEAK_MEMORY int kcsan_stack_depth; #endif #endif #ifdef CONFIG_KMSAN struct kmsan_ctx kmsan_ctx; #endif #if IS_ENABLED(CONFIG_KUNIT) struct kunit *kunit_test; #endif #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* Index of current stored address in ret_stack: */ int curr_ret_stack; int curr_ret_depth; /* Stack of return addresses for return function tracing: */ unsigned long *ret_stack; /* Timestamp for last schedule: */ unsigned long long ftrace_timestamp; unsigned long long ftrace_sleeptime; /* * Number of functions that haven't been traced * because of depth overrun: */ atomic_t trace_overrun; /* Pause tracing: */ atomic_t tracing_graph_pause; #endif #ifdef CONFIG_TRACING /* Bitmask and counter of trace recursion: */ unsigned long trace_recursion; #endif /* CONFIG_TRACING */ #ifdef CONFIG_KCOV /* See kernel/kcov.c for more details. */ /* Coverage collection mode enabled for this task (0 if disabled): */ unsigned int kcov_mode; /* Size of the kcov_area: */ unsigned int kcov_size; /* Buffer for coverage collection: */ void *kcov_area; /* KCOV descriptor wired with this task or NULL: */ struct kcov *kcov; /* KCOV common handle for remote coverage collection: */ u64 kcov_handle; /* KCOV sequence number: */ int kcov_sequence; /* Collect coverage from softirq context: */ unsigned int kcov_softirq; #endif #ifdef CONFIG_MEMCG_V1 struct mem_cgroup *memcg_in_oom; #endif #ifdef CONFIG_MEMCG /* Number of pages to reclaim on returning to userland: */ unsigned int memcg_nr_pages_over_high; /* Used by memcontrol for targeted memcg charge: */ struct mem_cgroup *active_memcg; /* Cache for current->cgroups->memcg->objcg lookups: */ struct obj_cgroup *objcg; #endif #ifdef CONFIG_BLK_CGROUP struct gendisk *throttle_disk; #endif #ifdef CONFIG_UPROBES struct uprobe_task *utask; #endif #if defined(CONFIG_BCACHE) || defined(CONFIG_BCACHE_MODULE) unsigned int sequential_io; unsigned int sequential_io_avg; #endif struct kmap_ctrl kmap_ctrl; #ifdef CONFIG_DEBUG_ATOMIC_SLEEP unsigned long task_state_change; # ifdef CONFIG_PREEMPT_RT unsigned long saved_state_change; # endif #endif struct rcu_head rcu; refcount_t rcu_users; int pagefault_disabled; #ifdef CONFIG_MMU struct task_struct *oom_reaper_list; struct timer_list oom_reaper_timer; #endif #ifdef CONFIG_VMAP_STACK struct vm_struct *stack_vm_area; #endif #ifdef CONFIG_THREAD_INFO_IN_TASK /* A live task holds one reference: */ refcount_t stack_refcount; #endif #ifdef CONFIG_LIVEPATCH int patch_state; #endif #ifdef CONFIG_SECURITY /* Used by LSM modules for access restriction: */ void *security; #endif #ifdef CONFIG_BPF_SYSCALL /* Used by BPF task local storage */ struct bpf_local_storage __rcu *bpf_storage; /* Used for BPF run context */ struct bpf_run_ctx *bpf_ctx; #endif /* Used by BPF for per-TASK xdp storage */ struct bpf_net_context *bpf_net_context; #ifdef CONFIG_GCC_PLUGIN_STACKLEAK unsigned long lowest_stack; unsigned long prev_lowest_stack; #endif #ifdef CONFIG_X86_MCE void __user *mce_vaddr; __u64 mce_kflags; u64 mce_addr; __u64 mce_ripv : 1, mce_whole_page : 1, __mce_reserved : 62; struct callback_head mce_kill_me; int mce_count; #endif #ifdef CONFIG_KRETPROBES struct llist_head kretprobe_instances; #endif #ifdef CONFIG_RETHOOK struct llist_head rethooks; #endif #ifdef CONFIG_ARCH_HAS_PARANOID_L1D_FLUSH /* * If L1D flush is supported on mm context switch * then we use this callback head to queue kill work * to kill tasks that are not running on SMT disabled * cores */ struct callback_head l1d_flush_kill; #endif #ifdef CONFIG_RV /* * Per-task RV monitor. Nowadays fixed in RV_PER_TASK_MONITORS. * If we find justification for more monitors, we can think * about adding more or developing a dynamic method. So far, * none of these are justified. */ union rv_task_monitor rv[RV_PER_TASK_MONITORS]; #endif #ifdef CONFIG_USER_EVENTS struct user_event_mm *user_event_mm; #endif /* * New fields for task_struct should be added above here, so that * they are included in the randomized portion of task_struct. */ randomized_struct_fields_end /* CPU-specific state of this task: */ struct thread_struct thread; /* * WARNING: on x86, 'thread_struct' contains a variable-sized * structure. It *MUST* be at the end of 'task_struct'. * * Do not put anything below here! */ }; #define TASK_REPORT_IDLE (TASK_REPORT + 1) #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1) static inline unsigned int __task_state_index(unsigned int tsk_state, unsigned int tsk_exit_state) { unsigned int state = (tsk_state | tsk_exit_state) & TASK_REPORT; BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX); if ((tsk_state & TASK_IDLE) == TASK_IDLE) state = TASK_REPORT_IDLE; /* * We're lying here, but rather than expose a completely new task state * to userspace, we can make this appear as if the task has gone through * a regular rt_mutex_lock() call. */ if (tsk_state & TASK_RTLOCK_WAIT) state = TASK_UNINTERRUPTIBLE; return fls(state); } static inline unsigned int task_state_index(struct task_struct *tsk) { return __task_state_index(READ_ONCE(tsk->__state), tsk->exit_state); } static inline char task_index_to_char(unsigned int state) { static const char state_char[] = "RSDTtXZPI"; BUILD_BUG_ON(TASK_REPORT_MAX * 2 != 1 << (sizeof(state_char) - 1)); return state_char[state]; } static inline char task_state_to_char(struct task_struct *tsk) { return task_index_to_char(task_state_index(tsk)); } extern struct pid *cad_pid; /* * Per process flags */ #define PF_VCPU 0x00000001 /* I'm a virtual CPU */ #define PF_IDLE 0x00000002 /* I am an IDLE thread */ #define PF_EXITING 0x00000004 /* Getting shut down */ #define PF_POSTCOREDUMP 0x00000008 /* Coredumps should ignore this task */ #define PF_IO_WORKER 0x00000010 /* Task is an IO worker */ #define PF_WQ_WORKER 0x00000020 /* I'm a workqueue worker */ #define PF_FORKNOEXEC 0x00000040 /* Forked but didn't exec */ #define PF_MCE_PROCESS 0x00000080 /* Process policy on mce errors */ #define PF_SUPERPRIV 0x00000100 /* Used super-user privileges */ #define PF_DUMPCORE 0x00000200 /* Dumped core */ #define PF_SIGNALED 0x00000400 /* Killed by a signal */ #define PF_MEMALLOC 0x00000800 /* Allocating memory to free memory. See memalloc_noreclaim_save() */ #define PF_NPROC_EXCEEDED 0x00001000 /* set_user() noticed that RLIMIT_NPROC was exceeded */ #define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */ #define PF_USER_WORKER 0x00004000 /* Kernel thread cloned from userspace thread */ #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ #define PF__HOLE__00010000 0x00010000 #define PF_KSWAPD 0x00020000 /* I am kswapd */ #define PF_MEMALLOC_NOFS 0x00040000 /* All allocations inherit GFP_NOFS. See memalloc_nfs_save() */ #define PF_MEMALLOC_NOIO 0x00080000 /* All allocations inherit GFP_NOIO. See memalloc_noio_save() */ #define PF_LOCAL_THROTTLE 0x00100000 /* Throttle writes only against the bdi I write to, * I am cleaning dirty pages from some other bdi. */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ #define PF__HOLE__00800000 0x00800000 #define PF__HOLE__01000000 0x01000000 #define PF__HOLE__02000000 0x02000000 #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMALLOC_PIN 0x10000000 /* Allocations constrained to zones which allow long term pinning. * See memalloc_pin_save() */ #define PF_BLOCK_TS 0x20000000 /* plug has ts that needs updating */ #define PF__HOLE__40000000 0x40000000 #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ /* * Only the _current_ task can read/write to tsk->flags, but other * tasks can access tsk->flags in readonly mode for example * with tsk_used_math (like during threaded core dumping). * There is however an exception to this rule during ptrace * or during fork: the ptracer task is allowed to write to the * child->flags of its traced child (same goes for fork, the parent * can write to the child->flags), because we're guaranteed the * child is not running and in turn not changing child->flags * at the same time the parent does it. */ #define clear_stopped_child_used_math(child) do { (child)->flags &= ~PF_USED_MATH; } while (0) #define set_stopped_child_used_math(child) do { (child)->flags |= PF_USED_MATH; } while (0) #define clear_used_math() clear_stopped_child_used_math(current) #define set_used_math() set_stopped_child_used_math(current) #define conditional_stopped_child_used_math(condition, child) \ do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= (condition) ? PF_USED_MATH : 0; } while (0) #define conditional_used_math(condition) conditional_stopped_child_used_math(condition, current) #define copy_to_stopped_child_used_math(child) \ do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= current->flags & PF_USED_MATH; } while (0) /* NOTE: this will return 0 or PF_USED_MATH, it will never return 1 */ #define tsk_used_math(p) ((p)->flags & PF_USED_MATH) #define used_math() tsk_used_math(current) static __always_inline bool is_percpu_thread(void) { #ifdef CONFIG_SMP return (current->flags & PF_NO_SETAFFINITY) && (current->nr_cpus_allowed == 1); #else return true; #endif } /* Per-process atomic flags. */ #define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */ #define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */ #define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */ #define PFA_SPEC_SSB_DISABLE 3 /* Speculative Store Bypass disabled */ #define PFA_SPEC_SSB_FORCE_DISABLE 4 /* Speculative Store Bypass force disabled*/ #define PFA_SPEC_IB_DISABLE 5 /* Indirect branch speculation restricted */ #define PFA_SPEC_IB_FORCE_DISABLE 6 /* Indirect branch speculation permanently restricted */ #define PFA_SPEC_SSB_NOEXEC 7 /* Speculative Store Bypass clear on execve() */ #define TASK_PFA_TEST(name, func) \ static inline bool task_##func(struct task_struct *p) \ { return test_bit(PFA_##name, &p->atomic_flags); } #define TASK_PFA_SET(name, func) \ static inline void task_set_##func(struct task_struct *p) \ { set_bit(PFA_##name, &p->atomic_flags); } #define TASK_PFA_CLEAR(name, func) \ static inline void task_clear_##func(struct task_struct *p) \ { clear_bit(PFA_##name, &p->atomic_flags); } TASK_PFA_TEST(NO_NEW_PRIVS, no_new_privs) TASK_PFA_SET(NO_NEW_PRIVS, no_new_privs) TASK_PFA_TEST(SPREAD_PAGE, spread_page) TASK_PFA_SET(SPREAD_PAGE, spread_page) TASK_PFA_CLEAR(SPREAD_PAGE, spread_page) TASK_PFA_TEST(SPREAD_SLAB, spread_slab) TASK_PFA_SET(SPREAD_SLAB, spread_slab) TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab) TASK_PFA_TEST(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_SET(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_TEST(SPEC_SSB_NOEXEC, spec_ssb_noexec) TASK_PFA_SET(SPEC_SSB_NOEXEC, spec_ssb_noexec) TASK_PFA_CLEAR(SPEC_SSB_NOEXEC, spec_ssb_noexec) TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) TASK_PFA_TEST(SPEC_IB_DISABLE, spec_ib_disable) TASK_PFA_SET(SPEC_IB_DISABLE, spec_ib_disable) TASK_PFA_CLEAR(SPEC_IB_DISABLE, spec_ib_disable) TASK_PFA_TEST(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) TASK_PFA_SET(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) static inline void current_restore_flags(unsigned long orig_flags, unsigned long flags) { current->flags &= ~flags; current->flags |= orig_flags & flags; } extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); extern int task_can_attach(struct task_struct *p); extern int dl_bw_alloc(int cpu, u64 dl_bw); extern void dl_bw_free(int cpu, u64 dl_bw); #ifdef CONFIG_SMP /* do_set_cpus_allowed() - consider using set_cpus_allowed_ptr() instead */ extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask); /** * set_cpus_allowed_ptr - set CPU affinity mask of a task * @p: the task * @new_mask: CPU affinity mask * * Return: zero if successful, or a negative error code */ extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask); extern int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node); extern void release_user_cpus_ptr(struct task_struct *p); extern int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask); extern void force_compatible_cpus_allowed_ptr(struct task_struct *p); extern void relax_compatible_cpus_allowed_ptr(struct task_struct *p); #else static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) { } static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) { /* Opencoded cpumask_test_cpu(0, new_mask) to avoid dependency on cpumask.h */ if ((*cpumask_bits(new_mask) & 1) == 0) return -EINVAL; return 0; } static inline int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node) { if (src->user_cpus_ptr) return -EINVAL; return 0; } static inline void release_user_cpus_ptr(struct task_struct *p) { WARN_ON(p->user_cpus_ptr); } static inline int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask) { return 0; } #endif extern int yield_to(struct task_struct *p, bool preempt); extern void set_user_nice(struct task_struct *p, long nice); extern int task_prio(const struct task_struct *p); /** * task_nice - return the nice value of a given task. * @p: the task in question. * * Return: The nice value [ -20 ... 0 ... 19 ]. */ static inline int task_nice(const struct task_struct *p) { return PRIO_TO_NICE((p)->static_prio); } extern int can_nice(const struct task_struct *p, const int nice); extern int task_curr(const struct task_struct *p); extern int idle_cpu(int cpu); extern int available_idle_cpu(int cpu); extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *); extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *); extern void sched_set_fifo(struct task_struct *p); extern void sched_set_fifo_low(struct task_struct *p); extern void sched_set_normal(struct task_struct *p, int nice); extern int sched_setattr(struct task_struct *, const struct sched_attr *); extern int sched_setattr_nocheck(struct task_struct *, const struct sched_attr *); extern struct task_struct *idle_task(int cpu); /** * is_idle_task - is the specified task an idle task? * @p: the task in question. * * Return: 1 if @p is an idle task. 0 otherwise. */ static __always_inline bool is_idle_task(const struct task_struct *p) { return !!(p->flags & PF_IDLE); } extern struct task_struct *curr_task(int cpu); extern void ia64_set_curr_task(int cpu, struct task_struct *p); void yield(void); union thread_union { struct task_struct task; #ifndef CONFIG_THREAD_INFO_IN_TASK struct thread_info thread_info; #endif unsigned long stack[THREAD_SIZE/sizeof(long)]; }; #ifndef CONFIG_THREAD_INFO_IN_TASK extern struct thread_info init_thread_info; #endif extern unsigned long init_stack[THREAD_SIZE / sizeof(unsigned long)]; #ifdef CONFIG_THREAD_INFO_IN_TASK # define task_thread_info(task) (&(task)->thread_info) #else # define task_thread_info(task) ((struct thread_info *)(task)->stack) #endif /* * find a task by one of its numerical ids * * find_task_by_pid_ns(): * finds a task by its pid in the specified namespace * find_task_by_vpid(): * finds a task by its virtual pid * * see also find_vpid() etc in include/linux/pid.h */ extern struct task_struct *find_task_by_vpid(pid_t nr); extern struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns); /* * find a task by its virtual pid and get the task struct */ extern struct task_struct *find_get_task_by_vpid(pid_t nr); extern int wake_up_state(struct task_struct *tsk, unsigned int state); extern int wake_up_process(struct task_struct *tsk); extern void wake_up_new_task(struct task_struct *tsk); #ifdef CONFIG_SMP extern void kick_process(struct task_struct *tsk); #else static inline void kick_process(struct task_struct *tsk) { } #endif extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec); static inline void set_task_comm(struct task_struct *tsk, const char *from) { __set_task_comm(tsk, from, false); } /* * - Why not use task_lock()? * User space can randomly change their names anyway, so locking for readers * doesn't make sense. For writers, locking is probably necessary, as a race * condition could lead to long-term mixed results. * The strscpy_pad() in __set_task_comm() can ensure that the task comm is * always NUL-terminated and zero-padded. Therefore the race condition between * reader and writer is not an issue. * * - BUILD_BUG_ON() can help prevent the buf from being truncated. * Since the callers don't perform any return value checks, this safeguard is * necessary. */ #define get_task_comm(buf, tsk) ({ \ BUILD_BUG_ON(sizeof(buf) < TASK_COMM_LEN); \ strscpy_pad(buf, (tsk)->comm); \ buf; \ }) #ifdef CONFIG_SMP static __always_inline void scheduler_ipi(void) { /* * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting * TIF_NEED_RESCHED remotely (for the first time) will also send * this IPI. */ preempt_fold_need_resched(); } #else static inline void scheduler_ipi(void) { } #endif extern unsigned long wait_task_inactive(struct task_struct *, unsigned int match_state); /* * Set thread flags in other task's structures. * See asm/thread_info.h for TIF_xxxx flags available: */ static inline void set_tsk_thread_flag(struct task_struct *tsk, int flag) { set_ti_thread_flag(task_thread_info(tsk), flag); } static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag) { clear_ti_thread_flag(task_thread_info(tsk), flag); } static inline void update_tsk_thread_flag(struct task_struct *tsk, int flag, bool value) { update_ti_thread_flag(task_thread_info(tsk), flag, value); } static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_and_set_ti_thread_flag(task_thread_info(tsk), flag); } static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_and_clear_ti_thread_flag(task_thread_info(tsk), flag); } static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_ti_thread_flag(task_thread_info(tsk), flag); } static inline void set_tsk_need_resched(struct task_struct *tsk) { set_tsk_thread_flag(tsk,TIF_NEED_RESCHED); } static inline void clear_tsk_need_resched(struct task_struct *tsk) { atomic_long_andnot(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY, (atomic_long_t *)&task_thread_info(tsk)->flags); } static inline int test_tsk_need_resched(struct task_struct *tsk) { return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED)); } /* * cond_resched() and cond_resched_lock(): latency reduction via * explicit rescheduling in places that are safe. The return * value indicates whether a reschedule was done in fact. * cond_resched_lock() will drop the spinlock before scheduling, */ #if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) extern int __cond_resched(void); #if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) void sched_dynamic_klp_enable(void); void sched_dynamic_klp_disable(void); DECLARE_STATIC_CALL(cond_resched, __cond_resched); static __always_inline int _cond_resched(void) { return static_call_mod(cond_resched)(); } #elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) extern int dynamic_cond_resched(void); static __always_inline int _cond_resched(void) { return dynamic_cond_resched(); } #else /* !CONFIG_PREEMPTION */ static inline int _cond_resched(void) { klp_sched_try_switch(); return __cond_resched(); } #endif /* PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */ #else /* CONFIG_PREEMPTION && !CONFIG_PREEMPT_DYNAMIC */ static inline int _cond_resched(void) { klp_sched_try_switch(); return 0; } #endif /* !CONFIG_PREEMPTION || CONFIG_PREEMPT_DYNAMIC */ #define cond_resched() ({ \ __might_resched(__FILE__, __LINE__, 0); \ _cond_resched(); \ }) extern int __cond_resched_lock(spinlock_t *lock); extern int __cond_resched_rwlock_read(rwlock_t *lock); extern int __cond_resched_rwlock_write(rwlock_t *lock); #define MIGHT_RESCHED_RCU_SHIFT 8 #define MIGHT_RESCHED_PREEMPT_MASK ((1U << MIGHT_RESCHED_RCU_SHIFT) - 1) #ifndef CONFIG_PREEMPT_RT /* * Non RT kernels have an elevated preempt count due to the held lock, * but are not allowed to be inside a RCU read side critical section */ # define PREEMPT_LOCK_RESCHED_OFFSETS PREEMPT_LOCK_OFFSET #else /* * spin/rw_lock() on RT implies rcu_read_lock(). The might_sleep() check in * cond_resched*lock() has to take that into account because it checks for * preempt_count() and rcu_preempt_depth(). */ # define PREEMPT_LOCK_RESCHED_OFFSETS \ (PREEMPT_LOCK_OFFSET + (1U << MIGHT_RESCHED_RCU_SHIFT)) #endif #define cond_resched_lock(lock) ({ \ __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \ __cond_resched_lock(lock); \ }) #define cond_resched_rwlock_read(lock) ({ \ __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \ __cond_resched_rwlock_read(lock); \ }) #define cond_resched_rwlock_write(lock) ({ \ __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \ __cond_resched_rwlock_write(lock); \ }) static __always_inline bool need_resched(void) { return unlikely(tif_need_resched()); } /* * Wrappers for p->thread_info->cpu access. No-op on UP. */ #ifdef CONFIG_SMP static inline unsigned int task_cpu(const struct task_struct *p) { return READ_ONCE(task_thread_info(p)->cpu); } extern void set_task_cpu(struct task_struct *p, unsigned int cpu); #else static inline unsigned int task_cpu(const struct task_struct *p) { return 0; } static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) { } #endif /* CONFIG_SMP */ static inline bool task_is_runnable(struct task_struct *p) { return p->on_rq && !p->se.sched_delayed; } extern bool sched_task_on_rq(struct task_struct *p); extern unsigned long get_wchan(struct task_struct *p); extern struct task_struct *cpu_curr_snapshot(int cpu); #include <linux/spinlock.h> /* * In order to reduce various lock holder preemption latencies provide an * interface to see if a vCPU is currently running or not. * * This allows us to terminate optimistic spin loops and block, analogous to * the native optimistic spin heuristic of testing if the lock owner task is * running or not. */ #ifndef vcpu_is_preempted static inline bool vcpu_is_preempted(int cpu) { return false; } #endif extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask); extern long sched_getaffinity(pid_t pid, struct cpumask *mask); #ifndef TASK_SIZE_OF #define TASK_SIZE_OF(tsk) TASK_SIZE #endif #ifdef CONFIG_SMP static inline bool owner_on_cpu(struct task_struct *owner) { /* * As lock holder preemption issue, we both skip spinning if * task is not on cpu or its cpu is preempted */ return READ_ONCE(owner->on_cpu) && !vcpu_is_preempted(task_cpu(owner)); } /* Returns effective CPU energy utilization, as seen by the scheduler */ unsigned long sched_cpu_util(int cpu); #endif /* CONFIG_SMP */ #ifdef CONFIG_SCHED_CORE extern void sched_core_free(struct task_struct *tsk); extern void sched_core_fork(struct task_struct *p); extern int sched_core_share_pid(unsigned int cmd, pid_t pid, enum pid_type type, unsigned long uaddr); extern int sched_core_idle_cpu(int cpu); #else static inline void sched_core_free(struct task_struct *tsk) { } static inline void sched_core_fork(struct task_struct *p) { } static inline int sched_core_idle_cpu(int cpu) { return idle_cpu(cpu); } #endif extern void sched_set_stop_task(int cpu, struct task_struct *stop); #ifdef CONFIG_MEM_ALLOC_PROFILING static __always_inline struct alloc_tag *alloc_tag_save(struct alloc_tag *tag) { swap(current->alloc_tag, tag); return tag; } static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct alloc_tag *old) { #ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG WARN(current->alloc_tag != tag, "current->alloc_tag was changed:\n"); #endif current->alloc_tag = old; } #else #define alloc_tag_save(_tag) NULL #define alloc_tag_restore(_tag, _old) do {} while (0) #endif #endif |
| 159 160 158 299 29 158 421 421 53 421 420 421 421 422 422 421 51 53 53 4 48 21 412 411 412 412 33 34 34 2 8 32 434 1024 1020 1 1022 1027 1035 1025 51 424 997 953 1004 4 4 51 14 65 66 64 11 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/file.c * * Copyright (C) 1998-1999, Stephen Tweedie and Bill Hawes * * Manage the dynamic fd arrays in the process files_struct. */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/close_range.h> #include <linux/file_ref.h> #include <net/sock.h> #include "internal.h" /** * __file_ref_put - Slowpath of file_ref_put() * @ref: Pointer to the reference count * @cnt: Current reference count * * Invoked when the reference count is outside of the valid zone. * * Return: * True if this was the last reference with no future references * possible. This signals the caller that it can safely schedule the * object, which is protected by the reference counter, for * deconstruction. * * False if there are still active references or the put() raced * with a concurrent get()/put() pair. Caller is not allowed to * deconstruct the protected object. */ bool __file_ref_put(file_ref_t *ref, unsigned long cnt) { /* Did this drop the last reference? */ if (likely(cnt == FILE_REF_NOREF)) { /* * Carefully try to set the reference count to FILE_REF_DEAD. * * This can fail if a concurrent get() operation has * elevated it again or the corresponding put() even marked * it dead already. Both are valid situations and do not * require a retry. If this fails the caller is not * allowed to deconstruct the object. */ if (!atomic_long_try_cmpxchg_release(&ref->refcnt, &cnt, FILE_REF_DEAD)) return false; /* * The caller can safely schedule the object for * deconstruction. Provide acquire ordering. */ smp_acquire__after_ctrl_dep(); return true; } /* * If the reference count was already in the dead zone, then this * put() operation is imbalanced. Warn, put the reference count back to * DEAD and tell the caller to not deconstruct the object. */ if (WARN_ONCE(cnt >= FILE_REF_RELEASED, "imbalanced put on file reference count")) { atomic_long_set(&ref->refcnt, FILE_REF_DEAD); return false; } /* * This is a put() operation on a saturated refcount. Restore the * mean saturation value and tell the caller to not deconstruct the * object. */ if (cnt > FILE_REF_MAXREF) atomic_long_set(&ref->refcnt, FILE_REF_SATURATED); return false; } EXPORT_SYMBOL_GPL(__file_ref_put); unsigned int sysctl_nr_open __read_mostly = 1024*1024; unsigned int sysctl_nr_open_min = BITS_PER_LONG; /* our min() is unusable in constant expressions ;-/ */ #define __const_min(x, y) ((x) < (y) ? (x) : (y)) unsigned int sysctl_nr_open_max = __const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & -BITS_PER_LONG; static void __free_fdtable(struct fdtable *fdt) { kvfree(fdt->fd); kvfree(fdt->open_fds); kfree(fdt); } static void free_fdtable_rcu(struct rcu_head *rcu) { __free_fdtable(container_of(rcu, struct fdtable, rcu)); } #define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr)) #define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long)) #define fdt_words(fdt) ((fdt)->max_fds / BITS_PER_LONG) // words in ->open_fds /* * Copy 'count' fd bits from the old table to the new table and clear the extra * space if any. This does not copy the file pointers. Called with the files * spinlock held for write. */ static inline void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, unsigned int copy_words) { unsigned int nwords = fdt_words(nfdt); bitmap_copy_and_extend(nfdt->open_fds, ofdt->open_fds, copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); bitmap_copy_and_extend(nfdt->close_on_exec, ofdt->close_on_exec, copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); bitmap_copy_and_extend(nfdt->full_fds_bits, ofdt->full_fds_bits, copy_words, nwords); } /* * Copy all file descriptors from the old table to the new, expanded table and * clear the extra space. Called with the files spinlock held for write. */ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt) { size_t cpy, set; BUG_ON(nfdt->max_fds < ofdt->max_fds); cpy = ofdt->max_fds * sizeof(struct file *); set = (nfdt->max_fds - ofdt->max_fds) * sizeof(struct file *); memcpy(nfdt->fd, ofdt->fd, cpy); memset((char *)nfdt->fd + cpy, 0, set); copy_fd_bitmaps(nfdt, ofdt, fdt_words(ofdt)); } /* * Note how the fdtable bitmap allocations very much have to be a multiple of * BITS_PER_LONG. This is not only because we walk those things in chunks of * 'unsigned long' in some places, but simply because that is how the Linux * kernel bitmaps are defined to work: they are not "bits in an array of bytes", * they are very much "bits in an array of unsigned long". */ static struct fdtable *alloc_fdtable(unsigned int slots_wanted) { struct fdtable *fdt; unsigned int nr; void *data; /* * Figure out how many fds we actually want to support in this fdtable. * Allocation steps are keyed to the size of the fdarray, since it * grows far faster than any of the other dynamic data. We try to fit * the fdarray into comfortable page-tuned chunks: starting at 1024B * and growing in powers of two from there on. Since we called only * with slots_wanted > BITS_PER_LONG (embedded instance in files->fdtab * already gives BITS_PER_LONG slots), the above boils down to * 1. use the smallest power of two large enough to give us that many * slots. * 2. on 32bit skip 64 and 128 - the minimal capacity we want there is * 256 slots (i.e. 1Kb fd array). * 3. on 64bit don't skip anything, 1Kb fd array means 128 slots there * and we are never going to be asked for 64 or less. */ if (IS_ENABLED(CONFIG_32BIT) && slots_wanted < 256) nr = 256; else nr = roundup_pow_of_two(slots_wanted); /* * Note that this can drive nr *below* what we had passed if sysctl_nr_open * had been set lower between the check in expand_files() and here. * * We make sure that nr remains a multiple of BITS_PER_LONG - otherwise * bitmaps handling below becomes unpleasant, to put it mildly... */ if (unlikely(nr > sysctl_nr_open)) { nr = round_down(sysctl_nr_open, BITS_PER_LONG); if (nr < slots_wanted) return ERR_PTR(-EMFILE); } fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL_ACCOUNT); if (!fdt) goto out; fdt->max_fds = nr; data = kvmalloc_array(nr, sizeof(struct file *), GFP_KERNEL_ACCOUNT); if (!data) goto out_fdt; fdt->fd = data; data = kvmalloc(max_t(size_t, 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES), GFP_KERNEL_ACCOUNT); if (!data) goto out_arr; fdt->open_fds = data; data += nr / BITS_PER_BYTE; fdt->close_on_exec = data; data += nr / BITS_PER_BYTE; fdt->full_fds_bits = data; return fdt; out_arr: kvfree(fdt->fd); out_fdt: kfree(fdt); out: return ERR_PTR(-ENOMEM); } /* * Expand the file descriptor table. * This function will allocate a new fdtable and both fd array and fdset, of * the given size. * Return <0 error code on error; 0 on successful completion. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_fdtable(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *new_fdt, *cur_fdt; spin_unlock(&files->file_lock); new_fdt = alloc_fdtable(nr + 1); /* make sure all fd_install() have seen resize_in_progress * or have finished their rcu_read_lock_sched() section. */ if (atomic_read(&files->count) > 1) synchronize_rcu(); spin_lock(&files->file_lock); if (IS_ERR(new_fdt)) return PTR_ERR(new_fdt); cur_fdt = files_fdtable(files); BUG_ON(nr < cur_fdt->max_fds); copy_fdtable(new_fdt, cur_fdt); rcu_assign_pointer(files->fdt, new_fdt); if (cur_fdt != &files->fdtab) call_rcu(&cur_fdt->rcu, free_fdtable_rcu); /* coupled with smp_rmb() in fd_install() */ smp_wmb(); return 0; } /* * Expand files. * This function will expand the file structures, if the requested size exceeds * the current capacity and there is room for expansion. * Return <0 error code on error; 0 on success. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_files(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *fdt; int error; repeat: fdt = files_fdtable(files); /* Do we need to expand? */ if (nr < fdt->max_fds) return 0; /* Can we expand? */ if (nr >= sysctl_nr_open) return -EMFILE; if (unlikely(files->resize_in_progress)) { spin_unlock(&files->file_lock); wait_event(files->resize_wait, !files->resize_in_progress); spin_lock(&files->file_lock); goto repeat; } /* All good, so we try */ files->resize_in_progress = true; error = expand_fdtable(files, nr); files->resize_in_progress = false; wake_up_all(&files->resize_wait); return error; } static inline void __set_close_on_exec(unsigned int fd, struct fdtable *fdt, bool set) { if (set) { __set_bit(fd, fdt->close_on_exec); } else { if (test_bit(fd, fdt->close_on_exec)) __clear_bit(fd, fdt->close_on_exec); } } static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt, bool set) { __set_bit(fd, fdt->open_fds); __set_close_on_exec(fd, fdt, set); fd /= BITS_PER_LONG; if (!~fdt->open_fds[fd]) __set_bit(fd, fdt->full_fds_bits); } static inline void __clear_open_fd(unsigned int fd, struct fdtable *fdt) { __clear_bit(fd, fdt->open_fds); fd /= BITS_PER_LONG; if (test_bit(fd, fdt->full_fds_bits)) __clear_bit(fd, fdt->full_fds_bits); } static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt) { return test_bit(fd, fdt->open_fds); } /* * Note that a sane fdtable size always has to be a multiple of * BITS_PER_LONG, since we have bitmaps that are sized by this. * * punch_hole is optional - when close_range() is asked to unshare * and close, we don't need to copy descriptors in that range, so * a smaller cloned descriptor table might suffice if the last * currently opened descriptor falls into that range. */ static unsigned int sane_fdtable_size(struct fdtable *fdt, struct fd_range *punch_hole) { unsigned int last = find_last_bit(fdt->open_fds, fdt->max_fds); if (last == fdt->max_fds) return NR_OPEN_DEFAULT; if (punch_hole && punch_hole->to >= last && punch_hole->from <= last) { last = find_last_bit(fdt->open_fds, punch_hole->from); if (last == punch_hole->from) return NR_OPEN_DEFAULT; } return ALIGN(last + 1, BITS_PER_LONG); } /* * Allocate a new descriptor table and copy contents from the passed in * instance. Returns a pointer to cloned table on success, ERR_PTR() * on failure. For 'punch_hole' see sane_fdtable_size(). */ struct files_struct *dup_fd(struct files_struct *oldf, struct fd_range *punch_hole) { struct files_struct *newf; struct file **old_fds, **new_fds; unsigned int open_files, i; struct fdtable *old_fdt, *new_fdt; newf = kmem_cache_alloc(files_cachep, GFP_KERNEL); if (!newf) return ERR_PTR(-ENOMEM); atomic_set(&newf->count, 1); spin_lock_init(&newf->file_lock); newf->resize_in_progress = false; init_waitqueue_head(&newf->resize_wait); newf->next_fd = 0; new_fdt = &newf->fdtab; new_fdt->max_fds = NR_OPEN_DEFAULT; new_fdt->close_on_exec = newf->close_on_exec_init; new_fdt->open_fds = newf->open_fds_init; new_fdt->full_fds_bits = newf->full_fds_bits_init; new_fdt->fd = &newf->fd_array[0]; spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, punch_hole); /* * Check whether we need to allocate a larger fd array and fd set. */ while (unlikely(open_files > new_fdt->max_fds)) { spin_unlock(&oldf->file_lock); if (new_fdt != &newf->fdtab) __free_fdtable(new_fdt); new_fdt = alloc_fdtable(open_files); if (IS_ERR(new_fdt)) { kmem_cache_free(files_cachep, newf); return ERR_CAST(new_fdt); } /* * Reacquire the oldf lock and a pointer to its fd table * who knows it may have a new bigger fd table. We need * the latest pointer. */ spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, punch_hole); } copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG); old_fds = old_fdt->fd; new_fds = new_fdt->fd; for (i = open_files; i != 0; i--) { struct file *f = *old_fds++; if (f) { get_file(f); } else { /* * The fd may be claimed in the fd bitmap but not yet * instantiated in the files array if a sibling thread * is partway through open(). So make sure that this * fd is available to the new process. */ __clear_open_fd(open_files - i, new_fdt); } rcu_assign_pointer(*new_fds++, f); } spin_unlock(&oldf->file_lock); /* clear the remainder */ memset(new_fds, 0, (new_fdt->max_fds - open_files) * sizeof(struct file *)); rcu_assign_pointer(newf->fdt, new_fdt); return newf; } static struct fdtable *close_files(struct files_struct * files) { /* * It is safe to dereference the fd table without RCU or * ->file_lock because this is the last reference to the * files structure. */ struct fdtable *fdt = rcu_dereference_raw(files->fdt); unsigned int i, j = 0; for (;;) { unsigned long set; i = j * BITS_PER_LONG; if (i >= fdt->max_fds) break; set = fdt->open_fds[j++]; while (set) { if (set & 1) { struct file *file = fdt->fd[i]; if (file) { filp_close(file, files); cond_resched(); } } i++; set >>= 1; } } return fdt; } void put_files_struct(struct files_struct *files) { if (atomic_dec_and_test(&files->count)) { struct fdtable *fdt = close_files(files); /* free the arrays if they are not embedded */ if (fdt != &files->fdtab) __free_fdtable(fdt); kmem_cache_free(files_cachep, files); } } void exit_files(struct task_struct *tsk) { struct files_struct * files = tsk->files; if (files) { task_lock(tsk); tsk->files = NULL; task_unlock(tsk); put_files_struct(files); } } struct files_struct init_files = { .count = ATOMIC_INIT(1), .fdt = &init_files.fdtab, .fdtab = { .max_fds = NR_OPEN_DEFAULT, .fd = &init_files.fd_array[0], .close_on_exec = init_files.close_on_exec_init, .open_fds = init_files.open_fds_init, .full_fds_bits = init_files.full_fds_bits_init, }, .file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock), .resize_wait = __WAIT_QUEUE_HEAD_INITIALIZER(init_files.resize_wait), }; static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start) { unsigned int maxfd = fdt->max_fds; /* always multiple of BITS_PER_LONG */ unsigned int maxbit = maxfd / BITS_PER_LONG; unsigned int bitbit = start / BITS_PER_LONG; unsigned int bit; /* * Try to avoid looking at the second level bitmap */ bit = find_next_zero_bit(&fdt->open_fds[bitbit], BITS_PER_LONG, start & (BITS_PER_LONG - 1)); if (bit < BITS_PER_LONG) return bit + bitbit * BITS_PER_LONG; bitbit = find_next_zero_bit(fdt->full_fds_bits, maxbit, bitbit) * BITS_PER_LONG; if (bitbit >= maxfd) return maxfd; if (bitbit > start) start = bitbit; return find_next_zero_bit(fdt->open_fds, maxfd, start); } /* * allocate a file descriptor, mark it busy. */ static int alloc_fd(unsigned start, unsigned end, unsigned flags) { struct files_struct *files = current->files; unsigned int fd; int error; struct fdtable *fdt; spin_lock(&files->file_lock); repeat: fdt = files_fdtable(files); fd = start; if (fd < files->next_fd) fd = files->next_fd; if (likely(fd < fdt->max_fds)) fd = find_next_fd(fdt, fd); /* * N.B. For clone tasks sharing a files structure, this test * will limit the total number of files that can be opened. */ error = -EMFILE; if (unlikely(fd >= end)) goto out; if (unlikely(fd >= fdt->max_fds)) { error = expand_files(files, fd); if (error < 0) goto out; goto repeat; } if (start <= files->next_fd) files->next_fd = fd + 1; __set_open_fd(fd, fdt, flags & O_CLOEXEC); error = fd; out: spin_unlock(&files->file_lock); return error; } int __get_unused_fd_flags(unsigned flags, unsigned long nofile) { return alloc_fd(0, nofile, flags); } int get_unused_fd_flags(unsigned flags) { return __get_unused_fd_flags(flags, rlimit(RLIMIT_NOFILE)); } EXPORT_SYMBOL(get_unused_fd_flags); static void __put_unused_fd(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = files_fdtable(files); __clear_open_fd(fd, fdt); if (fd < files->next_fd) files->next_fd = fd; } void put_unused_fd(unsigned int fd) { struct files_struct *files = current->files; spin_lock(&files->file_lock); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); } EXPORT_SYMBOL(put_unused_fd); /* * Install a file pointer in the fd array. * * The VFS is full of places where we drop the files lock between * setting the open_fds bitmap and installing the file in the file * array. At any such point, we are vulnerable to a dup2() race * installing a file in the array before us. We need to detect this and * fput() the struct file we are about to overwrite in this case. * * It should never happen - if we allow dup2() do it, _really_ bad things * will follow. * * This consumes the "file" refcount, so callers should treat it * as if they had called fput(file). */ void fd_install(unsigned int fd, struct file *file) { struct files_struct *files = current->files; struct fdtable *fdt; if (WARN_ON_ONCE(unlikely(file->f_mode & FMODE_BACKING))) return; rcu_read_lock_sched(); if (unlikely(files->resize_in_progress)) { rcu_read_unlock_sched(); spin_lock(&files->file_lock); fdt = files_fdtable(files); WARN_ON(fdt->fd[fd] != NULL); rcu_assign_pointer(fdt->fd[fd], file); spin_unlock(&files->file_lock); return; } /* coupled with smp_wmb() in expand_fdtable() */ smp_rmb(); fdt = rcu_dereference_sched(files->fdt); BUG_ON(fdt->fd[fd] != NULL); rcu_assign_pointer(fdt->fd[fd], file); rcu_read_unlock_sched(); } EXPORT_SYMBOL(fd_install); /** * file_close_fd_locked - return file associated with fd * @files: file struct to retrieve file from * @fd: file descriptor to retrieve file for * * Doesn't take a separate reference count. * * Context: files_lock must be held. * * Returns: The file associated with @fd (NULL if @fd is not open) */ struct file *file_close_fd_locked(struct files_struct *files, unsigned fd) { struct fdtable *fdt = files_fdtable(files); struct file *file; lockdep_assert_held(&files->file_lock); if (fd >= fdt->max_fds) return NULL; fd = array_index_nospec(fd, fdt->max_fds); file = fdt->fd[fd]; if (file) { rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); } return file; } int close_fd(unsigned fd) { struct files_struct *files = current->files; struct file *file; spin_lock(&files->file_lock); file = file_close_fd_locked(files, fd); spin_unlock(&files->file_lock); if (!file) return -EBADF; return filp_close(file, files); } EXPORT_SYMBOL(close_fd); /** * last_fd - return last valid index into fd table * @fdt: File descriptor table. * * Context: Either rcu read lock or files_lock must be held. * * Returns: Last valid index into fdtable. */ static inline unsigned last_fd(struct fdtable *fdt) { return fdt->max_fds - 1; } static inline void __range_cloexec(struct files_struct *cur_fds, unsigned int fd, unsigned int max_fd) { struct fdtable *fdt; /* make sure we're using the correct maximum value */ spin_lock(&cur_fds->file_lock); fdt = files_fdtable(cur_fds); max_fd = min(last_fd(fdt), max_fd); if (fd <= max_fd) bitmap_set(fdt->close_on_exec, fd, max_fd - fd + 1); spin_unlock(&cur_fds->file_lock); } static inline void __range_close(struct files_struct *files, unsigned int fd, unsigned int max_fd) { struct file *file; unsigned n; spin_lock(&files->file_lock); n = last_fd(files_fdtable(files)); max_fd = min(max_fd, n); for (; fd <= max_fd; fd++) { file = file_close_fd_locked(files, fd); if (file) { spin_unlock(&files->file_lock); filp_close(file, files); cond_resched(); spin_lock(&files->file_lock); } else if (need_resched()) { spin_unlock(&files->file_lock); cond_resched(); spin_lock(&files->file_lock); } } spin_unlock(&files->file_lock); } /** * sys_close_range() - Close all file descriptors in a given range. * * @fd: starting file descriptor to close * @max_fd: last file descriptor to close * @flags: CLOSE_RANGE flags. * * This closes a range of file descriptors. All file descriptors * from @fd up to and including @max_fd are closed. * Currently, errors to close a given file descriptor are ignored. */ SYSCALL_DEFINE3(close_range, unsigned int, fd, unsigned int, max_fd, unsigned int, flags) { struct task_struct *me = current; struct files_struct *cur_fds = me->files, *fds = NULL; if (flags & ~(CLOSE_RANGE_UNSHARE | CLOSE_RANGE_CLOEXEC)) return -EINVAL; if (fd > max_fd) return -EINVAL; if ((flags & CLOSE_RANGE_UNSHARE) && atomic_read(&cur_fds->count) > 1) { struct fd_range range = {fd, max_fd}, *punch_hole = ⦥ /* * If the caller requested all fds to be made cloexec we always * copy all of the file descriptors since they still want to * use them. */ if (flags & CLOSE_RANGE_CLOEXEC) punch_hole = NULL; fds = dup_fd(cur_fds, punch_hole); if (IS_ERR(fds)) return PTR_ERR(fds); /* * We used to share our file descriptor table, and have now * created a private one, make sure we're using it below. */ swap(cur_fds, fds); } if (flags & CLOSE_RANGE_CLOEXEC) __range_cloexec(cur_fds, fd, max_fd); else __range_close(cur_fds, fd, max_fd); if (fds) { /* * We're done closing the files we were supposed to. Time to install * the new file descriptor table and drop the old one. */ task_lock(me); me->files = cur_fds; task_unlock(me); put_files_struct(fds); } return 0; } /** * file_close_fd - return file associated with fd * @fd: file descriptor to retrieve file for * * Doesn't take a separate reference count. * * Returns: The file associated with @fd (NULL if @fd is not open) */ struct file *file_close_fd(unsigned int fd) { struct files_struct *files = current->files; struct file *file; spin_lock(&files->file_lock); file = file_close_fd_locked(files, fd); spin_unlock(&files->file_lock); return file; } void do_close_on_exec(struct files_struct *files) { unsigned i; struct fdtable *fdt; /* exec unshares first */ spin_lock(&files->file_lock); for (i = 0; ; i++) { unsigned long set; unsigned fd = i * BITS_PER_LONG; fdt = files_fdtable(files); if (fd >= fdt->max_fds) break; set = fdt->close_on_exec[i]; if (!set) continue; fdt->close_on_exec[i] = 0; for ( ; set ; fd++, set >>= 1) { struct file *file; if (!(set & 1)) continue; file = fdt->fd[fd]; if (!file) continue; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); filp_close(file, files); cond_resched(); spin_lock(&files->file_lock); } } spin_unlock(&files->file_lock); } static struct file *__get_file_rcu(struct file __rcu **f) { struct file __rcu *file; struct file __rcu *file_reloaded; struct file __rcu *file_reloaded_cmp; file = rcu_dereference_raw(*f); if (!file) return NULL; if (unlikely(!file_ref_get(&file->f_ref))) return ERR_PTR(-EAGAIN); file_reloaded = rcu_dereference_raw(*f); /* * Ensure that all accesses have a dependency on the load from * rcu_dereference_raw() above so we get correct ordering * between reuse/allocation and the pointer check below. */ file_reloaded_cmp = file_reloaded; OPTIMIZER_HIDE_VAR(file_reloaded_cmp); /* * file_ref_get() above provided a full memory barrier when we * acquired a reference. * * This is paired with the write barrier from assigning to the * __rcu protected file pointer so that if that pointer still * matches the current file, we know we have successfully * acquired a reference to the right file. * * If the pointers don't match the file has been reallocated by * SLAB_TYPESAFE_BY_RCU. */ if (file == file_reloaded_cmp) return file_reloaded; fput(file); return ERR_PTR(-EAGAIN); } /** * get_file_rcu - try go get a reference to a file under rcu * @f: the file to get a reference on * * This function tries to get a reference on @f carefully verifying that * @f hasn't been reused. * * This function should rarely have to be used and only by users who * understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it. * * Return: Returns @f with the reference count increased or NULL. */ struct file *get_file_rcu(struct file __rcu **f) { for (;;) { struct file __rcu *file; file = __get_file_rcu(f); if (!IS_ERR(file)) return file; } } EXPORT_SYMBOL_GPL(get_file_rcu); /** * get_file_active - try go get a reference to a file * @f: the file to get a reference on * * In contast to get_file_rcu() the pointer itself isn't part of the * reference counting. * * This function should rarely have to be used and only by users who * understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it. * * Return: Returns @f with the reference count increased or NULL. */ struct file *get_file_active(struct file **f) { struct file __rcu *file; rcu_read_lock(); file = __get_file_rcu(f); rcu_read_unlock(); if (IS_ERR(file)) file = NULL; return file; } EXPORT_SYMBOL_GPL(get_file_active); static inline struct file *__fget_files_rcu(struct files_struct *files, unsigned int fd, fmode_t mask) { for (;;) { struct file *file; struct fdtable *fdt = rcu_dereference_raw(files->fdt); struct file __rcu **fdentry; unsigned long nospec_mask; /* Mask is a 0 for invalid fd's, ~0 for valid ones */ nospec_mask = array_index_mask_nospec(fd, fdt->max_fds); /* * fdentry points to the 'fd' offset, or fdt->fd[0]. * Loading from fdt->fd[0] is always safe, because the * array always exists. */ fdentry = fdt->fd + (fd & nospec_mask); /* Do the load, then mask any invalid result */ file = rcu_dereference_raw(*fdentry); file = (void *)(nospec_mask & (unsigned long)file); if (unlikely(!file)) return NULL; /* * Ok, we have a file pointer that was valid at * some point, but it might have become stale since. * * We need to confirm it by incrementing the refcount * and then check the lookup again. * * file_ref_get() gives us a full memory barrier. We * only really need an 'acquire' one to protect the * loads below, but we don't have that. */ if (unlikely(!file_ref_get(&file->f_ref))) continue; /* * Such a race can take two forms: * * (a) the file ref already went down to zero and the * file hasn't been reused yet or the file count * isn't zero but the file has already been reused. * * (b) the file table entry has changed under us. * Note that we don't need to re-check the 'fdt->fd' * pointer having changed, because it always goes * hand-in-hand with 'fdt'. * * If so, we need to put our ref and try again. */ if (unlikely(file != rcu_dereference_raw(*fdentry)) || unlikely(rcu_dereference_raw(files->fdt) != fdt)) { fput(file); continue; } /* * This isn't the file we're looking for or we're not * allowed to get a reference to it. */ if (unlikely(file->f_mode & mask)) { fput(file); return NULL; } /* * Ok, we have a ref to the file, and checked that it * still exists. */ return file; } } static struct file *__fget_files(struct files_struct *files, unsigned int fd, fmode_t mask) { struct file *file; rcu_read_lock(); file = __fget_files_rcu(files, fd, mask); rcu_read_unlock(); return file; } static inline struct file *__fget(unsigned int fd, fmode_t mask) { return __fget_files(current->files, fd, mask); } struct file *fget(unsigned int fd) { return __fget(fd, FMODE_PATH); } EXPORT_SYMBOL(fget); struct file *fget_raw(unsigned int fd) { return __fget(fd, 0); } EXPORT_SYMBOL(fget_raw); struct file *fget_task(struct task_struct *task, unsigned int fd) { struct file *file = NULL; task_lock(task); if (task->files) file = __fget_files(task->files, fd, 0); task_unlock(task); return file; } struct file *fget_task_next(struct task_struct *task, unsigned int *ret_fd) { /* Must be called with rcu_read_lock held */ struct files_struct *files; unsigned int fd = *ret_fd; struct file *file = NULL; task_lock(task); files = task->files; if (files) { rcu_read_lock(); for (; fd < files_fdtable(files)->max_fds; fd++) { file = __fget_files_rcu(files, fd, 0); if (file) break; } rcu_read_unlock(); } task_unlock(task); *ret_fd = fd; return file; } EXPORT_SYMBOL(fget_task_next); /* * Lightweight file lookup - no refcnt increment if fd table isn't shared. * * You can use this instead of fget if you satisfy all of the following * conditions: * 1) You must call fput_light before exiting the syscall and returning control * to userspace (i.e. you cannot remember the returned struct file * after * returning to userspace). * 2) You must not call filp_close on the returned struct file * in between * calls to fget_light and fput_light. * 3) You must not clone the current task in between the calls to fget_light * and fput_light. * * The fput_needed flag returned by fget_light should be passed to the * corresponding fput_light. * * (As an exception to rule 2, you can call filp_close between fget_light and * fput_light provided that you capture a real refcount with get_file before * the call to filp_close, and ensure that this real refcount is fput *after* * the fput_light call.) * * See also the documentation in rust/kernel/file.rs. */ static inline struct fd __fget_light(unsigned int fd, fmode_t mask) { struct files_struct *files = current->files; struct file *file; /* * If another thread is concurrently calling close_fd() followed * by put_files_struct(), we must not observe the old table * entry combined with the new refcount - otherwise we could * return a file that is concurrently being freed. * * atomic_read_acquire() pairs with atomic_dec_and_test() in * put_files_struct(). */ if (likely(atomic_read_acquire(&files->count) == 1)) { file = files_lookup_fd_raw(files, fd); if (!file || unlikely(file->f_mode & mask)) return EMPTY_FD; return BORROWED_FD(file); } else { file = __fget_files(files, fd, mask); if (!file) return EMPTY_FD; return CLONED_FD(file); } } struct fd fdget(unsigned int fd) { return __fget_light(fd, FMODE_PATH); } EXPORT_SYMBOL(fdget); struct fd fdget_raw(unsigned int fd) { return __fget_light(fd, 0); } /* * Try to avoid f_pos locking. We only need it if the * file is marked for FMODE_ATOMIC_POS, and it can be * accessed multiple ways. * * Always do it for directories, because pidfd_getfd() * can make a file accessible even if it otherwise would * not be, and for directories this is a correctness * issue, not a "POSIX requirement". */ static inline bool file_needs_f_pos_lock(struct file *file) { return (file->f_mode & FMODE_ATOMIC_POS) && (file_count(file) > 1 || file->f_op->iterate_shared); } struct fd fdget_pos(unsigned int fd) { struct fd f = fdget(fd); struct file *file = fd_file(f); if (file && file_needs_f_pos_lock(file)) { f.word |= FDPUT_POS_UNLOCK; mutex_lock(&file->f_pos_lock); } return f; } void __f_unlock_pos(struct file *f) { mutex_unlock(&f->f_pos_lock); } /* * We only lock f_pos if we have threads or if the file might be * shared with another process. In both cases we'll have an elevated * file count (done either by fdget() or by fork()). */ void set_close_on_exec(unsigned int fd, int flag) { struct files_struct *files = current->files; spin_lock(&files->file_lock); __set_close_on_exec(fd, files_fdtable(files), flag); spin_unlock(&files->file_lock); } bool get_close_on_exec(unsigned int fd) { bool res; rcu_read_lock(); res = close_on_exec(fd, current->files); rcu_read_unlock(); return res; } static int do_dup2(struct files_struct *files, struct file *file, unsigned fd, unsigned flags) __releases(&files->file_lock) { struct file *tofree; struct fdtable *fdt; /* * We need to detect attempts to do dup2() over allocated but still * not finished descriptor. NB: OpenBSD avoids that at the price of * extra work in their equivalent of fget() - they insert struct * file immediately after grabbing descriptor, mark it larval if * more work (e.g. actual opening) is needed and make sure that * fget() treats larval files as absent. Potentially interesting, * but while extra work in fget() is trivial, locking implications * and amount of surgery on open()-related paths in VFS are not. * FreeBSD fails with -EBADF in the same situation, NetBSD "solution" * deadlocks in rather amusing ways, AFAICS. All of that is out of * scope of POSIX or SUS, since neither considers shared descriptor * tables and this condition does not arise without those. */ fdt = files_fdtable(files); fd = array_index_nospec(fd, fdt->max_fds); tofree = fdt->fd[fd]; if (!tofree && fd_is_open(fd, fdt)) goto Ebusy; get_file(file); rcu_assign_pointer(fdt->fd[fd], file); __set_open_fd(fd, fdt, flags & O_CLOEXEC); spin_unlock(&files->file_lock); if (tofree) filp_close(tofree, files); return fd; Ebusy: spin_unlock(&files->file_lock); return -EBUSY; } int replace_fd(unsigned fd, struct file *file, unsigned flags) { int err; struct files_struct *files = current->files; if (!file) return close_fd(fd); if (fd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, fd); if (unlikely(err < 0)) goto out_unlock; return do_dup2(files, file, fd, flags); out_unlock: spin_unlock(&files->file_lock); return err; } /** * receive_fd() - Install received file into file descriptor table * @file: struct file that was received from another process * @ufd: __user pointer to write new fd number to * @o_flags: the O_* flags to apply to the new fd entry * * Installs a received file into the file descriptor table, with appropriate * checks and count updates. Optionally writes the fd number to userspace, if * @ufd is non-NULL. * * This helper handles its own reference counting of the incoming * struct file. * * Returns newly install fd or -ve on error. */ int receive_fd(struct file *file, int __user *ufd, unsigned int o_flags) { int new_fd; int error; error = security_file_receive(file); if (error) return error; new_fd = get_unused_fd_flags(o_flags); if (new_fd < 0) return new_fd; if (ufd) { error = put_user(new_fd, ufd); if (error) { put_unused_fd(new_fd); return error; } } fd_install(new_fd, get_file(file)); __receive_sock(file); return new_fd; } EXPORT_SYMBOL_GPL(receive_fd); int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags) { int error; error = security_file_receive(file); if (error) return error; error = replace_fd(new_fd, file, o_flags); if (error) return error; __receive_sock(file); return new_fd; } static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags) { int err = -EBADF; struct file *file; struct files_struct *files = current->files; if ((flags & ~O_CLOEXEC) != 0) return -EINVAL; if (unlikely(oldfd == newfd)) return -EINVAL; if (newfd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, newfd); file = files_lookup_fd_locked(files, oldfd); if (unlikely(!file)) goto Ebadf; if (unlikely(err < 0)) { if (err == -EMFILE) goto Ebadf; goto out_unlock; } return do_dup2(files, file, newfd, flags); Ebadf: err = -EBADF; out_unlock: spin_unlock(&files->file_lock); return err; } SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags) { return ksys_dup3(oldfd, newfd, flags); } SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd) { if (unlikely(newfd == oldfd)) { /* corner case */ struct files_struct *files = current->files; struct file *f; int retval = oldfd; rcu_read_lock(); f = __fget_files_rcu(files, oldfd, 0); if (!f) retval = -EBADF; rcu_read_unlock(); if (f) fput(f); return retval; } return ksys_dup3(oldfd, newfd, 0); } SYSCALL_DEFINE1(dup, unsigned int, fildes) { int ret = -EBADF; struct file *file = fget_raw(fildes); if (file) { ret = get_unused_fd_flags(0); if (ret >= 0) fd_install(ret, file); else fput(file); } return ret; } int f_dupfd(unsigned int from, struct file *file, unsigned flags) { unsigned long nofile = rlimit(RLIMIT_NOFILE); int err; if (from >= nofile) return -EINVAL; err = alloc_fd(from, nofile, flags); if (err >= 0) { get_file(file); fd_install(err, file); } return err; } int iterate_fd(struct files_struct *files, unsigned n, int (*f)(const void *, struct file *, unsigned), const void *p) { struct fdtable *fdt; int res = 0; if (!files) return 0; spin_lock(&files->file_lock); for (fdt = files_fdtable(files); n < fdt->max_fds; n++) { struct file *file; file = rcu_dereference_check_fdtable(files, fdt->fd[n]); if (!file) continue; res = f(p, file, n); if (res) break; } spin_unlock(&files->file_lock); return res; } EXPORT_SYMBOL(iterate_fd); |
| 31 31 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Directory notifications for Linux. * * Copyright (C) 2000,2001,2002 Stephen Rothwell * * Copyright (C) 2009 Eric Paris <Red Hat Inc> * dnotify was largly rewritten to use the new fsnotify infrastructure */ #include <linux/fs.h> #include <linux/module.h> #include <linux/sched.h> #include <linux/sched/signal.h> #include <linux/dnotify.h> #include <linux/init.h> #include <linux/security.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/fsnotify_backend.h> static int dir_notify_enable __read_mostly = 1; #ifdef CONFIG_SYSCTL static struct ctl_table dnotify_sysctls[] = { { .procname = "dir-notify-enable", .data = &dir_notify_enable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, }; static void __init dnotify_sysctl_init(void) { register_sysctl_init("fs", dnotify_sysctls); } #else #define dnotify_sysctl_init() do { } while (0) #endif static struct kmem_cache *dnotify_struct_cache __ro_after_init; static struct kmem_cache *dnotify_mark_cache __ro_after_init; static struct fsnotify_group *dnotify_group __ro_after_init; /* * dnotify will attach one of these to each inode (i_fsnotify_marks) which * is being watched by dnotify. If multiple userspace applications are watching * the same directory with dnotify their information is chained in dn */ struct dnotify_mark { struct fsnotify_mark fsn_mark; struct dnotify_struct *dn; }; /* * When a process starts or stops watching an inode the set of events which * dnotify cares about for that inode may change. This function runs the * list of everything receiving dnotify events about this directory and calculates * the set of all those events. After it updates what dnotify is interested in * it calls the fsnotify function so it can update the set of all events relevant * to this inode. */ static void dnotify_recalc_inode_mask(struct fsnotify_mark *fsn_mark) { __u32 new_mask = 0; struct dnotify_struct *dn; struct dnotify_mark *dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); assert_spin_locked(&fsn_mark->lock); for (dn = dn_mark->dn; dn != NULL; dn = dn->dn_next) new_mask |= (dn->dn_mask & ~FS_DN_MULTISHOT); if (fsn_mark->mask == new_mask) return; fsn_mark->mask = new_mask; fsnotify_recalc_mask(fsn_mark->connector); } /* * Mains fsnotify call where events are delivered to dnotify. * Find the dnotify mark on the relevant inode, run the list of dnotify structs * on that mark and determine which of them has expressed interest in receiving * events of this type. When found send the correct process and signal and * destroy the dnotify struct if it was not registered to receive multiple * events. */ static int dnotify_handle_event(struct fsnotify_mark *inode_mark, u32 mask, struct inode *inode, struct inode *dir, const struct qstr *name, u32 cookie) { struct dnotify_mark *dn_mark; struct dnotify_struct *dn; struct dnotify_struct **prev; struct fown_struct *fown; __u32 test_mask = mask & ~FS_EVENT_ON_CHILD; /* not a dir, dnotify doesn't care */ if (!dir && !(mask & FS_ISDIR)) return 0; dn_mark = container_of(inode_mark, struct dnotify_mark, fsn_mark); spin_lock(&inode_mark->lock); prev = &dn_mark->dn; while ((dn = *prev) != NULL) { if ((dn->dn_mask & test_mask) == 0) { prev = &dn->dn_next; continue; } fown = file_f_owner(dn->dn_filp); send_sigio(fown, dn->dn_fd, POLL_MSG); if (dn->dn_mask & FS_DN_MULTISHOT) prev = &dn->dn_next; else { *prev = dn->dn_next; kmem_cache_free(dnotify_struct_cache, dn); dnotify_recalc_inode_mask(inode_mark); } } spin_unlock(&inode_mark->lock); return 0; } static void dnotify_free_mark(struct fsnotify_mark *fsn_mark) { struct dnotify_mark *dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); BUG_ON(dn_mark->dn); kmem_cache_free(dnotify_mark_cache, dn_mark); } static const struct fsnotify_ops dnotify_fsnotify_ops = { .handle_inode_event = dnotify_handle_event, .free_mark = dnotify_free_mark, }; /* * Called every time a file is closed. Looks first for a dnotify mark on the * inode. If one is found run all of the ->dn structures attached to that * mark for one relevant to this process closing the file and remove that * dnotify_struct. If that was the last dnotify_struct also remove the * fsnotify_mark. */ void dnotify_flush(struct file *filp, fl_owner_t id) { struct fsnotify_mark *fsn_mark; struct dnotify_mark *dn_mark; struct dnotify_struct *dn; struct dnotify_struct **prev; struct inode *inode; bool free = false; inode = file_inode(filp); if (!S_ISDIR(inode->i_mode)) return; fsn_mark = fsnotify_find_inode_mark(inode, dnotify_group); if (!fsn_mark) return; dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); fsnotify_group_lock(dnotify_group); spin_lock(&fsn_mark->lock); prev = &dn_mark->dn; while ((dn = *prev) != NULL) { if ((dn->dn_owner == id) && (dn->dn_filp == filp)) { *prev = dn->dn_next; kmem_cache_free(dnotify_struct_cache, dn); dnotify_recalc_inode_mask(fsn_mark); break; } prev = &dn->dn_next; } spin_unlock(&fsn_mark->lock); /* nothing else could have found us thanks to the dnotify_groups mark_mutex */ if (dn_mark->dn == NULL) { fsnotify_detach_mark(fsn_mark); free = true; } fsnotify_group_unlock(dnotify_group); if (free) fsnotify_free_mark(fsn_mark); fsnotify_put_mark(fsn_mark); } /* this conversion is done only at watch creation */ static __u32 convert_arg(unsigned int arg) { __u32 new_mask = FS_EVENT_ON_CHILD; if (arg & DN_MULTISHOT) new_mask |= FS_DN_MULTISHOT; if (arg & DN_DELETE) new_mask |= (FS_DELETE | FS_MOVED_FROM); if (arg & DN_MODIFY) new_mask |= FS_MODIFY; if (arg & DN_ACCESS) new_mask |= FS_ACCESS; if (arg & DN_ATTRIB) new_mask |= FS_ATTRIB; if (arg & DN_RENAME) new_mask |= FS_RENAME; if (arg & DN_CREATE) new_mask |= (FS_CREATE | FS_MOVED_TO); return new_mask; } /* * If multiple processes watch the same inode with dnotify there is only one * dnotify mark in inode->i_fsnotify_marks but we chain a dnotify_struct * onto that mark. This function either attaches the new dnotify_struct onto * that list, or it |= the mask onto an existing dnofiy_struct. */ static int attach_dn(struct dnotify_struct *dn, struct dnotify_mark *dn_mark, fl_owner_t id, int fd, struct file *filp, __u32 mask) { struct dnotify_struct *odn; odn = dn_mark->dn; while (odn != NULL) { /* adding more events to existing dnofiy_struct? */ if ((odn->dn_owner == id) && (odn->dn_filp == filp)) { odn->dn_fd = fd; odn->dn_mask |= mask; return -EEXIST; } odn = odn->dn_next; } dn->dn_mask = mask; dn->dn_fd = fd; dn->dn_filp = filp; dn->dn_owner = id; dn->dn_next = dn_mark->dn; dn_mark->dn = dn; return 0; } /* * When a process calls fcntl to attach a dnotify watch to a directory it ends * up here. Allocate both a mark for fsnotify to add and a dnotify_struct to be * attached to the fsnotify_mark. */ int fcntl_dirnotify(int fd, struct file *filp, unsigned int arg) { struct dnotify_mark *new_dn_mark, *dn_mark; struct fsnotify_mark *new_fsn_mark, *fsn_mark; struct dnotify_struct *dn; struct inode *inode; fl_owner_t id = current->files; struct file *f = NULL; int destroy = 0, error = 0; __u32 mask; /* we use these to tell if we need to kfree */ new_fsn_mark = NULL; dn = NULL; if (!dir_notify_enable) { error = -EINVAL; goto out_err; } /* a 0 mask means we are explicitly removing the watch */ if ((arg & ~DN_MULTISHOT) == 0) { dnotify_flush(filp, id); error = 0; goto out_err; } /* dnotify only works on directories */ inode = file_inode(filp); if (!S_ISDIR(inode->i_mode)) { error = -ENOTDIR; goto out_err; } /* * convert the userspace DN_* "arg" to the internal FS_* * defined in fsnotify */ mask = convert_arg(arg); error = security_path_notify(&filp->f_path, mask, FSNOTIFY_OBJ_TYPE_INODE); if (error) goto out_err; /* expect most fcntl to add new rather than augment old */ dn = kmem_cache_alloc(dnotify_struct_cache, GFP_KERNEL); if (!dn) { error = -ENOMEM; goto out_err; } /* new fsnotify mark, we expect most fcntl calls to add a new mark */ new_dn_mark = kmem_cache_alloc(dnotify_mark_cache, GFP_KERNEL); if (!new_dn_mark) { error = -ENOMEM; goto out_err; } error = file_f_owner_allocate(filp); if (error) goto out_err; /* set up the new_fsn_mark and new_dn_mark */ new_fsn_mark = &new_dn_mark->fsn_mark; fsnotify_init_mark(new_fsn_mark, dnotify_group); new_fsn_mark->mask = mask; new_dn_mark->dn = NULL; /* this is needed to prevent the fcntl/close race described below */ fsnotify_group_lock(dnotify_group); /* add the new_fsn_mark or find an old one. */ fsn_mark = fsnotify_find_inode_mark(inode, dnotify_group); if (fsn_mark) { dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); spin_lock(&fsn_mark->lock); } else { error = fsnotify_add_inode_mark_locked(new_fsn_mark, inode, 0); if (error) { fsnotify_group_unlock(dnotify_group); goto out_err; } spin_lock(&new_fsn_mark->lock); fsn_mark = new_fsn_mark; dn_mark = new_dn_mark; /* we used new_fsn_mark, so don't free it */ new_fsn_mark = NULL; } f = fget_raw(fd); /* if (f != filp) means that we lost a race and another task/thread * actually closed the fd we are still playing with before we grabbed * the dnotify_groups mark_mutex and fsn_mark->lock. Since closing the * fd is the only time we clean up the marks we need to get our mark * off the list. */ if (f != filp) { /* if we added ourselves, shoot ourselves, it's possible that * the flush actually did shoot this fsn_mark. That's fine too * since multiple calls to destroy_mark is perfectly safe, if * we found a dn_mark already attached to the inode, just sod * off silently as the flush at close time dealt with it. */ if (dn_mark == new_dn_mark) destroy = 1; error = 0; goto out; } __f_setown(filp, task_pid(current), PIDTYPE_TGID, 0); error = attach_dn(dn, dn_mark, id, fd, filp, mask); /* !error means that we attached the dn to the dn_mark, so don't free it */ if (!error) dn = NULL; /* -EEXIST means that we didn't add this new dn and used an old one. * that isn't an error (and the unused dn should be freed) */ else if (error == -EEXIST) error = 0; dnotify_recalc_inode_mask(fsn_mark); out: spin_unlock(&fsn_mark->lock); if (destroy) fsnotify_detach_mark(fsn_mark); fsnotify_group_unlock(dnotify_group); if (destroy) fsnotify_free_mark(fsn_mark); fsnotify_put_mark(fsn_mark); out_err: if (new_fsn_mark) fsnotify_put_mark(new_fsn_mark); if (dn) kmem_cache_free(dnotify_struct_cache, dn); if (f) fput(f); return error; } static int __init dnotify_init(void) { dnotify_struct_cache = KMEM_CACHE(dnotify_struct, SLAB_PANIC|SLAB_ACCOUNT); dnotify_mark_cache = KMEM_CACHE(dnotify_mark, SLAB_PANIC|SLAB_ACCOUNT); dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops, 0); if (IS_ERR(dnotify_group)) panic("unable to allocate fsnotify group for dnotify\n"); dnotify_sysctl_init(); return 0; } module_init(dnotify_init) |
| 749 749 750 749 768 768 769 769 746 767 769 767 767 767 87 741 742 741 742 741 742 76 768 770 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 | // SPDX-License-Identifier: GPL-2.0 /* * Lockless hierarchical page accounting & limiting * * Copyright (C) 2014 Red Hat, Inc., Johannes Weiner */ #include <linux/page_counter.h> #include <linux/atomic.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/sched.h> #include <linux/bug.h> #include <asm/page.h> static bool track_protection(struct page_counter *c) { return c->protection_support; } static void propagate_protected_usage(struct page_counter *c, unsigned long usage) { unsigned long protected, old_protected; long delta; if (!c->parent) return; protected = min(usage, READ_ONCE(c->min)); old_protected = atomic_long_read(&c->min_usage); if (protected != old_protected) { old_protected = atomic_long_xchg(&c->min_usage, protected); delta = protected - old_protected; if (delta) atomic_long_add(delta, &c->parent->children_min_usage); } protected = min(usage, READ_ONCE(c->low)); old_protected = atomic_long_read(&c->low_usage); if (protected != old_protected) { old_protected = atomic_long_xchg(&c->low_usage, protected); delta = protected - old_protected; if (delta) atomic_long_add(delta, &c->parent->children_low_usage); } } /** * page_counter_cancel - take pages out of the local counter * @counter: counter * @nr_pages: number of pages to cancel */ void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages) { long new; new = atomic_long_sub_return(nr_pages, &counter->usage); /* More uncharges than charges? */ if (WARN_ONCE(new < 0, "page_counter underflow: %ld nr_pages=%lu\n", new, nr_pages)) { new = 0; atomic_long_set(&counter->usage, new); } if (track_protection(counter)) propagate_protected_usage(counter, new); } /** * page_counter_charge - hierarchically charge pages * @counter: counter * @nr_pages: number of pages to charge * * NOTE: This does not consider any configured counter limits. */ void page_counter_charge(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; bool protection = track_protection(counter); for (c = counter; c; c = c->parent) { long new; new = atomic_long_add_return(nr_pages, &c->usage); if (protection) propagate_protected_usage(c, new); /* * This is indeed racy, but we can live with some * inaccuracy in the watermark. * * Notably, we have two watermarks to allow for both a globally * visible peak and one that can be reset at a smaller scope. * * Since we reset both watermarks when the global reset occurs, * we can guarantee that watermark >= local_watermark, so we * don't need to do both comparisons every time. * * On systems with branch predictors, the inner condition should * be almost free. */ if (new > READ_ONCE(c->local_watermark)) { WRITE_ONCE(c->local_watermark, new); if (new > READ_ONCE(c->watermark)) WRITE_ONCE(c->watermark, new); } } } /** * page_counter_try_charge - try to hierarchically charge pages * @counter: counter * @nr_pages: number of pages to charge * @fail: points first counter to hit its limit, if any * * Returns %true on success, or %false and @fail if the counter or one * of its ancestors has hit its configured limit. */ bool page_counter_try_charge(struct page_counter *counter, unsigned long nr_pages, struct page_counter **fail) { struct page_counter *c; bool protection = track_protection(counter); for (c = counter; c; c = c->parent) { long new; /* * Charge speculatively to avoid an expensive CAS. If * a bigger charge fails, it might falsely lock out a * racing smaller charge and send it into reclaim * early, but the error is limited to the difference * between the two sizes, which is less than 2M/4M in * case of a THP locking out a regular page charge. * * The atomic_long_add_return() implies a full memory * barrier between incrementing the count and reading * the limit. When racing with page_counter_set_max(), * we either see the new limit or the setter sees the * counter has changed and retries. */ new = atomic_long_add_return(nr_pages, &c->usage); if (new > c->max) { atomic_long_sub(nr_pages, &c->usage); /* * This is racy, but we can live with some * inaccuracy in the failcnt which is only used * to report stats. */ data_race(c->failcnt++); *fail = c; goto failed; } if (protection) propagate_protected_usage(c, new); /* see comment on page_counter_charge */ if (new > READ_ONCE(c->local_watermark)) { WRITE_ONCE(c->local_watermark, new); if (new > READ_ONCE(c->watermark)) WRITE_ONCE(c->watermark, new); } } return true; failed: for (c = counter; c != *fail; c = c->parent) page_counter_cancel(c, nr_pages); return false; } /** * page_counter_uncharge - hierarchically uncharge pages * @counter: counter * @nr_pages: number of pages to uncharge */ void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; for (c = counter; c; c = c->parent) page_counter_cancel(c, nr_pages); } /** * page_counter_set_max - set the maximum number of pages allowed * @counter: counter * @nr_pages: limit to set * * Returns 0 on success, -EBUSY if the current number of pages on the * counter already exceeds the specified limit. * * The caller must serialize invocations on the same counter. */ int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages) { for (;;) { unsigned long old; long usage; /* * Update the limit while making sure that it's not * below the concurrently-changing counter value. * * The xchg implies two full memory barriers before * and after, so the read-swap-read is ordered and * ensures coherency with page_counter_try_charge(): * that function modifies the count before checking * the limit, so if it sees the old limit, we see the * modified counter and retry. */ usage = page_counter_read(counter); if (usage > nr_pages) return -EBUSY; old = xchg(&counter->max, nr_pages); if (page_counter_read(counter) <= usage || nr_pages >= old) return 0; counter->max = old; cond_resched(); } } /** * page_counter_set_min - set the amount of protected memory * @counter: counter * @nr_pages: value to set * * The caller must serialize invocations on the same counter. */ void page_counter_set_min(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; WRITE_ONCE(counter->min, nr_pages); for (c = counter; c; c = c->parent) propagate_protected_usage(c, atomic_long_read(&c->usage)); } /** * page_counter_set_low - set the amount of protected memory * @counter: counter * @nr_pages: value to set * * The caller must serialize invocations on the same counter. */ void page_counter_set_low(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; WRITE_ONCE(counter->low, nr_pages); for (c = counter; c; c = c->parent) propagate_protected_usage(c, atomic_long_read(&c->usage)); } /** * page_counter_memparse - memparse() for page counter limits * @buf: string to parse * @max: string meaning maximum possible value * @nr_pages: returns the result in number of pages * * Returns -EINVAL, or 0 and @nr_pages on success. @nr_pages will be * limited to %PAGE_COUNTER_MAX. */ int page_counter_memparse(const char *buf, const char *max, unsigned long *nr_pages) { char *end; u64 bytes; if (!strcmp(buf, max)) { *nr_pages = PAGE_COUNTER_MAX; return 0; } bytes = memparse(buf, &end); if (*end != '\0') return -EINVAL; *nr_pages = min(bytes / PAGE_SIZE, (u64)PAGE_COUNTER_MAX); return 0; } #ifdef CONFIG_MEMCG /* * This function calculates an individual page counter's effective * protection which is derived from its own memory.min/low, its * parent's and siblings' settings, as well as the actual memory * distribution in the tree. * * The following rules apply to the effective protection values: * * 1. At the first level of reclaim, effective protection is equal to * the declared protection in memory.min and memory.low. * * 2. To enable safe delegation of the protection configuration, at * subsequent levels the effective protection is capped to the * parent's effective protection. * * 3. To make complex and dynamic subtrees easier to configure, the * user is allowed to overcommit the declared protection at a given * level. If that is the case, the parent's effective protection is * distributed to the children in proportion to how much protection * they have declared and how much of it they are utilizing. * * This makes distribution proportional, but also work-conserving: * if one counter claims much more protection than it uses memory, * the unused remainder is available to its siblings. * * 4. Conversely, when the declared protection is undercommitted at a * given level, the distribution of the larger parental protection * budget is NOT proportional. A counter's protection from a sibling * is capped to its own memory.min/low setting. * * 5. However, to allow protecting recursive subtrees from each other * without having to declare each individual counter's fixed share * of the ancestor's claim to protection, any unutilized - * "floating" - protection from up the tree is distributed in * proportion to each counter's *usage*. This makes the protection * neutral wrt sibling cgroups and lets them compete freely over * the shared parental protection budget, but it protects the * subtree as a whole from neighboring subtrees. * * Note that 4. and 5. are not in conflict: 4. is about protecting * against immediate siblings whereas 5. is about protecting against * neighboring subtrees. */ static unsigned long effective_protection(unsigned long usage, unsigned long parent_usage, unsigned long setting, unsigned long parent_effective, unsigned long siblings_protected, bool recursive_protection) { unsigned long protected; unsigned long ep; protected = min(usage, setting); /* * If all cgroups at this level combined claim and use more * protection than what the parent affords them, distribute * shares in proportion to utilization. * * We are using actual utilization rather than the statically * claimed protection in order to be work-conserving: claimed * but unused protection is available to siblings that would * otherwise get a smaller chunk than what they claimed. */ if (siblings_protected > parent_effective) return protected * parent_effective / siblings_protected; /* * Ok, utilized protection of all children is within what the * parent affords them, so we know whatever this child claims * and utilizes is effectively protected. * * If there is unprotected usage beyond this value, reclaim * will apply pressure in proportion to that amount. * * If there is unutilized protection, the cgroup will be fully * shielded from reclaim, but we do return a smaller value for * protection than what the group could enjoy in theory. This * is okay. With the overcommit distribution above, effective * protection is always dependent on how memory is actually * consumed among the siblings anyway. */ ep = protected; /* * If the children aren't claiming (all of) the protection * afforded to them by the parent, distribute the remainder in * proportion to the (unprotected) memory of each cgroup. That * way, cgroups that aren't explicitly prioritized wrt each * other compete freely over the allowance, but they are * collectively protected from neighboring trees. * * We're using unprotected memory for the weight so that if * some cgroups DO claim explicit protection, we don't protect * the same bytes twice. * * Check both usage and parent_usage against the respective * protected values. One should imply the other, but they * aren't read atomically - make sure the division is sane. */ if (!recursive_protection) return ep; if (parent_effective > siblings_protected && parent_usage > siblings_protected && usage > protected) { unsigned long unclaimed; unclaimed = parent_effective - siblings_protected; unclaimed *= usage - protected; unclaimed /= parent_usage - siblings_protected; ep += unclaimed; } return ep; } /** * page_counter_calculate_protection - check if memory consumption is in the normal range * @root: the top ancestor of the sub-tree being checked * @counter: the page_counter the counter to update * @recursive_protection: Whether to use memory_recursiveprot behavior. * * Calculates elow/emin thresholds for given page_counter. * * WARNING: This function is not stateless! It can only be used as part * of a top-down tree iteration, not for isolated queries. */ void page_counter_calculate_protection(struct page_counter *root, struct page_counter *counter, bool recursive_protection) { unsigned long usage, parent_usage; struct page_counter *parent = counter->parent; /* * Effective values of the reclaim targets are ignored so they * can be stale. Have a look at mem_cgroup_protection for more * details. * TODO: calculation should be more robust so that we do not need * that special casing. */ if (root == counter) return; usage = page_counter_read(counter); if (!usage) return; if (parent == root) { counter->emin = READ_ONCE(counter->min); counter->elow = READ_ONCE(counter->low); return; } parent_usage = page_counter_read(parent); WRITE_ONCE(counter->emin, effective_protection(usage, parent_usage, READ_ONCE(counter->min), READ_ONCE(parent->emin), atomic_long_read(&parent->children_min_usage), recursive_protection)); WRITE_ONCE(counter->elow, effective_protection(usage, parent_usage, READ_ONCE(counter->low), READ_ONCE(parent->elow), atomic_long_read(&parent->children_low_usage), recursive_protection)); } #endif /* CONFIG_MEMCG */ |
| 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/dsa/user.c - user device handling * Copyright (c) 2008-2009 Marvell Semiconductor */ #include <linux/list.h> #include <linux/etherdevice.h> #include <linux/netdevice.h> #include <linux/phy.h> #include <linux/phy_fixed.h> #include <linux/phylink.h> #include <linux/of_net.h> #include <linux/of_mdio.h> #include <linux/mdio.h> #include <net/rtnetlink.h> #include <net/pkt_cls.h> #include <net/selftests.h> #include <net/tc_act/tc_mirred.h> #include <linux/if_bridge.h> #include <linux/if_hsr.h> #include <net/dcbnl.h> #include <linux/netpoll.h> #include <linux/string.h> #include "conduit.h" #include "dsa.h" #include "netlink.h" #include "port.h" #include "switch.h" #include "tag.h" #include "user.h" struct dsa_switchdev_event_work { struct net_device *dev; struct net_device *orig_dev; struct work_struct work; unsigned long event; /* Specific for SWITCHDEV_FDB_ADD_TO_DEVICE and * SWITCHDEV_FDB_DEL_TO_DEVICE */ unsigned char addr[ETH_ALEN]; u16 vid; bool host_addr; }; enum dsa_standalone_event { DSA_UC_ADD, DSA_UC_DEL, DSA_MC_ADD, DSA_MC_DEL, }; struct dsa_standalone_event_work { struct work_struct work; struct net_device *dev; enum dsa_standalone_event event; unsigned char addr[ETH_ALEN]; u16 vid; }; struct dsa_host_vlan_rx_filtering_ctx { struct net_device *dev; const unsigned char *addr; enum dsa_standalone_event event; }; static bool dsa_switch_supports_uc_filtering(struct dsa_switch *ds) { return ds->ops->port_fdb_add && ds->ops->port_fdb_del && ds->fdb_isolation && !ds->vlan_filtering_is_global && !ds->needs_standalone_vlan_filtering; } static bool dsa_switch_supports_mc_filtering(struct dsa_switch *ds) { return ds->ops->port_mdb_add && ds->ops->port_mdb_del && ds->fdb_isolation && !ds->vlan_filtering_is_global && !ds->needs_standalone_vlan_filtering; } static void dsa_user_standalone_event_work(struct work_struct *work) { struct dsa_standalone_event_work *standalone_work = container_of(work, struct dsa_standalone_event_work, work); const unsigned char *addr = standalone_work->addr; struct net_device *dev = standalone_work->dev; struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_mdb mdb; struct dsa_switch *ds = dp->ds; u16 vid = standalone_work->vid; int err; switch (standalone_work->event) { case DSA_UC_ADD: err = dsa_port_standalone_host_fdb_add(dp, addr, vid); if (err) { dev_err(ds->dev, "port %d failed to add %pM vid %d to fdb: %d\n", dp->index, addr, vid, err); break; } break; case DSA_UC_DEL: err = dsa_port_standalone_host_fdb_del(dp, addr, vid); if (err) { dev_err(ds->dev, "port %d failed to delete %pM vid %d from fdb: %d\n", dp->index, addr, vid, err); } break; case DSA_MC_ADD: ether_addr_copy(mdb.addr, addr); mdb.vid = vid; err = dsa_port_standalone_host_mdb_add(dp, &mdb); if (err) { dev_err(ds->dev, "port %d failed to add %pM vid %d to mdb: %d\n", dp->index, addr, vid, err); break; } break; case DSA_MC_DEL: ether_addr_copy(mdb.addr, addr); mdb.vid = vid; err = dsa_port_standalone_host_mdb_del(dp, &mdb); if (err) { dev_err(ds->dev, "port %d failed to delete %pM vid %d from mdb: %d\n", dp->index, addr, vid, err); } break; } kfree(standalone_work); } static int dsa_user_schedule_standalone_work(struct net_device *dev, enum dsa_standalone_event event, const unsigned char *addr, u16 vid) { struct dsa_standalone_event_work *standalone_work; standalone_work = kzalloc(sizeof(*standalone_work), GFP_ATOMIC); if (!standalone_work) return -ENOMEM; INIT_WORK(&standalone_work->work, dsa_user_standalone_event_work); standalone_work->event = event; standalone_work->dev = dev; ether_addr_copy(standalone_work->addr, addr); standalone_work->vid = vid; dsa_schedule_work(&standalone_work->work); return 0; } static int dsa_user_host_vlan_rx_filtering(void *arg, int vid) { struct dsa_host_vlan_rx_filtering_ctx *ctx = arg; return dsa_user_schedule_standalone_work(ctx->dev, ctx->event, ctx->addr, vid); } static int dsa_user_vlan_for_each(struct net_device *dev, int (*cb)(void *arg, int vid), void *arg) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_vlan *v; int err; lockdep_assert_held(&dev->addr_list_lock); err = cb(arg, 0); if (err) return err; list_for_each_entry(v, &dp->user_vlans, list) { err = cb(arg, v->vid); if (err) return err; } return 0; } static int dsa_user_sync_uc(struct net_device *dev, const unsigned char *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_UC_ADD, }; dev_uc_add(conduit, addr); if (!dsa_switch_supports_uc_filtering(dp->ds)) return 0; return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } static int dsa_user_unsync_uc(struct net_device *dev, const unsigned char *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_UC_DEL, }; dev_uc_del(conduit, addr); if (!dsa_switch_supports_uc_filtering(dp->ds)) return 0; return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } static int dsa_user_sync_mc(struct net_device *dev, const unsigned char *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_MC_ADD, }; dev_mc_add(conduit, addr); if (!dsa_switch_supports_mc_filtering(dp->ds)) return 0; return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } static int dsa_user_unsync_mc(struct net_device *dev, const unsigned char *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_MC_DEL, }; dev_mc_del(conduit, addr); if (!dsa_switch_supports_mc_filtering(dp->ds)) return 0; return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } void dsa_user_sync_ha(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; netif_addr_lock_bh(dev); netdev_for_each_synced_mc_addr(ha, dev) dsa_user_sync_mc(dev, ha->addr); netdev_for_each_synced_uc_addr(ha, dev) dsa_user_sync_uc(dev, ha->addr); netif_addr_unlock_bh(dev); if (dsa_switch_supports_uc_filtering(ds) || dsa_switch_supports_mc_filtering(ds)) dsa_flush_workqueue(); } void dsa_user_unsync_ha(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; netif_addr_lock_bh(dev); netdev_for_each_synced_uc_addr(ha, dev) dsa_user_unsync_uc(dev, ha->addr); netdev_for_each_synced_mc_addr(ha, dev) dsa_user_unsync_mc(dev, ha->addr); netif_addr_unlock_bh(dev); if (dsa_switch_supports_uc_filtering(ds) || dsa_switch_supports_mc_filtering(ds)) dsa_flush_workqueue(); } /* user mii_bus handling ***************************************************/ static int dsa_user_phy_read(struct mii_bus *bus, int addr, int reg) { struct dsa_switch *ds = bus->priv; if (ds->phys_mii_mask & (1 << addr)) return ds->ops->phy_read(ds, addr, reg); return 0xffff; } static int dsa_user_phy_write(struct mii_bus *bus, int addr, int reg, u16 val) { struct dsa_switch *ds = bus->priv; if (ds->phys_mii_mask & (1 << addr)) return ds->ops->phy_write(ds, addr, reg, val); return 0; } void dsa_user_mii_bus_init(struct dsa_switch *ds) { ds->user_mii_bus->priv = (void *)ds; ds->user_mii_bus->name = "dsa user smi"; ds->user_mii_bus->read = dsa_user_phy_read; ds->user_mii_bus->write = dsa_user_phy_write; snprintf(ds->user_mii_bus->id, MII_BUS_ID_SIZE, "dsa-%d.%d", ds->dst->index, ds->index); ds->user_mii_bus->parent = ds->dev; ds->user_mii_bus->phy_mask = ~ds->phys_mii_mask; } /* user device handling ****************************************************/ static int dsa_user_get_iflink(const struct net_device *dev) { return READ_ONCE(dsa_user_to_conduit(dev)->ifindex); } int dsa_user_host_uc_install(struct net_device *dev, const u8 *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int err; if (dsa_switch_supports_uc_filtering(ds)) { err = dsa_port_standalone_host_fdb_add(dp, addr, 0); if (err) goto out; } if (!ether_addr_equal(addr, conduit->dev_addr)) { err = dev_uc_add(conduit, addr); if (err < 0) goto del_host_addr; } return 0; del_host_addr: if (dsa_switch_supports_uc_filtering(ds)) dsa_port_standalone_host_fdb_del(dp, addr, 0); out: return err; } void dsa_user_host_uc_uninstall(struct net_device *dev) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ether_addr_equal(dev->dev_addr, conduit->dev_addr)) dev_uc_del(conduit, dev->dev_addr); if (dsa_switch_supports_uc_filtering(ds)) dsa_port_standalone_host_fdb_del(dp, dev->dev_addr, 0); } static int dsa_user_open(struct net_device *dev) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); int err; err = dev_open(conduit, NULL); if (err < 0) { netdev_err(dev, "failed to open conduit %s\n", conduit->name); goto out; } err = dsa_user_host_uc_install(dev, dev->dev_addr); if (err) goto out; err = dsa_port_enable_rt(dp, dev->phydev); if (err) goto out_del_host_uc; return 0; out_del_host_uc: dsa_user_host_uc_uninstall(dev); out: return err; } static int dsa_user_close(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); dsa_port_disable_rt(dp); dsa_user_host_uc_uninstall(dev); return 0; } static void dsa_user_manage_host_flood(struct net_device *dev) { bool mc = dev->flags & (IFF_PROMISC | IFF_ALLMULTI); struct dsa_port *dp = dsa_user_to_port(dev); bool uc = dev->flags & IFF_PROMISC; dsa_port_set_host_flood(dp, uc, mc); } static void dsa_user_change_rx_flags(struct net_device *dev, int change) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (change & IFF_ALLMULTI) dev_set_allmulti(conduit, dev->flags & IFF_ALLMULTI ? 1 : -1); if (change & IFF_PROMISC) dev_set_promiscuity(conduit, dev->flags & IFF_PROMISC ? 1 : -1); if (dsa_switch_supports_uc_filtering(ds) && dsa_switch_supports_mc_filtering(ds)) dsa_user_manage_host_flood(dev); } static void dsa_user_set_rx_mode(struct net_device *dev) { __dev_mc_sync(dev, dsa_user_sync_mc, dsa_user_unsync_mc); __dev_uc_sync(dev, dsa_user_sync_uc, dsa_user_unsync_uc); } static int dsa_user_set_mac_address(struct net_device *dev, void *a) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct sockaddr *addr = a; int err; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; if (ds->ops->port_set_mac_address) { err = ds->ops->port_set_mac_address(ds, dp->index, addr->sa_data); if (err) return err; } /* If the port is down, the address isn't synced yet to hardware or * to the DSA conduit, so there is nothing to change. */ if (!(dev->flags & IFF_UP)) goto out_change_dev_addr; err = dsa_user_host_uc_install(dev, addr->sa_data); if (err) return err; dsa_user_host_uc_uninstall(dev); out_change_dev_addr: eth_hw_addr_set(dev, addr->sa_data); return 0; } struct dsa_user_dump_ctx { struct net_device *dev; struct sk_buff *skb; struct netlink_callback *cb; int idx; }; static int dsa_user_port_fdb_do_dump(const unsigned char *addr, u16 vid, bool is_static, void *data) { struct dsa_user_dump_ctx *dump = data; u32 portid = NETLINK_CB(dump->cb->skb).portid; u32 seq = dump->cb->nlh->nlmsg_seq; struct nlmsghdr *nlh; struct ndmsg *ndm; if (dump->idx < dump->cb->args[2]) goto skip; nlh = nlmsg_put(dump->skb, portid, seq, RTM_NEWNEIGH, sizeof(*ndm), NLM_F_MULTI); if (!nlh) return -EMSGSIZE; ndm = nlmsg_data(nlh); ndm->ndm_family = AF_BRIDGE; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; ndm->ndm_flags = NTF_SELF; ndm->ndm_type = 0; ndm->ndm_ifindex = dump->dev->ifindex; ndm->ndm_state = is_static ? NUD_NOARP : NUD_REACHABLE; if (nla_put(dump->skb, NDA_LLADDR, ETH_ALEN, addr)) goto nla_put_failure; if (vid && nla_put_u16(dump->skb, NDA_VLAN, vid)) goto nla_put_failure; nlmsg_end(dump->skb, nlh); skip: dump->idx++; return 0; nla_put_failure: nlmsg_cancel(dump->skb, nlh); return -EMSGSIZE; } static int dsa_user_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *filter_dev, int *idx) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_user_dump_ctx dump = { .dev = dev, .skb = skb, .cb = cb, .idx = *idx, }; int err; err = dsa_port_fdb_dump(dp, dsa_user_port_fdb_do_dump, &dump); *idx = dump.idx; return err; } static int dsa_user_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct dsa_user_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->dp->ds; int port = p->dp->index; /* Pass through to switch driver if it supports timestamping */ switch (cmd) { case SIOCGHWTSTAMP: if (ds->ops->port_hwtstamp_get) return ds->ops->port_hwtstamp_get(ds, port, ifr); break; case SIOCSHWTSTAMP: if (ds->ops->port_hwtstamp_set) return ds->ops->port_hwtstamp_set(ds, port, ifr); break; } return phylink_mii_ioctl(p->dp->pl, ifr, cmd); } static int dsa_user_port_attr_set(struct net_device *dev, const void *ctx, const struct switchdev_attr *attr, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_user_to_port(dev); int ret; if (ctx && ctx != dp) return 0; switch (attr->id) { case SWITCHDEV_ATTR_ID_PORT_STP_STATE: if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_set_state(dp, attr->u.stp_state, true); break; case SWITCHDEV_ATTR_ID_PORT_MST_STATE: if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_set_mst_state(dp, &attr->u.mst_state, extack); break; case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_vlan_filtering(dp, attr->u.vlan_filtering, extack); break; case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME: if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_ageing_time(dp, attr->u.ageing_time); break; case SWITCHDEV_ATTR_ID_BRIDGE_MST: if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_mst_enable(dp, attr->u.mst, extack); break; case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS: if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_pre_bridge_flags(dp, attr->u.brport_flags, extack); break; case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_bridge_flags(dp, attr->u.brport_flags, extack); break; case SWITCHDEV_ATTR_ID_VLAN_MSTI: if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_vlan_msti(dp, &attr->u.vlan_msti); break; default: ret = -EOPNOTSUPP; break; } return ret; } /* Must be called under rcu_read_lock() */ static int dsa_user_vlan_check_for_8021q_uppers(struct net_device *user, const struct switchdev_obj_port_vlan *vlan) { struct net_device *upper_dev; struct list_head *iter; netdev_for_each_upper_dev_rcu(user, upper_dev, iter) { u16 vid; if (!is_vlan_dev(upper_dev)) continue; vid = vlan_dev_vlan_id(upper_dev); if (vid == vlan->vid) return -EBUSY; } return 0; } static int dsa_user_vlan_add(struct net_device *dev, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan *vlan; int err; if (dsa_port_skip_vlan_configuration(dp)) { NL_SET_ERR_MSG_MOD(extack, "skipping configuration of VLAN"); return 0; } vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); /* Deny adding a bridge VLAN when there is already an 802.1Q upper with * the same VID. */ if (br_vlan_enabled(dsa_port_bridge_dev_get(dp))) { rcu_read_lock(); err = dsa_user_vlan_check_for_8021q_uppers(dev, vlan); rcu_read_unlock(); if (err) { NL_SET_ERR_MSG_MOD(extack, "Port already has a VLAN upper with this VID"); return err; } } return dsa_port_vlan_add(dp, vlan, extack); } /* Offload a VLAN installed on the bridge or on a foreign interface by * installing it as a VLAN towards the CPU port. */ static int dsa_user_host_vlan_add(struct net_device *dev, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan vlan; /* Do nothing if this is a software bridge */ if (!dp->bridge) return -EOPNOTSUPP; if (dsa_port_skip_vlan_configuration(dp)) { NL_SET_ERR_MSG_MOD(extack, "skipping configuration of VLAN"); return 0; } vlan = *SWITCHDEV_OBJ_PORT_VLAN(obj); /* Even though drivers often handle CPU membership in special ways, * it doesn't make sense to program a PVID, so clear this flag. */ vlan.flags &= ~BRIDGE_VLAN_INFO_PVID; return dsa_port_host_vlan_add(dp, &vlan, extack); } static int dsa_user_port_obj_add(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_user_to_port(dev); int err; if (ctx && ctx != dp) return 0; switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_MDB: if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_HOST_MDB: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_bridge_host_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: if (dsa_port_offloads_bridge_port(dp, obj->orig_dev)) err = dsa_user_vlan_add(dev, obj, extack); else err = dsa_user_host_vlan_add(dev, obj, extack); break; case SWITCHDEV_OBJ_ID_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mrp_add(dp, SWITCHDEV_OBJ_MRP(obj)); break; case SWITCHDEV_OBJ_ID_RING_ROLE_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mrp_add_ring_role(dp, SWITCHDEV_OBJ_RING_ROLE_MRP(obj)); break; default: err = -EOPNOTSUPP; break; } return err; } static int dsa_user_vlan_del(struct net_device *dev, const struct switchdev_obj *obj) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan *vlan; if (dsa_port_skip_vlan_configuration(dp)) return 0; vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); return dsa_port_vlan_del(dp, vlan); } static int dsa_user_host_vlan_del(struct net_device *dev, const struct switchdev_obj *obj) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan *vlan; /* Do nothing if this is a software bridge */ if (!dp->bridge) return -EOPNOTSUPP; if (dsa_port_skip_vlan_configuration(dp)) return 0; vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); return dsa_port_host_vlan_del(dp, vlan); } static int dsa_user_port_obj_del(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj) { struct dsa_port *dp = dsa_user_to_port(dev); int err; if (ctx && ctx != dp) return 0; switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_MDB: if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_HOST_MDB: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_bridge_host_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: if (dsa_port_offloads_bridge_port(dp, obj->orig_dev)) err = dsa_user_vlan_del(dev, obj); else err = dsa_user_host_vlan_del(dev, obj); break; case SWITCHDEV_OBJ_ID_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mrp_del(dp, SWITCHDEV_OBJ_MRP(obj)); break; case SWITCHDEV_OBJ_ID_RING_ROLE_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mrp_del_ring_role(dp, SWITCHDEV_OBJ_RING_ROLE_MRP(obj)); break; default: err = -EOPNOTSUPP; break; } return err; } static netdev_tx_t dsa_user_netpoll_send_skb(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_NET_POLL_CONTROLLER struct dsa_user_priv *p = netdev_priv(dev); return netpoll_send_skb(p->netpoll, skb); #else BUG(); return NETDEV_TX_OK; #endif } static void dsa_skb_tx_timestamp(struct dsa_user_priv *p, struct sk_buff *skb) { struct dsa_switch *ds = p->dp->ds; if (!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) return; if (!ds->ops->port_txtstamp) return; ds->ops->port_txtstamp(ds, p->dp->index, skb); } netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev) { /* SKB for netpoll still need to be mangled with the protocol-specific * tag to be successfully transmitted */ if (unlikely(netpoll_tx_running(dev))) return dsa_user_netpoll_send_skb(dev, skb); /* Queue the SKB for transmission on the parent interface, but * do not modify its EtherType */ skb->dev = dsa_user_to_conduit(dev); dev_queue_xmit(skb); return NETDEV_TX_OK; } EXPORT_SYMBOL_GPL(dsa_enqueue_skb); static netdev_tx_t dsa_user_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_user_priv *p = netdev_priv(dev); struct sk_buff *nskb; dev_sw_netstats_tx_add(dev, 1, skb->len); memset(skb->cb, 0, sizeof(skb->cb)); /* Handle tx timestamp if any */ dsa_skb_tx_timestamp(p, skb); if (skb_ensure_writable_head_tail(skb, dev)) { dev_kfree_skb_any(skb); return NETDEV_TX_OK; } /* needed_tailroom should still be 'warm' in the cache line from * skb_ensure_writable_head_tail(), which has also ensured that * padding is safe. */ if (dev->needed_tailroom) eth_skb_pad(skb); /* Transmit function may have to reallocate the original SKB, * in which case it must have freed it. Only free it here on error. */ nskb = p->xmit(skb, dev); if (!nskb) { kfree_skb(skb); return NETDEV_TX_OK; } return dsa_enqueue_skb(nskb, dev); } /* ethtool operations *******************************************************/ static void dsa_user_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->driver, "dsa", sizeof(drvinfo->driver)); strscpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version)); strscpy(drvinfo->bus_info, "platform", sizeof(drvinfo->bus_info)); } static int dsa_user_get_regs_len(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_regs_len) return ds->ops->get_regs_len(ds, dp->index); return -EOPNOTSUPP; } static void dsa_user_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *_p) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_regs) ds->ops->get_regs(ds, dp->index, regs, _p); } static int dsa_user_nway_reset(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_nway_reset(dp->pl); } static int dsa_user_get_eeprom_len(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->cd && ds->cd->eeprom_len) return ds->cd->eeprom_len; if (ds->ops->get_eeprom_len) return ds->ops->get_eeprom_len(ds); return 0; } static int dsa_user_get_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, u8 *data) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eeprom) return ds->ops->get_eeprom(ds, eeprom, data); return -EOPNOTSUPP; } static int dsa_user_set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, u8 *data) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->set_eeprom) return ds->ops->set_eeprom(ds, eeprom, data); return -EOPNOTSUPP; } static void dsa_user_get_strings(struct net_device *dev, uint32_t stringset, uint8_t *data) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (stringset == ETH_SS_STATS) { ethtool_puts(&data, "tx_packets"); ethtool_puts(&data, "tx_bytes"); ethtool_puts(&data, "rx_packets"); ethtool_puts(&data, "rx_bytes"); if (ds->ops->get_strings) ds->ops->get_strings(ds, dp->index, stringset, data); } else if (stringset == ETH_SS_TEST) { net_selftest_get_strings(data); } } static void dsa_user_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, uint64_t *data) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct pcpu_sw_netstats *s; unsigned int start; int i; for_each_possible_cpu(i) { u64 tx_packets, tx_bytes, rx_packets, rx_bytes; s = per_cpu_ptr(dev->tstats, i); do { start = u64_stats_fetch_begin(&s->syncp); tx_packets = u64_stats_read(&s->tx_packets); tx_bytes = u64_stats_read(&s->tx_bytes); rx_packets = u64_stats_read(&s->rx_packets); rx_bytes = u64_stats_read(&s->rx_bytes); } while (u64_stats_fetch_retry(&s->syncp, start)); data[0] += tx_packets; data[1] += tx_bytes; data[2] += rx_packets; data[3] += rx_bytes; } if (ds->ops->get_ethtool_stats) ds->ops->get_ethtool_stats(ds, dp->index, data + 4); } static int dsa_user_get_sset_count(struct net_device *dev, int sset) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (sset == ETH_SS_STATS) { int count = 0; if (ds->ops->get_sset_count) { count = ds->ops->get_sset_count(ds, dp->index, sset); if (count < 0) return count; } return count + 4; } else if (sset == ETH_SS_TEST) { return net_selftest_get_count(); } return -EOPNOTSUPP; } static void dsa_user_get_eth_phy_stats(struct net_device *dev, struct ethtool_eth_phy_stats *phy_stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eth_phy_stats) ds->ops->get_eth_phy_stats(ds, dp->index, phy_stats); } static void dsa_user_get_eth_mac_stats(struct net_device *dev, struct ethtool_eth_mac_stats *mac_stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eth_mac_stats) ds->ops->get_eth_mac_stats(ds, dp->index, mac_stats); } static void dsa_user_get_eth_ctrl_stats(struct net_device *dev, struct ethtool_eth_ctrl_stats *ctrl_stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eth_ctrl_stats) ds->ops->get_eth_ctrl_stats(ds, dp->index, ctrl_stats); } static void dsa_user_get_rmon_stats(struct net_device *dev, struct ethtool_rmon_stats *rmon_stats, const struct ethtool_rmon_hist_range **ranges) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_rmon_stats) ds->ops->get_rmon_stats(ds, dp->index, rmon_stats, ranges); } static void dsa_user_net_selftest(struct net_device *ndev, struct ethtool_test *etest, u64 *buf) { struct dsa_port *dp = dsa_user_to_port(ndev); struct dsa_switch *ds = dp->ds; if (ds->ops->self_test) { ds->ops->self_test(ds, dp->index, etest, buf); return; } net_selftest(ndev, etest, buf); } static int dsa_user_get_mm(struct net_device *dev, struct ethtool_mm_state *state) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->get_mm) return -EOPNOTSUPP; return ds->ops->get_mm(ds, dp->index, state); } static int dsa_user_set_mm(struct net_device *dev, struct ethtool_mm_cfg *cfg, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->set_mm) return -EOPNOTSUPP; return ds->ops->set_mm(ds, dp->index, cfg, extack); } static void dsa_user_get_mm_stats(struct net_device *dev, struct ethtool_mm_stats *stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_mm_stats) ds->ops->get_mm_stats(ds, dp->index, stats); } static void dsa_user_get_wol(struct net_device *dev, struct ethtool_wolinfo *w) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; phylink_ethtool_get_wol(dp->pl, w); if (ds->ops->get_wol) ds->ops->get_wol(ds, dp->index, w); } static int dsa_user_set_wol(struct net_device *dev, struct ethtool_wolinfo *w) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int ret = -EOPNOTSUPP; phylink_ethtool_set_wol(dp->pl, w); if (ds->ops->set_wol) ret = ds->ops->set_wol(ds, dp->index, w); return ret; } static int dsa_user_set_eee(struct net_device *dev, struct ethtool_keee *e) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int ret; /* Port's PHY and MAC both need to be EEE capable */ if (!dev->phydev || !dp->pl) return -ENODEV; if (!ds->ops->set_mac_eee) return -EOPNOTSUPP; ret = ds->ops->set_mac_eee(ds, dp->index, e); if (ret) return ret; return phylink_ethtool_set_eee(dp->pl, e); } static int dsa_user_get_eee(struct net_device *dev, struct ethtool_keee *e) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int ret; /* Port's PHY and MAC both need to be EEE capable */ if (!dev->phydev || !dp->pl) return -ENODEV; if (!ds->ops->get_mac_eee) return -EOPNOTSUPP; ret = ds->ops->get_mac_eee(ds, dp->index, e); if (ret) return ret; return phylink_ethtool_get_eee(dp->pl, e); } static int dsa_user_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_ksettings_get(dp->pl, cmd); } static int dsa_user_set_link_ksettings(struct net_device *dev, const struct ethtool_link_ksettings *cmd) { struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_ksettings_set(dp->pl, cmd); } static void dsa_user_get_pause_stats(struct net_device *dev, struct ethtool_pause_stats *pause_stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_pause_stats) ds->ops->get_pause_stats(ds, dp->index, pause_stats); } static void dsa_user_get_pauseparam(struct net_device *dev, struct ethtool_pauseparam *pause) { struct dsa_port *dp = dsa_user_to_port(dev); phylink_ethtool_get_pauseparam(dp->pl, pause); } static int dsa_user_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam *pause) { struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_set_pauseparam(dp->pl, pause); } #ifdef CONFIG_NET_POLL_CONTROLLER static int dsa_user_netpoll_setup(struct net_device *dev) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_user_priv *p = netdev_priv(dev); struct netpoll *netpoll; int err = 0; netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL); if (!netpoll) return -ENOMEM; err = __netpoll_setup(netpoll, conduit); if (err) { kfree(netpoll); goto out; } p->netpoll = netpoll; out: return err; } static void dsa_user_netpoll_cleanup(struct net_device *dev) { struct dsa_user_priv *p = netdev_priv(dev); struct netpoll *netpoll = p->netpoll; if (!netpoll) return; p->netpoll = NULL; __netpoll_free(netpoll); } static void dsa_user_poll_controller(struct net_device *dev) { } #endif static struct dsa_mall_tc_entry * dsa_user_mall_tc_entry_find(struct net_device *dev, unsigned long cookie) { struct dsa_user_priv *p = netdev_priv(dev); struct dsa_mall_tc_entry *mall_tc_entry; list_for_each_entry(mall_tc_entry, &p->mall_tc_list, list) if (mall_tc_entry->cookie == cookie) return mall_tc_entry; return NULL; } static int dsa_user_add_cls_matchall_mirred(struct net_device *dev, struct tc_cls_matchall_offload *cls, bool ingress, bool ingress_target) { struct netlink_ext_ack *extack = cls->common.extack; struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_user_priv *p = netdev_priv(dev); struct dsa_mall_mirror_tc_entry *mirror; struct dsa_mall_tc_entry *mall_tc_entry; struct dsa_switch *ds = dp->ds; struct flow_action_entry *act; struct dsa_port *to_dp; int err; if (cls->common.protocol != htons(ETH_P_ALL)) { NL_SET_ERR_MSG_MOD(extack, "Can only offload \"protocol all\" matchall filter"); return -EOPNOTSUPP; } if (!ds->ops->port_mirror_add) { NL_SET_ERR_MSG_MOD(extack, "Switch does not support mirroring operation"); return -EOPNOTSUPP; } if (!flow_action_basic_hw_stats_check(&cls->rule->action, extack)) return -EOPNOTSUPP; act = &cls->rule->action.entries[0]; if (!act->dev) return -EINVAL; if (dsa_user_dev_check(act->dev)) { if (ingress_target) { /* We can only fulfill this using software assist */ if (cls->common.skip_sw) { NL_SET_ERR_MSG_MOD(extack, "Can only mirred to ingress of DSA user port if filter also runs in software"); return -EOPNOTSUPP; } to_dp = dp->cpu_dp; } else { to_dp = dsa_user_to_port(act->dev); } } else { /* Handle mirroring to foreign target ports as a mirror towards * the CPU. The software tc rule will take the packets from * there. */ if (cls->common.skip_sw) { NL_SET_ERR_MSG_MOD(extack, "Can only mirred to CPU if filter also runs in software"); return -EOPNOTSUPP; } to_dp = dp->cpu_dp; } if (dp->ds != to_dp->ds) { NL_SET_ERR_MSG_MOD(extack, "Cross-chip mirroring not implemented"); return -EOPNOTSUPP; } mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL); if (!mall_tc_entry) return -ENOMEM; mall_tc_entry->cookie = cls->cookie; mall_tc_entry->type = DSA_PORT_MALL_MIRROR; mirror = &mall_tc_entry->mirror; mirror->to_local_port = to_dp->index; mirror->ingress = ingress; err = ds->ops->port_mirror_add(ds, dp->index, mirror, ingress, extack); if (err) { kfree(mall_tc_entry); return err; } list_add_tail(&mall_tc_entry->list, &p->mall_tc_list); return err; } static int dsa_user_add_cls_matchall_police(struct net_device *dev, struct tc_cls_matchall_offload *cls, bool ingress) { struct netlink_ext_ack *extack = cls->common.extack; struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_user_priv *p = netdev_priv(dev); struct dsa_mall_policer_tc_entry *policer; struct dsa_mall_tc_entry *mall_tc_entry; struct dsa_switch *ds = dp->ds; struct flow_action_entry *act; int err; if (!ds->ops->port_policer_add) { NL_SET_ERR_MSG_MOD(extack, "Policing offload not implemented"); return -EOPNOTSUPP; } if (!ingress) { NL_SET_ERR_MSG_MOD(extack, "Only supported on ingress qdisc"); return -EOPNOTSUPP; } if (!flow_action_basic_hw_stats_check(&cls->rule->action, extack)) return -EOPNOTSUPP; list_for_each_entry(mall_tc_entry, &p->mall_tc_list, list) { if (mall_tc_entry->type == DSA_PORT_MALL_POLICER) { NL_SET_ERR_MSG_MOD(extack, "Only one port policer allowed"); return -EEXIST; } } act = &cls->rule->action.entries[0]; mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL); if (!mall_tc_entry) return -ENOMEM; mall_tc_entry->cookie = cls->cookie; mall_tc_entry->type = DSA_PORT_MALL_POLICER; policer = &mall_tc_entry->policer; policer->rate_bytes_per_sec = act->police.rate_bytes_ps; policer->burst = act->police.burst; err = ds->ops->port_policer_add(ds, dp->index, policer); if (err) { kfree(mall_tc_entry); return err; } list_add_tail(&mall_tc_entry->list, &p->mall_tc_list); return err; } static int dsa_user_add_cls_matchall(struct net_device *dev, struct tc_cls_matchall_offload *cls, bool ingress) { const struct flow_action *action = &cls->rule->action; struct netlink_ext_ack *extack = cls->common.extack; if (!flow_offload_has_one_action(action)) { NL_SET_ERR_MSG_MOD(extack, "Cannot offload matchall filter with more than one action"); return -EOPNOTSUPP; } switch (action->entries[0].id) { case FLOW_ACTION_MIRRED: return dsa_user_add_cls_matchall_mirred(dev, cls, ingress, false); case FLOW_ACTION_MIRRED_INGRESS: return dsa_user_add_cls_matchall_mirred(dev, cls, ingress, true); case FLOW_ACTION_POLICE: return dsa_user_add_cls_matchall_police(dev, cls, ingress); default: NL_SET_ERR_MSG_MOD(extack, "Unknown action"); break; } return -EOPNOTSUPP; } static void dsa_user_del_cls_matchall(struct net_device *dev, struct tc_cls_matchall_offload *cls) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_mall_tc_entry *mall_tc_entry; struct dsa_switch *ds = dp->ds; mall_tc_entry = dsa_user_mall_tc_entry_find(dev, cls->cookie); if (!mall_tc_entry) return; list_del(&mall_tc_entry->list); switch (mall_tc_entry->type) { case DSA_PORT_MALL_MIRROR: if (ds->ops->port_mirror_del) ds->ops->port_mirror_del(ds, dp->index, &mall_tc_entry->mirror); break; case DSA_PORT_MALL_POLICER: if (ds->ops->port_policer_del) ds->ops->port_policer_del(ds, dp->index); break; default: WARN_ON(1); } kfree(mall_tc_entry); } static int dsa_user_setup_tc_cls_matchall(struct net_device *dev, struct tc_cls_matchall_offload *cls, bool ingress) { if (cls->common.chain_index) return -EOPNOTSUPP; switch (cls->command) { case TC_CLSMATCHALL_REPLACE: return dsa_user_add_cls_matchall(dev, cls, ingress); case TC_CLSMATCHALL_DESTROY: dsa_user_del_cls_matchall(dev, cls); return 0; default: return -EOPNOTSUPP; } } static int dsa_user_add_cls_flower(struct net_device *dev, struct flow_cls_offload *cls, bool ingress) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; if (!ds->ops->cls_flower_add) return -EOPNOTSUPP; return ds->ops->cls_flower_add(ds, port, cls, ingress); } static int dsa_user_del_cls_flower(struct net_device *dev, struct flow_cls_offload *cls, bool ingress) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; if (!ds->ops->cls_flower_del) return -EOPNOTSUPP; return ds->ops->cls_flower_del(ds, port, cls, ingress); } static int dsa_user_stats_cls_flower(struct net_device *dev, struct flow_cls_offload *cls, bool ingress) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; if (!ds->ops->cls_flower_stats) return -EOPNOTSUPP; return ds->ops->cls_flower_stats(ds, port, cls, ingress); } static int dsa_user_setup_tc_cls_flower(struct net_device *dev, struct flow_cls_offload *cls, bool ingress) { switch (cls->command) { case FLOW_CLS_REPLACE: return dsa_user_add_cls_flower(dev, cls, ingress); case FLOW_CLS_DESTROY: return dsa_user_del_cls_flower(dev, cls, ingress); case FLOW_CLS_STATS: return dsa_user_stats_cls_flower(dev, cls, ingress); default: return -EOPNOTSUPP; } } static int dsa_user_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv, bool ingress) { struct net_device *dev = cb_priv; if (!tc_can_offload(dev)) return -EOPNOTSUPP; switch (type) { case TC_SETUP_CLSMATCHALL: return dsa_user_setup_tc_cls_matchall(dev, type_data, ingress); case TC_SETUP_CLSFLOWER: return dsa_user_setup_tc_cls_flower(dev, type_data, ingress); default: return -EOPNOTSUPP; } } static int dsa_user_setup_tc_block_cb_ig(enum tc_setup_type type, void *type_data, void *cb_priv) { return dsa_user_setup_tc_block_cb(type, type_data, cb_priv, true); } static int dsa_user_setup_tc_block_cb_eg(enum tc_setup_type type, void *type_data, void *cb_priv) { return dsa_user_setup_tc_block_cb(type, type_data, cb_priv, false); } static LIST_HEAD(dsa_user_block_cb_list); static int dsa_user_setup_tc_block(struct net_device *dev, struct flow_block_offload *f) { struct flow_block_cb *block_cb; flow_setup_cb_t *cb; if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) cb = dsa_user_setup_tc_block_cb_ig; else if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS) cb = dsa_user_setup_tc_block_cb_eg; else return -EOPNOTSUPP; f->driver_block_list = &dsa_user_block_cb_list; switch (f->command) { case FLOW_BLOCK_BIND: if (flow_block_cb_is_busy(cb, dev, &dsa_user_block_cb_list)) return -EBUSY; block_cb = flow_block_cb_alloc(cb, dev, dev, NULL); if (IS_ERR(block_cb)) return PTR_ERR(block_cb); flow_block_cb_add(block_cb, f); list_add_tail(&block_cb->driver_list, &dsa_user_block_cb_list); return 0; case FLOW_BLOCK_UNBIND: block_cb = flow_block_cb_lookup(f->block, cb, dev); if (!block_cb) return -ENOENT; flow_block_cb_remove(block_cb, f); list_del(&block_cb->driver_list); return 0; default: return -EOPNOTSUPP; } } static int dsa_user_setup_ft_block(struct dsa_switch *ds, int port, void *type_data) { struct net_device *conduit = dsa_port_to_conduit(dsa_to_port(ds, port)); if (!conduit->netdev_ops->ndo_setup_tc) return -EOPNOTSUPP; return conduit->netdev_ops->ndo_setup_tc(conduit, TC_SETUP_FT, type_data); } static int dsa_user_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; switch (type) { case TC_SETUP_BLOCK: return dsa_user_setup_tc_block(dev, type_data); case TC_SETUP_FT: return dsa_user_setup_ft_block(ds, dp->index, type_data); default: break; } if (!ds->ops->port_setup_tc) return -EOPNOTSUPP; return ds->ops->port_setup_tc(ds, dp->index, type, type_data); } static int dsa_user_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *nfc, u32 *rule_locs) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->get_rxnfc) return -EOPNOTSUPP; return ds->ops->get_rxnfc(ds, dp->index, nfc, rule_locs); } static int dsa_user_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *nfc) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->set_rxnfc) return -EOPNOTSUPP; return ds->ops->set_rxnfc(ds, dp->index, nfc); } static int dsa_user_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *ts) { struct dsa_user_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->dp->ds; if (!ds->ops->get_ts_info) return -EOPNOTSUPP; return ds->ops->get_ts_info(ds, p->dp->index, ts); } static int dsa_user_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan vlan = { .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, .vid = vid, /* This API only allows programming tagged, non-PVID VIDs */ .flags = 0, }; struct netlink_ext_ack extack = {0}; struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; struct dsa_vlan *v; int ret; /* User port... */ ret = dsa_port_vlan_add(dp, &vlan, &extack); if (ret) { if (extack._msg) netdev_err(dev, "%s\n", extack._msg); return ret; } /* And CPU port... */ ret = dsa_port_host_vlan_add(dp, &vlan, &extack); if (ret) { if (extack._msg) netdev_err(dev, "CPU port %d: %s\n", dp->cpu_dp->index, extack._msg); return ret; } if (!dsa_switch_supports_uc_filtering(ds) && !dsa_switch_supports_mc_filtering(ds)) return 0; v = kzalloc(sizeof(*v), GFP_KERNEL); if (!v) { ret = -ENOMEM; goto rollback; } netif_addr_lock_bh(dev); v->vid = vid; list_add_tail(&v->list, &dp->user_vlans); if (dsa_switch_supports_mc_filtering(ds)) { netdev_for_each_synced_mc_addr(ha, dev) { dsa_user_schedule_standalone_work(dev, DSA_MC_ADD, ha->addr, vid); } } if (dsa_switch_supports_uc_filtering(ds)) { netdev_for_each_synced_uc_addr(ha, dev) { dsa_user_schedule_standalone_work(dev, DSA_UC_ADD, ha->addr, vid); } } netif_addr_unlock_bh(dev); dsa_flush_workqueue(); return 0; rollback: dsa_port_host_vlan_del(dp, &vlan); dsa_port_vlan_del(dp, &vlan); return ret; } static int dsa_user_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan vlan = { .vid = vid, /* This API only allows programming tagged, non-PVID VIDs */ .flags = 0, }; struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; struct dsa_vlan *v; int err; err = dsa_port_vlan_del(dp, &vlan); if (err) return err; err = dsa_port_host_vlan_del(dp, &vlan); if (err) return err; if (!dsa_switch_supports_uc_filtering(ds) && !dsa_switch_supports_mc_filtering(ds)) return 0; netif_addr_lock_bh(dev); v = dsa_vlan_find(&dp->user_vlans, &vlan); if (!v) { netif_addr_unlock_bh(dev); return -ENOENT; } list_del(&v->list); kfree(v); if (dsa_switch_supports_mc_filtering(ds)) { netdev_for_each_synced_mc_addr(ha, dev) { dsa_user_schedule_standalone_work(dev, DSA_MC_DEL, ha->addr, vid); } } if (dsa_switch_supports_uc_filtering(ds)) { netdev_for_each_synced_uc_addr(ha, dev) { dsa_user_schedule_standalone_work(dev, DSA_UC_DEL, ha->addr, vid); } } netif_addr_unlock_bh(dev); dsa_flush_workqueue(); return 0; } static int dsa_user_restore_vlan(struct net_device *vdev, int vid, void *arg) { __be16 proto = vdev ? vlan_dev_vlan_proto(vdev) : htons(ETH_P_8021Q); return dsa_user_vlan_rx_add_vid(arg, proto, vid); } static int dsa_user_clear_vlan(struct net_device *vdev, int vid, void *arg) { __be16 proto = vdev ? vlan_dev_vlan_proto(vdev) : htons(ETH_P_8021Q); return dsa_user_vlan_rx_kill_vid(arg, proto, vid); } /* Keep the VLAN RX filtering list in sync with the hardware only if VLAN * filtering is enabled. The baseline is that only ports that offload a * VLAN-aware bridge are VLAN-aware, and standalone ports are VLAN-unaware, * but there are exceptions for quirky hardware. * * If ds->vlan_filtering_is_global = true, then standalone ports which share * the same switch with other ports that offload a VLAN-aware bridge are also * inevitably VLAN-aware. * * To summarize, a DSA switch port offloads: * * - If standalone (this includes software bridge, software LAG): * - if ds->needs_standalone_vlan_filtering = true, OR if * (ds->vlan_filtering_is_global = true AND there are bridges spanning * this switch chip which have vlan_filtering=1) * - the 8021q upper VLANs * - else (standalone VLAN filtering is not needed, VLAN filtering is not * global, or it is, but no port is under a VLAN-aware bridge): * - no VLAN (any 8021q upper is a software VLAN) * * - If under a vlan_filtering=0 bridge which it offload: * - if ds->configure_vlan_while_not_filtering = true (default): * - the bridge VLANs. These VLANs are committed to hardware but inactive. * - else (deprecated): * - no VLAN. The bridge VLANs are not restored when VLAN awareness is * enabled, so this behavior is broken and discouraged. * * - If under a vlan_filtering=1 bridge which it offload: * - the bridge VLANs * - the 8021q upper VLANs */ int dsa_user_manage_vlan_filtering(struct net_device *user, bool vlan_filtering) { int err; if (vlan_filtering) { user->features |= NETIF_F_HW_VLAN_CTAG_FILTER; err = vlan_for_each(user, dsa_user_restore_vlan, user); if (err) { vlan_for_each(user, dsa_user_clear_vlan, user); user->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; return err; } } else { err = vlan_for_each(user, dsa_user_clear_vlan, user); if (err) return err; user->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; } return 0; } struct dsa_hw_port { struct list_head list; struct net_device *dev; int old_mtu; }; static int dsa_hw_port_list_set_mtu(struct list_head *hw_port_list, int mtu) { const struct dsa_hw_port *p; int err; list_for_each_entry(p, hw_port_list, list) { if (p->dev->mtu == mtu) continue; err = dev_set_mtu(p->dev, mtu); if (err) goto rollback; } return 0; rollback: list_for_each_entry_continue_reverse(p, hw_port_list, list) { if (p->dev->mtu == p->old_mtu) continue; if (dev_set_mtu(p->dev, p->old_mtu)) netdev_err(p->dev, "Failed to restore MTU\n"); } return err; } static void dsa_hw_port_list_free(struct list_head *hw_port_list) { struct dsa_hw_port *p, *n; list_for_each_entry_safe(p, n, hw_port_list, list) kfree(p); } /* Make the hardware datapath to/from @dev limited to a common MTU */ static void dsa_bridge_mtu_normalization(struct dsa_port *dp) { struct list_head hw_port_list; struct dsa_switch_tree *dst; int min_mtu = ETH_MAX_MTU; struct dsa_port *other_dp; int err; if (!dp->ds->mtu_enforcement_ingress) return; if (!dp->bridge) return; INIT_LIST_HEAD(&hw_port_list); /* Populate the list of ports that are part of the same bridge * as the newly added/modified port */ list_for_each_entry(dst, &dsa_tree_list, list) { list_for_each_entry(other_dp, &dst->ports, list) { struct dsa_hw_port *hw_port; struct net_device *user; if (other_dp->type != DSA_PORT_TYPE_USER) continue; if (!dsa_port_bridge_same(dp, other_dp)) continue; if (!other_dp->ds->mtu_enforcement_ingress) continue; user = other_dp->user; if (min_mtu > user->mtu) min_mtu = user->mtu; hw_port = kzalloc(sizeof(*hw_port), GFP_KERNEL); if (!hw_port) goto out; hw_port->dev = user; hw_port->old_mtu = user->mtu; list_add(&hw_port->list, &hw_port_list); } } /* Attempt to configure the entire hardware bridge to the newly added * interface's MTU first, regardless of whether the intention of the * user was to raise or lower it. */ err = dsa_hw_port_list_set_mtu(&hw_port_list, dp->user->mtu); if (!err) goto out; /* Clearly that didn't work out so well, so just set the minimum MTU on * all hardware bridge ports now. If this fails too, then all ports will * still have their old MTU rolled back anyway. */ dsa_hw_port_list_set_mtu(&hw_port_list, min_mtu); out: dsa_hw_port_list_free(&hw_port_list); } int dsa_user_change_mtu(struct net_device *dev, int new_mtu) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_port *cpu_dp = dp->cpu_dp; struct dsa_switch *ds = dp->ds; struct dsa_port *other_dp; int largest_mtu = 0; int new_conduit_mtu; int old_conduit_mtu; int mtu_limit; int overhead; int cpu_mtu; int err; if (!ds->ops->port_change_mtu) return -EOPNOTSUPP; dsa_tree_for_each_user_port(other_dp, ds->dst) { int user_mtu; /* During probe, this function will be called for each user * device, while not all of them have been allocated. That's * ok, it doesn't change what the maximum is, so ignore it. */ if (!other_dp->user) continue; /* Pretend that we already applied the setting, which we * actually haven't (still haven't done all integrity checks) */ if (dp == other_dp) user_mtu = new_mtu; else user_mtu = other_dp->user->mtu; if (largest_mtu < user_mtu) largest_mtu = user_mtu; } overhead = dsa_tag_protocol_overhead(cpu_dp->tag_ops); mtu_limit = min_t(int, conduit->max_mtu, dev->max_mtu + overhead); old_conduit_mtu = conduit->mtu; new_conduit_mtu = largest_mtu + overhead; if (new_conduit_mtu > mtu_limit) return -ERANGE; /* If the conduit MTU isn't over limit, there's no need to check the CPU * MTU, since that surely isn't either. */ cpu_mtu = largest_mtu; /* Start applying stuff */ if (new_conduit_mtu != old_conduit_mtu) { err = dev_set_mtu(conduit, new_conduit_mtu); if (err < 0) goto out_conduit_failed; /* We only need to propagate the MTU of the CPU port to * upstream switches, so emit a notifier which updates them. */ err = dsa_port_mtu_change(cpu_dp, cpu_mtu); if (err) goto out_cpu_failed; } err = ds->ops->port_change_mtu(ds, dp->index, new_mtu); if (err) goto out_port_failed; WRITE_ONCE(dev->mtu, new_mtu); dsa_bridge_mtu_normalization(dp); return 0; out_port_failed: if (new_conduit_mtu != old_conduit_mtu) dsa_port_mtu_change(cpu_dp, old_conduit_mtu - overhead); out_cpu_failed: if (new_conduit_mtu != old_conduit_mtu) dev_set_mtu(conduit, old_conduit_mtu); out_conduit_failed: return err; } static int __maybe_unused dsa_user_dcbnl_set_apptrust(struct net_device *dev, u8 *sel, int nsel) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; if (!ds->ops->port_set_apptrust) return -EOPNOTSUPP; return ds->ops->port_set_apptrust(ds, port, sel, nsel); } static int __maybe_unused dsa_user_dcbnl_get_apptrust(struct net_device *dev, u8 *sel, int *nsel) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; if (!ds->ops->port_get_apptrust) return -EOPNOTSUPP; return ds->ops->port_get_apptrust(ds, port, sel, nsel); } static int __maybe_unused dsa_user_dcbnl_set_default_prio(struct net_device *dev, struct dcb_app *app) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; unsigned long mask, new_prio; int err, port = dp->index; if (!ds->ops->port_set_default_prio) return -EOPNOTSUPP; err = dcb_ieee_setapp(dev, app); if (err) return err; mask = dcb_ieee_getapp_mask(dev, app); new_prio = __fls(mask); err = ds->ops->port_set_default_prio(ds, port, new_prio); if (err) { dcb_ieee_delapp(dev, app); return err; } return 0; } /* Update the DSCP prio entries on all user ports of the switch in case * the switch supports global DSCP prio instead of per port DSCP prios. */ static int dsa_user_dcbnl_ieee_global_dscp_setdel(struct net_device *dev, struct dcb_app *app, bool del) { int (*setdel)(struct net_device *dev, struct dcb_app *app); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct dsa_port *other_dp; int err, restore_err; if (del) setdel = dcb_ieee_delapp; else setdel = dcb_ieee_setapp; dsa_switch_for_each_user_port(other_dp, ds) { struct net_device *user = other_dp->user; if (!user || user == dev) continue; err = setdel(user, app); if (err) goto err_try_to_restore; } return 0; err_try_to_restore: /* Revert logic to restore previous state of app entries */ if (!del) setdel = dcb_ieee_delapp; else setdel = dcb_ieee_setapp; dsa_switch_for_each_user_port_continue_reverse(other_dp, ds) { struct net_device *user = other_dp->user; if (!user || user == dev) continue; restore_err = setdel(user, app); if (restore_err) netdev_err(user, "Failed to restore DSCP prio entry configuration\n"); } return err; } static int __maybe_unused dsa_user_dcbnl_add_dscp_prio(struct net_device *dev, struct dcb_app *app) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; unsigned long mask, new_prio; int err, port = dp->index; u8 dscp = app->protocol; if (!ds->ops->port_add_dscp_prio) return -EOPNOTSUPP; if (dscp >= 64) { netdev_err(dev, "DSCP APP entry with protocol value %u is invalid\n", dscp); return -EINVAL; } err = dcb_ieee_setapp(dev, app); if (err) return err; mask = dcb_ieee_getapp_mask(dev, app); new_prio = __fls(mask); err = ds->ops->port_add_dscp_prio(ds, port, dscp, new_prio); if (err) { dcb_ieee_delapp(dev, app); return err; } if (!ds->dscp_prio_mapping_is_global) return 0; err = dsa_user_dcbnl_ieee_global_dscp_setdel(dev, app, false); if (err) { if (ds->ops->port_del_dscp_prio) ds->ops->port_del_dscp_prio(ds, port, dscp, new_prio); dcb_ieee_delapp(dev, app); return err; } return 0; } static int __maybe_unused dsa_user_dcbnl_ieee_setapp(struct net_device *dev, struct dcb_app *app) { switch (app->selector) { case IEEE_8021QAZ_APP_SEL_ETHERTYPE: switch (app->protocol) { case 0: return dsa_user_dcbnl_set_default_prio(dev, app); default: return -EOPNOTSUPP; } break; case IEEE_8021QAZ_APP_SEL_DSCP: return dsa_user_dcbnl_add_dscp_prio(dev, app); default: return -EOPNOTSUPP; } } static int __maybe_unused dsa_user_dcbnl_del_default_prio(struct net_device *dev, struct dcb_app *app) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; unsigned long mask, new_prio; int err, port = dp->index; if (!ds->ops->port_set_default_prio) return -EOPNOTSUPP; err = dcb_ieee_delapp(dev, app); if (err) return err; mask = dcb_ieee_getapp_mask(dev, app); new_prio = mask ? __fls(mask) : 0; err = ds->ops->port_set_default_prio(ds, port, new_prio); if (err) { dcb_ieee_setapp(dev, app); return err; } return 0; } static int __maybe_unused dsa_user_dcbnl_del_dscp_prio(struct net_device *dev, struct dcb_app *app) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int err, port = dp->index; u8 dscp = app->protocol; if (!ds->ops->port_del_dscp_prio) return -EOPNOTSUPP; err = dcb_ieee_delapp(dev, app); if (err) return err; err = ds->ops->port_del_dscp_prio(ds, port, dscp, app->priority); if (err) { dcb_ieee_setapp(dev, app); return err; } if (!ds->dscp_prio_mapping_is_global) return 0; err = dsa_user_dcbnl_ieee_global_dscp_setdel(dev, app, true); if (err) { if (ds->ops->port_add_dscp_prio) ds->ops->port_add_dscp_prio(ds, port, dscp, app->priority); dcb_ieee_setapp(dev, app); return err; } return 0; } static int __maybe_unused dsa_user_dcbnl_ieee_delapp(struct net_device *dev, struct dcb_app *app) { switch (app->selector) { case IEEE_8021QAZ_APP_SEL_ETHERTYPE: switch (app->protocol) { case 0: return dsa_user_dcbnl_del_default_prio(dev, app); default: return -EOPNOTSUPP; } break; case IEEE_8021QAZ_APP_SEL_DSCP: return dsa_user_dcbnl_del_dscp_prio(dev, app); default: return -EOPNOTSUPP; } } /* Pre-populate the DCB application priority table with the priorities * configured during switch setup, which we read from hardware here. */ static int dsa_user_dcbnl_init(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; int err; if (ds->ops->port_get_default_prio) { int prio = ds->ops->port_get_default_prio(ds, port); struct dcb_app app = { .selector = IEEE_8021QAZ_APP_SEL_ETHERTYPE, .protocol = 0, .priority = prio, }; if (prio < 0) return prio; err = dcb_ieee_setapp(dev, &app); if (err) return err; } if (ds->ops->port_get_dscp_prio) { int protocol; for (protocol = 0; protocol < 64; protocol++) { struct dcb_app app = { .selector = IEEE_8021QAZ_APP_SEL_DSCP, .protocol = protocol, }; int prio; prio = ds->ops->port_get_dscp_prio(ds, port, protocol); if (prio == -EOPNOTSUPP) continue; if (prio < 0) return prio; app.priority = prio; err = dcb_ieee_setapp(dev, &app); if (err) return err; } } return 0; } static const struct ethtool_ops dsa_user_ethtool_ops = { .get_drvinfo = dsa_user_get_drvinfo, .get_regs_len = dsa_user_get_regs_len, .get_regs = dsa_user_get_regs, .nway_reset = dsa_user_nway_reset, .get_link = ethtool_op_get_link, .get_eeprom_len = dsa_user_get_eeprom_len, .get_eeprom = dsa_user_get_eeprom, .set_eeprom = dsa_user_set_eeprom, .get_strings = dsa_user_get_strings, .get_ethtool_stats = dsa_user_get_ethtool_stats, .get_sset_count = dsa_user_get_sset_count, .get_eth_phy_stats = dsa_user_get_eth_phy_stats, .get_eth_mac_stats = dsa_user_get_eth_mac_stats, .get_eth_ctrl_stats = dsa_user_get_eth_ctrl_stats, .get_rmon_stats = dsa_user_get_rmon_stats, .set_wol = dsa_user_set_wol, .get_wol = dsa_user_get_wol, .set_eee = dsa_user_set_eee, .get_eee = dsa_user_get_eee, .get_link_ksettings = dsa_user_get_link_ksettings, .set_link_ksettings = dsa_user_set_link_ksettings, .get_pause_stats = dsa_user_get_pause_stats, .get_pauseparam = dsa_user_get_pauseparam, .set_pauseparam = dsa_user_set_pauseparam, .get_rxnfc = dsa_user_get_rxnfc, .set_rxnfc = dsa_user_set_rxnfc, .get_ts_info = dsa_user_get_ts_info, .self_test = dsa_user_net_selftest, .get_mm = dsa_user_get_mm, .set_mm = dsa_user_set_mm, .get_mm_stats = dsa_user_get_mm_stats, }; static const struct dcbnl_rtnl_ops __maybe_unused dsa_user_dcbnl_ops = { .ieee_setapp = dsa_user_dcbnl_ieee_setapp, .ieee_delapp = dsa_user_dcbnl_ieee_delapp, .dcbnl_setapptrust = dsa_user_dcbnl_set_apptrust, .dcbnl_getapptrust = dsa_user_dcbnl_get_apptrust, }; static void dsa_user_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *s) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_stats64) ds->ops->get_stats64(ds, dp->index, s); else dev_get_tstats64(dev, s); } static int dsa_user_fill_forward_path(struct net_device_path_ctx *ctx, struct net_device_path *path) { struct dsa_port *dp = dsa_user_to_port(ctx->dev); struct net_device *conduit = dsa_port_to_conduit(dp); struct dsa_port *cpu_dp = dp->cpu_dp; path->dev = ctx->dev; path->type = DEV_PATH_DSA; path->dsa.proto = cpu_dp->tag_ops->proto; path->dsa.port = dp->index; ctx->dev = conduit; return 0; } static const struct net_device_ops dsa_user_netdev_ops = { .ndo_open = dsa_user_open, .ndo_stop = dsa_user_close, .ndo_start_xmit = dsa_user_xmit, .ndo_change_rx_flags = dsa_user_change_rx_flags, .ndo_set_rx_mode = dsa_user_set_rx_mode, .ndo_set_mac_address = dsa_user_set_mac_address, .ndo_fdb_dump = dsa_user_fdb_dump, .ndo_eth_ioctl = dsa_user_ioctl, .ndo_get_iflink = dsa_user_get_iflink, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_netpoll_setup = dsa_user_netpoll_setup, .ndo_netpoll_cleanup = dsa_user_netpoll_cleanup, .ndo_poll_controller = dsa_user_poll_controller, #endif .ndo_setup_tc = dsa_user_setup_tc, .ndo_get_stats64 = dsa_user_get_stats64, .ndo_vlan_rx_add_vid = dsa_user_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = dsa_user_vlan_rx_kill_vid, .ndo_change_mtu = dsa_user_change_mtu, .ndo_fill_forward_path = dsa_user_fill_forward_path, }; static const struct device_type dsa_type = { .name = "dsa", }; void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up) { const struct dsa_port *dp = dsa_to_port(ds, port); if (dp->pl) phylink_mac_change(dp->pl, up); } EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_change); static void dsa_user_phylink_fixed_state(struct phylink_config *config, struct phylink_link_state *state) { struct dsa_port *dp = dsa_phylink_to_port(config); struct dsa_switch *ds = dp->ds; /* No need to check that this operation is valid, the callback would * not be called if it was not. */ ds->ops->phylink_fixed_state(ds, dp->index, state); } /* user device setup *******************************************************/ static int dsa_user_phy_connect(struct net_device *user_dev, int addr, u32 flags) { struct dsa_port *dp = dsa_user_to_port(user_dev); struct dsa_switch *ds = dp->ds; user_dev->phydev = mdiobus_get_phy(ds->user_mii_bus, addr); if (!user_dev->phydev) { netdev_err(user_dev, "no phy at %d\n", addr); return -ENODEV; } user_dev->phydev->dev_flags |= flags; return phylink_connect_phy(dp->pl, user_dev->phydev); } static int dsa_user_phy_setup(struct net_device *user_dev) { struct dsa_port *dp = dsa_user_to_port(user_dev); struct device_node *port_dn = dp->dn; struct dsa_switch *ds = dp->ds; u32 phy_flags = 0; int ret; dp->pl_config.dev = &user_dev->dev; dp->pl_config.type = PHYLINK_NETDEV; /* The get_fixed_state callback takes precedence over polling the * link GPIO in PHYLINK (see phylink_get_fixed_state). Only set * this if the switch provides such a callback. */ if (ds->ops->phylink_fixed_state) { dp->pl_config.get_fixed_state = dsa_user_phylink_fixed_state; dp->pl_config.poll_fixed_state = true; } ret = dsa_port_phylink_create(dp); if (ret) return ret; if (ds->ops->get_phy_flags) phy_flags = ds->ops->get_phy_flags(ds, dp->index); ret = phylink_of_phy_connect(dp->pl, port_dn, phy_flags); if (ret == -ENODEV && ds->user_mii_bus) { /* We could not connect to a designated PHY or SFP, so try to * use the switch internal MDIO bus instead */ ret = dsa_user_phy_connect(user_dev, dp->index, phy_flags); } if (ret) { netdev_err(user_dev, "failed to connect to PHY: %pe\n", ERR_PTR(ret)); dsa_port_phylink_destroy(dp); } return ret; } void dsa_user_setup_tagger(struct net_device *user) { struct dsa_port *dp = dsa_user_to_port(user); struct net_device *conduit = dsa_port_to_conduit(dp); struct dsa_user_priv *p = netdev_priv(user); const struct dsa_port *cpu_dp = dp->cpu_dp; const struct dsa_switch *ds = dp->ds; user->needed_headroom = cpu_dp->tag_ops->needed_headroom; user->needed_tailroom = cpu_dp->tag_ops->needed_tailroom; /* Try to save one extra realloc later in the TX path (in the conduit) * by also inheriting the conduit's needed headroom and tailroom. * The 8021q driver also does this. */ user->needed_headroom += conduit->needed_headroom; user->needed_tailroom += conduit->needed_tailroom; p->xmit = cpu_dp->tag_ops->xmit; user->features = conduit->vlan_features | NETIF_F_HW_TC; user->hw_features |= NETIF_F_HW_TC; if (user->needed_tailroom) user->features &= ~(NETIF_F_SG | NETIF_F_FRAGLIST); if (ds->needs_standalone_vlan_filtering) user->features |= NETIF_F_HW_VLAN_CTAG_FILTER; user->lltx = true; } int dsa_user_suspend(struct net_device *user_dev) { struct dsa_port *dp = dsa_user_to_port(user_dev); if (!netif_running(user_dev)) return 0; netif_device_detach(user_dev); rtnl_lock(); phylink_stop(dp->pl); rtnl_unlock(); return 0; } int dsa_user_resume(struct net_device *user_dev) { struct dsa_port *dp = dsa_user_to_port(user_dev); if (!netif_running(user_dev)) return 0; netif_device_attach(user_dev); rtnl_lock(); phylink_start(dp->pl); rtnl_unlock(); return 0; } int dsa_user_create(struct dsa_port *port) { struct net_device *conduit = dsa_port_to_conduit(port); struct dsa_switch *ds = port->ds; struct net_device *user_dev; struct dsa_user_priv *p; const char *name; int assign_type; int ret; if (!ds->num_tx_queues) ds->num_tx_queues = 1; if (port->name) { name = port->name; assign_type = NET_NAME_PREDICTABLE; } else { name = "eth%d"; assign_type = NET_NAME_ENUM; } user_dev = alloc_netdev_mqs(sizeof(struct dsa_user_priv), name, assign_type, ether_setup, ds->num_tx_queues, 1); if (user_dev == NULL) return -ENOMEM; user_dev->rtnl_link_ops = &dsa_link_ops; user_dev->ethtool_ops = &dsa_user_ethtool_ops; #if IS_ENABLED(CONFIG_DCB) user_dev->dcbnl_ops = &dsa_user_dcbnl_ops; #endif if (!is_zero_ether_addr(port->mac)) eth_hw_addr_set(user_dev, port->mac); else eth_hw_addr_inherit(user_dev, conduit); user_dev->priv_flags |= IFF_NO_QUEUE; if (dsa_switch_supports_uc_filtering(ds)) user_dev->priv_flags |= IFF_UNICAST_FLT; user_dev->netdev_ops = &dsa_user_netdev_ops; if (ds->ops->port_max_mtu) user_dev->max_mtu = ds->ops->port_max_mtu(ds, port->index); SET_NETDEV_DEVTYPE(user_dev, &dsa_type); SET_NETDEV_DEV(user_dev, port->ds->dev); SET_NETDEV_DEVLINK_PORT(user_dev, &port->devlink_port); user_dev->dev.of_node = port->dn; user_dev->vlan_features = conduit->vlan_features; p = netdev_priv(user_dev); user_dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; ret = gro_cells_init(&p->gcells, user_dev); if (ret) goto out_free; p->dp = port; INIT_LIST_HEAD(&p->mall_tc_list); port->user = user_dev; dsa_user_setup_tagger(user_dev); netif_carrier_off(user_dev); ret = dsa_user_phy_setup(user_dev); if (ret) { netdev_err(user_dev, "error %d setting up PHY for tree %d, switch %d, port %d\n", ret, ds->dst->index, ds->index, port->index); goto out_gcells; } rtnl_lock(); ret = dsa_user_change_mtu(user_dev, ETH_DATA_LEN); if (ret && ret != -EOPNOTSUPP) dev_warn(ds->dev, "nonfatal error %d setting MTU to %d on port %d\n", ret, ETH_DATA_LEN, port->index); ret = register_netdevice(user_dev); if (ret) { netdev_err(conduit, "error %d registering interface %s\n", ret, user_dev->name); rtnl_unlock(); goto out_phy; } if (IS_ENABLED(CONFIG_DCB)) { ret = dsa_user_dcbnl_init(user_dev); if (ret) { netdev_err(user_dev, "failed to initialize DCB: %pe\n", ERR_PTR(ret)); rtnl_unlock(); goto out_unregister; } } ret = netdev_upper_dev_link(conduit, user_dev, NULL); rtnl_unlock(); if (ret) goto out_unregister; return 0; out_unregister: unregister_netdev(user_dev); out_phy: rtnl_lock(); phylink_disconnect_phy(p->dp->pl); rtnl_unlock(); dsa_port_phylink_destroy(p->dp); out_gcells: gro_cells_destroy(&p->gcells); out_free: free_netdev(user_dev); port->user = NULL; return ret; } void dsa_user_destroy(struct net_device *user_dev) { struct net_device *conduit = dsa_user_to_conduit(user_dev); struct dsa_port *dp = dsa_user_to_port(user_dev); struct dsa_user_priv *p = netdev_priv(user_dev); netif_carrier_off(user_dev); rtnl_lock(); netdev_upper_dev_unlink(conduit, user_dev); unregister_netdevice(user_dev); phylink_disconnect_phy(dp->pl); rtnl_unlock(); dsa_port_phylink_destroy(dp); gro_cells_destroy(&p->gcells); free_netdev(user_dev); } int dsa_user_change_conduit(struct net_device *dev, struct net_device *conduit, struct netlink_ext_ack *extack) { struct net_device *old_conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct net_device *upper; struct list_head *iter; int err; if (conduit == old_conduit) return 0; if (!ds->ops->port_change_conduit) { NL_SET_ERR_MSG_MOD(extack, "Driver does not support changing DSA conduit"); return -EOPNOTSUPP; } if (!netdev_uses_dsa(conduit)) { NL_SET_ERR_MSG_MOD(extack, "Interface not eligible as DSA conduit"); return -EOPNOTSUPP; } netdev_for_each_upper_dev_rcu(conduit, upper, iter) { if (dsa_user_dev_check(upper)) continue; if (netif_is_bridge_master(upper)) continue; NL_SET_ERR_MSG_MOD(extack, "Cannot join conduit with unknown uppers"); return -EOPNOTSUPP; } /* Since we allow live-changing the DSA conduit, plus we auto-open the * DSA conduit when the user port opens => we need to ensure that the * new DSA conduit is open too. */ if (dev->flags & IFF_UP) { err = dev_open(conduit, extack); if (err) return err; } netdev_upper_dev_unlink(old_conduit, dev); err = netdev_upper_dev_link(conduit, dev, extack); if (err) goto out_revert_old_conduit_unlink; err = dsa_port_change_conduit(dp, conduit, extack); if (err) goto out_revert_conduit_link; /* Update the MTU of the new CPU port through cross-chip notifiers */ err = dsa_user_change_mtu(dev, dev->mtu); if (err && err != -EOPNOTSUPP) { netdev_warn(dev, "nonfatal error updating MTU with new conduit: %pe\n", ERR_PTR(err)); } return 0; out_revert_conduit_link: netdev_upper_dev_unlink(conduit, dev); out_revert_old_conduit_unlink: netdev_upper_dev_link(old_conduit, dev, NULL); return err; } bool dsa_user_dev_check(const struct net_device *dev) { return dev->netdev_ops == &dsa_user_netdev_ops; } EXPORT_SYMBOL_GPL(dsa_user_dev_check); static int dsa_user_changeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *extack; int err = NOTIFY_DONE; struct dsa_port *dp; if (!dsa_user_dev_check(dev)) return err; dp = dsa_user_to_port(dev); extack = netdev_notifier_info_to_extack(&info->info); if (netif_is_bridge_master(info->upper_dev)) { if (info->linking) { err = dsa_port_bridge_join(dp, info->upper_dev, extack); if (!err) dsa_bridge_mtu_normalization(dp); if (err == -EOPNOTSUPP) { NL_SET_ERR_MSG_WEAK_MOD(extack, "Offloading not supported"); err = 0; } err = notifier_from_errno(err); } else { dsa_port_bridge_leave(dp, info->upper_dev); err = NOTIFY_OK; } } else if (netif_is_lag_master(info->upper_dev)) { if (info->linking) { err = dsa_port_lag_join(dp, info->upper_dev, info->upper_info, extack); if (err == -EOPNOTSUPP) { NL_SET_ERR_MSG_WEAK_MOD(extack, "Offloading not supported"); err = 0; } err = notifier_from_errno(err); } else { dsa_port_lag_leave(dp, info->upper_dev); err = NOTIFY_OK; } } else if (is_hsr_master(info->upper_dev)) { if (info->linking) { err = dsa_port_hsr_join(dp, info->upper_dev, extack); if (err == -EOPNOTSUPP) { NL_SET_ERR_MSG_WEAK_MOD(extack, "Offloading not supported"); err = 0; } err = notifier_from_errno(err); } else { dsa_port_hsr_leave(dp, info->upper_dev); err = NOTIFY_OK; } } return err; } static int dsa_user_prechangeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct dsa_port *dp; if (!dsa_user_dev_check(dev)) return NOTIFY_DONE; dp = dsa_user_to_port(dev); if (netif_is_bridge_master(info->upper_dev) && !info->linking) dsa_port_pre_bridge_leave(dp, info->upper_dev); else if (netif_is_lag_master(info->upper_dev) && !info->linking) dsa_port_pre_lag_leave(dp, info->upper_dev); /* dsa_port_pre_hsr_leave is not yet necessary since hsr devices cannot * meaningfully placed under a bridge yet */ return NOTIFY_DONE; } static int dsa_user_lag_changeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct net_device *lower; struct list_head *iter; int err = NOTIFY_DONE; struct dsa_port *dp; if (!netif_is_lag_master(dev)) return err; netdev_for_each_lower_dev(dev, lower, iter) { if (!dsa_user_dev_check(lower)) continue; dp = dsa_user_to_port(lower); if (!dp->lag) /* Software LAG */ continue; err = dsa_user_changeupper(lower, info); if (notifier_to_errno(err)) break; } return err; } /* Same as dsa_user_lag_changeupper() except that it calls * dsa_user_prechangeupper() */ static int dsa_user_lag_prechangeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct net_device *lower; struct list_head *iter; int err = NOTIFY_DONE; struct dsa_port *dp; if (!netif_is_lag_master(dev)) return err; netdev_for_each_lower_dev(dev, lower, iter) { if (!dsa_user_dev_check(lower)) continue; dp = dsa_user_to_port(lower); if (!dp->lag) /* Software LAG */ continue; err = dsa_user_prechangeupper(lower, info); if (notifier_to_errno(err)) break; } return err; } static int dsa_prevent_bridging_8021q_upper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *ext_ack; struct net_device *user, *br; struct dsa_port *dp; ext_ack = netdev_notifier_info_to_extack(&info->info); if (!is_vlan_dev(dev)) return NOTIFY_DONE; user = vlan_dev_real_dev(dev); if (!dsa_user_dev_check(user)) return NOTIFY_DONE; dp = dsa_user_to_port(user); br = dsa_port_bridge_dev_get(dp); if (!br) return NOTIFY_DONE; /* Deny enslaving a VLAN device into a VLAN-aware bridge */ if (br_vlan_enabled(br) && netif_is_bridge_master(info->upper_dev) && info->linking) { NL_SET_ERR_MSG_MOD(ext_ack, "Cannot make VLAN device join VLAN-aware bridge"); return notifier_from_errno(-EINVAL); } return NOTIFY_DONE; } static int dsa_user_check_8021q_upper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct dsa_port *dp = dsa_user_to_port(dev); struct net_device *br = dsa_port_bridge_dev_get(dp); struct bridge_vlan_info br_info; struct netlink_ext_ack *extack; int err = NOTIFY_DONE; u16 vid; if (!br || !br_vlan_enabled(br)) return NOTIFY_DONE; extack = netdev_notifier_info_to_extack(&info->info); vid = vlan_dev_vlan_id(info->upper_dev); /* br_vlan_get_info() returns -EINVAL or -ENOENT if the * device, respectively the VID is not found, returning * 0 means success, which is a failure for us here. */ err = br_vlan_get_info(br, vid, &br_info); if (err == 0) { NL_SET_ERR_MSG_MOD(extack, "This VLAN is already configured by the bridge"); return notifier_from_errno(-EBUSY); } return NOTIFY_DONE; } static int dsa_user_prechangeupper_sanity_check(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct dsa_switch *ds; struct dsa_port *dp; int err; if (!dsa_user_dev_check(dev)) return dsa_prevent_bridging_8021q_upper(dev, info); dp = dsa_user_to_port(dev); ds = dp->ds; if (ds->ops->port_prechangeupper) { err = ds->ops->port_prechangeupper(ds, dp->index, info); if (err) return notifier_from_errno(err); } if (is_vlan_dev(info->upper_dev)) return dsa_user_check_8021q_upper(dev, info); return NOTIFY_DONE; } /* To be eligible as a DSA conduit, a LAG must have all lower interfaces be * eligible DSA conduits. Additionally, all LAG slaves must be DSA conduits of * switches in the same switch tree. */ static int dsa_lag_conduit_validate(struct net_device *lag_dev, struct netlink_ext_ack *extack) { struct net_device *lower1, *lower2; struct list_head *iter1, *iter2; netdev_for_each_lower_dev(lag_dev, lower1, iter1) { netdev_for_each_lower_dev(lag_dev, lower2, iter2) { if (!netdev_uses_dsa(lower1) || !netdev_uses_dsa(lower2)) { NL_SET_ERR_MSG_MOD(extack, "All LAG ports must be eligible as DSA conduits"); return notifier_from_errno(-EINVAL); } if (lower1 == lower2) continue; if (!dsa_port_tree_same(lower1->dsa_ptr, lower2->dsa_ptr)) { NL_SET_ERR_MSG_MOD(extack, "LAG contains DSA conduits of disjoint switch trees"); return notifier_from_errno(-EINVAL); } } } return NOTIFY_DONE; } static int dsa_conduit_prechangeupper_sanity_check(struct net_device *conduit, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(&info->info); if (!netdev_uses_dsa(conduit)) return NOTIFY_DONE; if (!info->linking) return NOTIFY_DONE; /* Allow DSA switch uppers */ if (dsa_user_dev_check(info->upper_dev)) return NOTIFY_DONE; /* Allow bridge uppers of DSA conduits, subject to further * restrictions in dsa_bridge_prechangelower_sanity_check() */ if (netif_is_bridge_master(info->upper_dev)) return NOTIFY_DONE; /* Allow LAG uppers, subject to further restrictions in * dsa_lag_conduit_prechangelower_sanity_check() */ if (netif_is_lag_master(info->upper_dev)) return dsa_lag_conduit_validate(info->upper_dev, extack); NL_SET_ERR_MSG_MOD(extack, "DSA conduit cannot join unknown upper interfaces"); return notifier_from_errno(-EBUSY); } static int dsa_lag_conduit_prechangelower_sanity_check(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(&info->info); struct net_device *lag_dev = info->upper_dev; struct net_device *lower; struct list_head *iter; if (!netdev_uses_dsa(lag_dev) || !netif_is_lag_master(lag_dev)) return NOTIFY_DONE; if (!info->linking) return NOTIFY_DONE; if (!netdev_uses_dsa(dev)) { NL_SET_ERR_MSG(extack, "Only DSA conduits can join a LAG DSA conduit"); return notifier_from_errno(-EINVAL); } netdev_for_each_lower_dev(lag_dev, lower, iter) { if (!dsa_port_tree_same(dev->dsa_ptr, lower->dsa_ptr)) { NL_SET_ERR_MSG(extack, "Interface is DSA conduit for a different switch tree than this LAG"); return notifier_from_errno(-EINVAL); } break; } return NOTIFY_DONE; } /* Don't allow bridging of DSA conduits, since the bridge layer rx_handler * prevents the DSA fake ethertype handler to be invoked, so we don't get the * chance to strip off and parse the DSA switch tag protocol header (the bridge * layer just returns RX_HANDLER_CONSUMED, stopping RX processing for these * frames). * The only case where that would not be an issue is when bridging can already * be offloaded, such as when the DSA conduit is itself a DSA or plain switchdev * port, and is bridged only with other ports from the same hardware device. */ static int dsa_bridge_prechangelower_sanity_check(struct net_device *new_lower, struct netdev_notifier_changeupper_info *info) { struct net_device *br = info->upper_dev; struct netlink_ext_ack *extack; struct net_device *lower; struct list_head *iter; if (!netif_is_bridge_master(br)) return NOTIFY_DONE; if (!info->linking) return NOTIFY_DONE; extack = netdev_notifier_info_to_extack(&info->info); netdev_for_each_lower_dev(br, lower, iter) { if (!netdev_uses_dsa(new_lower) && !netdev_uses_dsa(lower)) continue; if (!netdev_port_same_parent_id(lower, new_lower)) { NL_SET_ERR_MSG(extack, "Cannot do software bridging with a DSA conduit"); return notifier_from_errno(-EINVAL); } } return NOTIFY_DONE; } static void dsa_tree_migrate_ports_from_lag_conduit(struct dsa_switch_tree *dst, struct net_device *lag_dev) { struct net_device *new_conduit = dsa_tree_find_first_conduit(dst); struct dsa_port *dp; int err; dsa_tree_for_each_user_port(dp, dst) { if (dsa_port_to_conduit(dp) != lag_dev) continue; err = dsa_user_change_conduit(dp->user, new_conduit, NULL); if (err) { netdev_err(dp->user, "failed to restore conduit to %s: %pe\n", new_conduit->name, ERR_PTR(err)); } } } static int dsa_conduit_lag_join(struct net_device *conduit, struct net_device *lag_dev, struct netdev_lag_upper_info *uinfo, struct netlink_ext_ack *extack) { struct dsa_port *cpu_dp = conduit->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->dst; struct dsa_port *dp; int err; err = dsa_conduit_lag_setup(lag_dev, cpu_dp, uinfo, extack); if (err) return err; dsa_tree_for_each_user_port(dp, dst) { if (dsa_port_to_conduit(dp) != conduit) continue; err = dsa_user_change_conduit(dp->user, lag_dev, extack); if (err) goto restore; } return 0; restore: dsa_tree_for_each_user_port_continue_reverse(dp, dst) { if (dsa_port_to_conduit(dp) != lag_dev) continue; err = dsa_user_change_conduit(dp->user, conduit, NULL); if (err) { netdev_err(dp->user, "failed to restore conduit to %s: %pe\n", conduit->name, ERR_PTR(err)); } } dsa_conduit_lag_teardown(lag_dev, conduit->dsa_ptr); return err; } static void dsa_conduit_lag_leave(struct net_device *conduit, struct net_device *lag_dev) { struct dsa_port *dp, *cpu_dp = lag_dev->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->dst; struct dsa_port *new_cpu_dp = NULL; struct net_device *lower; struct list_head *iter; netdev_for_each_lower_dev(lag_dev, lower, iter) { if (netdev_uses_dsa(lower)) { new_cpu_dp = lower->dsa_ptr; break; } } if (new_cpu_dp) { /* Update the CPU port of the user ports still under the LAG * so that dsa_port_to_conduit() continues to work properly */ dsa_tree_for_each_user_port(dp, dst) if (dsa_port_to_conduit(dp) == lag_dev) dp->cpu_dp = new_cpu_dp; /* Update the index of the virtual CPU port to match the lowest * physical CPU port */ lag_dev->dsa_ptr = new_cpu_dp; wmb(); } else { /* If the LAG DSA conduit has no ports left, migrate back all * user ports to the first physical CPU port */ dsa_tree_migrate_ports_from_lag_conduit(dst, lag_dev); } /* This DSA conduit has left its LAG in any case, so let * the CPU port leave the hardware LAG as well */ dsa_conduit_lag_teardown(lag_dev, conduit->dsa_ptr); } static int dsa_conduit_changeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *extack; int err = NOTIFY_DONE; if (!netdev_uses_dsa(dev)) return err; extack = netdev_notifier_info_to_extack(&info->info); if (netif_is_lag_master(info->upper_dev)) { if (info->linking) { err = dsa_conduit_lag_join(dev, info->upper_dev, info->upper_info, extack); err = notifier_from_errno(err); } else { dsa_conduit_lag_leave(dev, info->upper_dev); err = NOTIFY_OK; } } return err; } static int dsa_user_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (event) { case NETDEV_PRECHANGEUPPER: { struct netdev_notifier_changeupper_info *info = ptr; int err; err = dsa_user_prechangeupper_sanity_check(dev, info); if (notifier_to_errno(err)) return err; err = dsa_conduit_prechangeupper_sanity_check(dev, info); if (notifier_to_errno(err)) return err; err = dsa_lag_conduit_prechangelower_sanity_check(dev, info); if (notifier_to_errno(err)) return err; err = dsa_bridge_prechangelower_sanity_check(dev, info); if (notifier_to_errno(err)) return err; err = dsa_user_prechangeupper(dev, ptr); if (notifier_to_errno(err)) return err; err = dsa_user_lag_prechangeupper(dev, ptr); if (notifier_to_errno(err)) return err; break; } case NETDEV_CHANGEUPPER: { int err; err = dsa_user_changeupper(dev, ptr); if (notifier_to_errno(err)) return err; err = dsa_user_lag_changeupper(dev, ptr); if (notifier_to_errno(err)) return err; err = dsa_conduit_changeupper(dev, ptr); if (notifier_to_errno(err)) return err; break; } case NETDEV_CHANGELOWERSTATE: { struct netdev_notifier_changelowerstate_info *info = ptr; struct dsa_port *dp; int err = 0; if (dsa_user_dev_check(dev)) { dp = dsa_user_to_port(dev); err = dsa_port_lag_change(dp, info->lower_state_info); } /* Mirror LAG port events on DSA conduits that are in * a LAG towards their respective switch CPU ports */ if (netdev_uses_dsa(dev)) { dp = dev->dsa_ptr; err = dsa_port_lag_change(dp, info->lower_state_info); } return notifier_from_errno(err); } case NETDEV_CHANGE: case NETDEV_UP: { /* Track state of conduit port. * DSA driver may require the conduit port (and indirectly * the tagger) to be available for some special operation. */ if (netdev_uses_dsa(dev)) { struct dsa_port *cpu_dp = dev->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->ds->dst; /* Track when the conduit port is UP */ dsa_tree_conduit_oper_state_change(dst, dev, netif_oper_up(dev)); /* Track when the conduit port is ready and can accept * packet. * NETDEV_UP event is not enough to flag a port as ready. * We also have to wait for linkwatch_do_dev to dev_activate * and emit a NETDEV_CHANGE event. * We check if a conduit port is ready by checking if the dev * have a qdisc assigned and is not noop. */ dsa_tree_conduit_admin_state_change(dst, dev, !qdisc_tx_is_noop(dev)); return NOTIFY_OK; } return NOTIFY_DONE; } case NETDEV_GOING_DOWN: { struct dsa_port *dp, *cpu_dp; struct dsa_switch_tree *dst; LIST_HEAD(close_list); if (!netdev_uses_dsa(dev)) return NOTIFY_DONE; cpu_dp = dev->dsa_ptr; dst = cpu_dp->ds->dst; dsa_tree_conduit_admin_state_change(dst, dev, false); list_for_each_entry(dp, &dst->ports, list) { if (!dsa_port_is_user(dp)) continue; if (dp->cpu_dp != cpu_dp) continue; list_add(&dp->user->close_list, &close_list); } dev_close_many(&close_list, true); return NOTIFY_OK; } default: break; } return NOTIFY_DONE; } static void dsa_fdb_offload_notify(struct dsa_switchdev_event_work *switchdev_work) { struct switchdev_notifier_fdb_info info = {}; info.addr = switchdev_work->addr; info.vid = switchdev_work->vid; info.offloaded = true; call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED, switchdev_work->orig_dev, &info.info, NULL); } static void dsa_user_switchdev_event_work(struct work_struct *work) { struct dsa_switchdev_event_work *switchdev_work = container_of(work, struct dsa_switchdev_event_work, work); const unsigned char *addr = switchdev_work->addr; struct net_device *dev = switchdev_work->dev; u16 vid = switchdev_work->vid; struct dsa_switch *ds; struct dsa_port *dp; int err; dp = dsa_user_to_port(dev); ds = dp->ds; switch (switchdev_work->event) { case SWITCHDEV_FDB_ADD_TO_DEVICE: if (switchdev_work->host_addr) err = dsa_port_bridge_host_fdb_add(dp, addr, vid); else if (dp->lag) err = dsa_port_lag_fdb_add(dp, addr, vid); else err = dsa_port_fdb_add(dp, addr, vid); if (err) { dev_err(ds->dev, "port %d failed to add %pM vid %d to fdb: %d\n", dp->index, addr, vid, err); break; } dsa_fdb_offload_notify(switchdev_work); break; case SWITCHDEV_FDB_DEL_TO_DEVICE: if (switchdev_work->host_addr) err = dsa_port_bridge_host_fdb_del(dp, addr, vid); else if (dp->lag) err = dsa_port_lag_fdb_del(dp, addr, vid); else err = dsa_port_fdb_del(dp, addr, vid); if (err) { dev_err(ds->dev, "port %d failed to delete %pM vid %d from fdb: %d\n", dp->index, addr, vid, err); } break; } kfree(switchdev_work); } static bool dsa_foreign_dev_check(const struct net_device *dev, const struct net_device *foreign_dev) { const struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch_tree *dst = dp->ds->dst; if (netif_is_bridge_master(foreign_dev)) return !dsa_tree_offloads_bridge_dev(dst, foreign_dev); if (netif_is_bridge_port(foreign_dev)) return !dsa_tree_offloads_bridge_port(dst, foreign_dev); /* Everything else is foreign */ return true; } static int dsa_user_fdb_event(struct net_device *dev, struct net_device *orig_dev, unsigned long event, const void *ctx, const struct switchdev_notifier_fdb_info *fdb_info) { struct dsa_switchdev_event_work *switchdev_work; struct dsa_port *dp = dsa_user_to_port(dev); bool host_addr = fdb_info->is_local; struct dsa_switch *ds = dp->ds; if (ctx && ctx != dp) return 0; if (!dp->bridge) return 0; if (switchdev_fdb_is_dynamically_learned(fdb_info)) { if (dsa_port_offloads_bridge_port(dp, orig_dev)) return 0; /* FDB entries learned by the software bridge or by foreign * bridge ports should be installed as host addresses only if * the driver requests assisted learning. */ if (!ds->assisted_learning_on_cpu_port) return 0; } /* Also treat FDB entries on foreign interfaces bridged with us as host * addresses. */ if (dsa_foreign_dev_check(dev, orig_dev)) host_addr = true; /* Check early that we're not doing work in vain. * Host addresses on LAG ports still require regular FDB ops, * since the CPU port isn't in a LAG. */ if (dp->lag && !host_addr) { if (!ds->ops->lag_fdb_add || !ds->ops->lag_fdb_del) return -EOPNOTSUPP; } else { if (!ds->ops->port_fdb_add || !ds->ops->port_fdb_del) return -EOPNOTSUPP; } switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC); if (!switchdev_work) return -ENOMEM; netdev_dbg(dev, "%s FDB entry towards %s, addr %pM vid %d%s\n", event == SWITCHDEV_FDB_ADD_TO_DEVICE ? "Adding" : "Deleting", orig_dev->name, fdb_info->addr, fdb_info->vid, host_addr ? " as host address" : ""); INIT_WORK(&switchdev_work->work, dsa_user_switchdev_event_work); switchdev_work->event = event; switchdev_work->dev = dev; switchdev_work->orig_dev = orig_dev; ether_addr_copy(switchdev_work->addr, fdb_info->addr); switchdev_work->vid = fdb_info->vid; switchdev_work->host_addr = host_addr; dsa_schedule_work(&switchdev_work->work); return 0; } /* Called under rcu_read_lock() */ static int dsa_user_switchdev_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = switchdev_notifier_info_to_dev(ptr); int err; switch (event) { case SWITCHDEV_PORT_ATTR_SET: err = switchdev_handle_port_attr_set(dev, ptr, dsa_user_dev_check, dsa_user_port_attr_set); return notifier_from_errno(err); case SWITCHDEV_FDB_ADD_TO_DEVICE: case SWITCHDEV_FDB_DEL_TO_DEVICE: err = switchdev_handle_fdb_event_to_device(dev, event, ptr, dsa_user_dev_check, dsa_foreign_dev_check, dsa_user_fdb_event); return notifier_from_errno(err); default: return NOTIFY_DONE; } return NOTIFY_OK; } static int dsa_user_switchdev_blocking_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = switchdev_notifier_info_to_dev(ptr); int err; switch (event) { case SWITCHDEV_PORT_OBJ_ADD: err = switchdev_handle_port_obj_add_foreign(dev, ptr, dsa_user_dev_check, dsa_foreign_dev_check, dsa_user_port_obj_add); return notifier_from_errno(err); case SWITCHDEV_PORT_OBJ_DEL: err = switchdev_handle_port_obj_del_foreign(dev, ptr, dsa_user_dev_check, dsa_foreign_dev_check, dsa_user_port_obj_del); return notifier_from_errno(err); case SWITCHDEV_PORT_ATTR_SET: err = switchdev_handle_port_attr_set(dev, ptr, dsa_user_dev_check, dsa_user_port_attr_set); return notifier_from_errno(err); } return NOTIFY_DONE; } static struct notifier_block dsa_user_nb __read_mostly = { .notifier_call = dsa_user_netdevice_event, }; struct notifier_block dsa_user_switchdev_notifier = { .notifier_call = dsa_user_switchdev_event, }; struct notifier_block dsa_user_switchdev_blocking_notifier = { .notifier_call = dsa_user_switchdev_blocking_event, }; int dsa_user_register_notifier(void) { struct notifier_block *nb; int err; err = register_netdevice_notifier(&dsa_user_nb); if (err) return err; err = register_switchdev_notifier(&dsa_user_switchdev_notifier); if (err) goto err_switchdev_nb; nb = &dsa_user_switchdev_blocking_notifier; err = register_switchdev_blocking_notifier(nb); if (err) goto err_switchdev_blocking_nb; return 0; err_switchdev_blocking_nb: unregister_switchdev_notifier(&dsa_user_switchdev_notifier); err_switchdev_nb: unregister_netdevice_notifier(&dsa_user_nb); return err; } void dsa_user_unregister_notifier(void) { struct notifier_block *nb; int err; nb = &dsa_user_switchdev_blocking_notifier; err = unregister_switchdev_blocking_notifier(nb); if (err) pr_err("DSA: failed to unregister switchdev blocking notifier (%d)\n", err); err = unregister_switchdev_notifier(&dsa_user_switchdev_notifier); if (err) pr_err("DSA: failed to unregister switchdev notifier (%d)\n", err); err = unregister_netdevice_notifier(&dsa_user_nb); if (err) pr_err("DSA: failed to unregister user notifier (%d)\n", err); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_DAX_H #define _LINUX_DAX_H #include <linux/fs.h> #include <linux/mm.h> #include <linux/radix-tree.h> typedef unsigned long dax_entry_t; struct dax_device; struct gendisk; struct iomap_ops; struct iomap_iter; struct iomap; enum dax_access_mode { DAX_ACCESS, DAX_RECOVERY_WRITE, }; struct dax_operations { /* * direct_access: translate a device-relative * logical-page-offset into an absolute physical pfn. Return the * number of pages available for DAX at that pfn. */ long (*direct_access)(struct dax_device *, pgoff_t, long, enum dax_access_mode, void **, pfn_t *); /* zero_page_range: required operation. Zero page range */ int (*zero_page_range)(struct dax_device *, pgoff_t, size_t); /* * recovery_write: recover a poisoned range by DAX device driver * capable of clearing poison. */ size_t (*recovery_write)(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *iter); }; struct dax_holder_operations { /* * notify_failure - notify memory failure into inner holder device * @dax_dev: the dax device which contains the holder * @offset: offset on this dax device where memory failure occurs * @len: length of this memory failure event * @flags: action flags for memory failure handler */ int (*notify_failure)(struct dax_device *dax_dev, u64 offset, u64 len, int mf_flags); }; #if IS_ENABLED(CONFIG_DAX) struct dax_device *alloc_dax(void *private, const struct dax_operations *ops); void *dax_holder(struct dax_device *dax_dev); void put_dax(struct dax_device *dax_dev); void kill_dax(struct dax_device *dax_dev); void dax_write_cache(struct dax_device *dax_dev, bool wc); bool dax_write_cache_enabled(struct dax_device *dax_dev); bool dax_synchronous(struct dax_device *dax_dev); void set_dax_nocache(struct dax_device *dax_dev); void set_dax_nomc(struct dax_device *dax_dev); void set_dax_synchronous(struct dax_device *dax_dev); size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); /* * Check if given mapping is supported by the file / underlying device. */ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, struct dax_device *dax_dev) { if (!(vma->vm_flags & VM_SYNC)) return true; if (!IS_DAX(file_inode(vma->vm_file))) return false; return dax_synchronous(dax_dev); } #else static inline void *dax_holder(struct dax_device *dax_dev) { return NULL; } static inline struct dax_device *alloc_dax(void *private, const struct dax_operations *ops) { return ERR_PTR(-EOPNOTSUPP); } static inline void put_dax(struct dax_device *dax_dev) { } static inline void kill_dax(struct dax_device *dax_dev) { } static inline void dax_write_cache(struct dax_device *dax_dev, bool wc) { } static inline bool dax_write_cache_enabled(struct dax_device *dax_dev) { return false; } static inline bool dax_synchronous(struct dax_device *dax_dev) { return true; } static inline void set_dax_nocache(struct dax_device *dax_dev) { } static inline void set_dax_nomc(struct dax_device *dax_dev) { } static inline void set_dax_synchronous(struct dax_device *dax_dev) { } static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, struct dax_device *dax_dev) { return !(vma->vm_flags & VM_SYNC); } static inline size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) { return 0; } #endif struct writeback_control; #if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX) int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk); void dax_remove_host(struct gendisk *disk); struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off, void *holder, const struct dax_holder_operations *ops); void fs_put_dax(struct dax_device *dax_dev, void *holder); #else static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk) { return 0; } static inline void dax_remove_host(struct gendisk *disk) { } static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off, void *holder, const struct dax_holder_operations *ops) { return NULL; } static inline void fs_put_dax(struct dax_device *dax_dev, void *holder) { } #endif /* CONFIG_BLOCK && CONFIG_FS_DAX */ #if IS_ENABLED(CONFIG_FS_DAX) int dax_writeback_mapping_range(struct address_space *mapping, struct dax_device *dax_dev, struct writeback_control *wbc); struct page *dax_layout_busy_page(struct address_space *mapping); struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end); dax_entry_t dax_lock_folio(struct folio *folio); void dax_unlock_folio(struct folio *folio, dax_entry_t cookie); dax_entry_t dax_lock_mapping_entry(struct address_space *mapping, unsigned long index, struct page **page); void dax_unlock_mapping_entry(struct address_space *mapping, unsigned long index, dax_entry_t cookie); #else static inline struct page *dax_layout_busy_page(struct address_space *mapping) { return NULL; } static inline struct page *dax_layout_busy_page_range(struct address_space *mapping, pgoff_t start, pgoff_t nr_pages) { return NULL; } static inline int dax_writeback_mapping_range(struct address_space *mapping, struct dax_device *dax_dev, struct writeback_control *wbc) { return -EOPNOTSUPP; } static inline dax_entry_t dax_lock_folio(struct folio *folio) { if (IS_DAX(folio->mapping->host)) return ~0UL; return 0; } static inline void dax_unlock_folio(struct folio *folio, dax_entry_t cookie) { } static inline dax_entry_t dax_lock_mapping_entry(struct address_space *mapping, unsigned long index, struct page **page) { return 0; } static inline void dax_unlock_mapping_entry(struct address_space *mapping, unsigned long index, dax_entry_t cookie) { } #endif int dax_file_unshare(struct inode *inode, loff_t pos, loff_t len, const struct iomap_ops *ops); int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, const struct iomap_ops *ops); int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, const struct iomap_ops *ops); #if IS_ENABLED(CONFIG_DAX) int dax_read_lock(void); void dax_read_unlock(int id); #else static inline int dax_read_lock(void) { return 0; } static inline void dax_read_unlock(int id) { } #endif /* CONFIG_DAX */ bool dax_alive(struct dax_device *dax_dev); void *dax_get_private(struct dax_device *dax_dev); long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, enum dax_access_mode mode, void **kaddr, pfn_t *pfn); size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, size_t nr_pages); int dax_holder_notify_failure(struct dax_device *dax_dev, u64 off, u64 len, int mf_flags); void dax_flush(struct dax_device *dax_dev, void *addr, size_t size); ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops); vm_fault_t dax_iomap_fault(struct vm_fault *vmf, unsigned int order, pfn_t *pfnp, int *errp, const struct iomap_ops *ops); vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, unsigned int order, pfn_t pfn); int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff, struct inode *dest, loff_t destoff, loff_t len, bool *is_same, const struct iomap_ops *ops); int dax_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *len, unsigned int remap_flags, const struct iomap_ops *ops); static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); } /* * Due to dax's memory and block duo personalities, hwpoison reporting * takes into consideration which personality is presently visible. * When dax acts like a block device, such as in block IO, an encounter of * dax hwpoison is reported as -EIO. * When dax acts like memory, such as in page fault, a detection of hwpoison * is reported as -EHWPOISON which leads to VM_FAULT_HWPOISON. */ static inline int dax_mem2blk_err(int err) { return (err == -EHWPOISON) ? -EIO : err; } #ifdef CONFIG_DEV_DAX_HMEM_DEVICES void hmem_register_resource(int target_nid, struct resource *r); #else static inline void hmem_register_resource(int target_nid, struct resource *r) { } #endif typedef int (*walk_hmem_fn)(struct device *dev, int target_nid, const struct resource *res); int walk_hmem_resources(struct device *dev, walk_hmem_fn fn); #endif |
| 4 4 2 2 4 1 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/slab.h> #include <linux/stat.h> #include <linux/sched/xacct.h> #include <linux/fcntl.h> #include <linux/file.h> #include <linux/uio.h> #include <linux/fsnotify.h> #include <linux/security.h> #include <linux/export.h> #include <linux/syscalls.h> #include <linux/pagemap.h> #include <linux/splice.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/fs.h> #include <linux/dax.h> #include <linux/overflow.h> #include "internal.h" #include <linux/uaccess.h> #include <asm/unistd.h> /* * Performs necessary checks before doing a clone. * * Can adjust amount of bytes to clone via @req_count argument. * Returns appropriate error code that caller should return or * zero in case the clone should be allowed. */ static int generic_remap_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *req_count, unsigned int remap_flags) { struct inode *inode_in = file_in->f_mapping->host; struct inode *inode_out = file_out->f_mapping->host; uint64_t count = *req_count; uint64_t bcount; loff_t size_in, size_out; loff_t bs = inode_out->i_sb->s_blocksize; int ret; /* The start of both ranges must be aligned to an fs block. */ if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_out, bs)) return -EINVAL; /* Ensure offsets don't wrap. */ if (pos_in + count < pos_in || pos_out + count < pos_out) return -EINVAL; size_in = i_size_read(inode_in); size_out = i_size_read(inode_out); /* Dedupe requires both ranges to be within EOF. */ if ((remap_flags & REMAP_FILE_DEDUP) && (pos_in >= size_in || pos_in + count > size_in || pos_out >= size_out || pos_out + count > size_out)) return -EINVAL; /* Ensure the infile range is within the infile. */ if (pos_in >= size_in) return -EINVAL; count = min(count, size_in - (uint64_t)pos_in); ret = generic_write_check_limits(file_out, pos_out, &count); if (ret) return ret; /* * If the user wanted us to link to the infile's EOF, round up to the * next block boundary for this check. * * Otherwise, make sure the count is also block-aligned, having * already confirmed the starting offsets' block alignment. */ if (pos_in + count == size_in && (!(remap_flags & REMAP_FILE_DEDUP) || pos_out + count == size_out)) { bcount = ALIGN(size_in, bs) - pos_in; } else { if (!IS_ALIGNED(count, bs)) count = ALIGN_DOWN(count, bs); bcount = count; } /* Don't allow overlapped cloning within the same file. */ if (inode_in == inode_out && pos_out + bcount > pos_in && pos_out < pos_in + bcount) return -EINVAL; /* * We shortened the request but the caller can't deal with that, so * bounce the request back to userspace. */ if (*req_count != count && !(remap_flags & REMAP_FILE_CAN_SHORTEN)) return -EINVAL; *req_count = count; return 0; } int remap_verify_area(struct file *file, loff_t pos, loff_t len, bool write) { int mask = write ? MAY_WRITE : MAY_READ; loff_t tmp; int ret; if (unlikely(pos < 0 || len < 0)) return -EINVAL; if (unlikely(check_add_overflow(pos, len, &tmp))) return -EINVAL; ret = security_file_permission(file, mask); if (ret) return ret; return fsnotify_file_area_perm(file, mask, &pos, len); } EXPORT_SYMBOL_GPL(remap_verify_area); /* * Ensure that we don't remap a partial EOF block in the middle of something * else. Assume that the offsets have already been checked for block * alignment. * * For clone we only link a partial EOF block above or at the destination file's * EOF. For deduplication we accept a partial EOF block only if it ends at the * destination file's EOF (can not link it into the middle of a file). * * Shorten the request if possible. */ static int generic_remap_check_len(struct inode *inode_in, struct inode *inode_out, loff_t pos_out, loff_t *len, unsigned int remap_flags) { u64 blkmask = i_blocksize(inode_in) - 1; loff_t new_len = *len; if ((*len & blkmask) == 0) return 0; if (pos_out + *len < i_size_read(inode_out)) new_len &= ~blkmask; if (new_len == *len) return 0; if (remap_flags & REMAP_FILE_CAN_SHORTEN) { *len = new_len; return 0; } return (remap_flags & REMAP_FILE_DEDUP) ? -EBADE : -EINVAL; } /* Read a page's worth of file data into the page cache. */ static struct folio *vfs_dedupe_get_folio(struct file *file, loff_t pos) { return read_mapping_folio(file->f_mapping, pos >> PAGE_SHIFT, file); } /* * Lock two folios, ensuring that we lock in offset order if the folios * are from the same file. */ static void vfs_lock_two_folios(struct folio *folio1, struct folio *folio2) { /* Always lock in order of increasing index. */ if (folio1->index > folio2->index) swap(folio1, folio2); folio_lock(folio1); if (folio1 != folio2) folio_lock(folio2); } /* Unlock two folios, being careful not to unlock the same folio twice. */ static void vfs_unlock_two_folios(struct folio *folio1, struct folio *folio2) { folio_unlock(folio1); if (folio1 != folio2) folio_unlock(folio2); } /* * Compare extents of two files to see if they are the same. * Caller must have locked both inodes to prevent write races. */ static int vfs_dedupe_file_range_compare(struct file *src, loff_t srcoff, struct file *dest, loff_t dstoff, loff_t len, bool *is_same) { bool same = true; int error = -EINVAL; while (len) { struct folio *src_folio, *dst_folio; void *src_addr, *dst_addr; loff_t cmp_len = min(PAGE_SIZE - offset_in_page(srcoff), PAGE_SIZE - offset_in_page(dstoff)); cmp_len = min(cmp_len, len); if (cmp_len <= 0) goto out_error; src_folio = vfs_dedupe_get_folio(src, srcoff); if (IS_ERR(src_folio)) { error = PTR_ERR(src_folio); goto out_error; } dst_folio = vfs_dedupe_get_folio(dest, dstoff); if (IS_ERR(dst_folio)) { error = PTR_ERR(dst_folio); folio_put(src_folio); goto out_error; } vfs_lock_two_folios(src_folio, dst_folio); /* * Now that we've locked both folios, make sure they're still * mapped to the file data we're interested in. If not, * someone is invalidating pages on us and we lose. */ if (!folio_test_uptodate(src_folio) || !folio_test_uptodate(dst_folio) || src_folio->mapping != src->f_mapping || dst_folio->mapping != dest->f_mapping) { same = false; goto unlock; } src_addr = kmap_local_folio(src_folio, offset_in_folio(src_folio, srcoff)); dst_addr = kmap_local_folio(dst_folio, offset_in_folio(dst_folio, dstoff)); flush_dcache_folio(src_folio); flush_dcache_folio(dst_folio); if (memcmp(src_addr, dst_addr, cmp_len)) same = false; kunmap_local(dst_addr); kunmap_local(src_addr); unlock: vfs_unlock_two_folios(src_folio, dst_folio); folio_put(dst_folio); folio_put(src_folio); if (!same) break; srcoff += cmp_len; dstoff += cmp_len; len -= cmp_len; } *is_same = same; return 0; out_error: return error; } /* * Check that the two inodes are eligible for cloning, the ranges make * sense, and then flush all dirty data. Caller must ensure that the * inodes have been locked against any other modifications. * * If there's an error, then the usual negative error code is returned. * Otherwise returns 0 with *len set to the request length. */ int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *len, unsigned int remap_flags, const struct iomap_ops *dax_read_ops) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); bool same_inode = (inode_in == inode_out); int ret; /* Don't touch certain kinds of inodes */ if (IS_IMMUTABLE(inode_out)) return -EPERM; if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out)) return -ETXTBSY; /* Don't reflink dirs, pipes, sockets... */ if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) return -EISDIR; if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) return -EINVAL; /* Zero length dedupe exits immediately; reflink goes to EOF. */ if (*len == 0) { loff_t isize = i_size_read(inode_in); if ((remap_flags & REMAP_FILE_DEDUP) || pos_in == isize) return 0; if (pos_in > isize) return -EINVAL; *len = isize - pos_in; if (*len == 0) return 0; } /* Check that we don't violate system file offset limits. */ ret = generic_remap_checks(file_in, pos_in, file_out, pos_out, len, remap_flags); if (ret || *len == 0) return ret; /* Wait for the completion of any pending IOs on both files */ inode_dio_wait(inode_in); if (!same_inode) inode_dio_wait(inode_out); ret = filemap_write_and_wait_range(inode_in->i_mapping, pos_in, pos_in + *len - 1); if (ret) return ret; ret = filemap_write_and_wait_range(inode_out->i_mapping, pos_out, pos_out + *len - 1); if (ret) return ret; /* * Check that the extents are the same. */ if (remap_flags & REMAP_FILE_DEDUP) { bool is_same = false; if (!IS_DAX(inode_in)) ret = vfs_dedupe_file_range_compare(file_in, pos_in, file_out, pos_out, *len, &is_same); else if (dax_read_ops) ret = dax_dedupe_file_range_compare(inode_in, pos_in, inode_out, pos_out, *len, &is_same, dax_read_ops); else return -EINVAL; if (ret) return ret; if (!is_same) return -EBADE; } ret = generic_remap_check_len(inode_in, inode_out, pos_out, len, remap_flags); if (ret || *len == 0) return ret; /* If can't alter the file contents, we're done. */ if (!(remap_flags & REMAP_FILE_DEDUP)) ret = file_modified(file_out); return ret; } int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *len, unsigned int remap_flags) { return __generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out, len, remap_flags, NULL); } EXPORT_SYMBOL(generic_remap_file_range_prep); loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags) { loff_t ret; WARN_ON_ONCE(remap_flags & REMAP_FILE_DEDUP); if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) return -EXDEV; ret = generic_file_rw_checks(file_in, file_out); if (ret < 0) return ret; if (!file_in->f_op->remap_file_range) return -EOPNOTSUPP; ret = remap_verify_area(file_in, pos_in, len, false); if (ret) return ret; ret = remap_verify_area(file_out, pos_out, len, true); if (ret) return ret; file_start_write(file_out); ret = file_in->f_op->remap_file_range(file_in, pos_in, file_out, pos_out, len, remap_flags); file_end_write(file_out); if (ret < 0) return ret; fsnotify_access(file_in); fsnotify_modify(file_out); return ret; } EXPORT_SYMBOL(vfs_clone_file_range); /* Check whether we are allowed to dedupe the destination file */ static bool may_dedupe_file(struct file *file) { struct mnt_idmap *idmap = file_mnt_idmap(file); struct inode *inode = file_inode(file); if (capable(CAP_SYS_ADMIN)) return true; if (file->f_mode & FMODE_WRITE) return true; if (vfsuid_eq_kuid(i_uid_into_vfsuid(idmap, inode), current_fsuid())) return true; if (!inode_permission(idmap, inode, MAY_WRITE)) return true; return false; } loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, struct file *dst_file, loff_t dst_pos, loff_t len, unsigned int remap_flags) { loff_t ret; WARN_ON_ONCE(remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_CAN_SHORTEN)); /* * This is redundant if called from vfs_dedupe_file_range(), but other * callers need it and it's not performance sesitive... */ ret = remap_verify_area(src_file, src_pos, len, false); if (ret) return ret; ret = remap_verify_area(dst_file, dst_pos, len, true); if (ret) return ret; /* * This needs to be called after remap_verify_area() because of * sb_start_write() and before may_dedupe_file() because the mount's * MAY_WRITE need to be checked with mnt_get_write_access_file() held. */ ret = mnt_want_write_file(dst_file); if (ret) return ret; ret = -EPERM; if (!may_dedupe_file(dst_file)) goto out_drop_write; ret = -EXDEV; if (file_inode(src_file)->i_sb != file_inode(dst_file)->i_sb) goto out_drop_write; ret = -EISDIR; if (S_ISDIR(file_inode(dst_file)->i_mode)) goto out_drop_write; ret = -EINVAL; if (!dst_file->f_op->remap_file_range) goto out_drop_write; if (len == 0) { ret = 0; goto out_drop_write; } ret = dst_file->f_op->remap_file_range(src_file, src_pos, dst_file, dst_pos, len, remap_flags | REMAP_FILE_DEDUP); out_drop_write: mnt_drop_write_file(dst_file); return ret; } EXPORT_SYMBOL(vfs_dedupe_file_range_one); int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same) { struct file_dedupe_range_info *info; struct inode *src = file_inode(file); u64 off; u64 len; int i; int ret; u16 count = same->dest_count; loff_t deduped; if (!(file->f_mode & FMODE_READ)) return -EINVAL; if (same->reserved1 || same->reserved2) return -EINVAL; off = same->src_offset; len = same->src_length; if (S_ISDIR(src->i_mode)) return -EISDIR; if (!S_ISREG(src->i_mode)) return -EINVAL; if (!file->f_op->remap_file_range) return -EOPNOTSUPP; ret = remap_verify_area(file, off, len, false); if (ret < 0) return ret; ret = 0; if (off + len > i_size_read(src)) return -EINVAL; /* Arbitrary 1G limit on a single dedupe request, can be raised. */ len = min_t(u64, len, 1 << 30); /* pre-format output fields to sane values */ for (i = 0; i < count; i++) { same->info[i].bytes_deduped = 0ULL; same->info[i].status = FILE_DEDUPE_RANGE_SAME; } for (i = 0, info = same->info; i < count; i++, info++) { CLASS(fd, dst_fd)(info->dest_fd); if (fd_empty(dst_fd)) { info->status = -EBADF; goto next_loop; } if (info->reserved) { info->status = -EINVAL; goto next_loop; } deduped = vfs_dedupe_file_range_one(file, off, fd_file(dst_fd), info->dest_offset, len, REMAP_FILE_CAN_SHORTEN); if (deduped == -EBADE) info->status = FILE_DEDUPE_RANGE_DIFFERS; else if (deduped < 0) info->status = deduped; else info->bytes_deduped = len; next_loop: if (fatal_signal_pending(current)) break; } return ret; } EXPORT_SYMBOL(vfs_dedupe_file_range); |
| 226 226 226 226 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 | /* SPDX-License-Identifier: GPL-2.0 */ /* * generic net pointers */ #ifndef __NET_GENERIC_H__ #define __NET_GENERIC_H__ #include <linux/bug.h> #include <linux/rcupdate.h> #include <net/net_namespace.h> /* * Generic net pointers are to be used by modules to put some private * stuff on the struct net without explicit struct net modification * * The rules are simple: * 1. set pernet_operations->id. After register_pernet_device you * will have the id of your private pointer. * 2. set pernet_operations->size to have the code allocate and free * a private structure pointed to from struct net. * 3. do not change this pointer while the net is alive; * 4. do not try to have any private reference on the net_generic object. * * After accomplishing all of the above, the private pointer can be * accessed with the net_generic() call. */ struct net_generic { union { struct { unsigned int len; struct rcu_head rcu; } s; DECLARE_FLEX_ARRAY(void *, ptr); }; }; static inline void *net_generic(const struct net *net, unsigned int id) { struct net_generic *ng; void *ptr; rcu_read_lock(); ng = rcu_dereference(net->gen); ptr = ng->ptr[id]; rcu_read_unlock(); return ptr; } #endif |
| 3 3 3 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NET3 IP device support routines. * * Derived from the IP parts of dev.c 1.0.19 * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * * Additional Authors: * Alan Cox, <gw4pts@gw4pts.ampr.org> * Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Changes: * Alexey Kuznetsov: pa_* fields are replaced with ifaddr * lists. * Cyrus Durgin: updated for kmod * Matthias Andree: in devinet_ioctl, compare label and * address (4.4BSD alias style support), * fall back to comparing just the label * if no match found. */ #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/errno.h> #include <linux/interrupt.h> #include <linux/if_addr.h> #include <linux/if_ether.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/skbuff.h> #include <linux/init.h> #include <linux/notifier.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/slab.h> #include <linux/hash.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <linux/kmod.h> #include <linux/netconf.h> #include <net/arp.h> #include <net/ip.h> #include <net/route.h> #include <net/ip_fib.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/addrconf.h> #define IPV6ONLY_FLAGS \ (IFA_F_NODAD | IFA_F_OPTIMISTIC | IFA_F_DADFAILED | \ IFA_F_HOMEADDRESS | IFA_F_TENTATIVE | \ IFA_F_MANAGETEMPADDR | IFA_F_STABLE_PRIVACY) static struct ipv4_devconf ipv4_devconf = { .data = { [IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SEND_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SECURE_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SHARED_MEDIA - 1] = 1, [IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/, [IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/, [IPV4_DEVCONF_ARP_EVICT_NOCARRIER - 1] = 1, }, }; static struct ipv4_devconf ipv4_devconf_dflt = { .data = { [IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SEND_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SECURE_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SHARED_MEDIA - 1] = 1, [IPV4_DEVCONF_ACCEPT_SOURCE_ROUTE - 1] = 1, [IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/, [IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/, [IPV4_DEVCONF_ARP_EVICT_NOCARRIER - 1] = 1, }, }; #define IPV4_DEVCONF_DFLT(net, attr) \ IPV4_DEVCONF((*net->ipv4.devconf_dflt), attr) static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { [IFA_LOCAL] = { .type = NLA_U32 }, [IFA_ADDRESS] = { .type = NLA_U32 }, [IFA_BROADCAST] = { .type = NLA_U32 }, [IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) }, [IFA_FLAGS] = { .type = NLA_U32 }, [IFA_RT_PRIORITY] = { .type = NLA_U32 }, [IFA_TARGET_NETNSID] = { .type = NLA_S32 }, [IFA_PROTO] = { .type = NLA_U8 }, }; struct inet_fill_args { u32 portid; u32 seq; int event; unsigned int flags; int netnsid; int ifindex; }; #define IN4_ADDR_HSIZE_SHIFT 8 #define IN4_ADDR_HSIZE (1U << IN4_ADDR_HSIZE_SHIFT) static u32 inet_addr_hash(const struct net *net, __be32 addr) { u32 val = __ipv4_addr_hash(addr, net_hash_mix(net)); return hash_32(val, IN4_ADDR_HSIZE_SHIFT); } static void inet_hash_insert(struct net *net, struct in_ifaddr *ifa) { u32 hash = inet_addr_hash(net, ifa->ifa_local); ASSERT_RTNL(); hlist_add_head_rcu(&ifa->addr_lst, &net->ipv4.inet_addr_lst[hash]); } static void inet_hash_remove(struct in_ifaddr *ifa) { ASSERT_RTNL(); hlist_del_init_rcu(&ifa->addr_lst); } /** * __ip_dev_find - find the first device with a given source address. * @net: the net namespace * @addr: the source address * @devref: if true, take a reference on the found device * * If a caller uses devref=false, it should be protected by RCU, or RTNL */ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) { struct net_device *result = NULL; struct in_ifaddr *ifa; rcu_read_lock(); ifa = inet_lookup_ifaddr_rcu(net, addr); if (!ifa) { struct flowi4 fl4 = { .daddr = addr }; struct fib_result res = { 0 }; struct fib_table *local; /* Fallback to FIB local table so that communication * over loopback subnets work. */ local = fib_get_table(net, RT_TABLE_LOCAL); if (local && !fib_table_lookup(local, &fl4, &res, FIB_LOOKUP_NOREF) && res.type == RTN_LOCAL) result = FIB_RES_DEV(res); } else { result = ifa->ifa_dev->dev; } if (result && devref) dev_hold(result); rcu_read_unlock(); return result; } EXPORT_SYMBOL(__ip_dev_find); /* called under RCU lock */ struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr) { u32 hash = inet_addr_hash(net, addr); struct in_ifaddr *ifa; hlist_for_each_entry_rcu(ifa, &net->ipv4.inet_addr_lst[hash], addr_lst) if (ifa->ifa_local == addr) return ifa; return NULL; } static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32); static BLOCKING_NOTIFIER_HEAD(inetaddr_chain); static BLOCKING_NOTIFIER_HEAD(inetaddr_validator_chain); static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr __rcu **ifap, int destroy); #ifdef CONFIG_SYSCTL static int devinet_sysctl_register(struct in_device *idev); static void devinet_sysctl_unregister(struct in_device *idev); #else static int devinet_sysctl_register(struct in_device *idev) { return 0; } static void devinet_sysctl_unregister(struct in_device *idev) { } #endif /* Locks all the inet devices. */ static struct in_ifaddr *inet_alloc_ifa(struct in_device *in_dev) { struct in_ifaddr *ifa; ifa = kzalloc(sizeof(*ifa), GFP_KERNEL_ACCOUNT); if (!ifa) return NULL; in_dev_hold(in_dev); ifa->ifa_dev = in_dev; INIT_HLIST_NODE(&ifa->addr_lst); return ifa; } static void inet_rcu_free_ifa(struct rcu_head *head) { struct in_ifaddr *ifa = container_of(head, struct in_ifaddr, rcu_head); in_dev_put(ifa->ifa_dev); kfree(ifa); } static void inet_free_ifa(struct in_ifaddr *ifa) { /* Our reference to ifa->ifa_dev must be freed ASAP * to release the reference to the netdev the same way. * in_dev_put() -> in_dev_finish_destroy() -> netdev_put() */ call_rcu_hurry(&ifa->rcu_head, inet_rcu_free_ifa); } static void in_dev_free_rcu(struct rcu_head *head) { struct in_device *idev = container_of(head, struct in_device, rcu_head); kfree(rcu_dereference_protected(idev->mc_hash, 1)); kfree(idev); } void in_dev_finish_destroy(struct in_device *idev) { struct net_device *dev = idev->dev; WARN_ON(idev->ifa_list); WARN_ON(idev->mc_list); #ifdef NET_REFCNT_DEBUG pr_debug("%s: %p=%s\n", __func__, idev, dev ? dev->name : "NIL"); #endif netdev_put(dev, &idev->dev_tracker); if (!idev->dead) pr_err("Freeing alive in_device %p\n", idev); else call_rcu(&idev->rcu_head, in_dev_free_rcu); } EXPORT_SYMBOL(in_dev_finish_destroy); static struct in_device *inetdev_init(struct net_device *dev) { struct in_device *in_dev; int err = -ENOMEM; ASSERT_RTNL(); in_dev = kzalloc(sizeof(*in_dev), GFP_KERNEL); if (!in_dev) goto out; memcpy(&in_dev->cnf, dev_net(dev)->ipv4.devconf_dflt, sizeof(in_dev->cnf)); in_dev->cnf.sysctl = NULL; in_dev->dev = dev; in_dev->arp_parms = neigh_parms_alloc(dev, &arp_tbl); if (!in_dev->arp_parms) goto out_kfree; if (IPV4_DEVCONF(in_dev->cnf, FORWARDING)) dev_disable_lro(dev); /* Reference in_dev->dev */ netdev_hold(dev, &in_dev->dev_tracker, GFP_KERNEL); /* Account for reference dev->ip_ptr (below) */ refcount_set(&in_dev->refcnt, 1); if (dev != blackhole_netdev) { err = devinet_sysctl_register(in_dev); if (err) { in_dev->dead = 1; neigh_parms_release(&arp_tbl, in_dev->arp_parms); in_dev_put(in_dev); in_dev = NULL; goto out; } ip_mc_init_dev(in_dev); if (dev->flags & IFF_UP) ip_mc_up(in_dev); } /* we can receive as soon as ip_ptr is set -- do this last */ rcu_assign_pointer(dev->ip_ptr, in_dev); out: return in_dev ?: ERR_PTR(err); out_kfree: kfree(in_dev); in_dev = NULL; goto out; } static void inetdev_destroy(struct in_device *in_dev) { struct net_device *dev; struct in_ifaddr *ifa; ASSERT_RTNL(); dev = in_dev->dev; in_dev->dead = 1; ip_mc_destroy_dev(in_dev); while ((ifa = rtnl_dereference(in_dev->ifa_list)) != NULL) { inet_del_ifa(in_dev, &in_dev->ifa_list, 0); inet_free_ifa(ifa); } RCU_INIT_POINTER(dev->ip_ptr, NULL); devinet_sysctl_unregister(in_dev); neigh_parms_release(&arp_tbl, in_dev->arp_parms); arp_ifdown(dev); in_dev_put(in_dev); } static int __init inet_blackhole_dev_init(void) { int err = 0; rtnl_lock(); if (!inetdev_init(blackhole_netdev)) err = -ENOMEM; rtnl_unlock(); return err; } late_initcall(inet_blackhole_dev_init); int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b) { const struct in_ifaddr *ifa; rcu_read_lock(); in_dev_for_each_ifa_rcu(ifa, in_dev) { if (inet_ifa_match(a, ifa)) { if (!b || inet_ifa_match(b, ifa)) { rcu_read_unlock(); return 1; } } } rcu_read_unlock(); return 0; } static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr __rcu **ifap, int destroy, struct nlmsghdr *nlh, u32 portid) { struct in_ifaddr *promote = NULL; struct in_ifaddr *ifa, *ifa1; struct in_ifaddr __rcu **last_prim; struct in_ifaddr *prev_prom = NULL; int do_promote = IN_DEV_PROMOTE_SECONDARIES(in_dev); ASSERT_RTNL(); ifa1 = rtnl_dereference(*ifap); last_prim = ifap; if (in_dev->dead) goto no_promotions; /* 1. Deleting primary ifaddr forces deletion all secondaries * unless alias promotion is set **/ if (!(ifa1->ifa_flags & IFA_F_SECONDARY)) { struct in_ifaddr __rcu **ifap1 = &ifa1->ifa_next; while ((ifa = rtnl_dereference(*ifap1)) != NULL) { if (!(ifa->ifa_flags & IFA_F_SECONDARY) && ifa1->ifa_scope <= ifa->ifa_scope) last_prim = &ifa->ifa_next; if (!(ifa->ifa_flags & IFA_F_SECONDARY) || ifa1->ifa_mask != ifa->ifa_mask || !inet_ifa_match(ifa1->ifa_address, ifa)) { ifap1 = &ifa->ifa_next; prev_prom = ifa; continue; } if (!do_promote) { inet_hash_remove(ifa); *ifap1 = ifa->ifa_next; rtmsg_ifa(RTM_DELADDR, ifa, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa); inet_free_ifa(ifa); } else { promote = ifa; break; } } } /* On promotion all secondaries from subnet are changing * the primary IP, we must remove all their routes silently * and later to add them back with new prefsrc. Do this * while all addresses are on the device list. */ for (ifa = promote; ifa; ifa = rtnl_dereference(ifa->ifa_next)) { if (ifa1->ifa_mask == ifa->ifa_mask && inet_ifa_match(ifa1->ifa_address, ifa)) fib_del_ifaddr(ifa, ifa1); } no_promotions: /* 2. Unlink it */ *ifap = ifa1->ifa_next; inet_hash_remove(ifa1); /* 3. Announce address deletion */ /* Send message first, then call notifier. At first sight, FIB update triggered by notifier will refer to already deleted ifaddr, that could confuse netlink listeners. It is not true: look, gated sees that route deleted and if it still thinks that ifaddr is valid, it will try to restore deleted routes... Grr. So that, this order is correct. */ rtmsg_ifa(RTM_DELADDR, ifa1, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa1); if (promote) { struct in_ifaddr *next_sec; next_sec = rtnl_dereference(promote->ifa_next); if (prev_prom) { struct in_ifaddr *last_sec; rcu_assign_pointer(prev_prom->ifa_next, next_sec); last_sec = rtnl_dereference(*last_prim); rcu_assign_pointer(promote->ifa_next, last_sec); rcu_assign_pointer(*last_prim, promote); } promote->ifa_flags &= ~IFA_F_SECONDARY; rtmsg_ifa(RTM_NEWADDR, promote, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, promote); for (ifa = next_sec; ifa; ifa = rtnl_dereference(ifa->ifa_next)) { if (ifa1->ifa_mask != ifa->ifa_mask || !inet_ifa_match(ifa1->ifa_address, ifa)) continue; fib_add_ifaddr(ifa); } } if (destroy) inet_free_ifa(ifa1); } static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr __rcu **ifap, int destroy) { __inet_del_ifa(in_dev, ifap, destroy, NULL, 0); } static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, u32 portid, struct netlink_ext_ack *extack) { struct in_ifaddr __rcu **last_primary, **ifap; struct in_device *in_dev = ifa->ifa_dev; struct net *net = dev_net(in_dev->dev); struct in_validator_info ivi; struct in_ifaddr *ifa1; int ret; ASSERT_RTNL(); ifa->ifa_flags &= ~IFA_F_SECONDARY; last_primary = &in_dev->ifa_list; /* Don't set IPv6 only flags to IPv4 addresses */ ifa->ifa_flags &= ~IPV6ONLY_FLAGS; ifap = &in_dev->ifa_list; ifa1 = rtnl_dereference(*ifap); while (ifa1) { if (!(ifa1->ifa_flags & IFA_F_SECONDARY) && ifa->ifa_scope <= ifa1->ifa_scope) last_primary = &ifa1->ifa_next; if (ifa1->ifa_mask == ifa->ifa_mask && inet_ifa_match(ifa1->ifa_address, ifa)) { if (ifa1->ifa_local == ifa->ifa_local) { inet_free_ifa(ifa); return -EEXIST; } if (ifa1->ifa_scope != ifa->ifa_scope) { NL_SET_ERR_MSG(extack, "ipv4: Invalid scope value"); inet_free_ifa(ifa); return -EINVAL; } ifa->ifa_flags |= IFA_F_SECONDARY; } ifap = &ifa1->ifa_next; ifa1 = rtnl_dereference(*ifap); } /* Allow any devices that wish to register ifaddr validtors to weigh * in now, before changes are committed. The rntl lock is serializing * access here, so the state should not change between a validator call * and a final notify on commit. This isn't invoked on promotion under * the assumption that validators are checking the address itself, and * not the flags. */ ivi.ivi_addr = ifa->ifa_address; ivi.ivi_dev = ifa->ifa_dev; ivi.extack = extack; ret = blocking_notifier_call_chain(&inetaddr_validator_chain, NETDEV_UP, &ivi); ret = notifier_to_errno(ret); if (ret) { inet_free_ifa(ifa); return ret; } if (!(ifa->ifa_flags & IFA_F_SECONDARY)) ifap = last_primary; rcu_assign_pointer(ifa->ifa_next, *ifap); rcu_assign_pointer(*ifap, ifa); inet_hash_insert(dev_net(in_dev->dev), ifa); cancel_delayed_work(&net->ipv4.addr_chk_work); queue_delayed_work(system_power_efficient_wq, &net->ipv4.addr_chk_work, 0); /* Send message first, then call notifier. Notifier will trigger FIB update, so that listeners of netlink will know about new ifaddr */ rtmsg_ifa(RTM_NEWADDR, ifa, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa); return 0; } static int inet_insert_ifa(struct in_ifaddr *ifa) { if (!ifa->ifa_local) { inet_free_ifa(ifa); return 0; } return __inet_insert_ifa(ifa, NULL, 0, NULL); } static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa) { struct in_device *in_dev = __in_dev_get_rtnl_net(dev); ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); if (ipv4_is_loopback(ifa->ifa_local)) ifa->ifa_scope = RT_SCOPE_HOST; return inet_insert_ifa(ifa); } /* Caller must hold RCU or RTNL : * We dont take a reference on found in_device */ struct in_device *inetdev_by_index(struct net *net, int ifindex) { struct net_device *dev; struct in_device *in_dev = NULL; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (dev) in_dev = rcu_dereference_rtnl(dev->ip_ptr); rcu_read_unlock(); return in_dev; } EXPORT_SYMBOL(inetdev_by_index); /* Called only from RTNL semaphored context. No locks. */ struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask) { struct in_ifaddr *ifa; ASSERT_RTNL(); in_dev_for_each_ifa_rtnl(ifa, in_dev) { if (ifa->ifa_mask == mask && inet_ifa_match(prefix, ifa)) return ifa; } return NULL; } static int ip_mc_autojoin_config(struct net *net, bool join, const struct in_ifaddr *ifa) { #if defined(CONFIG_IP_MULTICAST) struct ip_mreqn mreq = { .imr_multiaddr.s_addr = ifa->ifa_address, .imr_ifindex = ifa->ifa_dev->dev->ifindex, }; struct sock *sk = net->ipv4.mc_autojoin_sk; int ret; ASSERT_RTNL_NET(net); lock_sock(sk); if (join) ret = ip_mc_join_group(sk, &mreq); else ret = ip_mc_leave_group(sk, &mreq); release_sock(sk); return ret; #else return -EOPNOTSUPP; #endif } static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct in_ifaddr __rcu **ifap; struct nlattr *tb[IFA_MAX+1]; struct in_device *in_dev; struct ifaddrmsg *ifm; struct in_ifaddr *ifa; int err; err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy, extack); if (err < 0) goto out; ifm = nlmsg_data(nlh); rtnl_net_lock(net); in_dev = inetdev_by_index(net, ifm->ifa_index); if (!in_dev) { NL_SET_ERR_MSG(extack, "ipv4: Device not found"); err = -ENODEV; goto unlock; } for (ifap = &in_dev->ifa_list; (ifa = rtnl_net_dereference(net, *ifap)) != NULL; ifap = &ifa->ifa_next) { if (tb[IFA_LOCAL] && ifa->ifa_local != nla_get_in_addr(tb[IFA_LOCAL])) continue; if (tb[IFA_LABEL] && nla_strcmp(tb[IFA_LABEL], ifa->ifa_label)) continue; if (tb[IFA_ADDRESS] && (ifm->ifa_prefixlen != ifa->ifa_prefixlen || !inet_ifa_match(nla_get_in_addr(tb[IFA_ADDRESS]), ifa))) continue; if (ipv4_is_multicast(ifa->ifa_address)) ip_mc_autojoin_config(net, false, ifa); __inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).portid); goto unlock; } NL_SET_ERR_MSG(extack, "ipv4: Address not found"); err = -EADDRNOTAVAIL; unlock: rtnl_net_unlock(net); out: return err; } static void check_lifetime(struct work_struct *work) { unsigned long now, next, next_sec, next_sched; struct in_ifaddr *ifa; struct hlist_node *n; struct net *net; int i; net = container_of(to_delayed_work(work), struct net, ipv4.addr_chk_work); now = jiffies; next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY); for (i = 0; i < IN4_ADDR_HSIZE; i++) { struct hlist_head *head = &net->ipv4.inet_addr_lst[i]; bool change_needed = false; rcu_read_lock(); hlist_for_each_entry_rcu(ifa, head, addr_lst) { unsigned long age, tstamp; u32 preferred_lft; u32 valid_lft; u32 flags; flags = READ_ONCE(ifa->ifa_flags); if (flags & IFA_F_PERMANENT) continue; preferred_lft = READ_ONCE(ifa->ifa_preferred_lft); valid_lft = READ_ONCE(ifa->ifa_valid_lft); tstamp = READ_ONCE(ifa->ifa_tstamp); /* We try to batch several events at once. */ age = (now - tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; if (valid_lft != INFINITY_LIFE_TIME && age >= valid_lft) { change_needed = true; } else if (preferred_lft == INFINITY_LIFE_TIME) { continue; } else if (age >= preferred_lft) { if (time_before(tstamp + valid_lft * HZ, next)) next = tstamp + valid_lft * HZ; if (!(flags & IFA_F_DEPRECATED)) change_needed = true; } else if (time_before(tstamp + preferred_lft * HZ, next)) { next = tstamp + preferred_lft * HZ; } } rcu_read_unlock(); if (!change_needed) continue; rtnl_net_lock(net); hlist_for_each_entry_safe(ifa, n, head, addr_lst) { unsigned long age; if (ifa->ifa_flags & IFA_F_PERMANENT) continue; /* We try to batch several events at once. */ age = (now - ifa->ifa_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME && age >= ifa->ifa_valid_lft) { struct in_ifaddr __rcu **ifap; struct in_ifaddr *tmp; ifap = &ifa->ifa_dev->ifa_list; tmp = rtnl_net_dereference(net, *ifap); while (tmp) { if (tmp == ifa) { inet_del_ifa(ifa->ifa_dev, ifap, 1); break; } ifap = &tmp->ifa_next; tmp = rtnl_net_dereference(net, *ifap); } } else if (ifa->ifa_preferred_lft != INFINITY_LIFE_TIME && age >= ifa->ifa_preferred_lft && !(ifa->ifa_flags & IFA_F_DEPRECATED)) { ifa->ifa_flags |= IFA_F_DEPRECATED; rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0); } } rtnl_net_unlock(net); } next_sec = round_jiffies_up(next); next_sched = next; /* If rounded timeout is accurate enough, accept it. */ if (time_before(next_sec, next + ADDRCONF_TIMER_FUZZ)) next_sched = next_sec; now = jiffies; /* And minimum interval is ADDRCONF_TIMER_FUZZ_MAX. */ if (time_before(next_sched, now + ADDRCONF_TIMER_FUZZ_MAX)) next_sched = now + ADDRCONF_TIMER_FUZZ_MAX; queue_delayed_work(system_power_efficient_wq, &net->ipv4.addr_chk_work, next_sched - now); } static void set_ifa_lifetime(struct in_ifaddr *ifa, __u32 valid_lft, __u32 prefered_lft) { unsigned long timeout; u32 flags; flags = ifa->ifa_flags & ~(IFA_F_PERMANENT | IFA_F_DEPRECATED); timeout = addrconf_timeout_fixup(valid_lft, HZ); if (addrconf_finite_timeout(timeout)) WRITE_ONCE(ifa->ifa_valid_lft, timeout); else flags |= IFA_F_PERMANENT; timeout = addrconf_timeout_fixup(prefered_lft, HZ); if (addrconf_finite_timeout(timeout)) { if (timeout == 0) flags |= IFA_F_DEPRECATED; WRITE_ONCE(ifa->ifa_preferred_lft, timeout); } WRITE_ONCE(ifa->ifa_flags, flags); WRITE_ONCE(ifa->ifa_tstamp, jiffies); if (!ifa->ifa_cstamp) WRITE_ONCE(ifa->ifa_cstamp, ifa->ifa_tstamp); } static int inet_validate_rtm(struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack, __u32 *valid_lft, __u32 *prefered_lft) { struct ifaddrmsg *ifm = nlmsg_data(nlh); int err; err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy, extack); if (err < 0) return err; if (ifm->ifa_prefixlen > 32) { NL_SET_ERR_MSG(extack, "ipv4: Invalid prefix length"); return -EINVAL; } if (!tb[IFA_LOCAL]) { NL_SET_ERR_MSG(extack, "ipv4: Local address is not supplied"); return -EINVAL; } if (tb[IFA_CACHEINFO]) { struct ifa_cacheinfo *ci; ci = nla_data(tb[IFA_CACHEINFO]); if (!ci->ifa_valid || ci->ifa_prefered > ci->ifa_valid) { NL_SET_ERR_MSG(extack, "ipv4: address lifetime invalid"); return -EINVAL; } *valid_lft = ci->ifa_valid; *prefered_lft = ci->ifa_prefered; } return 0; } static struct in_ifaddr *inet_rtm_to_ifa(struct net *net, struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct ifaddrmsg *ifm = nlmsg_data(nlh); struct in_device *in_dev; struct net_device *dev; struct in_ifaddr *ifa; int err; dev = __dev_get_by_index(net, ifm->ifa_index); err = -ENODEV; if (!dev) { NL_SET_ERR_MSG(extack, "ipv4: Device not found"); goto errout; } in_dev = __in_dev_get_rtnl_net(dev); err = -ENOBUFS; if (!in_dev) goto errout; ifa = inet_alloc_ifa(in_dev); if (!ifa) /* * A potential indev allocation can be left alive, it stays * assigned to its device and is destroy with it. */ goto errout; ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); if (!tb[IFA_ADDRESS]) tb[IFA_ADDRESS] = tb[IFA_LOCAL]; ifa->ifa_prefixlen = ifm->ifa_prefixlen; ifa->ifa_mask = inet_make_mask(ifm->ifa_prefixlen); ifa->ifa_flags = nla_get_u32_default(tb[IFA_FLAGS], ifm->ifa_flags); ifa->ifa_scope = ifm->ifa_scope; ifa->ifa_local = nla_get_in_addr(tb[IFA_LOCAL]); ifa->ifa_address = nla_get_in_addr(tb[IFA_ADDRESS]); if (tb[IFA_BROADCAST]) ifa->ifa_broadcast = nla_get_in_addr(tb[IFA_BROADCAST]); if (tb[IFA_LABEL]) nla_strscpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ); else memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); if (tb[IFA_RT_PRIORITY]) ifa->ifa_rt_priority = nla_get_u32(tb[IFA_RT_PRIORITY]); if (tb[IFA_PROTO]) ifa->ifa_proto = nla_get_u8(tb[IFA_PROTO]); return ifa; errout: return ERR_PTR(err); } static struct in_ifaddr *find_matching_ifa(struct net *net, struct in_ifaddr *ifa) { struct in_device *in_dev = ifa->ifa_dev; struct in_ifaddr *ifa1; in_dev_for_each_ifa_rtnl_net(net, ifa1, in_dev) { if (ifa1->ifa_mask == ifa->ifa_mask && inet_ifa_match(ifa1->ifa_address, ifa) && ifa1->ifa_local == ifa->ifa_local) return ifa1; } return NULL; } static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { __u32 prefered_lft = INFINITY_LIFE_TIME; __u32 valid_lft = INFINITY_LIFE_TIME; struct net *net = sock_net(skb->sk); struct in_ifaddr *ifa_existing; struct nlattr *tb[IFA_MAX + 1]; struct in_ifaddr *ifa; int ret; ret = inet_validate_rtm(nlh, tb, extack, &valid_lft, &prefered_lft); if (ret < 0) return ret; if (!nla_get_in_addr(tb[IFA_LOCAL])) return 0; rtnl_net_lock(net); ifa = inet_rtm_to_ifa(net, nlh, tb, extack); if (IS_ERR(ifa)) { ret = PTR_ERR(ifa); goto unlock; } ifa_existing = find_matching_ifa(net, ifa); if (!ifa_existing) { /* It would be best to check for !NLM_F_CREATE here but * userspace already relies on not having to provide this. */ set_ifa_lifetime(ifa, valid_lft, prefered_lft); if (ifa->ifa_flags & IFA_F_MCAUTOJOIN) { ret = ip_mc_autojoin_config(net, true, ifa); if (ret < 0) { NL_SET_ERR_MSG(extack, "ipv4: Multicast auto join failed"); inet_free_ifa(ifa); goto unlock; } } ret = __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid, extack); } else { u32 new_metric = ifa->ifa_rt_priority; u8 new_proto = ifa->ifa_proto; inet_free_ifa(ifa); if (nlh->nlmsg_flags & NLM_F_EXCL || !(nlh->nlmsg_flags & NLM_F_REPLACE)) { NL_SET_ERR_MSG(extack, "ipv4: Address already assigned"); ret = -EEXIST; goto unlock; } ifa = ifa_existing; if (ifa->ifa_rt_priority != new_metric) { fib_modify_prefix_metric(ifa, new_metric); ifa->ifa_rt_priority = new_metric; } ifa->ifa_proto = new_proto; set_ifa_lifetime(ifa, valid_lft, prefered_lft); cancel_delayed_work(&net->ipv4.addr_chk_work); queue_delayed_work(system_power_efficient_wq, &net->ipv4.addr_chk_work, 0); rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid); } unlock: rtnl_net_unlock(net); return ret; } /* * Determine a default network mask, based on the IP address. */ static int inet_abc_len(__be32 addr) { int rc = -1; /* Something else, probably a multicast. */ if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr)) rc = 0; else { __u32 haddr = ntohl(addr); if (IN_CLASSA(haddr)) rc = 8; else if (IN_CLASSB(haddr)) rc = 16; else if (IN_CLASSC(haddr)) rc = 24; else if (IN_CLASSE(haddr)) rc = 32; } return rc; } int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr) { struct sockaddr_in sin_orig; struct sockaddr_in *sin = (struct sockaddr_in *)&ifr->ifr_addr; struct in_ifaddr __rcu **ifap = NULL; struct in_device *in_dev; struct in_ifaddr *ifa = NULL; struct net_device *dev; char *colon; int ret = -EFAULT; int tryaddrmatch = 0; ifr->ifr_name[IFNAMSIZ - 1] = 0; /* save original address for comparison */ memcpy(&sin_orig, sin, sizeof(*sin)); colon = strchr(ifr->ifr_name, ':'); if (colon) *colon = 0; dev_load(net, ifr->ifr_name); switch (cmd) { case SIOCGIFADDR: /* Get interface address */ case SIOCGIFBRDADDR: /* Get the broadcast address */ case SIOCGIFDSTADDR: /* Get the destination address */ case SIOCGIFNETMASK: /* Get the netmask for the interface */ /* Note that these ioctls will not sleep, so that we do not impose a lock. One day we will be forced to put shlock here (I mean SMP) */ tryaddrmatch = (sin_orig.sin_family == AF_INET); memset(sin, 0, sizeof(*sin)); sin->sin_family = AF_INET; break; case SIOCSIFFLAGS: ret = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto out; break; case SIOCSIFADDR: /* Set interface address (and family) */ case SIOCSIFBRDADDR: /* Set the broadcast address */ case SIOCSIFDSTADDR: /* Set the destination address */ case SIOCSIFNETMASK: /* Set the netmask for the interface */ ret = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto out; ret = -EINVAL; if (sin->sin_family != AF_INET) goto out; break; default: ret = -EINVAL; goto out; } rtnl_net_lock(net); ret = -ENODEV; dev = __dev_get_by_name(net, ifr->ifr_name); if (!dev) goto done; if (colon) *colon = ':'; in_dev = __in_dev_get_rtnl_net(dev); if (in_dev) { if (tryaddrmatch) { /* Matthias Andree */ /* compare label and address (4.4BSD style) */ /* note: we only do this for a limited set of ioctls and only if the original address family was AF_INET. This is checked above. */ for (ifap = &in_dev->ifa_list; (ifa = rtnl_net_dereference(net, *ifap)) != NULL; ifap = &ifa->ifa_next) { if (!strcmp(ifr->ifr_name, ifa->ifa_label) && sin_orig.sin_addr.s_addr == ifa->ifa_local) { break; /* found */ } } } /* we didn't get a match, maybe the application is 4.3BSD-style and passed in junk so we fall back to comparing just the label */ if (!ifa) { for (ifap = &in_dev->ifa_list; (ifa = rtnl_net_dereference(net, *ifap)) != NULL; ifap = &ifa->ifa_next) if (!strcmp(ifr->ifr_name, ifa->ifa_label)) break; } } ret = -EADDRNOTAVAIL; if (!ifa && cmd != SIOCSIFADDR && cmd != SIOCSIFFLAGS) goto done; switch (cmd) { case SIOCGIFADDR: /* Get interface address */ ret = 0; sin->sin_addr.s_addr = ifa->ifa_local; break; case SIOCGIFBRDADDR: /* Get the broadcast address */ ret = 0; sin->sin_addr.s_addr = ifa->ifa_broadcast; break; case SIOCGIFDSTADDR: /* Get the destination address */ ret = 0; sin->sin_addr.s_addr = ifa->ifa_address; break; case SIOCGIFNETMASK: /* Get the netmask for the interface */ ret = 0; sin->sin_addr.s_addr = ifa->ifa_mask; break; case SIOCSIFFLAGS: if (colon) { ret = -EADDRNOTAVAIL; if (!ifa) break; ret = 0; if (!(ifr->ifr_flags & IFF_UP)) inet_del_ifa(in_dev, ifap, 1); break; } /* NETDEV_UP/DOWN/CHANGE could touch a peer dev */ ASSERT_RTNL(); ret = dev_change_flags(dev, ifr->ifr_flags, NULL); break; case SIOCSIFADDR: /* Set interface address (and family) */ ret = -EINVAL; if (inet_abc_len(sin->sin_addr.s_addr) < 0) break; if (!ifa) { ret = -ENOBUFS; if (!in_dev) break; ifa = inet_alloc_ifa(in_dev); if (!ifa) break; if (colon) memcpy(ifa->ifa_label, ifr->ifr_name, IFNAMSIZ); else memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); } else { ret = 0; if (ifa->ifa_local == sin->sin_addr.s_addr) break; inet_del_ifa(in_dev, ifap, 0); ifa->ifa_broadcast = 0; ifa->ifa_scope = 0; } ifa->ifa_address = ifa->ifa_local = sin->sin_addr.s_addr; if (!(dev->flags & IFF_POINTOPOINT)) { ifa->ifa_prefixlen = inet_abc_len(ifa->ifa_address); ifa->ifa_mask = inet_make_mask(ifa->ifa_prefixlen); if ((dev->flags & IFF_BROADCAST) && ifa->ifa_prefixlen < 31) ifa->ifa_broadcast = ifa->ifa_address | ~ifa->ifa_mask; } else { ifa->ifa_prefixlen = 32; ifa->ifa_mask = inet_make_mask(32); } set_ifa_lifetime(ifa, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); ret = inet_set_ifa(dev, ifa); break; case SIOCSIFBRDADDR: /* Set the broadcast address */ ret = 0; if (ifa->ifa_broadcast != sin->sin_addr.s_addr) { inet_del_ifa(in_dev, ifap, 0); ifa->ifa_broadcast = sin->sin_addr.s_addr; inet_insert_ifa(ifa); } break; case SIOCSIFDSTADDR: /* Set the destination address */ ret = 0; if (ifa->ifa_address == sin->sin_addr.s_addr) break; ret = -EINVAL; if (inet_abc_len(sin->sin_addr.s_addr) < 0) break; ret = 0; inet_del_ifa(in_dev, ifap, 0); ifa->ifa_address = sin->sin_addr.s_addr; inet_insert_ifa(ifa); break; case SIOCSIFNETMASK: /* Set the netmask for the interface */ /* * The mask we set must be legal. */ ret = -EINVAL; if (bad_mask(sin->sin_addr.s_addr, 0)) break; ret = 0; if (ifa->ifa_mask != sin->sin_addr.s_addr) { __be32 old_mask = ifa->ifa_mask; inet_del_ifa(in_dev, ifap, 0); ifa->ifa_mask = sin->sin_addr.s_addr; ifa->ifa_prefixlen = inet_mask_len(ifa->ifa_mask); /* See if current broadcast address matches * with current netmask, then recalculate * the broadcast address. Otherwise it's a * funny address, so don't touch it since * the user seems to know what (s)he's doing... */ if ((dev->flags & IFF_BROADCAST) && (ifa->ifa_prefixlen < 31) && (ifa->ifa_broadcast == (ifa->ifa_local|~old_mask))) { ifa->ifa_broadcast = (ifa->ifa_local | ~sin->sin_addr.s_addr); } inet_insert_ifa(ifa); } break; } done: rtnl_net_unlock(net); out: return ret; } int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size) { struct in_device *in_dev = __in_dev_get_rtnl_net(dev); const struct in_ifaddr *ifa; struct ifreq ifr; int done = 0; if (WARN_ON(size > sizeof(struct ifreq))) goto out; if (!in_dev) goto out; in_dev_for_each_ifa_rtnl_net(dev_net(dev), ifa, in_dev) { if (!buf) { done += size; continue; } if (len < size) break; memset(&ifr, 0, sizeof(struct ifreq)); strcpy(ifr.ifr_name, ifa->ifa_label); (*(struct sockaddr_in *)&ifr.ifr_addr).sin_family = AF_INET; (*(struct sockaddr_in *)&ifr.ifr_addr).sin_addr.s_addr = ifa->ifa_local; if (copy_to_user(buf + done, &ifr, size)) { done = -EFAULT; break; } len -= size; done += size; } out: return done; } static __be32 in_dev_select_addr(const struct in_device *in_dev, int scope) { const struct in_ifaddr *ifa; in_dev_for_each_ifa_rcu(ifa, in_dev) { if (READ_ONCE(ifa->ifa_flags) & IFA_F_SECONDARY) continue; if (ifa->ifa_scope != RT_SCOPE_LINK && ifa->ifa_scope <= scope) return ifa->ifa_local; } return 0; } __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) { const struct in_ifaddr *ifa; __be32 addr = 0; unsigned char localnet_scope = RT_SCOPE_HOST; struct in_device *in_dev; struct net *net = dev_net(dev); int master_idx; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto no_in_dev; if (unlikely(IN_DEV_ROUTE_LOCALNET(in_dev))) localnet_scope = RT_SCOPE_LINK; in_dev_for_each_ifa_rcu(ifa, in_dev) { if (READ_ONCE(ifa->ifa_flags) & IFA_F_SECONDARY) continue; if (min(ifa->ifa_scope, localnet_scope) > scope) continue; if (!dst || inet_ifa_match(dst, ifa)) { addr = ifa->ifa_local; break; } if (!addr) addr = ifa->ifa_local; } if (addr) goto out_unlock; no_in_dev: master_idx = l3mdev_master_ifindex_rcu(dev); /* For VRFs, the VRF device takes the place of the loopback device, * with addresses on it being preferred. Note in such cases the * loopback device will be among the devices that fail the master_idx * equality check in the loop below. */ if (master_idx && (dev = dev_get_by_index_rcu(net, master_idx)) && (in_dev = __in_dev_get_rcu(dev))) { addr = in_dev_select_addr(in_dev, scope); if (addr) goto out_unlock; } /* Not loopback addresses on loopback should be preferred in this case. It is important that lo is the first interface in dev_base list. */ for_each_netdev_rcu(net, dev) { if (l3mdev_master_ifindex_rcu(dev) != master_idx) continue; in_dev = __in_dev_get_rcu(dev); if (!in_dev) continue; addr = in_dev_select_addr(in_dev, scope); if (addr) goto out_unlock; } out_unlock: rcu_read_unlock(); return addr; } EXPORT_SYMBOL(inet_select_addr); static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst, __be32 local, int scope) { unsigned char localnet_scope = RT_SCOPE_HOST; const struct in_ifaddr *ifa; __be32 addr = 0; int same = 0; if (unlikely(IN_DEV_ROUTE_LOCALNET(in_dev))) localnet_scope = RT_SCOPE_LINK; in_dev_for_each_ifa_rcu(ifa, in_dev) { unsigned char min_scope = min(ifa->ifa_scope, localnet_scope); if (!addr && (local == ifa->ifa_local || !local) && min_scope <= scope) { addr = ifa->ifa_local; if (same) break; } if (!same) { same = (!local || inet_ifa_match(local, ifa)) && (!dst || inet_ifa_match(dst, ifa)); if (same && addr) { if (local || !dst) break; /* Is the selected addr into dst subnet? */ if (inet_ifa_match(addr, ifa)) break; /* No, then can we use new local src? */ if (min_scope <= scope) { addr = ifa->ifa_local; break; } /* search for large dst subnet for addr */ same = 0; } } } return same ? addr : 0; } /* * Confirm that local IP address exists using wildcards: * - net: netns to check, cannot be NULL * - in_dev: only on this interface, NULL=any interface * - dst: only in the same subnet as dst, 0=any dst * - local: address, 0=autoselect the local address * - scope: maximum allowed scope value for the local address */ __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst, __be32 local, int scope) { __be32 addr = 0; struct net_device *dev; if (in_dev) return confirm_addr_indev(in_dev, dst, local, scope); rcu_read_lock(); for_each_netdev_rcu(net, dev) { in_dev = __in_dev_get_rcu(dev); if (in_dev) { addr = confirm_addr_indev(in_dev, dst, local, scope); if (addr) break; } } rcu_read_unlock(); return addr; } EXPORT_SYMBOL(inet_confirm_addr); /* * Device notifier */ int register_inetaddr_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&inetaddr_chain, nb); } EXPORT_SYMBOL(register_inetaddr_notifier); int unregister_inetaddr_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&inetaddr_chain, nb); } EXPORT_SYMBOL(unregister_inetaddr_notifier); int register_inetaddr_validator_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&inetaddr_validator_chain, nb); } EXPORT_SYMBOL(register_inetaddr_validator_notifier); int unregister_inetaddr_validator_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&inetaddr_validator_chain, nb); } EXPORT_SYMBOL(unregister_inetaddr_validator_notifier); /* Rename ifa_labels for a device name change. Make some effort to preserve * existing alias numbering and to create unique labels if possible. */ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev) { struct in_ifaddr *ifa; int named = 0; in_dev_for_each_ifa_rtnl(ifa, in_dev) { char old[IFNAMSIZ], *dot; memcpy(old, ifa->ifa_label, IFNAMSIZ); memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); if (named++ == 0) goto skip; dot = strchr(old, ':'); if (!dot) { sprintf(old, ":%d", named); dot = old; } if (strlen(dot) + strlen(dev->name) < IFNAMSIZ) strcat(ifa->ifa_label, dot); else strcpy(ifa->ifa_label + (IFNAMSIZ - strlen(dot) - 1), dot); skip: rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0); } } static void inetdev_send_gratuitous_arp(struct net_device *dev, struct in_device *in_dev) { const struct in_ifaddr *ifa; in_dev_for_each_ifa_rtnl(ifa, in_dev) { arp_send(ARPOP_REQUEST, ETH_P_ARP, ifa->ifa_local, dev, ifa->ifa_local, NULL, dev->dev_addr, NULL); } } /* Called only under RTNL semaphore */ static int inetdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct in_device *in_dev = __in_dev_get_rtnl(dev); ASSERT_RTNL(); if (!in_dev) { if (event == NETDEV_REGISTER) { in_dev = inetdev_init(dev); if (IS_ERR(in_dev)) return notifier_from_errno(PTR_ERR(in_dev)); if (dev->flags & IFF_LOOPBACK) { IN_DEV_CONF_SET(in_dev, NOXFRM, 1); IN_DEV_CONF_SET(in_dev, NOPOLICY, 1); } } else if (event == NETDEV_CHANGEMTU) { /* Re-enabling IP */ if (inetdev_valid_mtu(dev->mtu)) in_dev = inetdev_init(dev); } goto out; } switch (event) { case NETDEV_REGISTER: pr_debug("%s: bug\n", __func__); RCU_INIT_POINTER(dev->ip_ptr, NULL); break; case NETDEV_UP: if (!inetdev_valid_mtu(dev->mtu)) break; if (dev->flags & IFF_LOOPBACK) { struct in_ifaddr *ifa = inet_alloc_ifa(in_dev); if (ifa) { ifa->ifa_local = ifa->ifa_address = htonl(INADDR_LOOPBACK); ifa->ifa_prefixlen = 8; ifa->ifa_mask = inet_make_mask(8); ifa->ifa_scope = RT_SCOPE_HOST; memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); set_ifa_lifetime(ifa, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); inet_insert_ifa(ifa); } } ip_mc_up(in_dev); fallthrough; case NETDEV_CHANGEADDR: if (!IN_DEV_ARP_NOTIFY(in_dev)) break; fallthrough; case NETDEV_NOTIFY_PEERS: /* Send gratuitous ARP to notify of link change */ inetdev_send_gratuitous_arp(dev, in_dev); break; case NETDEV_DOWN: ip_mc_down(in_dev); break; case NETDEV_PRE_TYPE_CHANGE: ip_mc_unmap(in_dev); break; case NETDEV_POST_TYPE_CHANGE: ip_mc_remap(in_dev); break; case NETDEV_CHANGEMTU: if (inetdev_valid_mtu(dev->mtu)) break; /* disable IP when MTU is not enough */ fallthrough; case NETDEV_UNREGISTER: inetdev_destroy(in_dev); break; case NETDEV_CHANGENAME: /* Do not notify about label change, this event is * not interesting to applications using netlink. */ inetdev_changename(dev, in_dev); devinet_sysctl_unregister(in_dev); devinet_sysctl_register(in_dev); break; } out: return NOTIFY_DONE; } static struct notifier_block ip_netdev_notifier = { .notifier_call = inetdev_event, }; static size_t inet_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + nla_total_size(4) /* IFA_ADDRESS */ + nla_total_size(4) /* IFA_LOCAL */ + nla_total_size(4) /* IFA_BROADCAST */ + nla_total_size(IFNAMSIZ) /* IFA_LABEL */ + nla_total_size(4) /* IFA_FLAGS */ + nla_total_size(1) /* IFA_PROTO */ + nla_total_size(4) /* IFA_RT_PRIORITY */ + nla_total_size(sizeof(struct ifa_cacheinfo)); /* IFA_CACHEINFO */ } static inline u32 cstamp_delta(unsigned long cstamp) { return (cstamp - INITIAL_JIFFIES) * 100UL / HZ; } static int put_cacheinfo(struct sk_buff *skb, unsigned long cstamp, unsigned long tstamp, u32 preferred, u32 valid) { struct ifa_cacheinfo ci; ci.cstamp = cstamp_delta(cstamp); ci.tstamp = cstamp_delta(tstamp); ci.ifa_prefered = preferred; ci.ifa_valid = valid; return nla_put(skb, IFA_CACHEINFO, sizeof(ci), &ci); } static int inet_fill_ifaddr(struct sk_buff *skb, const struct in_ifaddr *ifa, struct inet_fill_args *args) { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; unsigned long tstamp; u32 preferred, valid; u32 flags; nlh = nlmsg_put(skb, args->portid, args->seq, args->event, sizeof(*ifm), args->flags); if (!nlh) return -EMSGSIZE; ifm = nlmsg_data(nlh); ifm->ifa_family = AF_INET; ifm->ifa_prefixlen = ifa->ifa_prefixlen; flags = READ_ONCE(ifa->ifa_flags); /* Warning : ifm->ifa_flags is an __u8, it holds only 8 bits. * The 32bit value is given in IFA_FLAGS attribute. */ ifm->ifa_flags = (__u8)flags; ifm->ifa_scope = ifa->ifa_scope; ifm->ifa_index = ifa->ifa_dev->dev->ifindex; if (args->netnsid >= 0 && nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) goto nla_put_failure; tstamp = READ_ONCE(ifa->ifa_tstamp); if (!(flags & IFA_F_PERMANENT)) { preferred = READ_ONCE(ifa->ifa_preferred_lft); valid = READ_ONCE(ifa->ifa_valid_lft); if (preferred != INFINITY_LIFE_TIME) { long tval = (jiffies - tstamp) / HZ; if (preferred > tval) preferred -= tval; else preferred = 0; if (valid != INFINITY_LIFE_TIME) { if (valid > tval) valid -= tval; else valid = 0; } } } else { preferred = INFINITY_LIFE_TIME; valid = INFINITY_LIFE_TIME; } if ((ifa->ifa_address && nla_put_in_addr(skb, IFA_ADDRESS, ifa->ifa_address)) || (ifa->ifa_local && nla_put_in_addr(skb, IFA_LOCAL, ifa->ifa_local)) || (ifa->ifa_broadcast && nla_put_in_addr(skb, IFA_BROADCAST, ifa->ifa_broadcast)) || (ifa->ifa_label[0] && nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) || (ifa->ifa_proto && nla_put_u8(skb, IFA_PROTO, ifa->ifa_proto)) || nla_put_u32(skb, IFA_FLAGS, flags) || (ifa->ifa_rt_priority && nla_put_u32(skb, IFA_RT_PRIORITY, ifa->ifa_rt_priority)) || put_cacheinfo(skb, READ_ONCE(ifa->ifa_cstamp), tstamp, preferred, valid)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int inet_valid_dump_ifaddr_req(const struct nlmsghdr *nlh, struct inet_fill_args *fillargs, struct net **tgt_net, struct sock *sk, struct netlink_callback *cb) { struct netlink_ext_ack *extack = cb->extack; struct nlattr *tb[IFA_MAX+1]; struct ifaddrmsg *ifm; int err, i; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for address dump request"); return -EINVAL; } ifm = nlmsg_data(nlh); if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) { NL_SET_ERR_MSG(extack, "ipv4: Invalid values in header for address dump request"); return -EINVAL; } fillargs->ifindex = ifm->ifa_index; if (fillargs->ifindex) { cb->answer_flags |= NLM_F_DUMP_FILTERED; fillargs->flags |= NLM_F_DUMP_FILTERED; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy, extack); if (err < 0) return err; for (i = 0; i <= IFA_MAX; ++i) { if (!tb[i]) continue; if (i == IFA_TARGET_NETNSID) { struct net *net; fillargs->netnsid = nla_get_s32(tb[i]); net = rtnl_get_net_ns_capable(sk, fillargs->netnsid); if (IS_ERR(net)) { fillargs->netnsid = -1; NL_SET_ERR_MSG(extack, "ipv4: Invalid target network namespace id"); return PTR_ERR(net); } *tgt_net = net; } else { NL_SET_ERR_MSG(extack, "ipv4: Unsupported attribute in dump request"); return -EINVAL; } } return 0; } static int in_dev_dump_addr(struct in_device *in_dev, struct sk_buff *skb, struct netlink_callback *cb, int *s_ip_idx, struct inet_fill_args *fillargs) { struct in_ifaddr *ifa; int ip_idx = 0; int err; in_dev_for_each_ifa_rcu(ifa, in_dev) { if (ip_idx < *s_ip_idx) { ip_idx++; continue; } err = inet_fill_ifaddr(skb, ifa, fillargs); if (err < 0) goto done; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); ip_idx++; } err = 0; ip_idx = 0; done: *s_ip_idx = ip_idx; return err; } /* Combine dev_addr_genid and dev_base_seq to detect changes. */ static u32 inet_base_seq(const struct net *net) { u32 res = atomic_read(&net->ipv4.dev_addr_genid) + READ_ONCE(net->dev_base_seq); /* Must not return 0 (see nl_dump_check_consistent()). * Chose a value far away from 0. */ if (!res) res = 0x80000000; return res; } static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct inet_fill_args fillargs = { .portid = NETLINK_CB(cb->skb).portid, .seq = nlh->nlmsg_seq, .event = RTM_NEWADDR, .flags = NLM_F_MULTI, .netnsid = -1, }; struct net *net = sock_net(skb->sk); struct net *tgt_net = net; struct { unsigned long ifindex; int ip_idx; } *ctx = (void *)cb->ctx; struct in_device *in_dev; struct net_device *dev; int err = 0; rcu_read_lock(); if (cb->strict_check) { err = inet_valid_dump_ifaddr_req(nlh, &fillargs, &tgt_net, skb->sk, cb); if (err < 0) goto done; if (fillargs.ifindex) { dev = dev_get_by_index_rcu(tgt_net, fillargs.ifindex); if (!dev) { err = -ENODEV; goto done; } in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto done; err = in_dev_dump_addr(in_dev, skb, cb, &ctx->ip_idx, &fillargs); goto done; } } cb->seq = inet_base_seq(tgt_net); for_each_netdev_dump(tgt_net, dev, ctx->ifindex) { in_dev = __in_dev_get_rcu(dev); if (!in_dev) continue; err = in_dev_dump_addr(in_dev, skb, cb, &ctx->ip_idx, &fillargs); if (err < 0) goto done; } done: if (fillargs.netnsid >= 0) put_net(tgt_net); rcu_read_unlock(); return err; } static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, u32 portid) { struct inet_fill_args fillargs = { .portid = portid, .seq = nlh ? nlh->nlmsg_seq : 0, .event = event, .flags = 0, .netnsid = -1, }; struct sk_buff *skb; int err = -ENOBUFS; struct net *net; net = dev_net(ifa->ifa_dev->dev); skb = nlmsg_new(inet_nlmsg_size(), GFP_KERNEL); if (!skb) goto errout; err = inet_fill_ifaddr(skb, ifa, &fillargs); if (err < 0) { /* -EMSGSIZE implies BUG in inet_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, portid, RTNLGRP_IPV4_IFADDR, nlh, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV4_IFADDR, err); } static size_t inet_get_link_af_size(const struct net_device *dev, u32 ext_filter_mask) { struct in_device *in_dev = rcu_dereference_rtnl(dev->ip_ptr); if (!in_dev) return 0; return nla_total_size(IPV4_DEVCONF_MAX * 4); /* IFLA_INET_CONF */ } static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev, u32 ext_filter_mask) { struct in_device *in_dev = rcu_dereference_rtnl(dev->ip_ptr); struct nlattr *nla; int i; if (!in_dev) return -ENODATA; nla = nla_reserve(skb, IFLA_INET_CONF, IPV4_DEVCONF_MAX * 4); if (!nla) return -EMSGSIZE; for (i = 0; i < IPV4_DEVCONF_MAX; i++) ((u32 *) nla_data(nla))[i] = READ_ONCE(in_dev->cnf.data[i]); return 0; } static const struct nla_policy inet_af_policy[IFLA_INET_MAX+1] = { [IFLA_INET_CONF] = { .type = NLA_NESTED }, }; static int inet_validate_link_af(const struct net_device *dev, const struct nlattr *nla, struct netlink_ext_ack *extack) { struct nlattr *a, *tb[IFLA_INET_MAX+1]; int err, rem; if (dev && !__in_dev_get_rtnl(dev)) return -EAFNOSUPPORT; err = nla_parse_nested_deprecated(tb, IFLA_INET_MAX, nla, inet_af_policy, extack); if (err < 0) return err; if (tb[IFLA_INET_CONF]) { nla_for_each_nested(a, tb[IFLA_INET_CONF], rem) { int cfgid = nla_type(a); if (nla_len(a) < 4) return -EINVAL; if (cfgid <= 0 || cfgid > IPV4_DEVCONF_MAX) return -EINVAL; } } return 0; } static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla, struct netlink_ext_ack *extack) { struct in_device *in_dev = __in_dev_get_rtnl(dev); struct nlattr *a, *tb[IFLA_INET_MAX+1]; int rem; if (!in_dev) return -EAFNOSUPPORT; if (nla_parse_nested_deprecated(tb, IFLA_INET_MAX, nla, NULL, NULL) < 0) return -EINVAL; if (tb[IFLA_INET_CONF]) { nla_for_each_nested(a, tb[IFLA_INET_CONF], rem) ipv4_devconf_set(in_dev, nla_type(a), nla_get_u32(a)); } return 0; } static int inet_netconf_msgsize_devconf(int type) { int size = NLMSG_ALIGN(sizeof(struct netconfmsg)) + nla_total_size(4); /* NETCONFA_IFINDEX */ bool all = false; if (type == NETCONFA_ALL) all = true; if (all || type == NETCONFA_FORWARDING) size += nla_total_size(4); if (all || type == NETCONFA_RP_FILTER) size += nla_total_size(4); if (all || type == NETCONFA_MC_FORWARDING) size += nla_total_size(4); if (all || type == NETCONFA_BC_FORWARDING) size += nla_total_size(4); if (all || type == NETCONFA_PROXY_NEIGH) size += nla_total_size(4); if (all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) size += nla_total_size(4); return size; } static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex, const struct ipv4_devconf *devconf, u32 portid, u32 seq, int event, unsigned int flags, int type) { struct nlmsghdr *nlh; struct netconfmsg *ncm; bool all = false; nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg), flags); if (!nlh) return -EMSGSIZE; if (type == NETCONFA_ALL) all = true; ncm = nlmsg_data(nlh); ncm->ncm_family = AF_INET; if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0) goto nla_put_failure; if (!devconf) goto out; if ((all || type == NETCONFA_FORWARDING) && nla_put_s32(skb, NETCONFA_FORWARDING, IPV4_DEVCONF_RO(*devconf, FORWARDING)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_RP_FILTER) && nla_put_s32(skb, NETCONFA_RP_FILTER, IPV4_DEVCONF_RO(*devconf, RP_FILTER)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_MC_FORWARDING) && nla_put_s32(skb, NETCONFA_MC_FORWARDING, IPV4_DEVCONF_RO(*devconf, MC_FORWARDING)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_BC_FORWARDING) && nla_put_s32(skb, NETCONFA_BC_FORWARDING, IPV4_DEVCONF_RO(*devconf, BC_FORWARDING)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_PROXY_NEIGH) && nla_put_s32(skb, NETCONFA_PROXY_NEIGH, IPV4_DEVCONF_RO(*devconf, PROXY_ARP)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) && nla_put_s32(skb, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, IPV4_DEVCONF_RO(*devconf, IGNORE_ROUTES_WITH_LINKDOWN)) < 0) goto nla_put_failure; out: nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } void inet_netconf_notify_devconf(struct net *net, int event, int type, int ifindex, struct ipv4_devconf *devconf) { struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(inet_netconf_msgsize_devconf(type), GFP_KERNEL); if (!skb) goto errout; err = inet_netconf_fill_devconf(skb, ifindex, devconf, 0, 0, event, 0, type); if (err < 0) { /* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_IPV4_NETCONF, NULL, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV4_NETCONF, err); } static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = { [NETCONFA_IFINDEX] = { .len = sizeof(int) }, [NETCONFA_FORWARDING] = { .len = sizeof(int) }, [NETCONFA_RP_FILTER] = { .len = sizeof(int) }, [NETCONFA_PROXY_NEIGH] = { .len = sizeof(int) }, [NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN] = { .len = sizeof(int) }, }; static int inet_netconf_valid_get_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { int i, err; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(struct netconfmsg))) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for netconf get request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(struct netconfmsg), tb, NETCONFA_MAX, devconf_ipv4_policy, extack); err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct netconfmsg), tb, NETCONFA_MAX, devconf_ipv4_policy, extack); if (err) return err; for (i = 0; i <= NETCONFA_MAX; i++) { if (!tb[i]) continue; switch (i) { case NETCONFA_IFINDEX: break; default: NL_SET_ERR_MSG(extack, "ipv4: Unsupported attribute in netconf get request"); return -EINVAL; } } return 0; } static int inet_netconf_get_devconf(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[NETCONFA_MAX + 1]; const struct ipv4_devconf *devconf; struct in_device *in_dev = NULL; struct net_device *dev = NULL; struct sk_buff *skb; int ifindex; int err; err = inet_netconf_valid_get_req(in_skb, nlh, tb, extack); if (err) return err; if (!tb[NETCONFA_IFINDEX]) return -EINVAL; ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]); switch (ifindex) { case NETCONFA_IFINDEX_ALL: devconf = net->ipv4.devconf_all; break; case NETCONFA_IFINDEX_DEFAULT: devconf = net->ipv4.devconf_dflt; break; default: err = -ENODEV; dev = dev_get_by_index(net, ifindex); if (dev) in_dev = in_dev_get(dev); if (!in_dev) goto errout; devconf = &in_dev->cnf; break; } err = -ENOBUFS; skb = nlmsg_new(inet_netconf_msgsize_devconf(NETCONFA_ALL), GFP_KERNEL); if (!skb) goto errout; err = inet_netconf_fill_devconf(skb, ifindex, devconf, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, 0, NETCONFA_ALL); if (err < 0) { /* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: if (in_dev) in_dev_put(in_dev); dev_put(dev); return err; } static int inet_netconf_dump_devconf(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); struct { unsigned long ifindex; unsigned int all_default; } *ctx = (void *)cb->ctx; const struct in_device *in_dev; struct net_device *dev; int err = 0; if (cb->strict_check) { struct netlink_ext_ack *extack = cb->extack; struct netconfmsg *ncm; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ncm))) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for netconf dump request"); return -EINVAL; } if (nlmsg_attrlen(nlh, sizeof(*ncm))) { NL_SET_ERR_MSG(extack, "ipv4: Invalid data after header in netconf dump request"); return -EINVAL; } } rcu_read_lock(); for_each_netdev_dump(net, dev, ctx->ifindex) { in_dev = __in_dev_get_rcu(dev); if (!in_dev) continue; err = inet_netconf_fill_devconf(skb, dev->ifindex, &in_dev->cnf, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, NETCONFA_ALL); if (err < 0) goto done; } if (ctx->all_default == 0) { err = inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL, net->ipv4.devconf_all, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, NETCONFA_ALL); if (err < 0) goto done; ctx->all_default++; } if (ctx->all_default == 1) { err = inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT, net->ipv4.devconf_dflt, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, NETCONFA_ALL); if (err < 0) goto done; ctx->all_default++; } done: rcu_read_unlock(); return err; } #ifdef CONFIG_SYSCTL static void devinet_copy_dflt_conf(struct net *net, int i) { struct net_device *dev; rcu_read_lock(); for_each_netdev_rcu(net, dev) { struct in_device *in_dev; in_dev = __in_dev_get_rcu(dev); if (in_dev && !test_bit(i, in_dev->cnf.state)) in_dev->cnf.data[i] = net->ipv4.devconf_dflt->data[i]; } rcu_read_unlock(); } /* called with RTNL locked */ static void inet_forward_change(struct net *net) { struct net_device *dev; int on = IPV4_DEVCONF_ALL(net, FORWARDING); IPV4_DEVCONF_ALL(net, ACCEPT_REDIRECTS) = !on; IPV4_DEVCONF_DFLT(net, FORWARDING) = on; inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv4.devconf_all); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, NETCONFA_IFINDEX_DEFAULT, net->ipv4.devconf_dflt); for_each_netdev(net, dev) { struct in_device *in_dev; if (on) dev_disable_lro(dev); in_dev = __in_dev_get_rtnl_net(dev); if (in_dev) { IN_DEV_CONF_SET(in_dev, FORWARDING, on); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, dev->ifindex, &in_dev->cnf); } } } static int devinet_conf_ifindex(struct net *net, struct ipv4_devconf *cnf) { if (cnf == net->ipv4.devconf_dflt) return NETCONFA_IFINDEX_DEFAULT; else if (cnf == net->ipv4.devconf_all) return NETCONFA_IFINDEX_ALL; else { struct in_device *idev = container_of(cnf, struct in_device, cnf); return idev->dev->ifindex; } } static int devinet_conf_proc(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int old_value = *(int *)ctl->data; int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); int new_value = *(int *)ctl->data; if (write) { struct ipv4_devconf *cnf = ctl->extra1; struct net *net = ctl->extra2; int i = (int *)ctl->data - cnf->data; int ifindex; set_bit(i, cnf->state); if (cnf == net->ipv4.devconf_dflt) devinet_copy_dflt_conf(net, i); if (i == IPV4_DEVCONF_ACCEPT_LOCAL - 1 || i == IPV4_DEVCONF_ROUTE_LOCALNET - 1) if ((new_value == 0) && (old_value != 0)) rt_cache_flush(net); if (i == IPV4_DEVCONF_BC_FORWARDING - 1 && new_value != old_value) rt_cache_flush(net); if (i == IPV4_DEVCONF_RP_FILTER - 1 && new_value != old_value) { ifindex = devinet_conf_ifindex(net, cnf); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_RP_FILTER, ifindex, cnf); } if (i == IPV4_DEVCONF_PROXY_ARP - 1 && new_value != old_value) { ifindex = devinet_conf_ifindex(net, cnf); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_PROXY_NEIGH, ifindex, cnf); } if (i == IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN - 1 && new_value != old_value) { ifindex = devinet_conf_ifindex(net, cnf); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, ifindex, cnf); } } return ret; } static int devinet_sysctl_forward(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; loff_t pos = *ppos; struct net *net = ctl->extra2; int ret; if (write && !ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write && *valp != val) { if (valp != &IPV4_DEVCONF_DFLT(net, FORWARDING)) { if (!rtnl_net_trylock(net)) { /* Restore the original values before restarting */ *valp = val; *ppos = pos; return restart_syscall(); } if (valp == &IPV4_DEVCONF_ALL(net, FORWARDING)) { inet_forward_change(net); } else { struct ipv4_devconf *cnf = ctl->extra1; struct in_device *idev = container_of(cnf, struct in_device, cnf); if (*valp) dev_disable_lro(idev->dev); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, idev->dev->ifindex, cnf); } rtnl_net_unlock(net); rt_cache_flush(net); } else inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, NETCONFA_IFINDEX_DEFAULT, net->ipv4.devconf_dflt); } return ret; } static int ipv4_doint_and_flush(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); struct net *net = ctl->extra2; if (write && *valp != val) rt_cache_flush(net); return ret; } #define DEVINET_SYSCTL_ENTRY(attr, name, mval, proc) \ { \ .procname = name, \ .data = ipv4_devconf.data + \ IPV4_DEVCONF_ ## attr - 1, \ .maxlen = sizeof(int), \ .mode = mval, \ .proc_handler = proc, \ .extra1 = &ipv4_devconf, \ } #define DEVINET_SYSCTL_RW_ENTRY(attr, name) \ DEVINET_SYSCTL_ENTRY(attr, name, 0644, devinet_conf_proc) #define DEVINET_SYSCTL_RO_ENTRY(attr, name) \ DEVINET_SYSCTL_ENTRY(attr, name, 0444, devinet_conf_proc) #define DEVINET_SYSCTL_COMPLEX_ENTRY(attr, name, proc) \ DEVINET_SYSCTL_ENTRY(attr, name, 0644, proc) #define DEVINET_SYSCTL_FLUSHING_ENTRY(attr, name) \ DEVINET_SYSCTL_COMPLEX_ENTRY(attr, name, ipv4_doint_and_flush) static struct devinet_sysctl_table { struct ctl_table_header *sysctl_header; struct ctl_table devinet_vars[IPV4_DEVCONF_MAX]; } devinet_sysctl = { .devinet_vars = { DEVINET_SYSCTL_COMPLEX_ENTRY(FORWARDING, "forwarding", devinet_sysctl_forward), DEVINET_SYSCTL_RO_ENTRY(MC_FORWARDING, "mc_forwarding"), DEVINET_SYSCTL_RW_ENTRY(BC_FORWARDING, "bc_forwarding"), DEVINET_SYSCTL_RW_ENTRY(ACCEPT_REDIRECTS, "accept_redirects"), DEVINET_SYSCTL_RW_ENTRY(SECURE_REDIRECTS, "secure_redirects"), DEVINET_SYSCTL_RW_ENTRY(SHARED_MEDIA, "shared_media"), DEVINET_SYSCTL_RW_ENTRY(RP_FILTER, "rp_filter"), DEVINET_SYSCTL_RW_ENTRY(SEND_REDIRECTS, "send_redirects"), DEVINET_SYSCTL_RW_ENTRY(ACCEPT_SOURCE_ROUTE, "accept_source_route"), DEVINET_SYSCTL_RW_ENTRY(ACCEPT_LOCAL, "accept_local"), DEVINET_SYSCTL_RW_ENTRY(SRC_VMARK, "src_valid_mark"), DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP, "proxy_arp"), DEVINET_SYSCTL_RW_ENTRY(MEDIUM_ID, "medium_id"), DEVINET_SYSCTL_RW_ENTRY(BOOTP_RELAY, "bootp_relay"), DEVINET_SYSCTL_RW_ENTRY(LOG_MARTIANS, "log_martians"), DEVINET_SYSCTL_RW_ENTRY(TAG, "tag"), DEVINET_SYSCTL_RW_ENTRY(ARPFILTER, "arp_filter"), DEVINET_SYSCTL_RW_ENTRY(ARP_ANNOUNCE, "arp_announce"), DEVINET_SYSCTL_RW_ENTRY(ARP_IGNORE, "arp_ignore"), DEVINET_SYSCTL_RW_ENTRY(ARP_ACCEPT, "arp_accept"), DEVINET_SYSCTL_RW_ENTRY(ARP_NOTIFY, "arp_notify"), DEVINET_SYSCTL_RW_ENTRY(ARP_EVICT_NOCARRIER, "arp_evict_nocarrier"), DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP_PVLAN, "proxy_arp_pvlan"), DEVINET_SYSCTL_RW_ENTRY(FORCE_IGMP_VERSION, "force_igmp_version"), DEVINET_SYSCTL_RW_ENTRY(IGMPV2_UNSOLICITED_REPORT_INTERVAL, "igmpv2_unsolicited_report_interval"), DEVINET_SYSCTL_RW_ENTRY(IGMPV3_UNSOLICITED_REPORT_INTERVAL, "igmpv3_unsolicited_report_interval"), DEVINET_SYSCTL_RW_ENTRY(IGNORE_ROUTES_WITH_LINKDOWN, "ignore_routes_with_linkdown"), DEVINET_SYSCTL_RW_ENTRY(DROP_GRATUITOUS_ARP, "drop_gratuitous_arp"), DEVINET_SYSCTL_FLUSHING_ENTRY(NOXFRM, "disable_xfrm"), DEVINET_SYSCTL_FLUSHING_ENTRY(NOPOLICY, "disable_policy"), DEVINET_SYSCTL_FLUSHING_ENTRY(PROMOTE_SECONDARIES, "promote_secondaries"), DEVINET_SYSCTL_FLUSHING_ENTRY(ROUTE_LOCALNET, "route_localnet"), DEVINET_SYSCTL_FLUSHING_ENTRY(DROP_UNICAST_IN_L2_MULTICAST, "drop_unicast_in_l2_multicast"), }, }; static int __devinet_sysctl_register(struct net *net, char *dev_name, int ifindex, struct ipv4_devconf *p) { int i; struct devinet_sysctl_table *t; char path[sizeof("net/ipv4/conf/") + IFNAMSIZ]; t = kmemdup(&devinet_sysctl, sizeof(*t), GFP_KERNEL_ACCOUNT); if (!t) goto out; for (i = 0; i < ARRAY_SIZE(t->devinet_vars); i++) { t->devinet_vars[i].data += (char *)p - (char *)&ipv4_devconf; t->devinet_vars[i].extra1 = p; t->devinet_vars[i].extra2 = net; } snprintf(path, sizeof(path), "net/ipv4/conf/%s", dev_name); t->sysctl_header = register_net_sysctl(net, path, t->devinet_vars); if (!t->sysctl_header) goto free; p->sysctl = t; inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_ALL, ifindex, p); return 0; free: kfree(t); out: return -ENOMEM; } static void __devinet_sysctl_unregister(struct net *net, struct ipv4_devconf *cnf, int ifindex) { struct devinet_sysctl_table *t = cnf->sysctl; if (t) { cnf->sysctl = NULL; unregister_net_sysctl_table(t->sysctl_header); kfree(t); } inet_netconf_notify_devconf(net, RTM_DELNETCONF, 0, ifindex, NULL); } static int devinet_sysctl_register(struct in_device *idev) { int err; if (!sysctl_dev_name_is_allowed(idev->dev->name)) return -EINVAL; err = neigh_sysctl_register(idev->dev, idev->arp_parms, NULL); if (err) return err; err = __devinet_sysctl_register(dev_net(idev->dev), idev->dev->name, idev->dev->ifindex, &idev->cnf); if (err) neigh_sysctl_unregister(idev->arp_parms); return err; } static void devinet_sysctl_unregister(struct in_device *idev) { struct net *net = dev_net(idev->dev); __devinet_sysctl_unregister(net, &idev->cnf, idev->dev->ifindex); neigh_sysctl_unregister(idev->arp_parms); } static struct ctl_table ctl_forward_entry[] = { { .procname = "ip_forward", .data = &ipv4_devconf.data[ IPV4_DEVCONF_FORWARDING - 1], .maxlen = sizeof(int), .mode = 0644, .proc_handler = devinet_sysctl_forward, .extra1 = &ipv4_devconf, .extra2 = &init_net, }, }; #endif static __net_init int devinet_init_net(struct net *net) { #ifdef CONFIG_SYSCTL struct ctl_table_header *forw_hdr; struct ctl_table *tbl; #endif struct ipv4_devconf *all, *dflt; int err; int i; err = -ENOMEM; net->ipv4.inet_addr_lst = kmalloc_array(IN4_ADDR_HSIZE, sizeof(struct hlist_head), GFP_KERNEL); if (!net->ipv4.inet_addr_lst) goto err_alloc_hash; all = kmemdup(&ipv4_devconf, sizeof(ipv4_devconf), GFP_KERNEL); if (!all) goto err_alloc_all; dflt = kmemdup(&ipv4_devconf_dflt, sizeof(ipv4_devconf_dflt), GFP_KERNEL); if (!dflt) goto err_alloc_dflt; #ifdef CONFIG_SYSCTL tbl = kmemdup(ctl_forward_entry, sizeof(ctl_forward_entry), GFP_KERNEL); if (!tbl) goto err_alloc_ctl; tbl[0].data = &all->data[IPV4_DEVCONF_FORWARDING - 1]; tbl[0].extra1 = all; tbl[0].extra2 = net; #endif if (!net_eq(net, &init_net)) { switch (net_inherit_devconf()) { case 3: /* copy from the current netns */ memcpy(all, current->nsproxy->net_ns->ipv4.devconf_all, sizeof(ipv4_devconf)); memcpy(dflt, current->nsproxy->net_ns->ipv4.devconf_dflt, sizeof(ipv4_devconf_dflt)); break; case 0: case 1: /* copy from init_net */ memcpy(all, init_net.ipv4.devconf_all, sizeof(ipv4_devconf)); memcpy(dflt, init_net.ipv4.devconf_dflt, sizeof(ipv4_devconf_dflt)); break; case 2: /* use compiled values */ break; } } #ifdef CONFIG_SYSCTL err = __devinet_sysctl_register(net, "all", NETCONFA_IFINDEX_ALL, all); if (err < 0) goto err_reg_all; err = __devinet_sysctl_register(net, "default", NETCONFA_IFINDEX_DEFAULT, dflt); if (err < 0) goto err_reg_dflt; err = -ENOMEM; forw_hdr = register_net_sysctl_sz(net, "net/ipv4", tbl, ARRAY_SIZE(ctl_forward_entry)); if (!forw_hdr) goto err_reg_ctl; net->ipv4.forw_hdr = forw_hdr; #endif for (i = 0; i < IN4_ADDR_HSIZE; i++) INIT_HLIST_HEAD(&net->ipv4.inet_addr_lst[i]); INIT_DEFERRABLE_WORK(&net->ipv4.addr_chk_work, check_lifetime); net->ipv4.devconf_all = all; net->ipv4.devconf_dflt = dflt; return 0; #ifdef CONFIG_SYSCTL err_reg_ctl: __devinet_sysctl_unregister(net, dflt, NETCONFA_IFINDEX_DEFAULT); err_reg_dflt: __devinet_sysctl_unregister(net, all, NETCONFA_IFINDEX_ALL); err_reg_all: kfree(tbl); err_alloc_ctl: #endif kfree(dflt); err_alloc_dflt: kfree(all); err_alloc_all: kfree(net->ipv4.inet_addr_lst); err_alloc_hash: return err; } static __net_exit void devinet_exit_net(struct net *net) { #ifdef CONFIG_SYSCTL const struct ctl_table *tbl; #endif cancel_delayed_work_sync(&net->ipv4.addr_chk_work); #ifdef CONFIG_SYSCTL tbl = net->ipv4.forw_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.forw_hdr); __devinet_sysctl_unregister(net, net->ipv4.devconf_dflt, NETCONFA_IFINDEX_DEFAULT); __devinet_sysctl_unregister(net, net->ipv4.devconf_all, NETCONFA_IFINDEX_ALL); kfree(tbl); #endif kfree(net->ipv4.devconf_dflt); kfree(net->ipv4.devconf_all); kfree(net->ipv4.inet_addr_lst); } static __net_initdata struct pernet_operations devinet_ops = { .init = devinet_init_net, .exit = devinet_exit_net, }; static struct rtnl_af_ops inet_af_ops __read_mostly = { .family = AF_INET, .fill_link_af = inet_fill_link_af, .get_link_af_size = inet_get_link_af_size, .validate_link_af = inet_validate_link_af, .set_link_af = inet_set_link_af, }; static const struct rtnl_msg_handler devinet_rtnl_msg_handlers[] __initconst = { {.protocol = PF_INET, .msgtype = RTM_NEWADDR, .doit = inet_rtm_newaddr, .flags = RTNL_FLAG_DOIT_PERNET}, {.protocol = PF_INET, .msgtype = RTM_DELADDR, .doit = inet_rtm_deladdr, .flags = RTNL_FLAG_DOIT_PERNET}, {.protocol = PF_INET, .msgtype = RTM_GETADDR, .dumpit = inet_dump_ifaddr, .flags = RTNL_FLAG_DUMP_UNLOCKED | RTNL_FLAG_DUMP_SPLIT_NLM_DONE}, {.protocol = PF_INET, .msgtype = RTM_GETNETCONF, .doit = inet_netconf_get_devconf, .dumpit = inet_netconf_dump_devconf, .flags = RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED}, }; void __init devinet_init(void) { register_pernet_subsys(&devinet_ops); register_netdevice_notifier(&ip_netdev_notifier); if (rtnl_af_register(&inet_af_ops)) panic("Unable to register inet_af_ops\n"); rtnl_register_many(devinet_rtnl_msg_handlers); } |
| 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_BITMAP_H #define __LINUX_BITMAP_H #ifndef __ASSEMBLY__ #include <linux/align.h> #include <linux/bitops.h> #include <linux/cleanup.h> #include <linux/errno.h> #include <linux/find.h> #include <linux/limits.h> #include <linux/string.h> #include <linux/types.h> #include <linux/bitmap-str.h> struct device; /* * bitmaps provide bit arrays that consume one or more unsigned * longs. The bitmap interface and available operations are listed * here, in bitmap.h * * Function implementations generic to all architectures are in * lib/bitmap.c. Functions implementations that are architecture * specific are in various include/asm-<arch>/bitops.h headers * and other arch/<arch> specific files. * * See lib/bitmap.c for more details. */ /** * DOC: bitmap overview * * The available bitmap operations and their rough meaning in the * case that the bitmap is a single unsigned long are thus: * * The generated code is more efficient when nbits is known at * compile-time and at most BITS_PER_LONG. * * :: * * bitmap_zero(dst, nbits) *dst = 0UL * bitmap_fill(dst, nbits) *dst = ~0UL * bitmap_copy(dst, src, nbits) *dst = *src * bitmap_and(dst, src1, src2, nbits) *dst = *src1 & *src2 * bitmap_or(dst, src1, src2, nbits) *dst = *src1 | *src2 * bitmap_xor(dst, src1, src2, nbits) *dst = *src1 ^ *src2 * bitmap_andnot(dst, src1, src2, nbits) *dst = *src1 & ~(*src2) * bitmap_complement(dst, src, nbits) *dst = ~(*src) * bitmap_equal(src1, src2, nbits) Are *src1 and *src2 equal? * bitmap_intersects(src1, src2, nbits) Do *src1 and *src2 overlap? * bitmap_subset(src1, src2, nbits) Is *src1 a subset of *src2? * bitmap_empty(src, nbits) Are all bits zero in *src? * bitmap_full(src, nbits) Are all bits set in *src? * bitmap_weight(src, nbits) Hamming Weight: number set bits * bitmap_weight_and(src1, src2, nbits) Hamming Weight of and'ed bitmap * bitmap_weight_andnot(src1, src2, nbits) Hamming Weight of andnot'ed bitmap * bitmap_set(dst, pos, nbits) Set specified bit area * bitmap_clear(dst, pos, nbits) Clear specified bit area * bitmap_find_next_zero_area(buf, len, pos, n, mask) Find bit free area * bitmap_find_next_zero_area_off(buf, len, pos, n, mask, mask_off) as above * bitmap_shift_right(dst, src, n, nbits) *dst = *src >> n * bitmap_shift_left(dst, src, n, nbits) *dst = *src << n * bitmap_cut(dst, src, first, n, nbits) Cut n bits from first, copy rest * bitmap_replace(dst, old, new, mask, nbits) *dst = (*old & ~(*mask)) | (*new & *mask) * bitmap_scatter(dst, src, mask, nbits) *dst = map(dense, sparse)(src) * bitmap_gather(dst, src, mask, nbits) *dst = map(sparse, dense)(src) * bitmap_remap(dst, src, old, new, nbits) *dst = map(old, new)(src) * bitmap_bitremap(oldbit, old, new, nbits) newbit = map(old, new)(oldbit) * bitmap_onto(dst, orig, relmap, nbits) *dst = orig relative to relmap * bitmap_fold(dst, orig, sz, nbits) dst bits = orig bits mod sz * bitmap_parse(buf, buflen, dst, nbits) Parse bitmap dst from kernel buf * bitmap_parse_user(ubuf, ulen, dst, nbits) Parse bitmap dst from user buf * bitmap_parselist(buf, dst, nbits) Parse bitmap dst from kernel buf * bitmap_parselist_user(buf, dst, nbits) Parse bitmap dst from user buf * bitmap_find_free_region(bitmap, bits, order) Find and allocate bit region * bitmap_release_region(bitmap, pos, order) Free specified bit region * bitmap_allocate_region(bitmap, pos, order) Allocate specified bit region * bitmap_from_arr32(dst, buf, nbits) Copy nbits from u32[] buf to dst * bitmap_from_arr64(dst, buf, nbits) Copy nbits from u64[] buf to dst * bitmap_to_arr32(buf, src, nbits) Copy nbits from buf to u32[] dst * bitmap_to_arr64(buf, src, nbits) Copy nbits from buf to u64[] dst * bitmap_get_value8(map, start) Get 8bit value from map at start * bitmap_set_value8(map, value, start) Set 8bit value to map at start * bitmap_read(map, start, nbits) Read an nbits-sized value from * map at start * bitmap_write(map, value, start, nbits) Write an nbits-sized value to * map at start * * Note, bitmap_zero() and bitmap_fill() operate over the region of * unsigned longs, that is, bits behind bitmap till the unsigned long * boundary will be zeroed or filled as well. Consider to use * bitmap_clear() or bitmap_set() to make explicit zeroing or filling * respectively. */ /** * DOC: bitmap bitops * * Also the following operations in asm/bitops.h apply to bitmaps.:: * * set_bit(bit, addr) *addr |= bit * clear_bit(bit, addr) *addr &= ~bit * change_bit(bit, addr) *addr ^= bit * test_bit(bit, addr) Is bit set in *addr? * test_and_set_bit(bit, addr) Set bit and return old value * test_and_clear_bit(bit, addr) Clear bit and return old value * test_and_change_bit(bit, addr) Change bit and return old value * find_first_zero_bit(addr, nbits) Position first zero bit in *addr * find_first_bit(addr, nbits) Position first set bit in *addr * find_next_zero_bit(addr, nbits, bit) * Position next zero bit in *addr >= bit * find_next_bit(addr, nbits, bit) Position next set bit in *addr >= bit * find_next_and_bit(addr1, addr2, nbits, bit) * Same as find_next_bit, but in * (*addr1 & *addr2) * */ /** * DOC: declare bitmap * The DECLARE_BITMAP(name,bits) macro, in linux/types.h, can be used * to declare an array named 'name' of just enough unsigned longs to * contain all bit positions from 0 to 'bits' - 1. */ /* * Allocation and deallocation of bitmap. * Provided in lib/bitmap.c to avoid circular dependency. */ unsigned long *bitmap_alloc(unsigned int nbits, gfp_t flags); unsigned long *bitmap_zalloc(unsigned int nbits, gfp_t flags); unsigned long *bitmap_alloc_node(unsigned int nbits, gfp_t flags, int node); unsigned long *bitmap_zalloc_node(unsigned int nbits, gfp_t flags, int node); void bitmap_free(const unsigned long *bitmap); DEFINE_FREE(bitmap, unsigned long *, if (_T) bitmap_free(_T)) /* Managed variants of the above. */ unsigned long *devm_bitmap_alloc(struct device *dev, unsigned int nbits, gfp_t flags); unsigned long *devm_bitmap_zalloc(struct device *dev, unsigned int nbits, gfp_t flags); /* * lib/bitmap.c provides these functions: */ bool __bitmap_equal(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); bool __pure __bitmap_or_equal(const unsigned long *src1, const unsigned long *src2, const unsigned long *src3, unsigned int nbits); void __bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int nbits); void __bitmap_shift_right(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits); void __bitmap_shift_left(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits); void bitmap_cut(unsigned long *dst, const unsigned long *src, unsigned int first, unsigned int cut, unsigned int nbits); bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); bool __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); void __bitmap_replace(unsigned long *dst, const unsigned long *old, const unsigned long *new, const unsigned long *mask, unsigned int nbits); bool __bitmap_intersects(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); bool __bitmap_subset(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); unsigned int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits); unsigned int __bitmap_weight_and(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); unsigned int __bitmap_weight_andnot(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); void __bitmap_set(unsigned long *map, unsigned int start, int len); void __bitmap_clear(unsigned long *map, unsigned int start, int len); unsigned long bitmap_find_next_zero_area_off(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, unsigned long align_mask, unsigned long align_offset); /** * bitmap_find_next_zero_area - find a contiguous aligned zero area * @map: The address to base the search on * @size: The bitmap size in bits * @start: The bitnumber to start searching at * @nr: The number of zeroed bits we're looking for * @align_mask: Alignment mask for zero area * * The @align_mask should be one less than a power of 2; the effect is that * the bit offset of all zero areas this function finds is multiples of that * power of 2. A @align_mask of 0 means no alignment is required. */ static __always_inline unsigned long bitmap_find_next_zero_area(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, unsigned long align_mask) { return bitmap_find_next_zero_area_off(map, size, start, nr, align_mask, 0); } void bitmap_remap(unsigned long *dst, const unsigned long *src, const unsigned long *old, const unsigned long *new, unsigned int nbits); int bitmap_bitremap(int oldbit, const unsigned long *old, const unsigned long *new, int bits); void bitmap_onto(unsigned long *dst, const unsigned long *orig, const unsigned long *relmap, unsigned int bits); void bitmap_fold(unsigned long *dst, const unsigned long *orig, unsigned int sz, unsigned int nbits); #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1))) #define bitmap_size(nbits) (ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE) static __always_inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { unsigned int len = bitmap_size(nbits); if (small_const_nbits(nbits)) *dst = 0; else memset(dst, 0, len); } static __always_inline void bitmap_fill(unsigned long *dst, unsigned int nbits) { unsigned int len = bitmap_size(nbits); if (small_const_nbits(nbits)) *dst = ~0UL; else memset(dst, 0xff, len); } static __always_inline void bitmap_copy(unsigned long *dst, const unsigned long *src, unsigned int nbits) { unsigned int len = bitmap_size(nbits); if (small_const_nbits(nbits)) *dst = *src; else memcpy(dst, src, len); } /* * Copy bitmap and clear tail bits in last word. */ static __always_inline void bitmap_copy_clear_tail(unsigned long *dst, const unsigned long *src, unsigned int nbits) { bitmap_copy(dst, src, nbits); if (nbits % BITS_PER_LONG) dst[nbits / BITS_PER_LONG] &= BITMAP_LAST_WORD_MASK(nbits); } static inline void bitmap_copy_and_extend(unsigned long *to, const unsigned long *from, unsigned int count, unsigned int size) { unsigned int copy = BITS_TO_LONGS(count); memcpy(to, from, copy * sizeof(long)); if (count % BITS_PER_LONG) to[copy - 1] &= BITMAP_LAST_WORD_MASK(count); memset(to + copy, 0, bitmap_size(size) - copy * sizeof(long)); } /* * On 32-bit systems bitmaps are represented as u32 arrays internally. On LE64 * machines the order of hi and lo parts of numbers match the bitmap structure. * In both cases conversion is not needed when copying data from/to arrays of * u32. But in LE64 case, typecast in bitmap_copy_clear_tail() may lead * to out-of-bound access. To avoid that, both LE and BE variants of 64-bit * architectures are not using bitmap_copy_clear_tail(). */ #if BITS_PER_LONG == 64 void bitmap_from_arr32(unsigned long *bitmap, const u32 *buf, unsigned int nbits); void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap, unsigned int nbits); #else #define bitmap_from_arr32(bitmap, buf, nbits) \ bitmap_copy_clear_tail((unsigned long *) (bitmap), \ (const unsigned long *) (buf), (nbits)) #define bitmap_to_arr32(buf, bitmap, nbits) \ bitmap_copy_clear_tail((unsigned long *) (buf), \ (const unsigned long *) (bitmap), (nbits)) #endif /* * On 64-bit systems bitmaps are represented as u64 arrays internally. So, * the conversion is not needed when copying data from/to arrays of u64. */ #if BITS_PER_LONG == 32 void bitmap_from_arr64(unsigned long *bitmap, const u64 *buf, unsigned int nbits); void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits); #else #define bitmap_from_arr64(bitmap, buf, nbits) \ bitmap_copy_clear_tail((unsigned long *)(bitmap), (const unsigned long *)(buf), (nbits)) #define bitmap_to_arr64(buf, bitmap, nbits) \ bitmap_copy_clear_tail((unsigned long *)(buf), (const unsigned long *)(bitmap), (nbits)) #endif static __always_inline bool bitmap_and(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return (*dst = *src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits)) != 0; return __bitmap_and(dst, src1, src2, nbits); } static __always_inline void bitmap_or(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = *src1 | *src2; else __bitmap_or(dst, src1, src2, nbits); } static __always_inline void bitmap_xor(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = *src1 ^ *src2; else __bitmap_xor(dst, src1, src2, nbits); } static __always_inline bool bitmap_andnot(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return (*dst = *src1 & ~(*src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0; return __bitmap_andnot(dst, src1, src2, nbits); } static __always_inline void bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = ~(*src); else __bitmap_complement(dst, src, nbits); } #ifdef __LITTLE_ENDIAN #define BITMAP_MEM_ALIGNMENT 8 #else #define BITMAP_MEM_ALIGNMENT (8 * sizeof(unsigned long)) #endif #define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1) static __always_inline bool bitmap_equal(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); if (__builtin_constant_p(nbits & BITMAP_MEM_MASK) && IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT)) return !memcmp(src1, src2, nbits / 8); return __bitmap_equal(src1, src2, nbits); } /** * bitmap_or_equal - Check whether the or of two bitmaps is equal to a third * @src1: Pointer to bitmap 1 * @src2: Pointer to bitmap 2 will be or'ed with bitmap 1 * @src3: Pointer to bitmap 3. Compare to the result of *@src1 | *@src2 * @nbits: number of bits in each of these bitmaps * * Returns: True if (*@src1 | *@src2) == *@src3, false otherwise */ static __always_inline bool bitmap_or_equal(const unsigned long *src1, const unsigned long *src2, const unsigned long *src3, unsigned int nbits) { if (!small_const_nbits(nbits)) return __bitmap_or_equal(src1, src2, src3, nbits); return !(((*src1 | *src2) ^ *src3) & BITMAP_LAST_WORD_MASK(nbits)); } static __always_inline bool bitmap_intersects(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0; else return __bitmap_intersects(src1, src2, nbits); } static __always_inline bool bitmap_subset(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return ! ((*src1 & ~(*src2)) & BITMAP_LAST_WORD_MASK(nbits)); else return __bitmap_subset(src1, src2, nbits); } static __always_inline bool bitmap_empty(const unsigned long *src, unsigned nbits) { if (small_const_nbits(nbits)) return ! (*src & BITMAP_LAST_WORD_MASK(nbits)); return find_first_bit(src, nbits) == nbits; } static __always_inline bool bitmap_full(const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits)); return find_first_zero_bit(src, nbits) == nbits; } static __always_inline unsigned int bitmap_weight(const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits)); return __bitmap_weight(src, nbits); } static __always_inline unsigned long bitmap_weight_and(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return hweight_long(*src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits)); return __bitmap_weight_and(src1, src2, nbits); } static __always_inline unsigned long bitmap_weight_andnot(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return hweight_long(*src1 & ~(*src2) & BITMAP_LAST_WORD_MASK(nbits)); return __bitmap_weight_andnot(src1, src2, nbits); } static __always_inline void bitmap_set(unsigned long *map, unsigned int start, unsigned int nbits) { if (__builtin_constant_p(nbits) && nbits == 1) __set_bit(start, map); else if (small_const_nbits(start + nbits)) *map |= GENMASK(start + nbits - 1, start); else if (__builtin_constant_p(start & BITMAP_MEM_MASK) && IS_ALIGNED(start, BITMAP_MEM_ALIGNMENT) && __builtin_constant_p(nbits & BITMAP_MEM_MASK) && IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT)) memset((char *)map + start / 8, 0xff, nbits / 8); else __bitmap_set(map, start, nbits); } static __always_inline void bitmap_clear(unsigned long *map, unsigned int start, unsigned int nbits) { if (__builtin_constant_p(nbits) && nbits == 1) __clear_bit(start, map); else if (small_const_nbits(start + nbits)) *map &= ~GENMASK(start + nbits - 1, start); else if (__builtin_constant_p(start & BITMAP_MEM_MASK) && IS_ALIGNED(start, BITMAP_MEM_ALIGNMENT) && __builtin_constant_p(nbits & BITMAP_MEM_MASK) && IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT)) memset((char *)map + start / 8, 0, nbits / 8); else __bitmap_clear(map, start, nbits); } static __always_inline void bitmap_shift_right(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*src & BITMAP_LAST_WORD_MASK(nbits)) >> shift; else __bitmap_shift_right(dst, src, shift, nbits); } static __always_inline void bitmap_shift_left(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*src << shift) & BITMAP_LAST_WORD_MASK(nbits); else __bitmap_shift_left(dst, src, shift, nbits); } static __always_inline void bitmap_replace(unsigned long *dst, const unsigned long *old, const unsigned long *new, const unsigned long *mask, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*old & ~(*mask)) | (*new & *mask); else __bitmap_replace(dst, old, new, mask, nbits); } /** * bitmap_scatter - Scatter a bitmap according to the given mask * @dst: scattered bitmap * @src: gathered bitmap * @mask: mask representing bits to assign to in the scattered bitmap * @nbits: number of bits in each of these bitmaps * * Scatters bitmap with sequential bits according to the given @mask. * * Example: * If @src bitmap = 0x005a, with @mask = 0x1313, @dst will be 0x0302. * * Or in binary form * @src @mask @dst * 0000000001011010 0001001100010011 0000001100000010 * * (Bits 0, 1, 2, 3, 4, 5 are copied to the bits 0, 1, 4, 8, 9, 12) * * A more 'visual' description of the operation:: * * src: 0000000001011010 * |||||| * +------+||||| * | +----+|||| * | |+----+||| * | || +-+|| * | || | || * mask: ...v..vv...v..vv * ...0..11...0..10 * dst: 0000001100000010 * * A relationship exists between bitmap_scatter() and bitmap_gather(). * bitmap_gather() can be seen as the 'reverse' bitmap_scatter() operation. * See bitmap_scatter() for details related to this relationship. */ static __always_inline void bitmap_scatter(unsigned long *dst, const unsigned long *src, const unsigned long *mask, unsigned int nbits) { unsigned int n = 0; unsigned int bit; bitmap_zero(dst, nbits); for_each_set_bit(bit, mask, nbits) __assign_bit(bit, dst, test_bit(n++, src)); } /** * bitmap_gather - Gather a bitmap according to given mask * @dst: gathered bitmap * @src: scattered bitmap * @mask: mask representing bits to extract from in the scattered bitmap * @nbits: number of bits in each of these bitmaps * * Gathers bitmap with sparse bits according to the given @mask. * * Example: * If @src bitmap = 0x0302, with @mask = 0x1313, @dst will be 0x001a. * * Or in binary form * @src @mask @dst * 0000001100000010 0001001100010011 0000000000011010 * * (Bits 0, 1, 4, 8, 9, 12 are copied to the bits 0, 1, 2, 3, 4, 5) * * A more 'visual' description of the operation:: * * mask: ...v..vv...v..vv * src: 0000001100000010 * ^ ^^ ^ 0 * | || | 10 * | || > 010 * | |+--> 1010 * | +--> 11010 * +----> 011010 * dst: 0000000000011010 * * A relationship exists between bitmap_gather() and bitmap_scatter(). See * bitmap_scatter() for the bitmap scatter detailed operations. * Suppose scattered computed using bitmap_scatter(scattered, src, mask, n). * The operation bitmap_gather(result, scattered, mask, n) leads to a result * equal or equivalent to src. * * The result can be 'equivalent' because bitmap_scatter() and bitmap_gather() * are not bijective. * The result and src values are equivalent in that sense that a call to * bitmap_scatter(res, src, mask, n) and a call to * bitmap_scatter(res, result, mask, n) will lead to the same res value. */ static __always_inline void bitmap_gather(unsigned long *dst, const unsigned long *src, const unsigned long *mask, unsigned int nbits) { unsigned int n = 0; unsigned int bit; bitmap_zero(dst, nbits); for_each_set_bit(bit, mask, nbits) __assign_bit(n++, dst, test_bit(bit, src)); } static __always_inline void bitmap_next_set_region(unsigned long *bitmap, unsigned int *rs, unsigned int *re, unsigned int end) { *rs = find_next_bit(bitmap, end, *rs); *re = find_next_zero_bit(bitmap, end, *rs + 1); } /** * bitmap_release_region - release allocated bitmap region * @bitmap: array of unsigned longs corresponding to the bitmap * @pos: beginning of bit region to release * @order: region size (log base 2 of number of bits) to release * * This is the complement to __bitmap_find_free_region() and releases * the found region (by clearing it in the bitmap). */ static __always_inline void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order) { bitmap_clear(bitmap, pos, BIT(order)); } /** * bitmap_allocate_region - allocate bitmap region * @bitmap: array of unsigned longs corresponding to the bitmap * @pos: beginning of bit region to allocate * @order: region size (log base 2 of number of bits) to allocate * * Allocate (set bits in) a specified region of a bitmap. * * Returns: 0 on success, or %-EBUSY if specified region wasn't * free (not all bits were zero). */ static __always_inline int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order) { unsigned int len = BIT(order); if (find_next_bit(bitmap, pos + len, pos) < pos + len) return -EBUSY; bitmap_set(bitmap, pos, len); return 0; } /** * bitmap_find_free_region - find a contiguous aligned mem region * @bitmap: array of unsigned longs corresponding to the bitmap * @bits: number of bits in the bitmap * @order: region size (log base 2 of number of bits) to find * * Find a region of free (zero) bits in a @bitmap of @bits bits and * allocate them (set them to one). Only consider regions of length * a power (@order) of two, aligned to that power of two, which * makes the search algorithm much faster. * * Returns: the bit offset in bitmap of the allocated region, * or -errno on failure. */ static __always_inline int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order) { unsigned int pos, end; /* scans bitmap by regions of size order */ for (pos = 0; (end = pos + BIT(order)) <= bits; pos = end) { if (!bitmap_allocate_region(bitmap, pos, order)) return pos; } return -ENOMEM; } /** * BITMAP_FROM_U64() - Represent u64 value in the format suitable for bitmap. * @n: u64 value * * Linux bitmaps are internally arrays of unsigned longs, i.e. 32-bit * integers in 32-bit environment, and 64-bit integers in 64-bit one. * * There are four combinations of endianness and length of the word in linux * ABIs: LE64, BE64, LE32 and BE32. * * On 64-bit kernels 64-bit LE and BE numbers are naturally ordered in * bitmaps and therefore don't require any special handling. * * On 32-bit kernels 32-bit LE ABI orders lo word of 64-bit number in memory * prior to hi, and 32-bit BE orders hi word prior to lo. The bitmap on the * other hand is represented as an array of 32-bit words and the position of * bit N may therefore be calculated as: word #(N/32) and bit #(N%32) in that * word. For example, bit #42 is located at 10th position of 2nd word. * It matches 32-bit LE ABI, and we can simply let the compiler store 64-bit * values in memory as it usually does. But for BE we need to swap hi and lo * words manually. * * With all that, the macro BITMAP_FROM_U64() does explicit reordering of hi and * lo parts of u64. For LE32 it does nothing, and for BE environment it swaps * hi and lo words, as is expected by bitmap. */ #if __BITS_PER_LONG == 64 #define BITMAP_FROM_U64(n) (n) #else #define BITMAP_FROM_U64(n) ((unsigned long) ((u64)(n) & ULONG_MAX)), \ ((unsigned long) ((u64)(n) >> 32)) #endif /** * bitmap_from_u64 - Check and swap words within u64. * @mask: source bitmap * @dst: destination bitmap * * In 32-bit Big Endian kernel, when using ``(u32 *)(&val)[*]`` * to read u64 mask, we will get the wrong word. * That is ``(u32 *)(&val)[0]`` gets the upper 32 bits, * but we expect the lower 32-bits of u64. */ static __always_inline void bitmap_from_u64(unsigned long *dst, u64 mask) { bitmap_from_arr64(dst, &mask, 64); } /** * bitmap_read - read a value of n-bits from the memory region * @map: address to the bitmap memory region * @start: bit offset of the n-bit value * @nbits: size of value in bits, nonzero, up to BITS_PER_LONG * * Returns: value of @nbits bits located at the @start bit offset within the * @map memory region. For @nbits = 0 and @nbits > BITS_PER_LONG the return * value is undefined. */ static __always_inline unsigned long bitmap_read(const unsigned long *map, unsigned long start, unsigned long nbits) { size_t index = BIT_WORD(start); unsigned long offset = start % BITS_PER_LONG; unsigned long space = BITS_PER_LONG - offset; unsigned long value_low, value_high; if (unlikely(!nbits || nbits > BITS_PER_LONG)) return 0; if (space >= nbits) return (map[index] >> offset) & BITMAP_LAST_WORD_MASK(nbits); value_low = map[index] & BITMAP_FIRST_WORD_MASK(start); value_high = map[index + 1] & BITMAP_LAST_WORD_MASK(start + nbits); return (value_low >> offset) | (value_high << space); } /** * bitmap_write - write n-bit value within a memory region * @map: address to the bitmap memory region * @value: value to write, clamped to nbits * @start: bit offset of the n-bit value * @nbits: size of value in bits, nonzero, up to BITS_PER_LONG. * * bitmap_write() behaves as-if implemented as @nbits calls of __assign_bit(), * i.e. bits beyond @nbits are ignored: * * for (bit = 0; bit < nbits; bit++) * __assign_bit(start + bit, bitmap, val & BIT(bit)); * * For @nbits == 0 and @nbits > BITS_PER_LONG no writes are performed. */ static __always_inline void bitmap_write(unsigned long *map, unsigned long value, unsigned long start, unsigned long nbits) { size_t index; unsigned long offset; unsigned long space; unsigned long mask; bool fit; if (unlikely(!nbits || nbits > BITS_PER_LONG)) return; mask = BITMAP_LAST_WORD_MASK(nbits); value &= mask; offset = start % BITS_PER_LONG; space = BITS_PER_LONG - offset; fit = space >= nbits; index = BIT_WORD(start); map[index] &= (fit ? (~(mask << offset)) : ~BITMAP_FIRST_WORD_MASK(start)); map[index] |= value << offset; if (fit) return; map[index + 1] &= BITMAP_FIRST_WORD_MASK(start + nbits); map[index + 1] |= (value >> space); } #define bitmap_get_value8(map, start) \ bitmap_read(map, start, BITS_PER_BYTE) #define bitmap_set_value8(map, value, start) \ bitmap_write(map, value, start, BITS_PER_BYTE) #endif /* __ASSEMBLY__ */ #endif /* __LINUX_BITMAP_H */ |
| 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_INETDEVICE_H #define _LINUX_INETDEVICE_H #ifdef __KERNEL__ #include <linux/bitmap.h> #include <linux/if.h> #include <linux/ip.h> #include <linux/netdevice.h> #include <linux/rcupdate.h> #include <linux/timer.h> #include <linux/sysctl.h> #include <linux/rtnetlink.h> #include <linux/refcount.h> struct ipv4_devconf { void *sysctl; int data[IPV4_DEVCONF_MAX]; DECLARE_BITMAP(state, IPV4_DEVCONF_MAX); }; #define MC_HASH_SZ_LOG 9 struct in_device { struct net_device *dev; netdevice_tracker dev_tracker; refcount_t refcnt; int dead; struct in_ifaddr __rcu *ifa_list;/* IP ifaddr chain */ struct ip_mc_list __rcu *mc_list; /* IP multicast filter chain */ struct ip_mc_list __rcu * __rcu *mc_hash; int mc_count; /* Number of installed mcasts */ spinlock_t mc_tomb_lock; struct ip_mc_list *mc_tomb; unsigned long mr_v1_seen; unsigned long mr_v2_seen; unsigned long mr_maxdelay; unsigned long mr_qi; /* Query Interval */ unsigned long mr_qri; /* Query Response Interval */ unsigned char mr_qrv; /* Query Robustness Variable */ unsigned char mr_gq_running; u32 mr_ifc_count; struct timer_list mr_gq_timer; /* general query timer */ struct timer_list mr_ifc_timer; /* interface change timer */ struct neigh_parms *arp_parms; struct ipv4_devconf cnf; struct rcu_head rcu_head; }; #define IPV4_DEVCONF(cnf, attr) ((cnf).data[IPV4_DEVCONF_ ## attr - 1]) #define IPV4_DEVCONF_RO(cnf, attr) READ_ONCE(IPV4_DEVCONF(cnf, attr)) #define IPV4_DEVCONF_ALL(net, attr) \ IPV4_DEVCONF((*(net)->ipv4.devconf_all), attr) #define IPV4_DEVCONF_ALL_RO(net, attr) READ_ONCE(IPV4_DEVCONF_ALL(net, attr)) static inline int ipv4_devconf_get(const struct in_device *in_dev, int index) { index--; return READ_ONCE(in_dev->cnf.data[index]); } static inline void ipv4_devconf_set(struct in_device *in_dev, int index, int val) { index--; set_bit(index, in_dev->cnf.state); WRITE_ONCE(in_dev->cnf.data[index], val); } static inline void ipv4_devconf_setall(struct in_device *in_dev) { bitmap_fill(in_dev->cnf.state, IPV4_DEVCONF_MAX); } #define IN_DEV_CONF_GET(in_dev, attr) \ ipv4_devconf_get((in_dev), IPV4_DEVCONF_ ## attr) #define IN_DEV_CONF_SET(in_dev, attr, val) \ ipv4_devconf_set((in_dev), IPV4_DEVCONF_ ## attr, (val)) #define IN_DEV_ANDCONF(in_dev, attr) \ (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), attr) && \ IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_NET_ORCONF(in_dev, net, attr) \ (IPV4_DEVCONF_ALL_RO(net, attr) || \ IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_ORCONF(in_dev, attr) \ IN_DEV_NET_ORCONF(in_dev, dev_net(in_dev->dev), attr) #define IN_DEV_MAXCONF(in_dev, attr) \ (max(IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), attr), \ IN_DEV_CONF_GET((in_dev), attr))) #define IN_DEV_FORWARD(in_dev) IN_DEV_CONF_GET((in_dev), FORWARDING) #define IN_DEV_MFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), MC_FORWARDING) #define IN_DEV_BFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), BC_FORWARDING) #define IN_DEV_RPFILTER(in_dev) IN_DEV_MAXCONF((in_dev), RP_FILTER) #define IN_DEV_SRC_VMARK(in_dev) IN_DEV_ORCONF((in_dev), SRC_VMARK) #define IN_DEV_SOURCE_ROUTE(in_dev) IN_DEV_ANDCONF((in_dev), \ ACCEPT_SOURCE_ROUTE) #define IN_DEV_ACCEPT_LOCAL(in_dev) IN_DEV_ORCONF((in_dev), ACCEPT_LOCAL) #define IN_DEV_BOOTP_RELAY(in_dev) IN_DEV_ANDCONF((in_dev), BOOTP_RELAY) #define IN_DEV_LOG_MARTIANS(in_dev) IN_DEV_ORCONF((in_dev), LOG_MARTIANS) #define IN_DEV_PROXY_ARP(in_dev) IN_DEV_ORCONF((in_dev), PROXY_ARP) #define IN_DEV_PROXY_ARP_PVLAN(in_dev) IN_DEV_ORCONF((in_dev), PROXY_ARP_PVLAN) #define IN_DEV_SHARED_MEDIA(in_dev) IN_DEV_ORCONF((in_dev), SHARED_MEDIA) #define IN_DEV_TX_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), SEND_REDIRECTS) #define IN_DEV_SEC_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), \ SECURE_REDIRECTS) #define IN_DEV_IDTAG(in_dev) IN_DEV_CONF_GET(in_dev, TAG) #define IN_DEV_MEDIUM_ID(in_dev) IN_DEV_CONF_GET(in_dev, MEDIUM_ID) #define IN_DEV_PROMOTE_SECONDARIES(in_dev) \ IN_DEV_ORCONF((in_dev), \ PROMOTE_SECONDARIES) #define IN_DEV_ROUTE_LOCALNET(in_dev) IN_DEV_ORCONF(in_dev, ROUTE_LOCALNET) #define IN_DEV_NET_ROUTE_LOCALNET(in_dev, net) \ IN_DEV_NET_ORCONF(in_dev, net, ROUTE_LOCALNET) #define IN_DEV_RX_REDIRECTS(in_dev) \ ((IN_DEV_FORWARD(in_dev) && \ IN_DEV_ANDCONF((in_dev), ACCEPT_REDIRECTS)) \ || (!IN_DEV_FORWARD(in_dev) && \ IN_DEV_ORCONF((in_dev), ACCEPT_REDIRECTS))) #define IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) \ IN_DEV_ORCONF((in_dev), IGNORE_ROUTES_WITH_LINKDOWN) #define IN_DEV_ARPFILTER(in_dev) IN_DEV_ORCONF((in_dev), ARPFILTER) #define IN_DEV_ARP_ACCEPT(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ACCEPT) #define IN_DEV_ARP_ANNOUNCE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ANNOUNCE) #define IN_DEV_ARP_IGNORE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_IGNORE) #define IN_DEV_ARP_NOTIFY(in_dev) IN_DEV_MAXCONF((in_dev), ARP_NOTIFY) #define IN_DEV_ARP_EVICT_NOCARRIER(in_dev) IN_DEV_ANDCONF((in_dev), \ ARP_EVICT_NOCARRIER) struct in_ifaddr { struct hlist_node addr_lst; struct in_ifaddr __rcu *ifa_next; struct in_device *ifa_dev; struct rcu_head rcu_head; __be32 ifa_local; __be32 ifa_address; __be32 ifa_mask; __u32 ifa_rt_priority; __be32 ifa_broadcast; unsigned char ifa_scope; unsigned char ifa_prefixlen; unsigned char ifa_proto; __u32 ifa_flags; char ifa_label[IFNAMSIZ]; /* In seconds, relative to tstamp. Expiry is at tstamp + HZ * lft. */ __u32 ifa_valid_lft; __u32 ifa_preferred_lft; unsigned long ifa_cstamp; /* created timestamp */ unsigned long ifa_tstamp; /* updated timestamp */ }; struct in_validator_info { __be32 ivi_addr; struct in_device *ivi_dev; struct netlink_ext_ack *extack; }; int register_inetaddr_notifier(struct notifier_block *nb); int unregister_inetaddr_notifier(struct notifier_block *nb); int register_inetaddr_validator_notifier(struct notifier_block *nb); int unregister_inetaddr_validator_notifier(struct notifier_block *nb); void inet_netconf_notify_devconf(struct net *net, int event, int type, int ifindex, struct ipv4_devconf *devconf); struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref); static inline struct net_device *ip_dev_find(struct net *net, __be32 addr) { return __ip_dev_find(net, addr, true); } int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b); int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *); #ifdef CONFIG_INET int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size); #else static inline int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size) { return 0; } #endif void devinet_init(void); struct in_device *inetdev_by_index(struct net *, int); __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope); __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst, __be32 local, int scope); struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask); struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr); static inline bool inet_ifa_match(__be32 addr, const struct in_ifaddr *ifa) { return !((addr^ifa->ifa_address)&ifa->ifa_mask); } /* * Check if a mask is acceptable. */ static __inline__ bool bad_mask(__be32 mask, __be32 addr) { __u32 hmask; if (addr & (mask = ~mask)) return true; hmask = ntohl(mask); if (hmask & (hmask+1)) return true; return false; } #define in_dev_for_each_ifa_rtnl(ifa, in_dev) \ for (ifa = rtnl_dereference((in_dev)->ifa_list); ifa; \ ifa = rtnl_dereference(ifa->ifa_next)) #define in_dev_for_each_ifa_rtnl_net(net, ifa, in_dev) \ for (ifa = rtnl_net_dereference(net, (in_dev)->ifa_list); ifa; \ ifa = rtnl_net_dereference(net, ifa->ifa_next)) #define in_dev_for_each_ifa_rcu(ifa, in_dev) \ for (ifa = rcu_dereference((in_dev)->ifa_list); ifa; \ ifa = rcu_dereference(ifa->ifa_next)) static inline struct in_device *__in_dev_get_rcu(const struct net_device *dev) { return rcu_dereference(dev->ip_ptr); } static inline struct in_device *in_dev_get(const struct net_device *dev) { struct in_device *in_dev; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (in_dev) refcount_inc(&in_dev->refcnt); rcu_read_unlock(); return in_dev; } static inline struct in_device *__in_dev_get_rtnl(const struct net_device *dev) { return rtnl_dereference(dev->ip_ptr); } static inline struct in_device *__in_dev_get_rtnl_net(const struct net_device *dev) { return rtnl_net_dereference(dev_net(dev), dev->ip_ptr); } /* called with rcu_read_lock or rtnl held */ static inline bool ip_ignore_linkdown(const struct net_device *dev) { struct in_device *in_dev; bool rc = false; in_dev = rcu_dereference_rtnl(dev->ip_ptr); if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev)) rc = true; return rc; } static inline struct neigh_parms *__in_dev_arp_parms_get_rcu(const struct net_device *dev) { struct in_device *in_dev = __in_dev_get_rcu(dev); return in_dev ? in_dev->arp_parms : NULL; } void in_dev_finish_destroy(struct in_device *idev); static inline void in_dev_put(struct in_device *idev) { if (refcount_dec_and_test(&idev->refcnt)) in_dev_finish_destroy(idev); } #define __in_dev_put(idev) refcount_dec(&(idev)->refcnt) #define in_dev_hold(idev) refcount_inc(&(idev)->refcnt) #endif /* __KERNEL__ */ static __inline__ __be32 inet_make_mask(int logmask) { if (logmask) return htonl(~((1U<<(32-logmask))-1)); return 0; } static __inline__ int inet_mask_len(__be32 mask) { __u32 hmask = ntohl(mask); if (!hmask) return 0; return 32 - ffz(~hmask); } #endif /* _LINUX_INETDEVICE_H */ |
| 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2011 IBM Corporation * * Author: * Mimi Zohar <zohar@us.ibm.com> */ #include <linux/module.h> #include <linux/init.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/xattr.h> #include <linux/magic.h> #include <linux/ima.h> #include <linux/evm.h> #include <linux/fsverity.h> #include <keys/system_keyring.h> #include <uapi/linux/fsverity.h> #include "ima.h" #ifdef CONFIG_IMA_APPRAISE_BOOTPARAM static char *ima_appraise_cmdline_default __initdata; core_param(ima_appraise, ima_appraise_cmdline_default, charp, 0); void __init ima_appraise_parse_cmdline(void) { const char *str = ima_appraise_cmdline_default; bool sb_state = arch_ima_get_secureboot(); int appraisal_state = ima_appraise; if (!str) return; if (strncmp(str, "off", 3) == 0) appraisal_state = 0; else if (strncmp(str, "log", 3) == 0) appraisal_state = IMA_APPRAISE_LOG; else if (strncmp(str, "fix", 3) == 0) appraisal_state = IMA_APPRAISE_FIX; else if (strncmp(str, "enforce", 7) == 0) appraisal_state = IMA_APPRAISE_ENFORCE; else pr_err("invalid \"%s\" appraise option", str); /* If appraisal state was changed, but secure boot is enabled, * keep its default */ if (sb_state) { if (!(appraisal_state & IMA_APPRAISE_ENFORCE)) pr_info("Secure boot enabled: ignoring ima_appraise=%s option", str); } else { ima_appraise = appraisal_state; } } #endif /* * is_ima_appraise_enabled - return appraise status * * Only return enabled, if not in ima_appraise="fix" or "log" modes. */ bool is_ima_appraise_enabled(void) { return ima_appraise & IMA_APPRAISE_ENFORCE; } /* * ima_must_appraise - set appraise flag * * Return 1 to appraise or hash */ int ima_must_appraise(struct mnt_idmap *idmap, struct inode *inode, int mask, enum ima_hooks func) { struct lsm_prop prop; if (!ima_appraise) return 0; security_current_getlsmprop_subj(&prop); return ima_match_policy(idmap, inode, current_cred(), &prop, func, mask, IMA_APPRAISE | IMA_HASH, NULL, NULL, NULL, NULL); } static int ima_fix_xattr(struct dentry *dentry, struct ima_iint_cache *iint) { int rc, offset; u8 algo = iint->ima_hash->algo; if (algo <= HASH_ALGO_SHA1) { offset = 1; iint->ima_hash->xattr.sha1.type = IMA_XATTR_DIGEST; } else { offset = 0; iint->ima_hash->xattr.ng.type = IMA_XATTR_DIGEST_NG; iint->ima_hash->xattr.ng.algo = algo; } rc = __vfs_setxattr_noperm(&nop_mnt_idmap, dentry, XATTR_NAME_IMA, &iint->ima_hash->xattr.data[offset], (sizeof(iint->ima_hash->xattr) - offset) + iint->ima_hash->length, 0); return rc; } /* Return specific func appraised cached result */ enum integrity_status ima_get_cache_status(struct ima_iint_cache *iint, enum ima_hooks func) { switch (func) { case MMAP_CHECK: case MMAP_CHECK_REQPROT: return iint->ima_mmap_status; case BPRM_CHECK: return iint->ima_bprm_status; case CREDS_CHECK: return iint->ima_creds_status; case FILE_CHECK: case POST_SETATTR: return iint->ima_file_status; case MODULE_CHECK ... MAX_CHECK - 1: default: return iint->ima_read_status; } } static void ima_set_cache_status(struct ima_iint_cache *iint, enum ima_hooks func, enum integrity_status status) { switch (func) { case MMAP_CHECK: case MMAP_CHECK_REQPROT: iint->ima_mmap_status = status; break; case BPRM_CHECK: iint->ima_bprm_status = status; break; case CREDS_CHECK: iint->ima_creds_status = status; break; case FILE_CHECK: case POST_SETATTR: iint->ima_file_status = status; break; case MODULE_CHECK ... MAX_CHECK - 1: default: iint->ima_read_status = status; break; } } static void ima_cache_flags(struct ima_iint_cache *iint, enum ima_hooks func) { switch (func) { case MMAP_CHECK: case MMAP_CHECK_REQPROT: iint->flags |= (IMA_MMAP_APPRAISED | IMA_APPRAISED); break; case BPRM_CHECK: iint->flags |= (IMA_BPRM_APPRAISED | IMA_APPRAISED); break; case CREDS_CHECK: iint->flags |= (IMA_CREDS_APPRAISED | IMA_APPRAISED); break; case FILE_CHECK: case POST_SETATTR: iint->flags |= (IMA_FILE_APPRAISED | IMA_APPRAISED); break; case MODULE_CHECK ... MAX_CHECK - 1: default: iint->flags |= (IMA_READ_APPRAISED | IMA_APPRAISED); break; } } enum hash_algo ima_get_hash_algo(const struct evm_ima_xattr_data *xattr_value, int xattr_len) { struct signature_v2_hdr *sig; enum hash_algo ret; if (!xattr_value || xattr_len < 2) /* return default hash algo */ return ima_hash_algo; switch (xattr_value->type) { case IMA_VERITY_DIGSIG: sig = (typeof(sig))xattr_value; if (sig->version != 3 || xattr_len <= sizeof(*sig) || sig->hash_algo >= HASH_ALGO__LAST) return ima_hash_algo; return sig->hash_algo; case EVM_IMA_XATTR_DIGSIG: sig = (typeof(sig))xattr_value; if (sig->version != 2 || xattr_len <= sizeof(*sig) || sig->hash_algo >= HASH_ALGO__LAST) return ima_hash_algo; return sig->hash_algo; case IMA_XATTR_DIGEST_NG: /* first byte contains algorithm id */ ret = xattr_value->data[0]; if (ret < HASH_ALGO__LAST) return ret; break; case IMA_XATTR_DIGEST: /* this is for backward compatibility */ if (xattr_len == 21) { unsigned int zero = 0; if (!memcmp(&xattr_value->data[16], &zero, 4)) return HASH_ALGO_MD5; else return HASH_ALGO_SHA1; } else if (xattr_len == 17) return HASH_ALGO_MD5; break; } /* return default hash algo */ return ima_hash_algo; } int ima_read_xattr(struct dentry *dentry, struct evm_ima_xattr_data **xattr_value, int xattr_len) { int ret; ret = vfs_getxattr_alloc(&nop_mnt_idmap, dentry, XATTR_NAME_IMA, (char **)xattr_value, xattr_len, GFP_NOFS); if (ret == -EOPNOTSUPP) ret = 0; return ret; } /* * calc_file_id_hash - calculate the hash of the ima_file_id struct data * @type: xattr type [enum evm_ima_xattr_type] * @algo: hash algorithm [enum hash_algo] * @digest: pointer to the digest to be hashed * @hash: (out) pointer to the hash * * IMA signature version 3 disambiguates the data that is signed by * indirectly signing the hash of the ima_file_id structure data. * * Signing the ima_file_id struct is currently only supported for * IMA_VERITY_DIGSIG type xattrs. * * Return 0 on success, error code otherwise. */ static int calc_file_id_hash(enum evm_ima_xattr_type type, enum hash_algo algo, const u8 *digest, struct ima_digest_data *hash) { struct ima_file_id file_id = { .hash_type = IMA_VERITY_DIGSIG, .hash_algorithm = algo}; unsigned int unused = HASH_MAX_DIGESTSIZE - hash_digest_size[algo]; if (type != IMA_VERITY_DIGSIG) return -EINVAL; memcpy(file_id.hash, digest, hash_digest_size[algo]); hash->algo = algo; hash->length = hash_digest_size[algo]; return ima_calc_buffer_hash(&file_id, sizeof(file_id) - unused, hash); } /* * xattr_verify - verify xattr digest or signature * * Verify whether the hash or signature matches the file contents. * * Return 0 on success, error code otherwise. */ static int xattr_verify(enum ima_hooks func, struct ima_iint_cache *iint, struct evm_ima_xattr_data *xattr_value, int xattr_len, enum integrity_status *status, const char **cause) { struct ima_max_digest_data hash; struct signature_v2_hdr *sig; int rc = -EINVAL, hash_start = 0; int mask; switch (xattr_value->type) { case IMA_XATTR_DIGEST_NG: /* first byte contains algorithm id */ hash_start = 1; fallthrough; case IMA_XATTR_DIGEST: if (*status != INTEGRITY_PASS_IMMUTABLE) { if (iint->flags & IMA_DIGSIG_REQUIRED) { if (iint->flags & IMA_VERITY_REQUIRED) *cause = "verity-signature-required"; else *cause = "IMA-signature-required"; *status = INTEGRITY_FAIL; break; } clear_bit(IMA_DIGSIG, &iint->atomic_flags); } else { set_bit(IMA_DIGSIG, &iint->atomic_flags); } if (xattr_len - sizeof(xattr_value->type) - hash_start >= iint->ima_hash->length) /* * xattr length may be longer. md5 hash in previous * version occupied 20 bytes in xattr, instead of 16 */ rc = memcmp(&xattr_value->data[hash_start], iint->ima_hash->digest, iint->ima_hash->length); else rc = -EINVAL; if (rc) { *cause = "invalid-hash"; *status = INTEGRITY_FAIL; break; } *status = INTEGRITY_PASS; break; case EVM_IMA_XATTR_DIGSIG: set_bit(IMA_DIGSIG, &iint->atomic_flags); mask = IMA_DIGSIG_REQUIRED | IMA_VERITY_REQUIRED; if ((iint->flags & mask) == mask) { *cause = "verity-signature-required"; *status = INTEGRITY_FAIL; break; } sig = (typeof(sig))xattr_value; if (sig->version >= 3) { *cause = "invalid-signature-version"; *status = INTEGRITY_FAIL; break; } rc = integrity_digsig_verify(INTEGRITY_KEYRING_IMA, (const char *)xattr_value, xattr_len, iint->ima_hash->digest, iint->ima_hash->length); if (rc == -EOPNOTSUPP) { *status = INTEGRITY_UNKNOWN; break; } if (IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING) && rc && func == KEXEC_KERNEL_CHECK) rc = integrity_digsig_verify(INTEGRITY_KEYRING_PLATFORM, (const char *)xattr_value, xattr_len, iint->ima_hash->digest, iint->ima_hash->length); if (rc) { *cause = "invalid-signature"; *status = INTEGRITY_FAIL; } else { *status = INTEGRITY_PASS; } break; case IMA_VERITY_DIGSIG: set_bit(IMA_DIGSIG, &iint->atomic_flags); if (iint->flags & IMA_DIGSIG_REQUIRED) { if (!(iint->flags & IMA_VERITY_REQUIRED)) { *cause = "IMA-signature-required"; *status = INTEGRITY_FAIL; break; } } sig = (typeof(sig))xattr_value; if (sig->version != 3) { *cause = "invalid-signature-version"; *status = INTEGRITY_FAIL; break; } rc = calc_file_id_hash(IMA_VERITY_DIGSIG, iint->ima_hash->algo, iint->ima_hash->digest, container_of(&hash.hdr, struct ima_digest_data, hdr)); if (rc) { *cause = "sigv3-hashing-error"; *status = INTEGRITY_FAIL; break; } rc = integrity_digsig_verify(INTEGRITY_KEYRING_IMA, (const char *)xattr_value, xattr_len, hash.digest, hash.hdr.length); if (rc) { *cause = "invalid-verity-signature"; *status = INTEGRITY_FAIL; } else { *status = INTEGRITY_PASS; } break; default: *status = INTEGRITY_UNKNOWN; *cause = "unknown-ima-data"; break; } return rc; } /* * modsig_verify - verify modsig signature * * Verify whether the signature matches the file contents. * * Return 0 on success, error code otherwise. */ static int modsig_verify(enum ima_hooks func, const struct modsig *modsig, enum integrity_status *status, const char **cause) { int rc; rc = integrity_modsig_verify(INTEGRITY_KEYRING_IMA, modsig); if (IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING) && rc && func == KEXEC_KERNEL_CHECK) rc = integrity_modsig_verify(INTEGRITY_KEYRING_PLATFORM, modsig); if (rc) { *cause = "invalid-signature"; *status = INTEGRITY_FAIL; } else { *status = INTEGRITY_PASS; } return rc; } /* * ima_check_blacklist - determine if the binary is blacklisted. * * Add the hash of the blacklisted binary to the measurement list, based * on policy. * * Returns -EPERM if the hash is blacklisted. */ int ima_check_blacklist(struct ima_iint_cache *iint, const struct modsig *modsig, int pcr) { enum hash_algo hash_algo; const u8 *digest = NULL; u32 digestsize = 0; int rc = 0; if (!(iint->flags & IMA_CHECK_BLACKLIST)) return 0; if (iint->flags & IMA_MODSIG_ALLOWED && modsig) { ima_get_modsig_digest(modsig, &hash_algo, &digest, &digestsize); rc = is_binary_blacklisted(digest, digestsize); } else if (iint->flags & IMA_DIGSIG_REQUIRED && iint->ima_hash) rc = is_binary_blacklisted(iint->ima_hash->digest, iint->ima_hash->length); if ((rc == -EPERM) && (iint->flags & IMA_MEASURE)) process_buffer_measurement(&nop_mnt_idmap, NULL, digest, digestsize, "blacklisted-hash", NONE, pcr, NULL, false, NULL, 0); return rc; } /* * ima_appraise_measurement - appraise file measurement * * Call evm_verifyxattr() to verify the integrity of 'security.ima'. * Assuming success, compare the xattr hash with the collected measurement. * * Return 0 on success, error code otherwise */ int ima_appraise_measurement(enum ima_hooks func, struct ima_iint_cache *iint, struct file *file, const unsigned char *filename, struct evm_ima_xattr_data *xattr_value, int xattr_len, const struct modsig *modsig) { static const char op[] = "appraise_data"; const char *cause = "unknown"; struct dentry *dentry = file_dentry(file); struct inode *inode = d_backing_inode(dentry); enum integrity_status status = INTEGRITY_UNKNOWN; int rc = xattr_len; bool try_modsig = iint->flags & IMA_MODSIG_ALLOWED && modsig; /* If not appraising a modsig, we need an xattr. */ if (!(inode->i_opflags & IOP_XATTR) && !try_modsig) return INTEGRITY_UNKNOWN; /* If reading the xattr failed and there's no modsig, error out. */ if (rc <= 0 && !try_modsig) { if (rc && rc != -ENODATA) goto out; if (iint->flags & IMA_DIGSIG_REQUIRED) { if (iint->flags & IMA_VERITY_REQUIRED) cause = "verity-signature-required"; else cause = "IMA-signature-required"; } else { cause = "missing-hash"; } status = INTEGRITY_NOLABEL; if (file->f_mode & FMODE_CREATED) iint->flags |= IMA_NEW_FILE; if ((iint->flags & IMA_NEW_FILE) && (!(iint->flags & IMA_DIGSIG_REQUIRED) || (inode->i_size == 0))) status = INTEGRITY_PASS; goto out; } status = evm_verifyxattr(dentry, XATTR_NAME_IMA, xattr_value, rc < 0 ? 0 : rc); switch (status) { case INTEGRITY_PASS: case INTEGRITY_PASS_IMMUTABLE: case INTEGRITY_UNKNOWN: break; case INTEGRITY_NOXATTRS: /* No EVM protected xattrs. */ /* It's fine not to have xattrs when using a modsig. */ if (try_modsig) break; fallthrough; case INTEGRITY_NOLABEL: /* No security.evm xattr. */ cause = "missing-HMAC"; goto out; case INTEGRITY_FAIL_IMMUTABLE: set_bit(IMA_DIGSIG, &iint->atomic_flags); cause = "invalid-fail-immutable"; goto out; case INTEGRITY_FAIL: /* Invalid HMAC/signature. */ cause = "invalid-HMAC"; goto out; default: WARN_ONCE(true, "Unexpected integrity status %d\n", status); } if (xattr_value) rc = xattr_verify(func, iint, xattr_value, xattr_len, &status, &cause); /* * If we have a modsig and either no imasig or the imasig's key isn't * known, then try verifying the modsig. */ if (try_modsig && (!xattr_value || xattr_value->type == IMA_XATTR_DIGEST_NG || rc == -ENOKEY)) rc = modsig_verify(func, modsig, &status, &cause); out: /* * File signatures on some filesystems can not be properly verified. * When such filesystems are mounted by an untrusted mounter or on a * system not willing to accept such a risk, fail the file signature * verification. */ if ((inode->i_sb->s_iflags & SB_I_IMA_UNVERIFIABLE_SIGNATURE) && ((inode->i_sb->s_iflags & SB_I_UNTRUSTED_MOUNTER) || (iint->flags & IMA_FAIL_UNVERIFIABLE_SIGS))) { status = INTEGRITY_FAIL; cause = "unverifiable-signature"; integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, filename, op, cause, rc, 0); } else if (status != INTEGRITY_PASS) { /* Fix mode, but don't replace file signatures. */ if ((ima_appraise & IMA_APPRAISE_FIX) && !try_modsig && (!xattr_value || xattr_value->type != EVM_IMA_XATTR_DIGSIG)) { if (!ima_fix_xattr(dentry, iint)) status = INTEGRITY_PASS; } /* * Permit new files with file/EVM portable signatures, but * without data. */ if (inode->i_size == 0 && iint->flags & IMA_NEW_FILE && test_bit(IMA_DIGSIG, &iint->atomic_flags)) { status = INTEGRITY_PASS; } integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, filename, op, cause, rc, 0); } else { ima_cache_flags(iint, func); } ima_set_cache_status(iint, func, status); return status; } /* * ima_update_xattr - update 'security.ima' hash value */ void ima_update_xattr(struct ima_iint_cache *iint, struct file *file) { struct dentry *dentry = file_dentry(file); int rc = 0; /* do not collect and update hash for digital signatures */ if (test_bit(IMA_DIGSIG, &iint->atomic_flags)) return; if ((iint->ima_file_status != INTEGRITY_PASS) && !(iint->flags & IMA_HASH)) return; rc = ima_collect_measurement(iint, file, NULL, 0, ima_hash_algo, NULL); if (rc < 0) return; inode_lock(file_inode(file)); ima_fix_xattr(dentry, iint); inode_unlock(file_inode(file)); } /** * ima_inode_post_setattr - reflect file metadata changes * @idmap: idmap of the mount the inode was found from * @dentry: pointer to the affected dentry * @ia_valid: for the UID and GID status * * Changes to a dentry's metadata might result in needing to appraise. * * This function is called from notify_change(), which expects the caller * to lock the inode's i_mutex. */ static void ima_inode_post_setattr(struct mnt_idmap *idmap, struct dentry *dentry, int ia_valid) { struct inode *inode = d_backing_inode(dentry); struct ima_iint_cache *iint; int action; if (!(ima_policy_flag & IMA_APPRAISE) || !S_ISREG(inode->i_mode) || !(inode->i_opflags & IOP_XATTR)) return; action = ima_must_appraise(idmap, inode, MAY_ACCESS, POST_SETATTR); iint = ima_iint_find(inode); if (iint) { set_bit(IMA_CHANGE_ATTR, &iint->atomic_flags); if (!action) clear_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); } } /* * ima_protect_xattr - protect 'security.ima' * * Ensure that not just anyone can modify or remove 'security.ima'. */ static int ima_protect_xattr(struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len) { if (strcmp(xattr_name, XATTR_NAME_IMA) == 0) { if (!capable(CAP_SYS_ADMIN)) return -EPERM; return 1; } return 0; } static void ima_reset_appraise_flags(struct inode *inode, int digsig) { struct ima_iint_cache *iint; if (!(ima_policy_flag & IMA_APPRAISE) || !S_ISREG(inode->i_mode)) return; iint = ima_iint_find(inode); if (!iint) return; iint->measured_pcrs = 0; set_bit(IMA_CHANGE_XATTR, &iint->atomic_flags); if (digsig) set_bit(IMA_DIGSIG, &iint->atomic_flags); else clear_bit(IMA_DIGSIG, &iint->atomic_flags); } /** * validate_hash_algo() - Block setxattr with unsupported hash algorithms * @dentry: object of the setxattr() * @xattr_value: userland supplied xattr value * @xattr_value_len: length of xattr_value * * The xattr value is mapped to its hash algorithm, and this algorithm * must be built in the kernel for the setxattr to be allowed. * * Emit an audit message when the algorithm is invalid. * * Return: 0 on success, else an error. */ static int validate_hash_algo(struct dentry *dentry, const struct evm_ima_xattr_data *xattr_value, size_t xattr_value_len) { char *path = NULL, *pathbuf = NULL; enum hash_algo xattr_hash_algo; const char *errmsg = "unavailable-hash-algorithm"; unsigned int allowed_hashes; xattr_hash_algo = ima_get_hash_algo(xattr_value, xattr_value_len); allowed_hashes = atomic_read(&ima_setxattr_allowed_hash_algorithms); if (allowed_hashes) { /* success if the algorithm is allowed in the ima policy */ if (allowed_hashes & (1U << xattr_hash_algo)) return 0; /* * We use a different audit message when the hash algorithm * is denied by a policy rule, instead of not being built * in the kernel image */ errmsg = "denied-hash-algorithm"; } else { if (likely(xattr_hash_algo == ima_hash_algo)) return 0; /* allow any xattr using an algorithm built in the kernel */ if (crypto_has_alg(hash_algo_name[xattr_hash_algo], 0, 0)) return 0; } pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); if (!pathbuf) return -EACCES; path = dentry_path(dentry, pathbuf, PATH_MAX); integrity_audit_msg(AUDIT_INTEGRITY_DATA, d_inode(dentry), path, "set_data", errmsg, -EACCES, 0); kfree(pathbuf); return -EACCES; } static int ima_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len, int flags) { const struct evm_ima_xattr_data *xvalue = xattr_value; int digsig = 0; int result; int err; result = ima_protect_xattr(dentry, xattr_name, xattr_value, xattr_value_len); if (result == 1) { if (!xattr_value_len || (xvalue->type >= IMA_XATTR_LAST)) return -EINVAL; err = validate_hash_algo(dentry, xvalue, xattr_value_len); if (err) return err; digsig = (xvalue->type == EVM_IMA_XATTR_DIGSIG); } else if (!strcmp(xattr_name, XATTR_NAME_EVM) && xattr_value_len > 0) { digsig = (xvalue->type == EVM_XATTR_PORTABLE_DIGSIG); } if (result == 1 || evm_revalidate_status(xattr_name)) { ima_reset_appraise_flags(d_backing_inode(dentry), digsig); if (result == 1) result = 0; } return result; } static int ima_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { if (evm_revalidate_status(acl_name)) ima_reset_appraise_flags(d_backing_inode(dentry), 0); return 0; } static int ima_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name) { int result; result = ima_protect_xattr(dentry, xattr_name, NULL, 0); if (result == 1 || evm_revalidate_status(xattr_name)) { ima_reset_appraise_flags(d_backing_inode(dentry), 0); if (result == 1) result = 0; } return result; } static int ima_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return ima_inode_set_acl(idmap, dentry, acl_name, NULL); } static struct security_hook_list ima_appraise_hooks[] __ro_after_init = { LSM_HOOK_INIT(inode_post_setattr, ima_inode_post_setattr), LSM_HOOK_INIT(inode_setxattr, ima_inode_setxattr), LSM_HOOK_INIT(inode_set_acl, ima_inode_set_acl), LSM_HOOK_INIT(inode_removexattr, ima_inode_removexattr), LSM_HOOK_INIT(inode_remove_acl, ima_inode_remove_acl), }; void __init init_ima_appraise_lsm(const struct lsm_id *lsmid) { security_add_hooks(ima_appraise_hooks, ARRAY_SIZE(ima_appraise_hooks), lsmid); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Events for filesystem locks * * Copyright 2013 Jeff Layton <jlayton@poochiereds.net> */ #undef TRACE_SYSTEM #define TRACE_SYSTEM filelock #if !defined(_TRACE_FILELOCK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_FILELOCK_H #include <linux/tracepoint.h> #include <linux/fs.h> #include <linux/device.h> #include <linux/kdev_t.h> #define show_fl_flags(val) \ __print_flags(val, "|", \ { FL_POSIX, "FL_POSIX" }, \ { FL_FLOCK, "FL_FLOCK" }, \ { FL_DELEG, "FL_DELEG" }, \ { FL_ACCESS, "FL_ACCESS" }, \ { FL_EXISTS, "FL_EXISTS" }, \ { FL_LEASE, "FL_LEASE" }, \ { FL_CLOSE, "FL_CLOSE" }, \ { FL_SLEEP, "FL_SLEEP" }, \ { FL_DOWNGRADE_PENDING, "FL_DOWNGRADE_PENDING" }, \ { FL_UNLOCK_PENDING, "FL_UNLOCK_PENDING" }, \ { FL_OFDLCK, "FL_OFDLCK" }) #define show_fl_type(val) \ __print_symbolic(val, \ { F_RDLCK, "F_RDLCK" }, \ { F_WRLCK, "F_WRLCK" }, \ { F_UNLCK, "F_UNLCK" }) TRACE_EVENT(locks_get_lock_context, TP_PROTO(struct inode *inode, int type, struct file_lock_context *ctx), TP_ARGS(inode, type, ctx), TP_STRUCT__entry( __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(unsigned char, type) __field(struct file_lock_context *, ctx) ), TP_fast_assign( __entry->s_dev = inode->i_sb->s_dev; __entry->i_ino = inode->i_ino; __entry->type = type; __entry->ctx = ctx; ), TP_printk("dev=0x%x:0x%x ino=0x%lx type=%s ctx=%p", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, show_fl_type(__entry->type), __entry->ctx) ); DECLARE_EVENT_CLASS(filelock_lock, TP_PROTO(struct inode *inode, struct file_lock *fl, int ret), TP_ARGS(inode, fl, ret), TP_STRUCT__entry( __field(struct file_lock *, fl) __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(struct file_lock_core *, blocker) __field(fl_owner_t, owner) __field(unsigned int, pid) __field(unsigned int, flags) __field(unsigned char, type) __field(loff_t, fl_start) __field(loff_t, fl_end) __field(int, ret) ), TP_fast_assign( __entry->fl = fl ? fl : NULL; __entry->s_dev = inode->i_sb->s_dev; __entry->i_ino = inode->i_ino; __entry->blocker = fl ? fl->c.flc_blocker : NULL; __entry->owner = fl ? fl->c.flc_owner : NULL; __entry->pid = fl ? fl->c.flc_pid : 0; __entry->flags = fl ? fl->c.flc_flags : 0; __entry->type = fl ? fl->c.flc_type : 0; __entry->fl_start = fl ? fl->fl_start : 0; __entry->fl_end = fl ? fl->fl_end : 0; __entry->ret = ret; ), TP_printk("fl=%p dev=0x%x:0x%x ino=0x%lx fl_blocker=%p fl_owner=%p fl_pid=%u fl_flags=%s fl_type=%s fl_start=%lld fl_end=%lld ret=%d", __entry->fl, MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->blocker, __entry->owner, __entry->pid, show_fl_flags(__entry->flags), show_fl_type(__entry->type), __entry->fl_start, __entry->fl_end, __entry->ret) ); DEFINE_EVENT(filelock_lock, posix_lock_inode, TP_PROTO(struct inode *inode, struct file_lock *fl, int ret), TP_ARGS(inode, fl, ret)); DEFINE_EVENT(filelock_lock, fcntl_setlk, TP_PROTO(struct inode *inode, struct file_lock *fl, int ret), TP_ARGS(inode, fl, ret)); DEFINE_EVENT(filelock_lock, locks_remove_posix, TP_PROTO(struct inode *inode, struct file_lock *fl, int ret), TP_ARGS(inode, fl, ret)); DEFINE_EVENT(filelock_lock, flock_lock_inode, TP_PROTO(struct inode *inode, struct file_lock *fl, int ret), TP_ARGS(inode, fl, ret)); DECLARE_EVENT_CLASS(filelock_lease, TP_PROTO(struct inode *inode, struct file_lease *fl), TP_ARGS(inode, fl), TP_STRUCT__entry( __field(struct file_lease *, fl) __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(struct file_lock_core *, blocker) __field(fl_owner_t, owner) __field(unsigned int, flags) __field(unsigned char, type) __field(unsigned long, break_time) __field(unsigned long, downgrade_time) ), TP_fast_assign( __entry->fl = fl ? fl : NULL; __entry->s_dev = inode->i_sb->s_dev; __entry->i_ino = inode->i_ino; __entry->blocker = fl ? fl->c.flc_blocker : NULL; __entry->owner = fl ? fl->c.flc_owner : NULL; __entry->flags = fl ? fl->c.flc_flags : 0; __entry->type = fl ? fl->c.flc_type : 0; __entry->break_time = fl ? fl->fl_break_time : 0; __entry->downgrade_time = fl ? fl->fl_downgrade_time : 0; ), TP_printk("fl=%p dev=0x%x:0x%x ino=0x%lx fl_blocker=%p fl_owner=%p fl_flags=%s fl_type=%s fl_break_time=%lu fl_downgrade_time=%lu", __entry->fl, MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->blocker, __entry->owner, show_fl_flags(__entry->flags), show_fl_type(__entry->type), __entry->break_time, __entry->downgrade_time) ); DEFINE_EVENT(filelock_lease, break_lease_noblock, TP_PROTO(struct inode *inode, struct file_lease *fl), TP_ARGS(inode, fl)); DEFINE_EVENT(filelock_lease, break_lease_block, TP_PROTO(struct inode *inode, struct file_lease *fl), TP_ARGS(inode, fl)); DEFINE_EVENT(filelock_lease, break_lease_unblock, TP_PROTO(struct inode *inode, struct file_lease *fl), TP_ARGS(inode, fl)); DEFINE_EVENT(filelock_lease, generic_delete_lease, TP_PROTO(struct inode *inode, struct file_lease *fl), TP_ARGS(inode, fl)); DEFINE_EVENT(filelock_lease, time_out_leases, TP_PROTO(struct inode *inode, struct file_lease *fl), TP_ARGS(inode, fl)); TRACE_EVENT(generic_add_lease, TP_PROTO(struct inode *inode, struct file_lease *fl), TP_ARGS(inode, fl), TP_STRUCT__entry( __field(unsigned long, i_ino) __field(int, wcount) __field(int, rcount) __field(int, icount) __field(dev_t, s_dev) __field(fl_owner_t, owner) __field(unsigned int, flags) __field(unsigned char, type) ), TP_fast_assign( __entry->s_dev = inode->i_sb->s_dev; __entry->i_ino = inode->i_ino; __entry->wcount = atomic_read(&inode->i_writecount); __entry->rcount = atomic_read(&inode->i_readcount); __entry->icount = atomic_read(&inode->i_count); __entry->owner = fl->c.flc_owner; __entry->flags = fl->c.flc_flags; __entry->type = fl->c.flc_type; ), TP_printk("dev=0x%x:0x%x ino=0x%lx wcount=%d rcount=%d icount=%d fl_owner=%p fl_flags=%s fl_type=%s", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->wcount, __entry->rcount, __entry->icount, __entry->owner, show_fl_flags(__entry->flags), show_fl_type(__entry->type)) ); TRACE_EVENT(leases_conflict, TP_PROTO(bool conflict, struct file_lease *lease, struct file_lease *breaker), TP_ARGS(conflict, lease, breaker), TP_STRUCT__entry( __field(void *, lease) __field(void *, breaker) __field(unsigned int, l_fl_flags) __field(unsigned int, b_fl_flags) __field(unsigned char, l_fl_type) __field(unsigned char, b_fl_type) __field(bool, conflict) ), TP_fast_assign( __entry->lease = lease; __entry->l_fl_flags = lease->c.flc_flags; __entry->l_fl_type = lease->c.flc_type; __entry->breaker = breaker; __entry->b_fl_flags = breaker->c.flc_flags; __entry->b_fl_type = breaker->c.flc_type; __entry->conflict = conflict; ), TP_printk("conflict %d: lease=%p fl_flags=%s fl_type=%s; breaker=%p fl_flags=%s fl_type=%s", __entry->conflict, __entry->lease, show_fl_flags(__entry->l_fl_flags), show_fl_type(__entry->l_fl_type), __entry->breaker, show_fl_flags(__entry->b_fl_flags), show_fl_type(__entry->b_fl_type)) ); #endif /* _TRACE_FILELOCK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CPUSET_H #define _LINUX_CPUSET_H /* * cpuset interface * * Copyright (C) 2003 BULL SA * Copyright (C) 2004-2006 Silicon Graphics, Inc. * */ #include <linux/sched.h> #include <linux/sched/topology.h> #include <linux/sched/task.h> #include <linux/cpumask.h> #include <linux/nodemask.h> #include <linux/mm.h> #include <linux/mmu_context.h> #include <linux/jump_label.h> #ifdef CONFIG_CPUSETS /* * Static branch rewrites can happen in an arbitrary order for a given * key. In code paths where we need to loop with read_mems_allowed_begin() and * read_mems_allowed_retry() to get a consistent view of mems_allowed, we need * to ensure that begin() always gets rewritten before retry() in the * disabled -> enabled transition. If not, then if local irqs are disabled * around the loop, we can deadlock since retry() would always be * comparing the latest value of the mems_allowed seqcount against 0 as * begin() still would see cpusets_enabled() as false. The enabled -> disabled * transition should happen in reverse order for the same reasons (want to stop * looking at real value of mems_allowed.sequence in retry() first). */ extern struct static_key_false cpusets_pre_enable_key; extern struct static_key_false cpusets_enabled_key; extern struct static_key_false cpusets_insane_config_key; static inline bool cpusets_enabled(void) { return static_branch_unlikely(&cpusets_enabled_key); } static inline void cpuset_inc(void) { static_branch_inc_cpuslocked(&cpusets_pre_enable_key); static_branch_inc_cpuslocked(&cpusets_enabled_key); } static inline void cpuset_dec(void) { static_branch_dec_cpuslocked(&cpusets_enabled_key); static_branch_dec_cpuslocked(&cpusets_pre_enable_key); } /* * This will get enabled whenever a cpuset configuration is considered * unsupportable in general. E.g. movable only node which cannot satisfy * any non movable allocations (see update_nodemask). Page allocator * needs to make additional checks for those configurations and this * check is meant to guard those checks without any overhead for sane * configurations. */ static inline bool cpusets_insane_config(void) { return static_branch_unlikely(&cpusets_insane_config_key); } extern int cpuset_init(void); extern void cpuset_init_smp(void); extern void cpuset_force_rebuild(void); extern void cpuset_update_active_cpus(void); extern void inc_dl_tasks_cs(struct task_struct *task); extern void dec_dl_tasks_cs(struct task_struct *task); extern void cpuset_lock(void); extern void cpuset_unlock(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); extern bool cpuset_cpus_allowed_fallback(struct task_struct *p); extern bool cpuset_cpu_is_isolated(int cpu); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); #define cpuset_current_mems_allowed (current->mems_allowed) void cpuset_init_current_mems_allowed(void); int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask); extern bool cpuset_node_allowed(int node, gfp_t gfp_mask); static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return cpuset_node_allowed(zone_to_nid(z), gfp_mask); } static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { if (cpusets_enabled()) return __cpuset_zone_allowed(z, gfp_mask); return true; } extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, const struct task_struct *tsk2); #ifdef CONFIG_CPUSETS_V1 #define cpuset_memory_pressure_bump() \ do { \ if (cpuset_memory_pressure_enabled) \ __cpuset_memory_pressure_bump(); \ } while (0) extern int cpuset_memory_pressure_enabled; extern void __cpuset_memory_pressure_bump(void); #else static inline void cpuset_memory_pressure_bump(void) { } #endif extern void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task); extern int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk); extern int cpuset_mem_spread_node(void); static inline int cpuset_do_page_mem_spread(void) { return task_spread_page(current); } extern bool current_cpuset_is_being_rebound(void); extern void rebuild_sched_domains(void); extern void cpuset_print_current_mems_allowed(void); /* * read_mems_allowed_begin is required when making decisions involving * mems_allowed such as during page allocation. mems_allowed can be updated in * parallel and depending on the new value an operation can fail potentially * causing process failure. A retry loop with read_mems_allowed_begin and * read_mems_allowed_retry prevents these artificial failures. */ static inline unsigned int read_mems_allowed_begin(void) { if (!static_branch_unlikely(&cpusets_pre_enable_key)) return 0; return read_seqcount_begin(¤t->mems_allowed_seq); } /* * If this returns true, the operation that took place after * read_mems_allowed_begin may have failed artificially due to a concurrent * update of mems_allowed. It is up to the caller to retry the operation if * appropriate. */ static inline bool read_mems_allowed_retry(unsigned int seq) { if (!static_branch_unlikely(&cpusets_enabled_key)) return false; return read_seqcount_retry(¤t->mems_allowed_seq, seq); } static inline void set_mems_allowed(nodemask_t nodemask) { unsigned long flags; task_lock(current); local_irq_save(flags); write_seqcount_begin(¤t->mems_allowed_seq); current->mems_allowed = nodemask; write_seqcount_end(¤t->mems_allowed_seq); local_irq_restore(flags); task_unlock(current); } #else /* !CONFIG_CPUSETS */ static inline bool cpusets_enabled(void) { return false; } static inline bool cpusets_insane_config(void) { return false; } static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} static inline void cpuset_force_rebuild(void) { } static inline void cpuset_update_active_cpus(void) { partition_sched_domains(1, NULL, NULL); } static inline void inc_dl_tasks_cs(struct task_struct *task) { } static inline void dec_dl_tasks_cs(struct task_struct *task) { } static inline void cpuset_lock(void) { } static inline void cpuset_unlock(void) { } static inline void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask) { cpumask_copy(mask, task_cpu_possible_mask(p)); } static inline bool cpuset_cpus_allowed_fallback(struct task_struct *p) { return false; } static inline bool cpuset_cpu_is_isolated(int cpu) { return false; } static inline nodemask_t cpuset_mems_allowed(struct task_struct *p) { return node_possible_map; } #define cpuset_current_mems_allowed (node_states[N_MEMORY]) static inline void cpuset_init_current_mems_allowed(void) {} static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) { return 1; } static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return true; } static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return true; } static inline int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, const struct task_struct *tsk2) { return 1; } static inline void cpuset_memory_pressure_bump(void) {} static inline void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task) { } static inline int cpuset_mem_spread_node(void) { return 0; } static inline int cpuset_do_page_mem_spread(void) { return 0; } static inline bool current_cpuset_is_being_rebound(void) { return false; } static inline void rebuild_sched_domains(void) { partition_sched_domains(1, NULL, NULL); } static inline void cpuset_print_current_mems_allowed(void) { } static inline void set_mems_allowed(nodemask_t nodemask) { } static inline unsigned int read_mems_allowed_begin(void) { return 0; } static inline bool read_mems_allowed_retry(unsigned int seq) { return false; } #endif /* !CONFIG_CPUSETS */ #endif /* _LINUX_CPUSET_H */ |
| 48 212 212 212 212 212 212 212 3 212 212 212 212 212 212 212 3 212 69 69 69 69 212 212 212 68 212 212 212 212 212 212 19 19 19 19 19 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/mmu_notifier.c * * Copyright (C) 2008 Qumranet, Inc. * Copyright (C) 2008 SGI * Christoph Lameter <cl@linux.com> */ #include <linux/rculist.h> #include <linux/mmu_notifier.h> #include <linux/export.h> #include <linux/mm.h> #include <linux/err.h> #include <linux/interval_tree.h> #include <linux/srcu.h> #include <linux/rcupdate.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/slab.h> #include "vma.h" /* global SRCU for all MMs */ DEFINE_STATIC_SRCU(srcu); #ifdef CONFIG_LOCKDEP struct lockdep_map __mmu_notifier_invalidate_range_start_map = { .name = "mmu_notifier_invalidate_range_start" }; #endif /* * The mmu_notifier_subscriptions structure is allocated and installed in * mm->notifier_subscriptions inside the mm_take_all_locks() protected * critical section and it's released only when mm_count reaches zero * in mmdrop(). */ struct mmu_notifier_subscriptions { /* all mmu notifiers registered in this mm are queued in this list */ struct hlist_head list; bool has_itree; /* to serialize the list modifications and hlist_unhashed */ spinlock_t lock; unsigned long invalidate_seq; unsigned long active_invalidate_ranges; struct rb_root_cached itree; wait_queue_head_t wq; struct hlist_head deferred_list; }; /* * This is a collision-retry read-side/write-side 'lock', a lot like a * seqcount, however this allows multiple write-sides to hold it at * once. Conceptually the write side is protecting the values of the PTEs in * this mm, such that PTES cannot be read into SPTEs (shadow PTEs) while any * writer exists. * * Note that the core mm creates nested invalidate_range_start()/end() regions * within the same thread, and runs invalidate_range_start()/end() in parallel * on multiple CPUs. This is designed to not reduce concurrency or block * progress on the mm side. * * As a secondary function, holding the full write side also serves to prevent * writers for the itree, this is an optimization to avoid extra locking * during invalidate_range_start/end notifiers. * * The write side has two states, fully excluded: * - mm->active_invalidate_ranges != 0 * - subscriptions->invalidate_seq & 1 == True (odd) * - some range on the mm_struct is being invalidated * - the itree is not allowed to change * * And partially excluded: * - mm->active_invalidate_ranges != 0 * - subscriptions->invalidate_seq & 1 == False (even) * - some range on the mm_struct is being invalidated * - the itree is allowed to change * * Operations on notifier_subscriptions->invalidate_seq (under spinlock): * seq |= 1 # Begin writing * seq++ # Release the writing state * seq & 1 # True if a writer exists * * The later state avoids some expensive work on inv_end in the common case of * no mmu_interval_notifier monitoring the VA. */ static bool mn_itree_is_invalidating(struct mmu_notifier_subscriptions *subscriptions) { lockdep_assert_held(&subscriptions->lock); return subscriptions->invalidate_seq & 1; } static struct mmu_interval_notifier * mn_itree_inv_start_range(struct mmu_notifier_subscriptions *subscriptions, const struct mmu_notifier_range *range, unsigned long *seq) { struct interval_tree_node *node; struct mmu_interval_notifier *res = NULL; spin_lock(&subscriptions->lock); subscriptions->active_invalidate_ranges++; node = interval_tree_iter_first(&subscriptions->itree, range->start, range->end - 1); if (node) { subscriptions->invalidate_seq |= 1; res = container_of(node, struct mmu_interval_notifier, interval_tree); } *seq = subscriptions->invalidate_seq; spin_unlock(&subscriptions->lock); return res; } static struct mmu_interval_notifier * mn_itree_inv_next(struct mmu_interval_notifier *interval_sub, const struct mmu_notifier_range *range) { struct interval_tree_node *node; node = interval_tree_iter_next(&interval_sub->interval_tree, range->start, range->end - 1); if (!node) return NULL; return container_of(node, struct mmu_interval_notifier, interval_tree); } static void mn_itree_inv_end(struct mmu_notifier_subscriptions *subscriptions) { struct mmu_interval_notifier *interval_sub; struct hlist_node *next; spin_lock(&subscriptions->lock); if (--subscriptions->active_invalidate_ranges || !mn_itree_is_invalidating(subscriptions)) { spin_unlock(&subscriptions->lock); return; } /* Make invalidate_seq even */ subscriptions->invalidate_seq++; /* * The inv_end incorporates a deferred mechanism like rtnl_unlock(). * Adds and removes are queued until the final inv_end happens then * they are progressed. This arrangement for tree updates is used to * avoid using a blocking lock during invalidate_range_start. */ hlist_for_each_entry_safe(interval_sub, next, &subscriptions->deferred_list, deferred_item) { if (RB_EMPTY_NODE(&interval_sub->interval_tree.rb)) interval_tree_insert(&interval_sub->interval_tree, &subscriptions->itree); else interval_tree_remove(&interval_sub->interval_tree, &subscriptions->itree); hlist_del(&interval_sub->deferred_item); } spin_unlock(&subscriptions->lock); wake_up_all(&subscriptions->wq); } /** * mmu_interval_read_begin - Begin a read side critical section against a VA * range * @interval_sub: The interval subscription * * mmu_iterval_read_begin()/mmu_iterval_read_retry() implement a * collision-retry scheme similar to seqcount for the VA range under * subscription. If the mm invokes invalidation during the critical section * then mmu_interval_read_retry() will return true. * * This is useful to obtain shadow PTEs where teardown or setup of the SPTEs * require a blocking context. The critical region formed by this can sleep, * and the required 'user_lock' can also be a sleeping lock. * * The caller is required to provide a 'user_lock' to serialize both teardown * and setup. * * The return value should be passed to mmu_interval_read_retry(). */ unsigned long mmu_interval_read_begin(struct mmu_interval_notifier *interval_sub) { struct mmu_notifier_subscriptions *subscriptions = interval_sub->mm->notifier_subscriptions; unsigned long seq; bool is_invalidating; /* * If the subscription has a different seq value under the user_lock * than we started with then it has collided. * * If the subscription currently has the same seq value as the * subscriptions seq, then it is currently between * invalidate_start/end and is colliding. * * The locking looks broadly like this: * mn_itree_inv_start(): mmu_interval_read_begin(): * spin_lock * seq = READ_ONCE(interval_sub->invalidate_seq); * seq == subs->invalidate_seq * spin_unlock * spin_lock * seq = ++subscriptions->invalidate_seq * spin_unlock * op->invalidate(): * user_lock * mmu_interval_set_seq() * interval_sub->invalidate_seq = seq * user_unlock * * [Required: mmu_interval_read_retry() == true] * * mn_itree_inv_end(): * spin_lock * seq = ++subscriptions->invalidate_seq * spin_unlock * * user_lock * mmu_interval_read_retry(): * interval_sub->invalidate_seq != seq * user_unlock * * Barriers are not needed here as any races here are closed by an * eventual mmu_interval_read_retry(), which provides a barrier via the * user_lock. */ spin_lock(&subscriptions->lock); /* Pairs with the WRITE_ONCE in mmu_interval_set_seq() */ seq = READ_ONCE(interval_sub->invalidate_seq); is_invalidating = seq == subscriptions->invalidate_seq; spin_unlock(&subscriptions->lock); /* * interval_sub->invalidate_seq must always be set to an odd value via * mmu_interval_set_seq() using the provided cur_seq from * mn_itree_inv_start_range(). This ensures that if seq does wrap we * will always clear the below sleep in some reasonable time as * subscriptions->invalidate_seq is even in the idle state. */ lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); lock_map_release(&__mmu_notifier_invalidate_range_start_map); if (is_invalidating) wait_event(subscriptions->wq, READ_ONCE(subscriptions->invalidate_seq) != seq); /* * Notice that mmu_interval_read_retry() can already be true at this * point, avoiding loops here allows the caller to provide a global * time bound. */ return seq; } EXPORT_SYMBOL_GPL(mmu_interval_read_begin); static void mn_itree_release(struct mmu_notifier_subscriptions *subscriptions, struct mm_struct *mm) { struct mmu_notifier_range range = { .flags = MMU_NOTIFIER_RANGE_BLOCKABLE, .event = MMU_NOTIFY_RELEASE, .mm = mm, .start = 0, .end = ULONG_MAX, }; struct mmu_interval_notifier *interval_sub; unsigned long cur_seq; bool ret; for (interval_sub = mn_itree_inv_start_range(subscriptions, &range, &cur_seq); interval_sub; interval_sub = mn_itree_inv_next(interval_sub, &range)) { ret = interval_sub->ops->invalidate(interval_sub, &range, cur_seq); WARN_ON(!ret); } mn_itree_inv_end(subscriptions); } /* * This function can't run concurrently against mmu_notifier_register * because mm->mm_users > 0 during mmu_notifier_register and exit_mmap * runs with mm_users == 0. Other tasks may still invoke mmu notifiers * in parallel despite there being no task using this mm any more, * through the vmas outside of the exit_mmap context, such as with * vmtruncate. This serializes against mmu_notifier_unregister with * the notifier_subscriptions->lock in addition to SRCU and it serializes * against the other mmu notifiers with SRCU. struct mmu_notifier_subscriptions * can't go away from under us as exit_mmap holds an mm_count pin * itself. */ static void mn_hlist_release(struct mmu_notifier_subscriptions *subscriptions, struct mm_struct *mm) { struct mmu_notifier *subscription; int id; /* * SRCU here will block mmu_notifier_unregister until * ->release returns. */ id = srcu_read_lock(&srcu); hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist, srcu_read_lock_held(&srcu)) /* * If ->release runs before mmu_notifier_unregister it must be * handled, as it's the only way for the driver to flush all * existing sptes and stop the driver from establishing any more * sptes before all the pages in the mm are freed. */ if (subscription->ops->release) subscription->ops->release(subscription, mm); spin_lock(&subscriptions->lock); while (unlikely(!hlist_empty(&subscriptions->list))) { subscription = hlist_entry(subscriptions->list.first, struct mmu_notifier, hlist); /* * We arrived before mmu_notifier_unregister so * mmu_notifier_unregister will do nothing other than to wait * for ->release to finish and for mmu_notifier_unregister to * return. */ hlist_del_init_rcu(&subscription->hlist); } spin_unlock(&subscriptions->lock); srcu_read_unlock(&srcu, id); /* * synchronize_srcu here prevents mmu_notifier_release from returning to * exit_mmap (which would proceed with freeing all pages in the mm) * until the ->release method returns, if it was invoked by * mmu_notifier_unregister. * * The notifier_subscriptions can't go away from under us because * one mm_count is held by exit_mmap. */ synchronize_srcu(&srcu); } void __mmu_notifier_release(struct mm_struct *mm) { struct mmu_notifier_subscriptions *subscriptions = mm->notifier_subscriptions; if (subscriptions->has_itree) mn_itree_release(subscriptions, mm); if (!hlist_empty(&subscriptions->list)) mn_hlist_release(subscriptions, mm); } /* * If no young bitflag is supported by the hardware, ->clear_flush_young can * unmap the address and return 1 or 0 depending if the mapping previously * existed or not. */ int __mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long start, unsigned long end) { struct mmu_notifier *subscription; int young = 0, id; id = srcu_read_lock(&srcu); hlist_for_each_entry_rcu(subscription, &mm->notifier_subscriptions->list, hlist, srcu_read_lock_held(&srcu)) { if (subscription->ops->clear_flush_young) young |= subscription->ops->clear_flush_young( subscription, mm, start, end); } srcu_read_unlock(&srcu, id); return young; } int __mmu_notifier_clear_young(struct mm_struct *mm, unsigned long start, unsigned long end) { struct mmu_notifier *subscription; int young = 0, id; id = srcu_read_lock(&srcu); hlist_for_each_entry_rcu(subscription, &mm->notifier_subscriptions->list, hlist, srcu_read_lock_held(&srcu)) { if (subscription->ops->clear_young) young |= subscription->ops->clear_young(subscription, mm, start, end); } srcu_read_unlock(&srcu, id); return young; } int __mmu_notifier_test_young(struct mm_struct *mm, unsigned long address) { struct mmu_notifier *subscription; int young = 0, id; id = srcu_read_lock(&srcu); hlist_for_each_entry_rcu(subscription, &mm->notifier_subscriptions->list, hlist, srcu_read_lock_held(&srcu)) { if (subscription->ops->test_young) { young = subscription->ops->test_young(subscription, mm, address); if (young) break; } } srcu_read_unlock(&srcu, id); return young; } static int mn_itree_invalidate(struct mmu_notifier_subscriptions *subscriptions, const struct mmu_notifier_range *range) { struct mmu_interval_notifier *interval_sub; unsigned long cur_seq; for (interval_sub = mn_itree_inv_start_range(subscriptions, range, &cur_seq); interval_sub; interval_sub = mn_itree_inv_next(interval_sub, range)) { bool ret; ret = interval_sub->ops->invalidate(interval_sub, range, cur_seq); if (!ret) { if (WARN_ON(mmu_notifier_range_blockable(range))) continue; goto out_would_block; } } return 0; out_would_block: /* * On -EAGAIN the non-blocking caller is not allowed to call * invalidate_range_end() */ mn_itree_inv_end(subscriptions); return -EAGAIN; } static int mn_hlist_invalidate_range_start( struct mmu_notifier_subscriptions *subscriptions, struct mmu_notifier_range *range) { struct mmu_notifier *subscription; int ret = 0; int id; id = srcu_read_lock(&srcu); hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist, srcu_read_lock_held(&srcu)) { const struct mmu_notifier_ops *ops = subscription->ops; if (ops->invalidate_range_start) { int _ret; if (!mmu_notifier_range_blockable(range)) non_block_start(); _ret = ops->invalidate_range_start(subscription, range); if (!mmu_notifier_range_blockable(range)) non_block_end(); if (_ret) { pr_info("%pS callback failed with %d in %sblockable context.\n", ops->invalidate_range_start, _ret, !mmu_notifier_range_blockable(range) ? "non-" : ""); WARN_ON(mmu_notifier_range_blockable(range) || _ret != -EAGAIN); /* * We call all the notifiers on any EAGAIN, * there is no way for a notifier to know if * its start method failed, thus a start that * does EAGAIN can't also do end. */ WARN_ON(ops->invalidate_range_end); ret = _ret; } } } if (ret) { /* * Must be non-blocking to get here. If there are multiple * notifiers and one or more failed start, any that succeeded * start are expecting their end to be called. Do so now. */ hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist, srcu_read_lock_held(&srcu)) { if (!subscription->ops->invalidate_range_end) continue; subscription->ops->invalidate_range_end(subscription, range); } } srcu_read_unlock(&srcu, id); return ret; } int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) { struct mmu_notifier_subscriptions *subscriptions = range->mm->notifier_subscriptions; int ret; if (subscriptions->has_itree) { ret = mn_itree_invalidate(subscriptions, range); if (ret) return ret; } if (!hlist_empty(&subscriptions->list)) return mn_hlist_invalidate_range_start(subscriptions, range); return 0; } static void mn_hlist_invalidate_end(struct mmu_notifier_subscriptions *subscriptions, struct mmu_notifier_range *range) { struct mmu_notifier *subscription; int id; id = srcu_read_lock(&srcu); hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist, srcu_read_lock_held(&srcu)) { if (subscription->ops->invalidate_range_end) { if (!mmu_notifier_range_blockable(range)) non_block_start(); subscription->ops->invalidate_range_end(subscription, range); if (!mmu_notifier_range_blockable(range)) non_block_end(); } } srcu_read_unlock(&srcu, id); } void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range) { struct mmu_notifier_subscriptions *subscriptions = range->mm->notifier_subscriptions; lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); if (subscriptions->has_itree) mn_itree_inv_end(subscriptions); if (!hlist_empty(&subscriptions->list)) mn_hlist_invalidate_end(subscriptions, range); lock_map_release(&__mmu_notifier_invalidate_range_start_map); } void __mmu_notifier_arch_invalidate_secondary_tlbs(struct mm_struct *mm, unsigned long start, unsigned long end) { struct mmu_notifier *subscription; int id; id = srcu_read_lock(&srcu); hlist_for_each_entry_rcu(subscription, &mm->notifier_subscriptions->list, hlist, srcu_read_lock_held(&srcu)) { if (subscription->ops->arch_invalidate_secondary_tlbs) subscription->ops->arch_invalidate_secondary_tlbs( subscription, mm, start, end); } srcu_read_unlock(&srcu, id); } /* * Same as mmu_notifier_register but here the caller must hold the mmap_lock in * write mode. A NULL mn signals the notifier is being registered for itree * mode. */ int __mmu_notifier_register(struct mmu_notifier *subscription, struct mm_struct *mm) { struct mmu_notifier_subscriptions *subscriptions = NULL; int ret; mmap_assert_write_locked(mm); BUG_ON(atomic_read(&mm->mm_users) <= 0); /* * Subsystems should only register for invalidate_secondary_tlbs() or * invalidate_range_start()/end() callbacks, not both. */ if (WARN_ON_ONCE(subscription && (subscription->ops->arch_invalidate_secondary_tlbs && (subscription->ops->invalidate_range_start || subscription->ops->invalidate_range_end)))) return -EINVAL; if (!mm->notifier_subscriptions) { /* * kmalloc cannot be called under mm_take_all_locks(), but we * know that mm->notifier_subscriptions can't change while we * hold the write side of the mmap_lock. */ subscriptions = kzalloc( sizeof(struct mmu_notifier_subscriptions), GFP_KERNEL); if (!subscriptions) return -ENOMEM; INIT_HLIST_HEAD(&subscriptions->list); spin_lock_init(&subscriptions->lock); subscriptions->invalidate_seq = 2; subscriptions->itree = RB_ROOT_CACHED; init_waitqueue_head(&subscriptions->wq); INIT_HLIST_HEAD(&subscriptions->deferred_list); } ret = mm_take_all_locks(mm); if (unlikely(ret)) goto out_clean; /* * Serialize the update against mmu_notifier_unregister. A * side note: mmu_notifier_release can't run concurrently with * us because we hold the mm_users pin (either implicitly as * current->mm or explicitly with get_task_mm() or similar). * We can't race against any other mmu notifier method either * thanks to mm_take_all_locks(). * * release semantics on the initialization of the * mmu_notifier_subscriptions's contents are provided for unlocked * readers. acquire can only be used while holding the mmgrab or * mmget, and is safe because once created the * mmu_notifier_subscriptions is not freed until the mm is destroyed. * As above, users holding the mmap_lock or one of the * mm_take_all_locks() do not need to use acquire semantics. */ if (subscriptions) smp_store_release(&mm->notifier_subscriptions, subscriptions); if (subscription) { /* Pairs with the mmdrop in mmu_notifier_unregister_* */ mmgrab(mm); subscription->mm = mm; subscription->users = 1; spin_lock(&mm->notifier_subscriptions->lock); hlist_add_head_rcu(&subscription->hlist, &mm->notifier_subscriptions->list); spin_unlock(&mm->notifier_subscriptions->lock); } else mm->notifier_subscriptions->has_itree = true; mm_drop_all_locks(mm); BUG_ON(atomic_read(&mm->mm_users) <= 0); return 0; out_clean: kfree(subscriptions); return ret; } EXPORT_SYMBOL_GPL(__mmu_notifier_register); /** * mmu_notifier_register - Register a notifier on a mm * @subscription: The notifier to attach * @mm: The mm to attach the notifier to * * Must not hold mmap_lock nor any other VM related lock when calling * this registration function. Must also ensure mm_users can't go down * to zero while this runs to avoid races with mmu_notifier_release, * so mm has to be current->mm or the mm should be pinned safely such * as with get_task_mm(). If the mm is not current->mm, the mm_users * pin should be released by calling mmput after mmu_notifier_register * returns. * * mmu_notifier_unregister() or mmu_notifier_put() must be always called to * unregister the notifier. * * While the caller has a mmu_notifier get the subscription->mm pointer will remain * valid, and can be converted to an active mm pointer via mmget_not_zero(). */ int mmu_notifier_register(struct mmu_notifier *subscription, struct mm_struct *mm) { int ret; mmap_write_lock(mm); ret = __mmu_notifier_register(subscription, mm); mmap_write_unlock(mm); return ret; } EXPORT_SYMBOL_GPL(mmu_notifier_register); static struct mmu_notifier * find_get_mmu_notifier(struct mm_struct *mm, const struct mmu_notifier_ops *ops) { struct mmu_notifier *subscription; spin_lock(&mm->notifier_subscriptions->lock); hlist_for_each_entry_rcu(subscription, &mm->notifier_subscriptions->list, hlist, lockdep_is_held(&mm->notifier_subscriptions->lock)) { if (subscription->ops != ops) continue; if (likely(subscription->users != UINT_MAX)) subscription->users++; else subscription = ERR_PTR(-EOVERFLOW); spin_unlock(&mm->notifier_subscriptions->lock); return subscription; } spin_unlock(&mm->notifier_subscriptions->lock); return NULL; } /** * mmu_notifier_get_locked - Return the single struct mmu_notifier for * the mm & ops * @ops: The operations struct being subscribe with * @mm : The mm to attach notifiers too * * This function either allocates a new mmu_notifier via * ops->alloc_notifier(), or returns an already existing notifier on the * list. The value of the ops pointer is used to determine when two notifiers * are the same. * * Each call to mmu_notifier_get() must be paired with a call to * mmu_notifier_put(). The caller must hold the write side of mm->mmap_lock. * * While the caller has a mmu_notifier get the mm pointer will remain valid, * and can be converted to an active mm pointer via mmget_not_zero(). */ struct mmu_notifier *mmu_notifier_get_locked(const struct mmu_notifier_ops *ops, struct mm_struct *mm) { struct mmu_notifier *subscription; int ret; mmap_assert_write_locked(mm); if (mm->notifier_subscriptions) { subscription = find_get_mmu_notifier(mm, ops); if (subscription) return subscription; } subscription = ops->alloc_notifier(mm); if (IS_ERR(subscription)) return subscription; subscription->ops = ops; ret = __mmu_notifier_register(subscription, mm); if (ret) goto out_free; return subscription; out_free: subscription->ops->free_notifier(subscription); return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(mmu_notifier_get_locked); /* this is called after the last mmu_notifier_unregister() returned */ void __mmu_notifier_subscriptions_destroy(struct mm_struct *mm) { BUG_ON(!hlist_empty(&mm->notifier_subscriptions->list)); kfree(mm->notifier_subscriptions); mm->notifier_subscriptions = LIST_POISON1; /* debug */ } /* * This releases the mm_count pin automatically and frees the mm * structure if it was the last user of it. It serializes against * running mmu notifiers with SRCU and against mmu_notifier_unregister * with the unregister lock + SRCU. All sptes must be dropped before * calling mmu_notifier_unregister. ->release or any other notifier * method may be invoked concurrently with mmu_notifier_unregister, * and only after mmu_notifier_unregister returned we're guaranteed * that ->release or any other method can't run anymore. */ void mmu_notifier_unregister(struct mmu_notifier *subscription, struct mm_struct *mm) { BUG_ON(atomic_read(&mm->mm_count) <= 0); if (!hlist_unhashed(&subscription->hlist)) { /* * SRCU here will force exit_mmap to wait for ->release to * finish before freeing the pages. */ int id; id = srcu_read_lock(&srcu); /* * exit_mmap will block in mmu_notifier_release to guarantee * that ->release is called before freeing the pages. */ if (subscription->ops->release) subscription->ops->release(subscription, mm); srcu_read_unlock(&srcu, id); spin_lock(&mm->notifier_subscriptions->lock); /* * Can not use list_del_rcu() since __mmu_notifier_release * can delete it before we hold the lock. */ hlist_del_init_rcu(&subscription->hlist); spin_unlock(&mm->notifier_subscriptions->lock); } /* * Wait for any running method to finish, of course including * ->release if it was run by mmu_notifier_release instead of us. */ synchronize_srcu(&srcu); BUG_ON(atomic_read(&mm->mm_count) <= 0); mmdrop(mm); } EXPORT_SYMBOL_GPL(mmu_notifier_unregister); static void mmu_notifier_free_rcu(struct rcu_head *rcu) { struct mmu_notifier *subscription = container_of(rcu, struct mmu_notifier, rcu); struct mm_struct *mm = subscription->mm; subscription->ops->free_notifier(subscription); /* Pairs with the get in __mmu_notifier_register() */ mmdrop(mm); } /** * mmu_notifier_put - Release the reference on the notifier * @subscription: The notifier to act on * * This function must be paired with each mmu_notifier_get(), it releases the * reference obtained by the get. If this is the last reference then process * to free the notifier will be run asynchronously. * * Unlike mmu_notifier_unregister() the get/put flow only calls ops->release * when the mm_struct is destroyed. Instead free_notifier is always called to * release any resources held by the user. * * As ops->release is not guaranteed to be called, the user must ensure that * all sptes are dropped, and no new sptes can be established before * mmu_notifier_put() is called. * * This function can be called from the ops->release callback, however the * caller must still ensure it is called pairwise with mmu_notifier_get(). * * Modules calling this function must call mmu_notifier_synchronize() in * their __exit functions to ensure the async work is completed. */ void mmu_notifier_put(struct mmu_notifier *subscription) { struct mm_struct *mm = subscription->mm; spin_lock(&mm->notifier_subscriptions->lock); if (WARN_ON(!subscription->users) || --subscription->users) goto out_unlock; hlist_del_init_rcu(&subscription->hlist); spin_unlock(&mm->notifier_subscriptions->lock); call_srcu(&srcu, &subscription->rcu, mmu_notifier_free_rcu); return; out_unlock: spin_unlock(&mm->notifier_subscriptions->lock); } EXPORT_SYMBOL_GPL(mmu_notifier_put); static int __mmu_interval_notifier_insert( struct mmu_interval_notifier *interval_sub, struct mm_struct *mm, struct mmu_notifier_subscriptions *subscriptions, unsigned long start, unsigned long length, const struct mmu_interval_notifier_ops *ops) { interval_sub->mm = mm; interval_sub->ops = ops; RB_CLEAR_NODE(&interval_sub->interval_tree.rb); interval_sub->interval_tree.start = start; /* * Note that the representation of the intervals in the interval tree * considers the ending point as contained in the interval. */ if (length == 0 || check_add_overflow(start, length - 1, &interval_sub->interval_tree.last)) return -EOVERFLOW; /* Must call with a mmget() held */ if (WARN_ON(atomic_read(&mm->mm_users) <= 0)) return -EINVAL; /* pairs with mmdrop in mmu_interval_notifier_remove() */ mmgrab(mm); /* * If some invalidate_range_start/end region is going on in parallel * we don't know what VA ranges are affected, so we must assume this * new range is included. * * If the itree is invalidating then we are not allowed to change * it. Retrying until invalidation is done is tricky due to the * possibility for live lock, instead defer the add to * mn_itree_inv_end() so this algorithm is deterministic. * * In all cases the value for the interval_sub->invalidate_seq should be * odd, see mmu_interval_read_begin() */ spin_lock(&subscriptions->lock); if (subscriptions->active_invalidate_ranges) { if (mn_itree_is_invalidating(subscriptions)) hlist_add_head(&interval_sub->deferred_item, &subscriptions->deferred_list); else { subscriptions->invalidate_seq |= 1; interval_tree_insert(&interval_sub->interval_tree, &subscriptions->itree); } interval_sub->invalidate_seq = subscriptions->invalidate_seq; } else { WARN_ON(mn_itree_is_invalidating(subscriptions)); /* * The starting seq for a subscription not under invalidation * should be odd, not equal to the current invalidate_seq and * invalidate_seq should not 'wrap' to the new seq any time * soon. */ interval_sub->invalidate_seq = subscriptions->invalidate_seq - 1; interval_tree_insert(&interval_sub->interval_tree, &subscriptions->itree); } spin_unlock(&subscriptions->lock); return 0; } /** * mmu_interval_notifier_insert - Insert an interval notifier * @interval_sub: Interval subscription to register * @start: Starting virtual address to monitor * @length: Length of the range to monitor * @mm: mm_struct to attach to * @ops: Interval notifier operations to be called on matching events * * This function subscribes the interval notifier for notifications from the * mm. Upon return the ops related to mmu_interval_notifier will be called * whenever an event that intersects with the given range occurs. * * Upon return the range_notifier may not be present in the interval tree yet. * The caller must use the normal interval notifier read flow via * mmu_interval_read_begin() to establish SPTEs for this range. */ int mmu_interval_notifier_insert(struct mmu_interval_notifier *interval_sub, struct mm_struct *mm, unsigned long start, unsigned long length, const struct mmu_interval_notifier_ops *ops) { struct mmu_notifier_subscriptions *subscriptions; int ret; might_lock(&mm->mmap_lock); subscriptions = smp_load_acquire(&mm->notifier_subscriptions); if (!subscriptions || !subscriptions->has_itree) { ret = mmu_notifier_register(NULL, mm); if (ret) return ret; subscriptions = mm->notifier_subscriptions; } return __mmu_interval_notifier_insert(interval_sub, mm, subscriptions, start, length, ops); } EXPORT_SYMBOL_GPL(mmu_interval_notifier_insert); int mmu_interval_notifier_insert_locked( struct mmu_interval_notifier *interval_sub, struct mm_struct *mm, unsigned long start, unsigned long length, const struct mmu_interval_notifier_ops *ops) { struct mmu_notifier_subscriptions *subscriptions = mm->notifier_subscriptions; int ret; mmap_assert_write_locked(mm); if (!subscriptions || !subscriptions->has_itree) { ret = __mmu_notifier_register(NULL, mm); if (ret) return ret; subscriptions = mm->notifier_subscriptions; } return __mmu_interval_notifier_insert(interval_sub, mm, subscriptions, start, length, ops); } EXPORT_SYMBOL_GPL(mmu_interval_notifier_insert_locked); static bool mmu_interval_seq_released(struct mmu_notifier_subscriptions *subscriptions, unsigned long seq) { bool ret; spin_lock(&subscriptions->lock); ret = subscriptions->invalidate_seq != seq; spin_unlock(&subscriptions->lock); return ret; } /** * mmu_interval_notifier_remove - Remove a interval notifier * @interval_sub: Interval subscription to unregister * * This function must be paired with mmu_interval_notifier_insert(). It cannot * be called from any ops callback. * * Once this returns ops callbacks are no longer running on other CPUs and * will not be called in future. */ void mmu_interval_notifier_remove(struct mmu_interval_notifier *interval_sub) { struct mm_struct *mm = interval_sub->mm; struct mmu_notifier_subscriptions *subscriptions = mm->notifier_subscriptions; unsigned long seq = 0; might_sleep(); spin_lock(&subscriptions->lock); if (mn_itree_is_invalidating(subscriptions)) { /* * remove is being called after insert put this on the * deferred list, but before the deferred list was processed. */ if (RB_EMPTY_NODE(&interval_sub->interval_tree.rb)) { hlist_del(&interval_sub->deferred_item); } else { hlist_add_head(&interval_sub->deferred_item, &subscriptions->deferred_list); seq = subscriptions->invalidate_seq; } } else { WARN_ON(RB_EMPTY_NODE(&interval_sub->interval_tree.rb)); interval_tree_remove(&interval_sub->interval_tree, &subscriptions->itree); } spin_unlock(&subscriptions->lock); /* * The possible sleep on progress in the invalidation requires the * caller not hold any locks held by invalidation callbacks. */ lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); lock_map_release(&__mmu_notifier_invalidate_range_start_map); if (seq) wait_event(subscriptions->wq, mmu_interval_seq_released(subscriptions, seq)); /* pairs with mmgrab in mmu_interval_notifier_insert() */ mmdrop(mm); } EXPORT_SYMBOL_GPL(mmu_interval_notifier_remove); /** * mmu_notifier_synchronize - Ensure all mmu_notifiers are freed * * This function ensures that all outstanding async SRU work from * mmu_notifier_put() is completed. After it returns any mmu_notifier_ops * associated with an unused mmu_notifier will no longer be called. * * Before using the caller must ensure that all of its mmu_notifiers have been * fully released via mmu_notifier_put(). * * Modules using the mmu_notifier_put() API should call this in their __exit * function to avoid module unloading races. */ void mmu_notifier_synchronize(void) { synchronize_srcu(&srcu); } EXPORT_SYMBOL_GPL(mmu_notifier_synchronize); |
| 100 100 101 101 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/tlb.h * * Copyright (C) 2002 Russell King * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_TLB_H #define __ASM_TLB_H #include <linux/pagemap.h> #include <linux/swap.h> static inline void __tlb_remove_table(void *_table) { free_page_and_swap_cache((struct page *)_table); } #define tlb_flush tlb_flush static void tlb_flush(struct mmu_gather *tlb); #include <asm-generic/tlb.h> /* * get the tlbi levels in arm64. Default value is TLBI_TTL_UNKNOWN if more than * one of cleared_* is set or neither is set - this elides the level hinting to * the hardware. */ static inline int tlb_get_level(struct mmu_gather *tlb) { /* The TTL field is only valid for the leaf entry. */ if (tlb->freed_tables) return TLBI_TTL_UNKNOWN; if (tlb->cleared_ptes && !(tlb->cleared_pmds || tlb->cleared_puds || tlb->cleared_p4ds)) return 3; if (tlb->cleared_pmds && !(tlb->cleared_ptes || tlb->cleared_puds || tlb->cleared_p4ds)) return 2; if (tlb->cleared_puds && !(tlb->cleared_ptes || tlb->cleared_pmds || tlb->cleared_p4ds)) return 1; if (tlb->cleared_p4ds && !(tlb->cleared_ptes || tlb->cleared_pmds || tlb->cleared_puds)) return 0; return TLBI_TTL_UNKNOWN; } static inline void tlb_flush(struct mmu_gather *tlb) { struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0); bool last_level = !tlb->freed_tables; unsigned long stride = tlb_get_unmap_size(tlb); int tlb_level = tlb_get_level(tlb); /* * If we're tearing down the address space then we only care about * invalidating the walk-cache, since the ASID allocator won't * reallocate our ASID without invalidating the entire TLB. */ if (tlb->fullmm) { if (!last_level) flush_tlb_mm(tlb->mm); return; } __flush_tlb_range(&vma, tlb->start, tlb->end, stride, last_level, tlb_level); } static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr) { struct ptdesc *ptdesc = page_ptdesc(pte); pagetable_pte_dtor(ptdesc); tlb_remove_ptdesc(tlb, ptdesc); } #if CONFIG_PGTABLE_LEVELS > 2 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr) { struct ptdesc *ptdesc = virt_to_ptdesc(pmdp); pagetable_pmd_dtor(ptdesc); tlb_remove_ptdesc(tlb, ptdesc); } #endif #if CONFIG_PGTABLE_LEVELS > 3 static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp, unsigned long addr) { struct ptdesc *ptdesc = virt_to_ptdesc(pudp); if (!pgtable_l4_enabled()) return; pagetable_pud_dtor(ptdesc); tlb_remove_ptdesc(tlb, ptdesc); } #endif #endif |
| 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 44 5 44 43 44 43 44 25 44 44 44 24 19 25 19 187 186 187 186 187 186 187 187 186 187 186 171 19 187 185 186 187 187 187 230 230 230 230 230 230 230 230 230 230 230 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 | // SPDX-License-Identifier: GPL-2.0-only /* * Implementation of the security services. * * Authors : Stephen Smalley, <stephen.smalley.work@gmail.com> * James Morris <jmorris@redhat.com> * * Updated: Trusted Computer Solutions, Inc. <dgoeddel@trustedcs.com> * * Support for enhanced MLS infrastructure. * Support for context based audit filters. * * Updated: Frank Mayer <mayerf@tresys.com> and Karl MacMillan <kmacmillan@tresys.com> * * Added conditional policy language extensions * * Updated: Hewlett-Packard <paul@paul-moore.com> * * Added support for NetLabel * Added support for the policy capability bitmap * * Updated: Chad Sellers <csellers@tresys.com> * * Added validation of kernel classes and permissions * * Updated: KaiGai Kohei <kaigai@ak.jp.nec.com> * * Added support for bounds domain and audit messaged on masked permissions * * Updated: Guido Trentalancia <guido@trentalancia.com> * * Added support for runtime switching of the policy type * * Copyright (C) 2008, 2009 NEC Corporation * Copyright (C) 2006, 2007 Hewlett-Packard Development Company, L.P. * Copyright (C) 2004-2006 Trusted Computer Solutions, Inc. * Copyright (C) 2003 - 2004, 2006 Tresys Technology, LLC * Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com> */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/errno.h> #include <linux/in.h> #include <linux/sched.h> #include <linux/audit.h> #include <linux/vmalloc.h> #include <linux/lsm_hooks.h> #include <net/netlabel.h> #include "flask.h" #include "avc.h" #include "avc_ss.h" #include "security.h" #include "context.h" #include "policydb.h" #include "sidtab.h" #include "services.h" #include "conditional.h" #include "mls.h" #include "objsec.h" #include "netlabel.h" #include "xfrm.h" #include "ebitmap.h" #include "audit.h" #include "policycap_names.h" #include "ima.h" struct selinux_policy_convert_data { struct convert_context_args args; struct sidtab_convert_params sidtab_params; }; /* Forward declaration. */ static int context_struct_to_string(struct policydb *policydb, struct context *context, char **scontext, u32 *scontext_len); static int sidtab_entry_to_string(struct policydb *policydb, struct sidtab *sidtab, struct sidtab_entry *entry, char **scontext, u32 *scontext_len); static void context_struct_compute_av(struct policydb *policydb, struct context *scontext, struct context *tcontext, u16 tclass, struct av_decision *avd, struct extended_perms *xperms); static int selinux_set_mapping(struct policydb *pol, const struct security_class_mapping *map, struct selinux_map *out_map) { u16 i, j; bool print_unknown_handle = false; /* Find number of classes in the input mapping */ if (!map) return -EINVAL; i = 0; while (map[i].name) i++; /* Allocate space for the class records, plus one for class zero */ out_map->mapping = kcalloc(++i, sizeof(*out_map->mapping), GFP_ATOMIC); if (!out_map->mapping) return -ENOMEM; /* Store the raw class and permission values */ j = 0; while (map[j].name) { const struct security_class_mapping *p_in = map + (j++); struct selinux_mapping *p_out = out_map->mapping + j; u16 k; /* An empty class string skips ahead */ if (!strcmp(p_in->name, "")) { p_out->num_perms = 0; continue; } p_out->value = string_to_security_class(pol, p_in->name); if (!p_out->value) { pr_info("SELinux: Class %s not defined in policy.\n", p_in->name); if (pol->reject_unknown) goto err; p_out->num_perms = 0; print_unknown_handle = true; continue; } k = 0; while (p_in->perms[k]) { /* An empty permission string skips ahead */ if (!*p_in->perms[k]) { k++; continue; } p_out->perms[k] = string_to_av_perm(pol, p_out->value, p_in->perms[k]); if (!p_out->perms[k]) { pr_info("SELinux: Permission %s in class %s not defined in policy.\n", p_in->perms[k], p_in->name); if (pol->reject_unknown) goto err; print_unknown_handle = true; } k++; } p_out->num_perms = k; } if (print_unknown_handle) pr_info("SELinux: the above unknown classes and permissions will be %s\n", pol->allow_unknown ? "allowed" : "denied"); out_map->size = i; return 0; err: kfree(out_map->mapping); out_map->mapping = NULL; return -EINVAL; } /* * Get real, policy values from mapped values */ static u16 unmap_class(struct selinux_map *map, u16 tclass) { if (tclass < map->size) return map->mapping[tclass].value; return tclass; } /* * Get kernel value for class from its policy value */ static u16 map_class(struct selinux_map *map, u16 pol_value) { u16 i; for (i = 1; i < map->size; i++) { if (map->mapping[i].value == pol_value) return i; } return SECCLASS_NULL; } static void map_decision(struct selinux_map *map, u16 tclass, struct av_decision *avd, int allow_unknown) { if (tclass < map->size) { struct selinux_mapping *mapping = &map->mapping[tclass]; unsigned int i, n = mapping->num_perms; u32 result; for (i = 0, result = 0; i < n; i++) { if (avd->allowed & mapping->perms[i]) result |= (u32)1<<i; if (allow_unknown && !mapping->perms[i]) result |= (u32)1<<i; } avd->allowed = result; for (i = 0, result = 0; i < n; i++) if (avd->auditallow & mapping->perms[i]) result |= (u32)1<<i; avd->auditallow = result; for (i = 0, result = 0; i < n; i++) { if (avd->auditdeny & mapping->perms[i]) result |= (u32)1<<i; if (!allow_unknown && !mapping->perms[i]) result |= (u32)1<<i; } /* * In case the kernel has a bug and requests a permission * between num_perms and the maximum permission number, we * should audit that denial */ for (; i < (sizeof(u32)*8); i++) result |= (u32)1<<i; avd->auditdeny = result; } } int security_mls_enabled(void) { int mls_enabled; struct selinux_policy *policy; if (!selinux_initialized()) return 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); mls_enabled = policy->policydb.mls_enabled; rcu_read_unlock(); return mls_enabled; } /* * Return the boolean value of a constraint expression * when it is applied to the specified source and target * security contexts. * * xcontext is a special beast... It is used by the validatetrans rules * only. For these rules, scontext is the context before the transition, * tcontext is the context after the transition, and xcontext is the context * of the process performing the transition. All other callers of * constraint_expr_eval should pass in NULL for xcontext. */ static int constraint_expr_eval(struct policydb *policydb, struct context *scontext, struct context *tcontext, struct context *xcontext, struct constraint_expr *cexpr) { u32 val1, val2; struct context *c; struct role_datum *r1, *r2; struct mls_level *l1, *l2; struct constraint_expr *e; int s[CEXPR_MAXDEPTH]; int sp = -1; for (e = cexpr; e; e = e->next) { switch (e->expr_type) { case CEXPR_NOT: BUG_ON(sp < 0); s[sp] = !s[sp]; break; case CEXPR_AND: BUG_ON(sp < 1); sp--; s[sp] &= s[sp + 1]; break; case CEXPR_OR: BUG_ON(sp < 1); sp--; s[sp] |= s[sp + 1]; break; case CEXPR_ATTR: if (sp == (CEXPR_MAXDEPTH - 1)) return 0; switch (e->attr) { case CEXPR_USER: val1 = scontext->user; val2 = tcontext->user; break; case CEXPR_TYPE: val1 = scontext->type; val2 = tcontext->type; break; case CEXPR_ROLE: val1 = scontext->role; val2 = tcontext->role; r1 = policydb->role_val_to_struct[val1 - 1]; r2 = policydb->role_val_to_struct[val2 - 1]; switch (e->op) { case CEXPR_DOM: s[++sp] = ebitmap_get_bit(&r1->dominates, val2 - 1); continue; case CEXPR_DOMBY: s[++sp] = ebitmap_get_bit(&r2->dominates, val1 - 1); continue; case CEXPR_INCOMP: s[++sp] = (!ebitmap_get_bit(&r1->dominates, val2 - 1) && !ebitmap_get_bit(&r2->dominates, val1 - 1)); continue; default: break; } break; case CEXPR_L1L2: l1 = &(scontext->range.level[0]); l2 = &(tcontext->range.level[0]); goto mls_ops; case CEXPR_L1H2: l1 = &(scontext->range.level[0]); l2 = &(tcontext->range.level[1]); goto mls_ops; case CEXPR_H1L2: l1 = &(scontext->range.level[1]); l2 = &(tcontext->range.level[0]); goto mls_ops; case CEXPR_H1H2: l1 = &(scontext->range.level[1]); l2 = &(tcontext->range.level[1]); goto mls_ops; case CEXPR_L1H1: l1 = &(scontext->range.level[0]); l2 = &(scontext->range.level[1]); goto mls_ops; case CEXPR_L2H2: l1 = &(tcontext->range.level[0]); l2 = &(tcontext->range.level[1]); goto mls_ops; mls_ops: switch (e->op) { case CEXPR_EQ: s[++sp] = mls_level_eq(l1, l2); continue; case CEXPR_NEQ: s[++sp] = !mls_level_eq(l1, l2); continue; case CEXPR_DOM: s[++sp] = mls_level_dom(l1, l2); continue; case CEXPR_DOMBY: s[++sp] = mls_level_dom(l2, l1); continue; case CEXPR_INCOMP: s[++sp] = mls_level_incomp(l2, l1); continue; default: BUG(); return 0; } break; default: BUG(); return 0; } switch (e->op) { case CEXPR_EQ: s[++sp] = (val1 == val2); break; case CEXPR_NEQ: s[++sp] = (val1 != val2); break; default: BUG(); return 0; } break; case CEXPR_NAMES: if (sp == (CEXPR_MAXDEPTH-1)) return 0; c = scontext; if (e->attr & CEXPR_TARGET) c = tcontext; else if (e->attr & CEXPR_XTARGET) { c = xcontext; if (!c) { BUG(); return 0; } } if (e->attr & CEXPR_USER) val1 = c->user; else if (e->attr & CEXPR_ROLE) val1 = c->role; else if (e->attr & CEXPR_TYPE) val1 = c->type; else { BUG(); return 0; } switch (e->op) { case CEXPR_EQ: s[++sp] = ebitmap_get_bit(&e->names, val1 - 1); break; case CEXPR_NEQ: s[++sp] = !ebitmap_get_bit(&e->names, val1 - 1); break; default: BUG(); return 0; } break; default: BUG(); return 0; } } BUG_ON(sp != 0); return s[0]; } /* * security_dump_masked_av - dumps masked permissions during * security_compute_av due to RBAC, MLS/Constraint and Type bounds. */ static int dump_masked_av_helper(void *k, void *d, void *args) { struct perm_datum *pdatum = d; char **permission_names = args; BUG_ON(pdatum->value < 1 || pdatum->value > 32); permission_names[pdatum->value - 1] = (char *)k; return 0; } static void security_dump_masked_av(struct policydb *policydb, struct context *scontext, struct context *tcontext, u16 tclass, u32 permissions, const char *reason) { struct common_datum *common_dat; struct class_datum *tclass_dat; struct audit_buffer *ab; char *tclass_name; char *scontext_name = NULL; char *tcontext_name = NULL; char *permission_names[32]; int index; u32 length; bool need_comma = false; if (!permissions) return; tclass_name = sym_name(policydb, SYM_CLASSES, tclass - 1); tclass_dat = policydb->class_val_to_struct[tclass - 1]; common_dat = tclass_dat->comdatum; /* init permission_names */ if (common_dat && hashtab_map(&common_dat->permissions.table, dump_masked_av_helper, permission_names) < 0) goto out; if (hashtab_map(&tclass_dat->permissions.table, dump_masked_av_helper, permission_names) < 0) goto out; /* get scontext/tcontext in text form */ if (context_struct_to_string(policydb, scontext, &scontext_name, &length) < 0) goto out; if (context_struct_to_string(policydb, tcontext, &tcontext_name, &length) < 0) goto out; /* audit a message */ ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR); if (!ab) goto out; audit_log_format(ab, "op=security_compute_av reason=%s " "scontext=%s tcontext=%s tclass=%s perms=", reason, scontext_name, tcontext_name, tclass_name); for (index = 0; index < 32; index++) { u32 mask = (1 << index); if ((mask & permissions) == 0) continue; audit_log_format(ab, "%s%s", need_comma ? "," : "", permission_names[index] ? permission_names[index] : "????"); need_comma = true; } audit_log_end(ab); out: /* release scontext/tcontext */ kfree(tcontext_name); kfree(scontext_name); } /* * security_boundary_permission - drops violated permissions * on boundary constraint. */ static void type_attribute_bounds_av(struct policydb *policydb, struct context *scontext, struct context *tcontext, u16 tclass, struct av_decision *avd) { struct context lo_scontext; struct context lo_tcontext, *tcontextp = tcontext; struct av_decision lo_avd; struct type_datum *source; struct type_datum *target; u32 masked = 0; source = policydb->type_val_to_struct[scontext->type - 1]; BUG_ON(!source); if (!source->bounds) return; target = policydb->type_val_to_struct[tcontext->type - 1]; BUG_ON(!target); memset(&lo_avd, 0, sizeof(lo_avd)); memcpy(&lo_scontext, scontext, sizeof(lo_scontext)); lo_scontext.type = source->bounds; if (target->bounds) { memcpy(&lo_tcontext, tcontext, sizeof(lo_tcontext)); lo_tcontext.type = target->bounds; tcontextp = &lo_tcontext; } context_struct_compute_av(policydb, &lo_scontext, tcontextp, tclass, &lo_avd, NULL); masked = ~lo_avd.allowed & avd->allowed; if (likely(!masked)) return; /* no masked permission */ /* mask violated permissions */ avd->allowed &= ~masked; /* audit masked permissions */ security_dump_masked_av(policydb, scontext, tcontext, tclass, masked, "bounds"); } /* * Flag which drivers have permissions. */ void services_compute_xperms_drivers( struct extended_perms *xperms, struct avtab_node *node) { unsigned int i; switch (node->datum.u.xperms->specified) { case AVTAB_XPERMS_IOCTLDRIVER: /* if one or more driver has all permissions allowed */ for (i = 0; i < ARRAY_SIZE(xperms->drivers.p); i++) xperms->drivers.p[i] |= node->datum.u.xperms->perms.p[i]; break; case AVTAB_XPERMS_IOCTLFUNCTION: case AVTAB_XPERMS_NLMSG: /* if allowing permissions within a driver */ security_xperm_set(xperms->drivers.p, node->datum.u.xperms->driver); break; } xperms->len = 1; } /* * Compute access vectors and extended permissions based on a context * structure pair for the permissions in a particular class. */ static void context_struct_compute_av(struct policydb *policydb, struct context *scontext, struct context *tcontext, u16 tclass, struct av_decision *avd, struct extended_perms *xperms) { struct constraint_node *constraint; struct role_allow *ra; struct avtab_key avkey; struct avtab_node *node; struct class_datum *tclass_datum; struct ebitmap *sattr, *tattr; struct ebitmap_node *snode, *tnode; unsigned int i, j; avd->allowed = 0; avd->auditallow = 0; avd->auditdeny = 0xffffffff; if (xperms) { memset(&xperms->drivers, 0, sizeof(xperms->drivers)); xperms->len = 0; } if (unlikely(!tclass || tclass > policydb->p_classes.nprim)) { pr_warn_ratelimited("SELinux: Invalid class %u\n", tclass); return; } tclass_datum = policydb->class_val_to_struct[tclass - 1]; /* * If a specific type enforcement rule was defined for * this permission check, then use it. */ avkey.target_class = tclass; avkey.specified = AVTAB_AV | AVTAB_XPERMS; sattr = &policydb->type_attr_map_array[scontext->type - 1]; tattr = &policydb->type_attr_map_array[tcontext->type - 1]; ebitmap_for_each_positive_bit(sattr, snode, i) { ebitmap_for_each_positive_bit(tattr, tnode, j) { avkey.source_type = i + 1; avkey.target_type = j + 1; for (node = avtab_search_node(&policydb->te_avtab, &avkey); node; node = avtab_search_node_next(node, avkey.specified)) { if (node->key.specified == AVTAB_ALLOWED) avd->allowed |= node->datum.u.data; else if (node->key.specified == AVTAB_AUDITALLOW) avd->auditallow |= node->datum.u.data; else if (node->key.specified == AVTAB_AUDITDENY) avd->auditdeny &= node->datum.u.data; else if (xperms && (node->key.specified & AVTAB_XPERMS)) services_compute_xperms_drivers(xperms, node); } /* Check conditional av table for additional permissions */ cond_compute_av(&policydb->te_cond_avtab, &avkey, avd, xperms); } } /* * Remove any permissions prohibited by a constraint (this includes * the MLS policy). */ constraint = tclass_datum->constraints; while (constraint) { if ((constraint->permissions & (avd->allowed)) && !constraint_expr_eval(policydb, scontext, tcontext, NULL, constraint->expr)) { avd->allowed &= ~(constraint->permissions); } constraint = constraint->next; } /* * If checking process transition permission and the * role is changing, then check the (current_role, new_role) * pair. */ if (tclass == policydb->process_class && (avd->allowed & policydb->process_trans_perms) && scontext->role != tcontext->role) { for (ra = policydb->role_allow; ra; ra = ra->next) { if (scontext->role == ra->role && tcontext->role == ra->new_role) break; } if (!ra) avd->allowed &= ~policydb->process_trans_perms; } /* * If the given source and target types have boundary * constraint, lazy checks have to mask any violated * permission and notice it to userspace via audit. */ type_attribute_bounds_av(policydb, scontext, tcontext, tclass, avd); } static int security_validtrans_handle_fail(struct selinux_policy *policy, struct sidtab_entry *oentry, struct sidtab_entry *nentry, struct sidtab_entry *tentry, u16 tclass) { struct policydb *p = &policy->policydb; struct sidtab *sidtab = policy->sidtab; char *o = NULL, *n = NULL, *t = NULL; u32 olen, nlen, tlen; if (sidtab_entry_to_string(p, sidtab, oentry, &o, &olen)) goto out; if (sidtab_entry_to_string(p, sidtab, nentry, &n, &nlen)) goto out; if (sidtab_entry_to_string(p, sidtab, tentry, &t, &tlen)) goto out; audit_log(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR, "op=security_validate_transition seresult=denied" " oldcontext=%s newcontext=%s taskcontext=%s tclass=%s", o, n, t, sym_name(p, SYM_CLASSES, tclass-1)); out: kfree(o); kfree(n); kfree(t); if (!enforcing_enabled()) return 0; return -EPERM; } static int security_compute_validatetrans(u32 oldsid, u32 newsid, u32 tasksid, u16 orig_tclass, bool user) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct sidtab_entry *oentry; struct sidtab_entry *nentry; struct sidtab_entry *tentry; struct class_datum *tclass_datum; struct constraint_node *constraint; u16 tclass; int rc = 0; if (!selinux_initialized()) return 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; if (!user) tclass = unmap_class(&policy->map, orig_tclass); else tclass = orig_tclass; if (!tclass || tclass > policydb->p_classes.nprim) { rc = -EINVAL; goto out; } tclass_datum = policydb->class_val_to_struct[tclass - 1]; oentry = sidtab_search_entry(sidtab, oldsid); if (!oentry) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, oldsid); rc = -EINVAL; goto out; } nentry = sidtab_search_entry(sidtab, newsid); if (!nentry) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, newsid); rc = -EINVAL; goto out; } tentry = sidtab_search_entry(sidtab, tasksid); if (!tentry) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, tasksid); rc = -EINVAL; goto out; } constraint = tclass_datum->validatetrans; while (constraint) { if (!constraint_expr_eval(policydb, &oentry->context, &nentry->context, &tentry->context, constraint->expr)) { if (user) rc = -EPERM; else rc = security_validtrans_handle_fail(policy, oentry, nentry, tentry, tclass); goto out; } constraint = constraint->next; } out: rcu_read_unlock(); return rc; } int security_validate_transition_user(u32 oldsid, u32 newsid, u32 tasksid, u16 tclass) { return security_compute_validatetrans(oldsid, newsid, tasksid, tclass, true); } int security_validate_transition(u32 oldsid, u32 newsid, u32 tasksid, u16 orig_tclass) { return security_compute_validatetrans(oldsid, newsid, tasksid, orig_tclass, false); } /* * security_bounded_transition - check whether the given * transition is directed to bounded, or not. * It returns 0, if @newsid is bounded by @oldsid. * Otherwise, it returns error code. * * @oldsid : current security identifier * @newsid : destinated security identifier */ int security_bounded_transition(u32 old_sid, u32 new_sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct sidtab_entry *old_entry, *new_entry; struct type_datum *type; u32 index; int rc; if (!selinux_initialized()) return 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; rc = -EINVAL; old_entry = sidtab_search_entry(sidtab, old_sid); if (!old_entry) { pr_err("SELinux: %s: unrecognized SID %u\n", __func__, old_sid); goto out; } rc = -EINVAL; new_entry = sidtab_search_entry(sidtab, new_sid); if (!new_entry) { pr_err("SELinux: %s: unrecognized SID %u\n", __func__, new_sid); goto out; } rc = 0; /* type/domain unchanged */ if (old_entry->context.type == new_entry->context.type) goto out; index = new_entry->context.type; while (true) { type = policydb->type_val_to_struct[index - 1]; BUG_ON(!type); /* not bounded anymore */ rc = -EPERM; if (!type->bounds) break; /* @newsid is bounded by @oldsid */ rc = 0; if (type->bounds == old_entry->context.type) break; index = type->bounds; } if (rc) { char *old_name = NULL; char *new_name = NULL; u32 length; if (!sidtab_entry_to_string(policydb, sidtab, old_entry, &old_name, &length) && !sidtab_entry_to_string(policydb, sidtab, new_entry, &new_name, &length)) { audit_log(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR, "op=security_bounded_transition " "seresult=denied " "oldcontext=%s newcontext=%s", old_name, new_name); } kfree(new_name); kfree(old_name); } out: rcu_read_unlock(); return rc; } static void avd_init(struct selinux_policy *policy, struct av_decision *avd) { avd->allowed = 0; avd->auditallow = 0; avd->auditdeny = 0xffffffff; if (policy) avd->seqno = policy->latest_granting; else avd->seqno = 0; avd->flags = 0; } static void update_xperms_extended_data(u8 specified, struct extended_perms_data *from, struct extended_perms_data *xp_data) { unsigned int i; switch (specified) { case AVTAB_XPERMS_IOCTLDRIVER: memset(xp_data->p, 0xff, sizeof(xp_data->p)); break; case AVTAB_XPERMS_IOCTLFUNCTION: case AVTAB_XPERMS_NLMSG: for (i = 0; i < ARRAY_SIZE(xp_data->p); i++) xp_data->p[i] |= from->p[i]; break; } } void services_compute_xperms_decision(struct extended_perms_decision *xpermd, struct avtab_node *node) { switch (node->datum.u.xperms->specified) { case AVTAB_XPERMS_IOCTLFUNCTION: case AVTAB_XPERMS_NLMSG: if (xpermd->driver != node->datum.u.xperms->driver) return; break; case AVTAB_XPERMS_IOCTLDRIVER: if (!security_xperm_test(node->datum.u.xperms->perms.p, xpermd->driver)) return; break; default: BUG(); } if (node->key.specified == AVTAB_XPERMS_ALLOWED) { xpermd->used |= XPERMS_ALLOWED; update_xperms_extended_data(node->datum.u.xperms->specified, &node->datum.u.xperms->perms, xpermd->allowed); } else if (node->key.specified == AVTAB_XPERMS_AUDITALLOW) { xpermd->used |= XPERMS_AUDITALLOW; update_xperms_extended_data(node->datum.u.xperms->specified, &node->datum.u.xperms->perms, xpermd->auditallow); } else if (node->key.specified == AVTAB_XPERMS_DONTAUDIT) { xpermd->used |= XPERMS_DONTAUDIT; update_xperms_extended_data(node->datum.u.xperms->specified, &node->datum.u.xperms->perms, xpermd->dontaudit); } else { BUG(); } } void security_compute_xperms_decision(u32 ssid, u32 tsid, u16 orig_tclass, u8 driver, struct extended_perms_decision *xpermd) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; u16 tclass; struct context *scontext, *tcontext; struct avtab_key avkey; struct avtab_node *node; struct ebitmap *sattr, *tattr; struct ebitmap_node *snode, *tnode; unsigned int i, j; xpermd->driver = driver; xpermd->used = 0; memset(xpermd->allowed->p, 0, sizeof(xpermd->allowed->p)); memset(xpermd->auditallow->p, 0, sizeof(xpermd->auditallow->p)); memset(xpermd->dontaudit->p, 0, sizeof(xpermd->dontaudit->p)); rcu_read_lock(); if (!selinux_initialized()) goto allow; policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; scontext = sidtab_search(sidtab, ssid); if (!scontext) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, ssid); goto out; } tcontext = sidtab_search(sidtab, tsid); if (!tcontext) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, tsid); goto out; } tclass = unmap_class(&policy->map, orig_tclass); if (unlikely(orig_tclass && !tclass)) { if (policydb->allow_unknown) goto allow; goto out; } if (unlikely(!tclass || tclass > policydb->p_classes.nprim)) { pr_warn_ratelimited("SELinux: Invalid class %hu\n", tclass); goto out; } avkey.target_class = tclass; avkey.specified = AVTAB_XPERMS; sattr = &policydb->type_attr_map_array[scontext->type - 1]; tattr = &policydb->type_attr_map_array[tcontext->type - 1]; ebitmap_for_each_positive_bit(sattr, snode, i) { ebitmap_for_each_positive_bit(tattr, tnode, j) { avkey.source_type = i + 1; avkey.target_type = j + 1; for (node = avtab_search_node(&policydb->te_avtab, &avkey); node; node = avtab_search_node_next(node, avkey.specified)) services_compute_xperms_decision(xpermd, node); cond_compute_xperms(&policydb->te_cond_avtab, &avkey, xpermd); } } out: rcu_read_unlock(); return; allow: memset(xpermd->allowed->p, 0xff, sizeof(xpermd->allowed->p)); goto out; } /** * security_compute_av - Compute access vector decisions. * @ssid: source security identifier * @tsid: target security identifier * @orig_tclass: target security class * @avd: access vector decisions * @xperms: extended permissions * * Compute a set of access vector decisions based on the * SID pair (@ssid, @tsid) for the permissions in @tclass. */ void security_compute_av(u32 ssid, u32 tsid, u16 orig_tclass, struct av_decision *avd, struct extended_perms *xperms) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; u16 tclass; struct context *scontext = NULL, *tcontext = NULL; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); avd_init(policy, avd); xperms->len = 0; if (!selinux_initialized()) goto allow; policydb = &policy->policydb; sidtab = policy->sidtab; scontext = sidtab_search(sidtab, ssid); if (!scontext) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, ssid); goto out; } /* permissive domain? */ if (ebitmap_get_bit(&policydb->permissive_map, scontext->type)) avd->flags |= AVD_FLAGS_PERMISSIVE; tcontext = sidtab_search(sidtab, tsid); if (!tcontext) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, tsid); goto out; } tclass = unmap_class(&policy->map, orig_tclass); if (unlikely(orig_tclass && !tclass)) { if (policydb->allow_unknown) goto allow; goto out; } context_struct_compute_av(policydb, scontext, tcontext, tclass, avd, xperms); map_decision(&policy->map, orig_tclass, avd, policydb->allow_unknown); out: rcu_read_unlock(); return; allow: avd->allowed = 0xffffffff; goto out; } void security_compute_av_user(u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct context *scontext = NULL, *tcontext = NULL; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); avd_init(policy, avd); if (!selinux_initialized()) goto allow; policydb = &policy->policydb; sidtab = policy->sidtab; scontext = sidtab_search(sidtab, ssid); if (!scontext) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, ssid); goto out; } /* permissive domain? */ if (ebitmap_get_bit(&policydb->permissive_map, scontext->type)) avd->flags |= AVD_FLAGS_PERMISSIVE; tcontext = sidtab_search(sidtab, tsid); if (!tcontext) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, tsid); goto out; } if (unlikely(!tclass)) { if (policydb->allow_unknown) goto allow; goto out; } context_struct_compute_av(policydb, scontext, tcontext, tclass, avd, NULL); out: rcu_read_unlock(); return; allow: avd->allowed = 0xffffffff; goto out; } /* * Write the security context string representation of * the context structure `context' into a dynamically * allocated string of the correct size. Set `*scontext' * to point to this string and set `*scontext_len' to * the length of the string. */ static int context_struct_to_string(struct policydb *p, struct context *context, char **scontext, u32 *scontext_len) { char *scontextp; if (scontext) *scontext = NULL; *scontext_len = 0; if (context->len) { *scontext_len = context->len; if (scontext) { *scontext = kstrdup(context->str, GFP_ATOMIC); if (!(*scontext)) return -ENOMEM; } return 0; } /* Compute the size of the context. */ *scontext_len += strlen(sym_name(p, SYM_USERS, context->user - 1)) + 1; *scontext_len += strlen(sym_name(p, SYM_ROLES, context->role - 1)) + 1; *scontext_len += strlen(sym_name(p, SYM_TYPES, context->type - 1)) + 1; *scontext_len += mls_compute_context_len(p, context); if (!scontext) return 0; /* Allocate space for the context; caller must free this space. */ scontextp = kmalloc(*scontext_len, GFP_ATOMIC); if (!scontextp) return -ENOMEM; *scontext = scontextp; /* * Copy the user name, role name and type name into the context. */ scontextp += sprintf(scontextp, "%s:%s:%s", sym_name(p, SYM_USERS, context->user - 1), sym_name(p, SYM_ROLES, context->role - 1), sym_name(p, SYM_TYPES, context->type - 1)); mls_sid_to_context(p, context, &scontextp); *scontextp = 0; return 0; } static int sidtab_entry_to_string(struct policydb *p, struct sidtab *sidtab, struct sidtab_entry *entry, char **scontext, u32 *scontext_len) { int rc = sidtab_sid2str_get(sidtab, entry, scontext, scontext_len); if (rc != -ENOENT) return rc; rc = context_struct_to_string(p, &entry->context, scontext, scontext_len); if (!rc && scontext) sidtab_sid2str_put(sidtab, entry, *scontext, *scontext_len); return rc; } #include "initial_sid_to_string.h" int security_sidtab_hash_stats(char *page) { struct selinux_policy *policy; int rc; if (!selinux_initialized()) { pr_err("SELinux: %s: called before initial load_policy\n", __func__); return -EINVAL; } rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); rc = sidtab_hash_stats(policy->sidtab, page); rcu_read_unlock(); return rc; } const char *security_get_initial_sid_context(u32 sid) { if (unlikely(sid > SECINITSID_NUM)) return NULL; return initial_sid_to_string[sid]; } static int security_sid_to_context_core(u32 sid, char **scontext, u32 *scontext_len, int force, int only_invalid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct sidtab_entry *entry; int rc = 0; if (scontext) *scontext = NULL; *scontext_len = 0; if (!selinux_initialized()) { if (sid <= SECINITSID_NUM) { char *scontextp; const char *s; /* * Before the policy is loaded, translate * SECINITSID_INIT to "kernel", because systemd and * libselinux < 2.6 take a getcon_raw() result that is * both non-null and not "kernel" to mean that a policy * is already loaded. */ if (sid == SECINITSID_INIT) sid = SECINITSID_KERNEL; s = initial_sid_to_string[sid]; if (!s) return -EINVAL; *scontext_len = strlen(s) + 1; if (!scontext) return 0; scontextp = kmemdup(s, *scontext_len, GFP_ATOMIC); if (!scontextp) return -ENOMEM; *scontext = scontextp; return 0; } pr_err("SELinux: %s: called before initial " "load_policy on unknown SID %d\n", __func__, sid); return -EINVAL; } rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; if (force) entry = sidtab_search_entry_force(sidtab, sid); else entry = sidtab_search_entry(sidtab, sid); if (!entry) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, sid); rc = -EINVAL; goto out_unlock; } if (only_invalid && !entry->context.len) goto out_unlock; rc = sidtab_entry_to_string(policydb, sidtab, entry, scontext, scontext_len); out_unlock: rcu_read_unlock(); return rc; } /** * security_sid_to_context - Obtain a context for a given SID. * @sid: security identifier, SID * @scontext: security context * @scontext_len: length in bytes * * Write the string representation of the context associated with @sid * into a dynamically allocated string of the correct size. Set @scontext * to point to this string and set @scontext_len to the length of the string. */ int security_sid_to_context(u32 sid, char **scontext, u32 *scontext_len) { return security_sid_to_context_core(sid, scontext, scontext_len, 0, 0); } int security_sid_to_context_force(u32 sid, char **scontext, u32 *scontext_len) { return security_sid_to_context_core(sid, scontext, scontext_len, 1, 0); } /** * security_sid_to_context_inval - Obtain a context for a given SID if it * is invalid. * @sid: security identifier, SID * @scontext: security context * @scontext_len: length in bytes * * Write the string representation of the context associated with @sid * into a dynamically allocated string of the correct size, but only if the * context is invalid in the current policy. Set @scontext to point to * this string (or NULL if the context is valid) and set @scontext_len to * the length of the string (or 0 if the context is valid). */ int security_sid_to_context_inval(u32 sid, char **scontext, u32 *scontext_len) { return security_sid_to_context_core(sid, scontext, scontext_len, 1, 1); } /* * Caveat: Mutates scontext. */ static int string_to_context_struct(struct policydb *pol, struct sidtab *sidtabp, char *scontext, struct context *ctx, u32 def_sid) { struct role_datum *role; struct type_datum *typdatum; struct user_datum *usrdatum; char *scontextp, *p, oldc; int rc = 0; context_init(ctx); /* Parse the security context. */ rc = -EINVAL; scontextp = scontext; /* Extract the user. */ p = scontextp; while (*p && *p != ':') p++; if (*p == 0) goto out; *p++ = 0; usrdatum = symtab_search(&pol->p_users, scontextp); if (!usrdatum) goto out; ctx->user = usrdatum->value; /* Extract role. */ scontextp = p; while (*p && *p != ':') p++; if (*p == 0) goto out; *p++ = 0; role = symtab_search(&pol->p_roles, scontextp); if (!role) goto out; ctx->role = role->value; /* Extract type. */ scontextp = p; while (*p && *p != ':') p++; oldc = *p; *p++ = 0; typdatum = symtab_search(&pol->p_types, scontextp); if (!typdatum || typdatum->attribute) goto out; ctx->type = typdatum->value; rc = mls_context_to_sid(pol, oldc, p, ctx, sidtabp, def_sid); if (rc) goto out; /* Check the validity of the new context. */ rc = -EINVAL; if (!policydb_context_isvalid(pol, ctx)) goto out; rc = 0; out: if (rc) context_destroy(ctx); return rc; } static int security_context_to_sid_core(const char *scontext, u32 scontext_len, u32 *sid, u32 def_sid, gfp_t gfp_flags, int force) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; char *scontext2, *str = NULL; struct context context; int rc = 0; /* An empty security context is never valid. */ if (!scontext_len) return -EINVAL; /* Copy the string to allow changes and ensure a NUL terminator */ scontext2 = kmemdup_nul(scontext, scontext_len, gfp_flags); if (!scontext2) return -ENOMEM; if (!selinux_initialized()) { u32 i; for (i = 1; i < SECINITSID_NUM; i++) { const char *s = initial_sid_to_string[i]; if (s && !strcmp(s, scontext2)) { *sid = i; goto out; } } *sid = SECINITSID_KERNEL; goto out; } *sid = SECSID_NULL; if (force) { /* Save another copy for storing in uninterpreted form */ rc = -ENOMEM; str = kstrdup(scontext2, gfp_flags); if (!str) goto out; } retry: rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; rc = string_to_context_struct(policydb, sidtab, scontext2, &context, def_sid); if (rc == -EINVAL && force) { context.str = str; context.len = strlen(str) + 1; str = NULL; } else if (rc) goto out_unlock; rc = sidtab_context_to_sid(sidtab, &context, sid); if (rc == -ESTALE) { rcu_read_unlock(); if (context.str) { str = context.str; context.str = NULL; } context_destroy(&context); goto retry; } context_destroy(&context); out_unlock: rcu_read_unlock(); out: kfree(scontext2); kfree(str); return rc; } /** * security_context_to_sid - Obtain a SID for a given security context. * @scontext: security context * @scontext_len: length in bytes * @sid: security identifier, SID * @gfp: context for the allocation * * Obtains a SID associated with the security context that * has the string representation specified by @scontext. * Returns -%EINVAL if the context is invalid, -%ENOMEM if insufficient * memory is available, or 0 on success. */ int security_context_to_sid(const char *scontext, u32 scontext_len, u32 *sid, gfp_t gfp) { return security_context_to_sid_core(scontext, scontext_len, sid, SECSID_NULL, gfp, 0); } int security_context_str_to_sid(const char *scontext, u32 *sid, gfp_t gfp) { return security_context_to_sid(scontext, strlen(scontext), sid, gfp); } /** * security_context_to_sid_default - Obtain a SID for a given security context, * falling back to specified default if needed. * * @scontext: security context * @scontext_len: length in bytes * @sid: security identifier, SID * @def_sid: default SID to assign on error * @gfp_flags: the allocator get-free-page (GFP) flags * * Obtains a SID associated with the security context that * has the string representation specified by @scontext. * The default SID is passed to the MLS layer to be used to allow * kernel labeling of the MLS field if the MLS field is not present * (for upgrading to MLS without full relabel). * Implicitly forces adding of the context even if it cannot be mapped yet. * Returns -%EINVAL if the context is invalid, -%ENOMEM if insufficient * memory is available, or 0 on success. */ int security_context_to_sid_default(const char *scontext, u32 scontext_len, u32 *sid, u32 def_sid, gfp_t gfp_flags) { return security_context_to_sid_core(scontext, scontext_len, sid, def_sid, gfp_flags, 1); } int security_context_to_sid_force(const char *scontext, u32 scontext_len, u32 *sid) { return security_context_to_sid_core(scontext, scontext_len, sid, SECSID_NULL, GFP_KERNEL, 1); } static int compute_sid_handle_invalid_context( struct selinux_policy *policy, struct sidtab_entry *sentry, struct sidtab_entry *tentry, u16 tclass, struct context *newcontext) { struct policydb *policydb = &policy->policydb; struct sidtab *sidtab = policy->sidtab; char *s = NULL, *t = NULL, *n = NULL; u32 slen, tlen, nlen; struct audit_buffer *ab; if (sidtab_entry_to_string(policydb, sidtab, sentry, &s, &slen)) goto out; if (sidtab_entry_to_string(policydb, sidtab, tentry, &t, &tlen)) goto out; if (context_struct_to_string(policydb, newcontext, &n, &nlen)) goto out; ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR); if (!ab) goto out; audit_log_format(ab, "op=security_compute_sid invalid_context="); /* no need to record the NUL with untrusted strings */ audit_log_n_untrustedstring(ab, n, nlen - 1); audit_log_format(ab, " scontext=%s tcontext=%s tclass=%s", s, t, sym_name(policydb, SYM_CLASSES, tclass-1)); audit_log_end(ab); out: kfree(s); kfree(t); kfree(n); if (!enforcing_enabled()) return 0; return -EACCES; } static void filename_compute_type(struct policydb *policydb, struct context *newcontext, u32 stype, u32 ttype, u16 tclass, const char *objname) { struct filename_trans_key ft; struct filename_trans_datum *datum; /* * Most filename trans rules are going to live in specific directories * like /dev or /var/run. This bitmap will quickly skip rule searches * if the ttype does not contain any rules. */ if (!ebitmap_get_bit(&policydb->filename_trans_ttypes, ttype)) return; ft.ttype = ttype; ft.tclass = tclass; ft.name = objname; datum = policydb_filenametr_search(policydb, &ft); while (datum) { if (ebitmap_get_bit(&datum->stypes, stype - 1)) { newcontext->type = datum->otype; return; } datum = datum->next; } } static int security_compute_sid(u32 ssid, u32 tsid, u16 orig_tclass, u16 specified, const char *objname, u32 *out_sid, bool kern) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct class_datum *cladatum; struct context *scontext, *tcontext, newcontext; struct sidtab_entry *sentry, *tentry; struct avtab_key avkey; struct avtab_node *avnode, *node; u16 tclass; int rc = 0; bool sock; if (!selinux_initialized()) { switch (orig_tclass) { case SECCLASS_PROCESS: /* kernel value */ *out_sid = ssid; break; default: *out_sid = tsid; break; } goto out; } retry: cladatum = NULL; context_init(&newcontext); rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); if (kern) { tclass = unmap_class(&policy->map, orig_tclass); sock = security_is_socket_class(orig_tclass); } else { tclass = orig_tclass; sock = security_is_socket_class(map_class(&policy->map, tclass)); } policydb = &policy->policydb; sidtab = policy->sidtab; sentry = sidtab_search_entry(sidtab, ssid); if (!sentry) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, ssid); rc = -EINVAL; goto out_unlock; } tentry = sidtab_search_entry(sidtab, tsid); if (!tentry) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, tsid); rc = -EINVAL; goto out_unlock; } scontext = &sentry->context; tcontext = &tentry->context; if (tclass && tclass <= policydb->p_classes.nprim) cladatum = policydb->class_val_to_struct[tclass - 1]; /* Set the user identity. */ switch (specified) { case AVTAB_TRANSITION: case AVTAB_CHANGE: if (cladatum && cladatum->default_user == DEFAULT_TARGET) { newcontext.user = tcontext->user; } else { /* notice this gets both DEFAULT_SOURCE and unset */ /* Use the process user identity. */ newcontext.user = scontext->user; } break; case AVTAB_MEMBER: /* Use the related object owner. */ newcontext.user = tcontext->user; break; } /* Set the role to default values. */ if (cladatum && cladatum->default_role == DEFAULT_SOURCE) { newcontext.role = scontext->role; } else if (cladatum && cladatum->default_role == DEFAULT_TARGET) { newcontext.role = tcontext->role; } else { if ((tclass == policydb->process_class) || sock) newcontext.role = scontext->role; else newcontext.role = OBJECT_R_VAL; } /* Set the type. * Look for a type transition/member/change rule. */ avkey.source_type = scontext->type; avkey.target_type = tcontext->type; avkey.target_class = tclass; avkey.specified = specified; avnode = avtab_search_node(&policydb->te_avtab, &avkey); /* If no permanent rule, also check for enabled conditional rules */ if (!avnode) { node = avtab_search_node(&policydb->te_cond_avtab, &avkey); for (; node; node = avtab_search_node_next(node, specified)) { if (node->key.specified & AVTAB_ENABLED) { avnode = node; break; } } } /* If a permanent rule is found, use the type from * the type transition/member/change rule. Otherwise, * set the type to its default values. */ if (avnode) { newcontext.type = avnode->datum.u.data; } else if (cladatum && cladatum->default_type == DEFAULT_SOURCE) { newcontext.type = scontext->type; } else if (cladatum && cladatum->default_type == DEFAULT_TARGET) { newcontext.type = tcontext->type; } else { if ((tclass == policydb->process_class) || sock) { /* Use the type of process. */ newcontext.type = scontext->type; } else { /* Use the type of the related object. */ newcontext.type = tcontext->type; } } /* if we have a objname this is a file trans check so check those rules */ if (objname) filename_compute_type(policydb, &newcontext, scontext->type, tcontext->type, tclass, objname); /* Check for class-specific changes. */ if (specified & AVTAB_TRANSITION) { /* Look for a role transition rule. */ struct role_trans_datum *rtd; struct role_trans_key rtk = { .role = scontext->role, .type = tcontext->type, .tclass = tclass, }; rtd = policydb_roletr_search(policydb, &rtk); if (rtd) newcontext.role = rtd->new_role; } /* Set the MLS attributes. This is done last because it may allocate memory. */ rc = mls_compute_sid(policydb, scontext, tcontext, tclass, specified, &newcontext, sock); if (rc) goto out_unlock; /* Check the validity of the context. */ if (!policydb_context_isvalid(policydb, &newcontext)) { rc = compute_sid_handle_invalid_context(policy, sentry, tentry, tclass, &newcontext); if (rc) goto out_unlock; } /* Obtain the sid for the context. */ rc = sidtab_context_to_sid(sidtab, &newcontext, out_sid); if (rc == -ESTALE) { rcu_read_unlock(); context_destroy(&newcontext); goto retry; } out_unlock: rcu_read_unlock(); context_destroy(&newcontext); out: return rc; } /** * security_transition_sid - Compute the SID for a new subject/object. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @qstr: object name * @out_sid: security identifier for new subject/object * * Compute a SID to use for labeling a new subject or object in the * class @tclass based on a SID pair (@ssid, @tsid). * Return -%EINVAL if any of the parameters are invalid, -%ENOMEM * if insufficient memory is available, or %0 if the new SID was * computed successfully. */ int security_transition_sid(u32 ssid, u32 tsid, u16 tclass, const struct qstr *qstr, u32 *out_sid) { return security_compute_sid(ssid, tsid, tclass, AVTAB_TRANSITION, qstr ? qstr->name : NULL, out_sid, true); } int security_transition_sid_user(u32 ssid, u32 tsid, u16 tclass, const char *objname, u32 *out_sid) { return security_compute_sid(ssid, tsid, tclass, AVTAB_TRANSITION, objname, out_sid, false); } /** * security_member_sid - Compute the SID for member selection. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @out_sid: security identifier for selected member * * Compute a SID to use when selecting a member of a polyinstantiated * object of class @tclass based on a SID pair (@ssid, @tsid). * Return -%EINVAL if any of the parameters are invalid, -%ENOMEM * if insufficient memory is available, or %0 if the SID was * computed successfully. */ int security_member_sid(u32 ssid, u32 tsid, u16 tclass, u32 *out_sid) { return security_compute_sid(ssid, tsid, tclass, AVTAB_MEMBER, NULL, out_sid, false); } /** * security_change_sid - Compute the SID for object relabeling. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @out_sid: security identifier for selected member * * Compute a SID to use for relabeling an object of class @tclass * based on a SID pair (@ssid, @tsid). * Return -%EINVAL if any of the parameters are invalid, -%ENOMEM * if insufficient memory is available, or %0 if the SID was * computed successfully. */ int security_change_sid(u32 ssid, u32 tsid, u16 tclass, u32 *out_sid) { return security_compute_sid(ssid, tsid, tclass, AVTAB_CHANGE, NULL, out_sid, false); } static inline int convert_context_handle_invalid_context( struct policydb *policydb, struct context *context) { char *s; u32 len; if (enforcing_enabled()) return -EINVAL; if (!context_struct_to_string(policydb, context, &s, &len)) { pr_warn("SELinux: Context %s would be invalid if enforcing\n", s); kfree(s); } return 0; } /** * services_convert_context - Convert a security context across policies. * @args: populated convert_context_args struct * @oldc: original context * @newc: converted context * @gfp_flags: allocation flags * * Convert the values in the security context structure @oldc from the values * specified in the policy @args->oldp to the values specified in the policy * @args->newp, storing the new context in @newc, and verifying that the * context is valid under the new policy. */ int services_convert_context(struct convert_context_args *args, struct context *oldc, struct context *newc, gfp_t gfp_flags) { struct ocontext *oc; struct role_datum *role; struct type_datum *typdatum; struct user_datum *usrdatum; char *s; u32 len; int rc; if (oldc->str) { s = kstrdup(oldc->str, gfp_flags); if (!s) return -ENOMEM; rc = string_to_context_struct(args->newp, NULL, s, newc, SECSID_NULL); if (rc == -EINVAL) { /* * Retain string representation for later mapping. * * IMPORTANT: We need to copy the contents of oldc->str * back into s again because string_to_context_struct() * may have garbled it. */ memcpy(s, oldc->str, oldc->len); context_init(newc); newc->str = s; newc->len = oldc->len; return 0; } kfree(s); if (rc) { /* Other error condition, e.g. ENOMEM. */ pr_err("SELinux: Unable to map context %s, rc = %d.\n", oldc->str, -rc); return rc; } pr_info("SELinux: Context %s became valid (mapped).\n", oldc->str); return 0; } context_init(newc); /* Convert the user. */ usrdatum = symtab_search(&args->newp->p_users, sym_name(args->oldp, SYM_USERS, oldc->user - 1)); if (!usrdatum) goto bad; newc->user = usrdatum->value; /* Convert the role. */ role = symtab_search(&args->newp->p_roles, sym_name(args->oldp, SYM_ROLES, oldc->role - 1)); if (!role) goto bad; newc->role = role->value; /* Convert the type. */ typdatum = symtab_search(&args->newp->p_types, sym_name(args->oldp, SYM_TYPES, oldc->type - 1)); if (!typdatum) goto bad; newc->type = typdatum->value; /* Convert the MLS fields if dealing with MLS policies */ if (args->oldp->mls_enabled && args->newp->mls_enabled) { rc = mls_convert_context(args->oldp, args->newp, oldc, newc); if (rc) goto bad; } else if (!args->oldp->mls_enabled && args->newp->mls_enabled) { /* * Switching between non-MLS and MLS policy: * ensure that the MLS fields of the context for all * existing entries in the sidtab are filled in with a * suitable default value, likely taken from one of the * initial SIDs. */ oc = args->newp->ocontexts[OCON_ISID]; while (oc && oc->sid[0] != SECINITSID_UNLABELED) oc = oc->next; if (!oc) { pr_err("SELinux: unable to look up" " the initial SIDs list\n"); goto bad; } rc = mls_range_set(newc, &oc->context[0].range); if (rc) goto bad; } /* Check the validity of the new context. */ if (!policydb_context_isvalid(args->newp, newc)) { rc = convert_context_handle_invalid_context(args->oldp, oldc); if (rc) goto bad; } return 0; bad: /* Map old representation to string and save it. */ rc = context_struct_to_string(args->oldp, oldc, &s, &len); if (rc) return rc; context_destroy(newc); newc->str = s; newc->len = len; pr_info("SELinux: Context %s became invalid (unmapped).\n", newc->str); return 0; } static void security_load_policycaps(struct selinux_policy *policy) { struct policydb *p; unsigned int i; struct ebitmap_node *node; p = &policy->policydb; for (i = 0; i < ARRAY_SIZE(selinux_state.policycap); i++) WRITE_ONCE(selinux_state.policycap[i], ebitmap_get_bit(&p->policycaps, i)); for (i = 0; i < ARRAY_SIZE(selinux_policycap_names); i++) pr_info("SELinux: policy capability %s=%d\n", selinux_policycap_names[i], ebitmap_get_bit(&p->policycaps, i)); ebitmap_for_each_positive_bit(&p->policycaps, node, i) { if (i >= ARRAY_SIZE(selinux_policycap_names)) pr_info("SELinux: unknown policy capability %u\n", i); } } static int security_preserve_bools(struct selinux_policy *oldpolicy, struct selinux_policy *newpolicy); static void selinux_policy_free(struct selinux_policy *policy) { if (!policy) return; sidtab_destroy(policy->sidtab); kfree(policy->map.mapping); policydb_destroy(&policy->policydb); kfree(policy->sidtab); kfree(policy); } static void selinux_policy_cond_free(struct selinux_policy *policy) { cond_policydb_destroy_dup(&policy->policydb); kfree(policy); } void selinux_policy_cancel(struct selinux_load_state *load_state) { struct selinux_state *state = &selinux_state; struct selinux_policy *oldpolicy; oldpolicy = rcu_dereference_protected(state->policy, lockdep_is_held(&state->policy_mutex)); sidtab_cancel_convert(oldpolicy->sidtab); selinux_policy_free(load_state->policy); kfree(load_state->convert_data); } static void selinux_notify_policy_change(u32 seqno) { /* Flush external caches and notify userspace of policy load */ avc_ss_reset(seqno); selnl_notify_policyload(seqno); selinux_status_update_policyload(seqno); selinux_netlbl_cache_invalidate(); selinux_xfrm_notify_policyload(); selinux_ima_measure_state_locked(); } void selinux_policy_commit(struct selinux_load_state *load_state) { struct selinux_state *state = &selinux_state; struct selinux_policy *oldpolicy, *newpolicy = load_state->policy; unsigned long flags; u32 seqno; oldpolicy = rcu_dereference_protected(state->policy, lockdep_is_held(&state->policy_mutex)); /* If switching between different policy types, log MLS status */ if (oldpolicy) { if (oldpolicy->policydb.mls_enabled && !newpolicy->policydb.mls_enabled) pr_info("SELinux: Disabling MLS support...\n"); else if (!oldpolicy->policydb.mls_enabled && newpolicy->policydb.mls_enabled) pr_info("SELinux: Enabling MLS support...\n"); } /* Set latest granting seqno for new policy. */ if (oldpolicy) newpolicy->latest_granting = oldpolicy->latest_granting + 1; else newpolicy->latest_granting = 1; seqno = newpolicy->latest_granting; /* Install the new policy. */ if (oldpolicy) { sidtab_freeze_begin(oldpolicy->sidtab, &flags); rcu_assign_pointer(state->policy, newpolicy); sidtab_freeze_end(oldpolicy->sidtab, &flags); } else { rcu_assign_pointer(state->policy, newpolicy); } /* Load the policycaps from the new policy */ security_load_policycaps(newpolicy); if (!selinux_initialized()) { /* * After first policy load, the security server is * marked as initialized and ready to handle requests and * any objects created prior to policy load are then labeled. */ selinux_mark_initialized(); selinux_complete_init(); } /* Free the old policy */ synchronize_rcu(); selinux_policy_free(oldpolicy); kfree(load_state->convert_data); /* Notify others of the policy change */ selinux_notify_policy_change(seqno); } /** * security_load_policy - Load a security policy configuration. * @data: binary policy data * @len: length of data in bytes * @load_state: policy load state * * Load a new set of security policy configuration data, * validate it and convert the SID table as necessary. * This function will flush the access vector cache after * loading the new policy. */ int security_load_policy(void *data, size_t len, struct selinux_load_state *load_state) { struct selinux_state *state = &selinux_state; struct selinux_policy *newpolicy, *oldpolicy; struct selinux_policy_convert_data *convert_data; int rc = 0; struct policy_file file = { data, len }, *fp = &file; newpolicy = kzalloc(sizeof(*newpolicy), GFP_KERNEL); if (!newpolicy) return -ENOMEM; newpolicy->sidtab = kzalloc(sizeof(*newpolicy->sidtab), GFP_KERNEL); if (!newpolicy->sidtab) { rc = -ENOMEM; goto err_policy; } rc = policydb_read(&newpolicy->policydb, fp); if (rc) goto err_sidtab; newpolicy->policydb.len = len; rc = selinux_set_mapping(&newpolicy->policydb, secclass_map, &newpolicy->map); if (rc) goto err_policydb; rc = policydb_load_isids(&newpolicy->policydb, newpolicy->sidtab); if (rc) { pr_err("SELinux: unable to load the initial SIDs\n"); goto err_mapping; } if (!selinux_initialized()) { /* First policy load, so no need to preserve state from old policy */ load_state->policy = newpolicy; load_state->convert_data = NULL; return 0; } oldpolicy = rcu_dereference_protected(state->policy, lockdep_is_held(&state->policy_mutex)); /* Preserve active boolean values from the old policy */ rc = security_preserve_bools(oldpolicy, newpolicy); if (rc) { pr_err("SELinux: unable to preserve booleans\n"); goto err_free_isids; } /* * Convert the internal representations of contexts * in the new SID table. */ convert_data = kmalloc(sizeof(*convert_data), GFP_KERNEL); if (!convert_data) { rc = -ENOMEM; goto err_free_isids; } convert_data->args.oldp = &oldpolicy->policydb; convert_data->args.newp = &newpolicy->policydb; convert_data->sidtab_params.args = &convert_data->args; convert_data->sidtab_params.target = newpolicy->sidtab; rc = sidtab_convert(oldpolicy->sidtab, &convert_data->sidtab_params); if (rc) { pr_err("SELinux: unable to convert the internal" " representation of contexts in the new SID" " table\n"); goto err_free_convert_data; } load_state->policy = newpolicy; load_state->convert_data = convert_data; return 0; err_free_convert_data: kfree(convert_data); err_free_isids: sidtab_destroy(newpolicy->sidtab); err_mapping: kfree(newpolicy->map.mapping); err_policydb: policydb_destroy(&newpolicy->policydb); err_sidtab: kfree(newpolicy->sidtab); err_policy: kfree(newpolicy); return rc; } /** * ocontext_to_sid - Helper to safely get sid for an ocontext * @sidtab: SID table * @c: ocontext structure * @index: index of the context entry (0 or 1) * @out_sid: pointer to the resulting SID value * * For all ocontexts except OCON_ISID the SID fields are populated * on-demand when needed. Since updating the SID value is an SMP-sensitive * operation, this helper must be used to do that safely. * * WARNING: This function may return -ESTALE, indicating that the caller * must retry the operation after re-acquiring the policy pointer! */ static int ocontext_to_sid(struct sidtab *sidtab, struct ocontext *c, size_t index, u32 *out_sid) { int rc; u32 sid; /* Ensure the associated sidtab entry is visible to this thread. */ sid = smp_load_acquire(&c->sid[index]); if (!sid) { rc = sidtab_context_to_sid(sidtab, &c->context[index], &sid); if (rc) return rc; /* * Ensure the new sidtab entry is visible to other threads * when they see the SID. */ smp_store_release(&c->sid[index], sid); } *out_sid = sid; return 0; } /** * security_port_sid - Obtain the SID for a port. * @protocol: protocol number * @port: port number * @out_sid: security identifier */ int security_port_sid(u8 protocol, u16 port, u32 *out_sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct ocontext *c; int rc; if (!selinux_initialized()) { *out_sid = SECINITSID_PORT; return 0; } retry: rc = 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; c = policydb->ocontexts[OCON_PORT]; while (c) { if (c->u.port.protocol == protocol && c->u.port.low_port <= port && c->u.port.high_port >= port) break; c = c->next; } if (c) { rc = ocontext_to_sid(sidtab, c, 0, out_sid); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) goto out; } else { *out_sid = SECINITSID_PORT; } out: rcu_read_unlock(); return rc; } /** * security_ib_pkey_sid - Obtain the SID for a pkey. * @subnet_prefix: Subnet Prefix * @pkey_num: pkey number * @out_sid: security identifier */ int security_ib_pkey_sid(u64 subnet_prefix, u16 pkey_num, u32 *out_sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct ocontext *c; int rc; if (!selinux_initialized()) { *out_sid = SECINITSID_UNLABELED; return 0; } retry: rc = 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; c = policydb->ocontexts[OCON_IBPKEY]; while (c) { if (c->u.ibpkey.low_pkey <= pkey_num && c->u.ibpkey.high_pkey >= pkey_num && c->u.ibpkey.subnet_prefix == subnet_prefix) break; c = c->next; } if (c) { rc = ocontext_to_sid(sidtab, c, 0, out_sid); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) goto out; } else *out_sid = SECINITSID_UNLABELED; out: rcu_read_unlock(); return rc; } /** * security_ib_endport_sid - Obtain the SID for a subnet management interface. * @dev_name: device name * @port_num: port number * @out_sid: security identifier */ int security_ib_endport_sid(const char *dev_name, u8 port_num, u32 *out_sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct ocontext *c; int rc; if (!selinux_initialized()) { *out_sid = SECINITSID_UNLABELED; return 0; } retry: rc = 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; c = policydb->ocontexts[OCON_IBENDPORT]; while (c) { if (c->u.ibendport.port == port_num && !strncmp(c->u.ibendport.dev_name, dev_name, IB_DEVICE_NAME_MAX)) break; c = c->next; } if (c) { rc = ocontext_to_sid(sidtab, c, 0, out_sid); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) goto out; } else *out_sid = SECINITSID_UNLABELED; out: rcu_read_unlock(); return rc; } /** * security_netif_sid - Obtain the SID for a network interface. * @name: interface name * @if_sid: interface SID */ int security_netif_sid(char *name, u32 *if_sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; int rc; struct ocontext *c; if (!selinux_initialized()) { *if_sid = SECINITSID_NETIF; return 0; } retry: rc = 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; c = policydb->ocontexts[OCON_NETIF]; while (c) { if (strcmp(name, c->u.name) == 0) break; c = c->next; } if (c) { rc = ocontext_to_sid(sidtab, c, 0, if_sid); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) goto out; } else *if_sid = SECINITSID_NETIF; out: rcu_read_unlock(); return rc; } static int match_ipv6_addrmask(u32 *input, u32 *addr, u32 *mask) { int i, fail = 0; for (i = 0; i < 4; i++) if (addr[i] != (input[i] & mask[i])) { fail = 1; break; } return !fail; } /** * security_node_sid - Obtain the SID for a node (host). * @domain: communication domain aka address family * @addrp: address * @addrlen: address length in bytes * @out_sid: security identifier */ int security_node_sid(u16 domain, void *addrp, u32 addrlen, u32 *out_sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; int rc; struct ocontext *c; if (!selinux_initialized()) { *out_sid = SECINITSID_NODE; return 0; } retry: rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; switch (domain) { case AF_INET: { u32 addr; rc = -EINVAL; if (addrlen != sizeof(u32)) goto out; addr = *((u32 *)addrp); c = policydb->ocontexts[OCON_NODE]; while (c) { if (c->u.node.addr == (addr & c->u.node.mask)) break; c = c->next; } break; } case AF_INET6: rc = -EINVAL; if (addrlen != sizeof(u64) * 2) goto out; c = policydb->ocontexts[OCON_NODE6]; while (c) { if (match_ipv6_addrmask(addrp, c->u.node6.addr, c->u.node6.mask)) break; c = c->next; } break; default: rc = 0; *out_sid = SECINITSID_NODE; goto out; } if (c) { rc = ocontext_to_sid(sidtab, c, 0, out_sid); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) goto out; } else { *out_sid = SECINITSID_NODE; } rc = 0; out: rcu_read_unlock(); return rc; } #define SIDS_NEL 25 /** * security_get_user_sids - Obtain reachable SIDs for a user. * @fromsid: starting SID * @username: username * @sids: array of reachable SIDs for user * @nel: number of elements in @sids * * Generate the set of SIDs for legal security contexts * for a given user that can be reached by @fromsid. * Set *@sids to point to a dynamically allocated * array containing the set of SIDs. Set *@nel to the * number of elements in the array. */ int security_get_user_sids(u32 fromsid, char *username, u32 **sids, u32 *nel) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct context *fromcon, usercon; u32 *mysids = NULL, *mysids2, sid; u32 i, j, mynel, maxnel = SIDS_NEL; struct user_datum *user; struct role_datum *role; struct ebitmap_node *rnode, *tnode; int rc; *sids = NULL; *nel = 0; if (!selinux_initialized()) return 0; mysids = kcalloc(maxnel, sizeof(*mysids), GFP_KERNEL); if (!mysids) return -ENOMEM; retry: mynel = 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; context_init(&usercon); rc = -EINVAL; fromcon = sidtab_search(sidtab, fromsid); if (!fromcon) goto out_unlock; rc = -EINVAL; user = symtab_search(&policydb->p_users, username); if (!user) goto out_unlock; usercon.user = user->value; ebitmap_for_each_positive_bit(&user->roles, rnode, i) { role = policydb->role_val_to_struct[i]; usercon.role = i + 1; ebitmap_for_each_positive_bit(&role->types, tnode, j) { usercon.type = j + 1; if (mls_setup_user_range(policydb, fromcon, user, &usercon)) continue; rc = sidtab_context_to_sid(sidtab, &usercon, &sid); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) goto out_unlock; if (mynel < maxnel) { mysids[mynel++] = sid; } else { rc = -ENOMEM; maxnel += SIDS_NEL; mysids2 = kcalloc(maxnel, sizeof(*mysids2), GFP_ATOMIC); if (!mysids2) goto out_unlock; memcpy(mysids2, mysids, mynel * sizeof(*mysids2)); kfree(mysids); mysids = mysids2; mysids[mynel++] = sid; } } } rc = 0; out_unlock: rcu_read_unlock(); if (rc || !mynel) { kfree(mysids); return rc; } rc = -ENOMEM; mysids2 = kcalloc(mynel, sizeof(*mysids2), GFP_KERNEL); if (!mysids2) { kfree(mysids); return rc; } for (i = 0, j = 0; i < mynel; i++) { struct av_decision dummy_avd; rc = avc_has_perm_noaudit(fromsid, mysids[i], SECCLASS_PROCESS, /* kernel value */ PROCESS__TRANSITION, AVC_STRICT, &dummy_avd); if (!rc) mysids2[j++] = mysids[i]; cond_resched(); } kfree(mysids); *sids = mysids2; *nel = j; return 0; } /** * __security_genfs_sid - Helper to obtain a SID for a file in a filesystem * @policy: policy * @fstype: filesystem type * @path: path from root of mount * @orig_sclass: file security class * @sid: SID for path * * Obtain a SID to use for a file in a filesystem that * cannot support xattr or use a fixed labeling behavior like * transition SIDs or task SIDs. * * WARNING: This function may return -ESTALE, indicating that the caller * must retry the operation after re-acquiring the policy pointer! */ static inline int __security_genfs_sid(struct selinux_policy *policy, const char *fstype, const char *path, u16 orig_sclass, u32 *sid) { struct policydb *policydb = &policy->policydb; struct sidtab *sidtab = policy->sidtab; u16 sclass; struct genfs *genfs; struct ocontext *c; int cmp = 0; while (path[0] == '/' && path[1] == '/') path++; sclass = unmap_class(&policy->map, orig_sclass); *sid = SECINITSID_UNLABELED; for (genfs = policydb->genfs; genfs; genfs = genfs->next) { cmp = strcmp(fstype, genfs->fstype); if (cmp <= 0) break; } if (!genfs || cmp) return -ENOENT; for (c = genfs->head; c; c = c->next) { size_t len = strlen(c->u.name); if ((!c->v.sclass || sclass == c->v.sclass) && (strncmp(c->u.name, path, len) == 0)) break; } if (!c) return -ENOENT; return ocontext_to_sid(sidtab, c, 0, sid); } /** * security_genfs_sid - Obtain a SID for a file in a filesystem * @fstype: filesystem type * @path: path from root of mount * @orig_sclass: file security class * @sid: SID for path * * Acquire policy_rwlock before calling __security_genfs_sid() and release * it afterward. */ int security_genfs_sid(const char *fstype, const char *path, u16 orig_sclass, u32 *sid) { struct selinux_policy *policy; int retval; if (!selinux_initialized()) { *sid = SECINITSID_UNLABELED; return 0; } do { rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); retval = __security_genfs_sid(policy, fstype, path, orig_sclass, sid); rcu_read_unlock(); } while (retval == -ESTALE); return retval; } int selinux_policy_genfs_sid(struct selinux_policy *policy, const char *fstype, const char *path, u16 orig_sclass, u32 *sid) { /* no lock required, policy is not yet accessible by other threads */ return __security_genfs_sid(policy, fstype, path, orig_sclass, sid); } /** * security_fs_use - Determine how to handle labeling for a filesystem. * @sb: superblock in question */ int security_fs_use(struct super_block *sb) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; int rc; struct ocontext *c; struct superblock_security_struct *sbsec = selinux_superblock(sb); const char *fstype = sb->s_type->name; if (!selinux_initialized()) { sbsec->behavior = SECURITY_FS_USE_NONE; sbsec->sid = SECINITSID_UNLABELED; return 0; } retry: rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; c = policydb->ocontexts[OCON_FSUSE]; while (c) { if (strcmp(fstype, c->u.name) == 0) break; c = c->next; } if (c) { sbsec->behavior = c->v.behavior; rc = ocontext_to_sid(sidtab, c, 0, &sbsec->sid); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) goto out; } else { rc = __security_genfs_sid(policy, fstype, "/", SECCLASS_DIR, &sbsec->sid); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) { sbsec->behavior = SECURITY_FS_USE_NONE; rc = 0; } else { sbsec->behavior = SECURITY_FS_USE_GENFS; } } out: rcu_read_unlock(); return rc; } int security_get_bools(struct selinux_policy *policy, u32 *len, char ***names, int **values) { struct policydb *policydb; u32 i; int rc; policydb = &policy->policydb; *names = NULL; *values = NULL; rc = 0; *len = policydb->p_bools.nprim; if (!*len) goto out; rc = -ENOMEM; *names = kcalloc(*len, sizeof(char *), GFP_ATOMIC); if (!*names) goto err; rc = -ENOMEM; *values = kcalloc(*len, sizeof(int), GFP_ATOMIC); if (!*values) goto err; for (i = 0; i < *len; i++) { (*values)[i] = policydb->bool_val_to_struct[i]->state; rc = -ENOMEM; (*names)[i] = kstrdup(sym_name(policydb, SYM_BOOLS, i), GFP_ATOMIC); if (!(*names)[i]) goto err; } rc = 0; out: return rc; err: if (*names) { for (i = 0; i < *len; i++) kfree((*names)[i]); kfree(*names); } kfree(*values); *len = 0; *names = NULL; *values = NULL; goto out; } int security_set_bools(u32 len, int *values) { struct selinux_state *state = &selinux_state; struct selinux_policy *newpolicy, *oldpolicy; int rc; u32 i, seqno = 0; if (!selinux_initialized()) return -EINVAL; oldpolicy = rcu_dereference_protected(state->policy, lockdep_is_held(&state->policy_mutex)); /* Consistency check on number of booleans, should never fail */ if (WARN_ON(len != oldpolicy->policydb.p_bools.nprim)) return -EINVAL; newpolicy = kmemdup(oldpolicy, sizeof(*newpolicy), GFP_KERNEL); if (!newpolicy) return -ENOMEM; /* * Deep copy only the parts of the policydb that might be * modified as a result of changing booleans. */ rc = cond_policydb_dup(&newpolicy->policydb, &oldpolicy->policydb); if (rc) { kfree(newpolicy); return -ENOMEM; } /* Update the boolean states in the copy */ for (i = 0; i < len; i++) { int new_state = !!values[i]; int old_state = newpolicy->policydb.bool_val_to_struct[i]->state; if (new_state != old_state) { audit_log(audit_context(), GFP_ATOMIC, AUDIT_MAC_CONFIG_CHANGE, "bool=%s val=%d old_val=%d auid=%u ses=%u", sym_name(&newpolicy->policydb, SYM_BOOLS, i), new_state, old_state, from_kuid(&init_user_ns, audit_get_loginuid(current)), audit_get_sessionid(current)); newpolicy->policydb.bool_val_to_struct[i]->state = new_state; } } /* Re-evaluate the conditional rules in the copy */ evaluate_cond_nodes(&newpolicy->policydb); /* Set latest granting seqno for new policy */ newpolicy->latest_granting = oldpolicy->latest_granting + 1; seqno = newpolicy->latest_granting; /* Install the new policy */ rcu_assign_pointer(state->policy, newpolicy); /* * Free the conditional portions of the old policydb * that were copied for the new policy, and the oldpolicy * structure itself but not what it references. */ synchronize_rcu(); selinux_policy_cond_free(oldpolicy); /* Notify others of the policy change */ selinux_notify_policy_change(seqno); return 0; } int security_get_bool_value(u32 index) { struct selinux_policy *policy; struct policydb *policydb; int rc; u32 len; if (!selinux_initialized()) return 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; rc = -EFAULT; len = policydb->p_bools.nprim; if (index >= len) goto out; rc = policydb->bool_val_to_struct[index]->state; out: rcu_read_unlock(); return rc; } static int security_preserve_bools(struct selinux_policy *oldpolicy, struct selinux_policy *newpolicy) { int rc, *bvalues = NULL; char **bnames = NULL; struct cond_bool_datum *booldatum; u32 i, nbools = 0; rc = security_get_bools(oldpolicy, &nbools, &bnames, &bvalues); if (rc) goto out; for (i = 0; i < nbools; i++) { booldatum = symtab_search(&newpolicy->policydb.p_bools, bnames[i]); if (booldatum) booldatum->state = bvalues[i]; } evaluate_cond_nodes(&newpolicy->policydb); out: if (bnames) { for (i = 0; i < nbools; i++) kfree(bnames[i]); } kfree(bnames); kfree(bvalues); return rc; } /* * security_sid_mls_copy() - computes a new sid based on the given * sid and the mls portion of mls_sid. */ int security_sid_mls_copy(u32 sid, u32 mls_sid, u32 *new_sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct context *context1; struct context *context2; struct context newcon; char *s; u32 len; int rc; if (!selinux_initialized()) { *new_sid = sid; return 0; } retry: rc = 0; context_init(&newcon); rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; if (!policydb->mls_enabled) { *new_sid = sid; goto out_unlock; } rc = -EINVAL; context1 = sidtab_search(sidtab, sid); if (!context1) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, sid); goto out_unlock; } rc = -EINVAL; context2 = sidtab_search(sidtab, mls_sid); if (!context2) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, mls_sid); goto out_unlock; } newcon.user = context1->user; newcon.role = context1->role; newcon.type = context1->type; rc = mls_context_cpy(&newcon, context2); if (rc) goto out_unlock; /* Check the validity of the new context. */ if (!policydb_context_isvalid(policydb, &newcon)) { rc = convert_context_handle_invalid_context(policydb, &newcon); if (rc) { if (!context_struct_to_string(policydb, &newcon, &s, &len)) { struct audit_buffer *ab; ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR); audit_log_format(ab, "op=security_sid_mls_copy invalid_context="); /* don't record NUL with untrusted strings */ audit_log_n_untrustedstring(ab, s, len - 1); audit_log_end(ab); kfree(s); } goto out_unlock; } } rc = sidtab_context_to_sid(sidtab, &newcon, new_sid); if (rc == -ESTALE) { rcu_read_unlock(); context_destroy(&newcon); goto retry; } out_unlock: rcu_read_unlock(); context_destroy(&newcon); return rc; } /** * security_net_peersid_resolve - Compare and resolve two network peer SIDs * @nlbl_sid: NetLabel SID * @nlbl_type: NetLabel labeling protocol type * @xfrm_sid: XFRM SID * @peer_sid: network peer sid * * Description: * Compare the @nlbl_sid and @xfrm_sid values and if the two SIDs can be * resolved into a single SID it is returned via @peer_sid and the function * returns zero. Otherwise @peer_sid is set to SECSID_NULL and the function * returns a negative value. A table summarizing the behavior is below: * * | function return | @sid * ------------------------------+-----------------+----------------- * no peer labels | 0 | SECSID_NULL * single peer label | 0 | <peer_label> * multiple, consistent labels | 0 | <peer_label> * multiple, inconsistent labels | -<errno> | SECSID_NULL * */ int security_net_peersid_resolve(u32 nlbl_sid, u32 nlbl_type, u32 xfrm_sid, u32 *peer_sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; int rc; struct context *nlbl_ctx; struct context *xfrm_ctx; *peer_sid = SECSID_NULL; /* handle the common (which also happens to be the set of easy) cases * right away, these two if statements catch everything involving a * single or absent peer SID/label */ if (xfrm_sid == SECSID_NULL) { *peer_sid = nlbl_sid; return 0; } /* NOTE: an nlbl_type == NETLBL_NLTYPE_UNLABELED is a "fallback" label * and is treated as if nlbl_sid == SECSID_NULL when a XFRM SID/label * is present */ if (nlbl_sid == SECSID_NULL || nlbl_type == NETLBL_NLTYPE_UNLABELED) { *peer_sid = xfrm_sid; return 0; } if (!selinux_initialized()) return 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; /* * We don't need to check initialized here since the only way both * nlbl_sid and xfrm_sid are not equal to SECSID_NULL would be if the * security server was initialized and state->initialized was true. */ if (!policydb->mls_enabled) { rc = 0; goto out; } rc = -EINVAL; nlbl_ctx = sidtab_search(sidtab, nlbl_sid); if (!nlbl_ctx) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, nlbl_sid); goto out; } rc = -EINVAL; xfrm_ctx = sidtab_search(sidtab, xfrm_sid); if (!xfrm_ctx) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, xfrm_sid); goto out; } rc = (mls_context_cmp(nlbl_ctx, xfrm_ctx) ? 0 : -EACCES); if (rc) goto out; /* at present NetLabel SIDs/labels really only carry MLS * information so if the MLS portion of the NetLabel SID * matches the MLS portion of the labeled XFRM SID/label * then pass along the XFRM SID as it is the most * expressive */ *peer_sid = xfrm_sid; out: rcu_read_unlock(); return rc; } static int get_classes_callback(void *k, void *d, void *args) { struct class_datum *datum = d; char *name = k, **classes = args; u32 value = datum->value - 1; classes[value] = kstrdup(name, GFP_ATOMIC); if (!classes[value]) return -ENOMEM; return 0; } int security_get_classes(struct selinux_policy *policy, char ***classes, u32 *nclasses) { struct policydb *policydb; int rc; policydb = &policy->policydb; rc = -ENOMEM; *nclasses = policydb->p_classes.nprim; *classes = kcalloc(*nclasses, sizeof(**classes), GFP_ATOMIC); if (!*classes) goto out; rc = hashtab_map(&policydb->p_classes.table, get_classes_callback, *classes); if (rc) { u32 i; for (i = 0; i < *nclasses; i++) kfree((*classes)[i]); kfree(*classes); } out: return rc; } static int get_permissions_callback(void *k, void *d, void *args) { struct perm_datum *datum = d; char *name = k, **perms = args; u32 value = datum->value - 1; perms[value] = kstrdup(name, GFP_ATOMIC); if (!perms[value]) return -ENOMEM; return 0; } int security_get_permissions(struct selinux_policy *policy, const char *class, char ***perms, u32 *nperms) { struct policydb *policydb; u32 i; int rc; struct class_datum *match; policydb = &policy->policydb; rc = -EINVAL; match = symtab_search(&policydb->p_classes, class); if (!match) { pr_err("SELinux: %s: unrecognized class %s\n", __func__, class); goto out; } rc = -ENOMEM; *nperms = match->permissions.nprim; *perms = kcalloc(*nperms, sizeof(**perms), GFP_ATOMIC); if (!*perms) goto out; if (match->comdatum) { rc = hashtab_map(&match->comdatum->permissions.table, get_permissions_callback, *perms); if (rc) goto err; } rc = hashtab_map(&match->permissions.table, get_permissions_callback, *perms); if (rc) goto err; out: return rc; err: for (i = 0; i < *nperms; i++) kfree((*perms)[i]); kfree(*perms); return rc; } int security_get_reject_unknown(void) { struct selinux_policy *policy; int value; if (!selinux_initialized()) return 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); value = policy->policydb.reject_unknown; rcu_read_unlock(); return value; } int security_get_allow_unknown(void) { struct selinux_policy *policy; int value; if (!selinux_initialized()) return 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); value = policy->policydb.allow_unknown; rcu_read_unlock(); return value; } /** * security_policycap_supported - Check for a specific policy capability * @req_cap: capability * * Description: * This function queries the currently loaded policy to see if it supports the * capability specified by @req_cap. Returns true (1) if the capability is * supported, false (0) if it isn't supported. * */ int security_policycap_supported(unsigned int req_cap) { struct selinux_policy *policy; int rc; if (!selinux_initialized()) return 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); rc = ebitmap_get_bit(&policy->policydb.policycaps, req_cap); rcu_read_unlock(); return rc; } struct selinux_audit_rule { u32 au_seqno; struct context au_ctxt; }; void selinux_audit_rule_free(void *vrule) { struct selinux_audit_rule *rule = vrule; if (rule) { context_destroy(&rule->au_ctxt); kfree(rule); } } int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule, gfp_t gfp) { struct selinux_state *state = &selinux_state; struct selinux_policy *policy; struct policydb *policydb; struct selinux_audit_rule *tmprule; struct role_datum *roledatum; struct type_datum *typedatum; struct user_datum *userdatum; struct selinux_audit_rule **rule = (struct selinux_audit_rule **)vrule; int rc = 0; *rule = NULL; if (!selinux_initialized()) return -EOPNOTSUPP; switch (field) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: /* only 'equals' and 'not equals' fit user, role, and type */ if (op != Audit_equal && op != Audit_not_equal) return -EINVAL; break; case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: /* we do not allow a range, indicated by the presence of '-' */ if (strchr(rulestr, '-')) return -EINVAL; break; default: /* only the above fields are valid */ return -EINVAL; } tmprule = kzalloc(sizeof(struct selinux_audit_rule), gfp); if (!tmprule) return -ENOMEM; context_init(&tmprule->au_ctxt); rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; tmprule->au_seqno = policy->latest_granting; switch (field) { case AUDIT_SUBJ_USER: case AUDIT_OBJ_USER: userdatum = symtab_search(&policydb->p_users, rulestr); if (!userdatum) { rc = -EINVAL; goto err; } tmprule->au_ctxt.user = userdatum->value; break; case AUDIT_SUBJ_ROLE: case AUDIT_OBJ_ROLE: roledatum = symtab_search(&policydb->p_roles, rulestr); if (!roledatum) { rc = -EINVAL; goto err; } tmprule->au_ctxt.role = roledatum->value; break; case AUDIT_SUBJ_TYPE: case AUDIT_OBJ_TYPE: typedatum = symtab_search(&policydb->p_types, rulestr); if (!typedatum) { rc = -EINVAL; goto err; } tmprule->au_ctxt.type = typedatum->value; break; case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: rc = mls_from_string(policydb, rulestr, &tmprule->au_ctxt, GFP_ATOMIC); if (rc) goto err; break; } rcu_read_unlock(); *rule = tmprule; return 0; err: rcu_read_unlock(); selinux_audit_rule_free(tmprule); *rule = NULL; return rc; } /* Check to see if the rule contains any selinux fields */ int selinux_audit_rule_known(struct audit_krule *rule) { u32 i; for (i = 0; i < rule->field_count; i++) { struct audit_field *f = &rule->fields[i]; switch (f->type) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: return 1; } } return 0; } int selinux_audit_rule_match(struct lsm_prop *prop, u32 field, u32 op, void *vrule) { struct selinux_state *state = &selinux_state; struct selinux_policy *policy; struct context *ctxt; struct mls_level *level; struct selinux_audit_rule *rule = vrule; int match = 0; if (unlikely(!rule)) { WARN_ONCE(1, "selinux_audit_rule_match: missing rule\n"); return -ENOENT; } if (!selinux_initialized()) return 0; rcu_read_lock(); policy = rcu_dereference(state->policy); if (rule->au_seqno < policy->latest_granting) { match = -ESTALE; goto out; } ctxt = sidtab_search(policy->sidtab, prop->selinux.secid); if (unlikely(!ctxt)) { WARN_ONCE(1, "selinux_audit_rule_match: unrecognized SID %d\n", prop->selinux.secid); match = -ENOENT; goto out; } /* a field/op pair that is not caught here will simply fall through without a match */ switch (field) { case AUDIT_SUBJ_USER: case AUDIT_OBJ_USER: switch (op) { case Audit_equal: match = (ctxt->user == rule->au_ctxt.user); break; case Audit_not_equal: match = (ctxt->user != rule->au_ctxt.user); break; } break; case AUDIT_SUBJ_ROLE: case AUDIT_OBJ_ROLE: switch (op) { case Audit_equal: match = (ctxt->role == rule->au_ctxt.role); break; case Audit_not_equal: match = (ctxt->role != rule->au_ctxt.role); break; } break; case AUDIT_SUBJ_TYPE: case AUDIT_OBJ_TYPE: switch (op) { case Audit_equal: match = (ctxt->type == rule->au_ctxt.type); break; case Audit_not_equal: match = (ctxt->type != rule->au_ctxt.type); break; } break; case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: level = ((field == AUDIT_SUBJ_SEN || field == AUDIT_OBJ_LEV_LOW) ? &ctxt->range.level[0] : &ctxt->range.level[1]); switch (op) { case Audit_equal: match = mls_level_eq(&rule->au_ctxt.range.level[0], level); break; case Audit_not_equal: match = !mls_level_eq(&rule->au_ctxt.range.level[0], level); break; case Audit_lt: match = (mls_level_dom(&rule->au_ctxt.range.level[0], level) && !mls_level_eq(&rule->au_ctxt.range.level[0], level)); break; case Audit_le: match = mls_level_dom(&rule->au_ctxt.range.level[0], level); break; case Audit_gt: match = (mls_level_dom(level, &rule->au_ctxt.range.level[0]) && !mls_level_eq(level, &rule->au_ctxt.range.level[0])); break; case Audit_ge: match = mls_level_dom(level, &rule->au_ctxt.range.level[0]); break; } } out: rcu_read_unlock(); return match; } static int aurule_avc_callback(u32 event) { if (event == AVC_CALLBACK_RESET) return audit_update_lsm_rules(); return 0; } static int __init aurule_init(void) { int err; err = avc_add_callback(aurule_avc_callback, AVC_CALLBACK_RESET); if (err) panic("avc_add_callback() failed, error %d\n", err); return err; } __initcall(aurule_init); #ifdef CONFIG_NETLABEL /** * security_netlbl_cache_add - Add an entry to the NetLabel cache * @secattr: the NetLabel packet security attributes * @sid: the SELinux SID * * Description: * Attempt to cache the context in @ctx, which was derived from the packet in * @skb, in the NetLabel subsystem cache. This function assumes @secattr has * already been initialized. * */ static void security_netlbl_cache_add(struct netlbl_lsm_secattr *secattr, u32 sid) { u32 *sid_cache; sid_cache = kmalloc(sizeof(*sid_cache), GFP_ATOMIC); if (sid_cache == NULL) return; secattr->cache = netlbl_secattr_cache_alloc(GFP_ATOMIC); if (secattr->cache == NULL) { kfree(sid_cache); return; } *sid_cache = sid; secattr->cache->free = kfree; secattr->cache->data = sid_cache; secattr->flags |= NETLBL_SECATTR_CACHE; } /** * security_netlbl_secattr_to_sid - Convert a NetLabel secattr to a SELinux SID * @secattr: the NetLabel packet security attributes * @sid: the SELinux SID * * Description: * Convert the given NetLabel security attributes in @secattr into a * SELinux SID. If the @secattr field does not contain a full SELinux * SID/context then use SECINITSID_NETMSG as the foundation. If possible the * 'cache' field of @secattr is set and the CACHE flag is set; this is to * allow the @secattr to be used by NetLabel to cache the secattr to SID * conversion for future lookups. Returns zero on success, negative values on * failure. * */ int security_netlbl_secattr_to_sid(struct netlbl_lsm_secattr *secattr, u32 *sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; int rc; struct context *ctx; struct context ctx_new; if (!selinux_initialized()) { *sid = SECSID_NULL; return 0; } retry: rc = 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; if (secattr->flags & NETLBL_SECATTR_CACHE) *sid = *(u32 *)secattr->cache->data; else if (secattr->flags & NETLBL_SECATTR_SECID) *sid = secattr->attr.secid; else if (secattr->flags & NETLBL_SECATTR_MLS_LVL) { rc = -EIDRM; ctx = sidtab_search(sidtab, SECINITSID_NETMSG); if (ctx == NULL) goto out; context_init(&ctx_new); ctx_new.user = ctx->user; ctx_new.role = ctx->role; ctx_new.type = ctx->type; mls_import_netlbl_lvl(policydb, &ctx_new, secattr); if (secattr->flags & NETLBL_SECATTR_MLS_CAT) { rc = mls_import_netlbl_cat(policydb, &ctx_new, secattr); if (rc) goto out; } rc = -EIDRM; if (!mls_context_isvalid(policydb, &ctx_new)) { ebitmap_destroy(&ctx_new.range.level[0].cat); goto out; } rc = sidtab_context_to_sid(sidtab, &ctx_new, sid); ebitmap_destroy(&ctx_new.range.level[0].cat); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) goto out; security_netlbl_cache_add(secattr, *sid); } else *sid = SECSID_NULL; out: rcu_read_unlock(); return rc; } /** * security_netlbl_sid_to_secattr - Convert a SELinux SID to a NetLabel secattr * @sid: the SELinux SID * @secattr: the NetLabel packet security attributes * * Description: * Convert the given SELinux SID in @sid into a NetLabel security attribute. * Returns zero on success, negative values on failure. * */ int security_netlbl_sid_to_secattr(u32 sid, struct netlbl_lsm_secattr *secattr) { struct selinux_policy *policy; struct policydb *policydb; int rc; struct context *ctx; if (!selinux_initialized()) return 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; rc = -ENOENT; ctx = sidtab_search(policy->sidtab, sid); if (ctx == NULL) goto out; rc = -ENOMEM; secattr->domain = kstrdup(sym_name(policydb, SYM_TYPES, ctx->type - 1), GFP_ATOMIC); if (secattr->domain == NULL) goto out; secattr->attr.secid = sid; secattr->flags |= NETLBL_SECATTR_DOMAIN_CPY | NETLBL_SECATTR_SECID; mls_export_netlbl_lvl(policydb, ctx, secattr); rc = mls_export_netlbl_cat(policydb, ctx, secattr); out: rcu_read_unlock(); return rc; } #endif /* CONFIG_NETLABEL */ /** * __security_read_policy - read the policy. * @policy: SELinux policy * @data: binary policy data * @len: length of data in bytes * */ static int __security_read_policy(struct selinux_policy *policy, void *data, size_t *len) { int rc; struct policy_file fp; fp.data = data; fp.len = *len; rc = policydb_write(&policy->policydb, &fp); if (rc) return rc; *len = (unsigned long)fp.data - (unsigned long)data; return 0; } /** * security_read_policy - read the policy. * @data: binary policy data * @len: length of data in bytes * */ int security_read_policy(void **data, size_t *len) { struct selinux_state *state = &selinux_state; struct selinux_policy *policy; policy = rcu_dereference_protected( state->policy, lockdep_is_held(&state->policy_mutex)); if (!policy) return -EINVAL; *len = policy->policydb.len; *data = vmalloc_user(*len); if (!*data) return -ENOMEM; return __security_read_policy(policy, *data, len); } /** * security_read_state_kernel - read the policy. * @data: binary policy data * @len: length of data in bytes * * Allocates kernel memory for reading SELinux policy. * This function is for internal use only and should not * be used for returning data to user space. * * This function must be called with policy_mutex held. */ int security_read_state_kernel(void **data, size_t *len) { int err; struct selinux_state *state = &selinux_state; struct selinux_policy *policy; policy = rcu_dereference_protected( state->policy, lockdep_is_held(&state->policy_mutex)); if (!policy) return -EINVAL; *len = policy->policydb.len; *data = vmalloc(*len); if (!*data) return -ENOMEM; err = __security_read_policy(policy, *data, len); if (err) { vfree(*data); *data = NULL; *len = 0; } return err; } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 2014-2015, The Linux Foundation. All rights reserved. */ #undef TRACE_SYSTEM #define TRACE_SYSTEM clk #if !defined(_TRACE_CLK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_CLK_H #include <linux/tracepoint.h> struct clk_core; DECLARE_EVENT_CLASS(clk, TP_PROTO(struct clk_core *core), TP_ARGS(core), TP_STRUCT__entry( __string( name, core->name ) ), TP_fast_assign( __assign_str(name); ), TP_printk("%s", __get_str(name)) ); DEFINE_EVENT(clk, clk_enable, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_enable_complete, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_disable, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_disable_complete, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_prepare, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_prepare_complete, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_unprepare, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_unprepare_complete, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DECLARE_EVENT_CLASS(clk_rate, TP_PROTO(struct clk_core *core, unsigned long rate), TP_ARGS(core, rate), TP_STRUCT__entry( __string( name, core->name ) __field(unsigned long, rate ) ), TP_fast_assign( __assign_str(name); __entry->rate = rate; ), TP_printk("%s %lu", __get_str(name), (unsigned long)__entry->rate) ); DEFINE_EVENT(clk_rate, clk_set_rate, TP_PROTO(struct clk_core *core, unsigned long rate), TP_ARGS(core, rate) ); DEFINE_EVENT(clk_rate, clk_set_rate_complete, TP_PROTO(struct clk_core *core, unsigned long rate), TP_ARGS(core, rate) ); DEFINE_EVENT(clk_rate, clk_set_min_rate, TP_PROTO(struct clk_core *core, unsigned long rate), TP_ARGS(core, rate) ); DEFINE_EVENT(clk_rate, clk_set_max_rate, TP_PROTO(struct clk_core *core, unsigned long rate), TP_ARGS(core, rate) ); DECLARE_EVENT_CLASS(clk_rate_range, TP_PROTO(struct clk_core *core, unsigned long min, unsigned long max), TP_ARGS(core, min, max), TP_STRUCT__entry( __string( name, core->name ) __field(unsigned long, min ) __field(unsigned long, max ) ), TP_fast_assign( __assign_str(name); __entry->min = min; __entry->max = max; ), TP_printk("%s min %lu max %lu", __get_str(name), (unsigned long)__entry->min, (unsigned long)__entry->max) ); DEFINE_EVENT(clk_rate_range, clk_set_rate_range, TP_PROTO(struct clk_core *core, unsigned long min, unsigned long max), TP_ARGS(core, min, max) ); DECLARE_EVENT_CLASS(clk_parent, TP_PROTO(struct clk_core *core, struct clk_core *parent), TP_ARGS(core, parent), TP_STRUCT__entry( __string( name, core->name ) __string( pname, parent ? parent->name : "none" ) ), TP_fast_assign( __assign_str(name); __assign_str(pname); ), TP_printk("%s %s", __get_str(name), __get_str(pname)) ); DEFINE_EVENT(clk_parent, clk_set_parent, TP_PROTO(struct clk_core *core, struct clk_core *parent), TP_ARGS(core, parent) ); DEFINE_EVENT(clk_parent, clk_set_parent_complete, TP_PROTO(struct clk_core *core, struct clk_core *parent), TP_ARGS(core, parent) ); DECLARE_EVENT_CLASS(clk_phase, TP_PROTO(struct clk_core *core, int phase), TP_ARGS(core, phase), TP_STRUCT__entry( __string( name, core->name ) __field( int, phase ) ), TP_fast_assign( __assign_str(name); __entry->phase = phase; ), TP_printk("%s %d", __get_str(name), (int)__entry->phase) ); DEFINE_EVENT(clk_phase, clk_set_phase, TP_PROTO(struct clk_core *core, int phase), TP_ARGS(core, phase) ); DEFINE_EVENT(clk_phase, clk_set_phase_complete, TP_PROTO(struct clk_core *core, int phase), TP_ARGS(core, phase) ); DECLARE_EVENT_CLASS(clk_duty_cycle, TP_PROTO(struct clk_core *core, struct clk_duty *duty), TP_ARGS(core, duty), TP_STRUCT__entry( __string( name, core->name ) __field( unsigned int, num ) __field( unsigned int, den ) ), TP_fast_assign( __assign_str(name); __entry->num = duty->num; __entry->den = duty->den; ), TP_printk("%s %u/%u", __get_str(name), (unsigned int)__entry->num, (unsigned int)__entry->den) ); DEFINE_EVENT(clk_duty_cycle, clk_set_duty_cycle, TP_PROTO(struct clk_core *core, struct clk_duty *duty), TP_ARGS(core, duty) ); DEFINE_EVENT(clk_duty_cycle, clk_set_duty_cycle_complete, TP_PROTO(struct clk_core *core, struct clk_duty *duty), TP_ARGS(core, duty) ); DECLARE_EVENT_CLASS(clk_rate_request, TP_PROTO(struct clk_rate_request *req), TP_ARGS(req), TP_STRUCT__entry( __string( name, req->core ? req->core->name : "none") __string( pname, req->best_parent_hw ? clk_hw_get_name(req->best_parent_hw) : "none" ) __field(unsigned long, min ) __field(unsigned long, max ) __field(unsigned long, prate ) ), TP_fast_assign( __assign_str(name); __assign_str(pname); __entry->min = req->min_rate; __entry->max = req->max_rate; __entry->prate = req->best_parent_rate; ), TP_printk("%s min %lu max %lu, parent %s (%lu)", __get_str(name), (unsigned long)__entry->min, (unsigned long)__entry->max, __get_str(pname), (unsigned long)__entry->prate) ); DEFINE_EVENT(clk_rate_request, clk_rate_request_start, TP_PROTO(struct clk_rate_request *req), TP_ARGS(req) ); DEFINE_EVENT(clk_rate_request, clk_rate_request_done, TP_PROTO(struct clk_rate_request *req), TP_ARGS(req) ); #endif /* _TRACE_CLK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 | // SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* gw.c - CAN frame Gateway/Router/Bridge with netlink interface * * Copyright (c) 2019 Volkswagen Group Electronic Research * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of Volkswagen nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * Alternatively, provided that this notice is retained in full, this * software may be distributed under the terms of the GNU General * Public License ("GPL") version 2, in which case the provisions of the * GPL apply INSTEAD OF those given above. * * The provided data structures and external interfaces from this code * are not restricted to be used by modules with a GPL compatible license. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. * */ #include <linux/module.h> #include <linux/init.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/rculist.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/can.h> #include <linux/can/core.h> #include <linux/can/skb.h> #include <linux/can/gw.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/sock.h> #define CAN_GW_NAME "can-gw" MODULE_DESCRIPTION("PF_CAN netlink gateway"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>"); MODULE_ALIAS(CAN_GW_NAME); #define CGW_MIN_HOPS 1 #define CGW_MAX_HOPS 6 #define CGW_DEFAULT_HOPS 1 static unsigned int max_hops __read_mostly = CGW_DEFAULT_HOPS; module_param(max_hops, uint, 0444); MODULE_PARM_DESC(max_hops, "maximum " CAN_GW_NAME " routing hops for CAN frames " "(valid values: " __stringify(CGW_MIN_HOPS) "-" __stringify(CGW_MAX_HOPS) " hops, " "default: " __stringify(CGW_DEFAULT_HOPS) ")"); static struct notifier_block notifier; static struct kmem_cache *cgw_cache __read_mostly; /* structure that contains the (on-the-fly) CAN frame modifications */ struct cf_mod { struct { struct canfd_frame and; struct canfd_frame or; struct canfd_frame xor; struct canfd_frame set; } modframe; struct { u8 and; u8 or; u8 xor; u8 set; } modtype; void (*modfunc[MAX_MODFUNCTIONS])(struct canfd_frame *cf, struct cf_mod *mod); /* CAN frame checksum calculation after CAN frame modifications */ struct { struct cgw_csum_xor xor; struct cgw_csum_crc8 crc8; } csum; struct { void (*xor)(struct canfd_frame *cf, struct cgw_csum_xor *xor); void (*crc8)(struct canfd_frame *cf, struct cgw_csum_crc8 *crc8); } csumfunc; u32 uid; }; /* So far we just support CAN -> CAN routing and frame modifications. * * The internal can_can_gw structure contains data and attributes for * a CAN -> CAN gateway job. */ struct can_can_gw { struct can_filter filter; int src_idx; int dst_idx; }; /* list entry for CAN gateways jobs */ struct cgw_job { struct hlist_node list; struct rcu_head rcu; u32 handled_frames; u32 dropped_frames; u32 deleted_frames; struct cf_mod mod; union { /* CAN frame data source */ struct net_device *dev; } src; union { /* CAN frame data destination */ struct net_device *dev; } dst; union { struct can_can_gw ccgw; /* tbc */ }; u8 gwtype; u8 limit_hops; u16 flags; }; /* modification functions that are invoked in the hot path in can_can_gw_rcv */ #define MODFUNC(func, op) static void func(struct canfd_frame *cf, \ struct cf_mod *mod) { op ; } MODFUNC(mod_and_id, cf->can_id &= mod->modframe.and.can_id) MODFUNC(mod_and_len, cf->len &= mod->modframe.and.len) MODFUNC(mod_and_flags, cf->flags &= mod->modframe.and.flags) MODFUNC(mod_and_data, *(u64 *)cf->data &= *(u64 *)mod->modframe.and.data) MODFUNC(mod_or_id, cf->can_id |= mod->modframe.or.can_id) MODFUNC(mod_or_len, cf->len |= mod->modframe.or.len) MODFUNC(mod_or_flags, cf->flags |= mod->modframe.or.flags) MODFUNC(mod_or_data, *(u64 *)cf->data |= *(u64 *)mod->modframe.or.data) MODFUNC(mod_xor_id, cf->can_id ^= mod->modframe.xor.can_id) MODFUNC(mod_xor_len, cf->len ^= mod->modframe.xor.len) MODFUNC(mod_xor_flags, cf->flags ^= mod->modframe.xor.flags) MODFUNC(mod_xor_data, *(u64 *)cf->data ^= *(u64 *)mod->modframe.xor.data) MODFUNC(mod_set_id, cf->can_id = mod->modframe.set.can_id) MODFUNC(mod_set_len, cf->len = mod->modframe.set.len) MODFUNC(mod_set_flags, cf->flags = mod->modframe.set.flags) MODFUNC(mod_set_data, *(u64 *)cf->data = *(u64 *)mod->modframe.set.data) static void mod_and_fddata(struct canfd_frame *cf, struct cf_mod *mod) { int i; for (i = 0; i < CANFD_MAX_DLEN; i += 8) *(u64 *)(cf->data + i) &= *(u64 *)(mod->modframe.and.data + i); } static void mod_or_fddata(struct canfd_frame *cf, struct cf_mod *mod) { int i; for (i = 0; i < CANFD_MAX_DLEN; i += 8) *(u64 *)(cf->data + i) |= *(u64 *)(mod->modframe.or.data + i); } static void mod_xor_fddata(struct canfd_frame *cf, struct cf_mod *mod) { int i; for (i = 0; i < CANFD_MAX_DLEN; i += 8) *(u64 *)(cf->data + i) ^= *(u64 *)(mod->modframe.xor.data + i); } static void mod_set_fddata(struct canfd_frame *cf, struct cf_mod *mod) { memcpy(cf->data, mod->modframe.set.data, CANFD_MAX_DLEN); } /* retrieve valid CC DLC value and store it into 'len' */ static void mod_retrieve_ccdlc(struct canfd_frame *cf) { struct can_frame *ccf = (struct can_frame *)cf; /* len8_dlc is only valid if len == CAN_MAX_DLEN */ if (ccf->len != CAN_MAX_DLEN) return; /* do we have a valid len8_dlc value from 9 .. 15 ? */ if (ccf->len8_dlc > CAN_MAX_DLEN && ccf->len8_dlc <= CAN_MAX_RAW_DLC) ccf->len = ccf->len8_dlc; } /* convert valid CC DLC value in 'len' into struct can_frame elements */ static void mod_store_ccdlc(struct canfd_frame *cf) { struct can_frame *ccf = (struct can_frame *)cf; /* clear potential leftovers */ ccf->len8_dlc = 0; /* plain data length 0 .. 8 - that was easy */ if (ccf->len <= CAN_MAX_DLEN) return; /* potentially broken values are caught in can_can_gw_rcv() */ if (ccf->len > CAN_MAX_RAW_DLC) return; /* we have a valid dlc value from 9 .. 15 in ccf->len */ ccf->len8_dlc = ccf->len; ccf->len = CAN_MAX_DLEN; } static void mod_and_ccdlc(struct canfd_frame *cf, struct cf_mod *mod) { mod_retrieve_ccdlc(cf); mod_and_len(cf, mod); mod_store_ccdlc(cf); } static void mod_or_ccdlc(struct canfd_frame *cf, struct cf_mod *mod) { mod_retrieve_ccdlc(cf); mod_or_len(cf, mod); mod_store_ccdlc(cf); } static void mod_xor_ccdlc(struct canfd_frame *cf, struct cf_mod *mod) { mod_retrieve_ccdlc(cf); mod_xor_len(cf, mod); mod_store_ccdlc(cf); } static void mod_set_ccdlc(struct canfd_frame *cf, struct cf_mod *mod) { mod_set_len(cf, mod); mod_store_ccdlc(cf); } static void canframecpy(struct canfd_frame *dst, struct can_frame *src) { /* Copy the struct members separately to ensure that no uninitialized * data are copied in the 3 bytes hole of the struct. This is needed * to make easy compares of the data in the struct cf_mod. */ dst->can_id = src->can_id; dst->len = src->len; *(u64 *)dst->data = *(u64 *)src->data; } static void canfdframecpy(struct canfd_frame *dst, struct canfd_frame *src) { /* Copy the struct members separately to ensure that no uninitialized * data are copied in the 2 bytes hole of the struct. This is needed * to make easy compares of the data in the struct cf_mod. */ dst->can_id = src->can_id; dst->flags = src->flags; dst->len = src->len; memcpy(dst->data, src->data, CANFD_MAX_DLEN); } static int cgw_chk_csum_parms(s8 fr, s8 to, s8 re, struct rtcanmsg *r) { s8 dlen = CAN_MAX_DLEN; if (r->flags & CGW_FLAGS_CAN_FD) dlen = CANFD_MAX_DLEN; /* absolute dlc values 0 .. 7 => 0 .. 7, e.g. data [0] * relative to received dlc -1 .. -8 : * e.g. for received dlc = 8 * -1 => index = 7 (data[7]) * -3 => index = 5 (data[5]) * -8 => index = 0 (data[0]) */ if (fr >= -dlen && fr < dlen && to >= -dlen && to < dlen && re >= -dlen && re < dlen) return 0; else return -EINVAL; } static inline int calc_idx(int idx, int rx_len) { if (idx < 0) return rx_len + idx; else return idx; } static void cgw_csum_xor_rel(struct canfd_frame *cf, struct cgw_csum_xor *xor) { int from = calc_idx(xor->from_idx, cf->len); int to = calc_idx(xor->to_idx, cf->len); int res = calc_idx(xor->result_idx, cf->len); u8 val = xor->init_xor_val; int i; if (from < 0 || to < 0 || res < 0) return; if (from <= to) { for (i = from; i <= to; i++) val ^= cf->data[i]; } else { for (i = from; i >= to; i--) val ^= cf->data[i]; } cf->data[res] = val; } static void cgw_csum_xor_pos(struct canfd_frame *cf, struct cgw_csum_xor *xor) { u8 val = xor->init_xor_val; int i; for (i = xor->from_idx; i <= xor->to_idx; i++) val ^= cf->data[i]; cf->data[xor->result_idx] = val; } static void cgw_csum_xor_neg(struct canfd_frame *cf, struct cgw_csum_xor *xor) { u8 val = xor->init_xor_val; int i; for (i = xor->from_idx; i >= xor->to_idx; i--) val ^= cf->data[i]; cf->data[xor->result_idx] = val; } static void cgw_csum_crc8_rel(struct canfd_frame *cf, struct cgw_csum_crc8 *crc8) { int from = calc_idx(crc8->from_idx, cf->len); int to = calc_idx(crc8->to_idx, cf->len); int res = calc_idx(crc8->result_idx, cf->len); u8 crc = crc8->init_crc_val; int i; if (from < 0 || to < 0 || res < 0) return; if (from <= to) { for (i = crc8->from_idx; i <= crc8->to_idx; i++) crc = crc8->crctab[crc ^ cf->data[i]]; } else { for (i = crc8->from_idx; i >= crc8->to_idx; i--) crc = crc8->crctab[crc ^ cf->data[i]]; } switch (crc8->profile) { case CGW_CRC8PRF_1U8: crc = crc8->crctab[crc ^ crc8->profile_data[0]]; break; case CGW_CRC8PRF_16U8: crc = crc8->crctab[crc ^ crc8->profile_data[cf->data[1] & 0xF]]; break; case CGW_CRC8PRF_SFFID_XOR: crc = crc8->crctab[crc ^ (cf->can_id & 0xFF) ^ (cf->can_id >> 8 & 0xFF)]; break; } cf->data[crc8->result_idx] = crc ^ crc8->final_xor_val; } static void cgw_csum_crc8_pos(struct canfd_frame *cf, struct cgw_csum_crc8 *crc8) { u8 crc = crc8->init_crc_val; int i; for (i = crc8->from_idx; i <= crc8->to_idx; i++) crc = crc8->crctab[crc ^ cf->data[i]]; switch (crc8->profile) { case CGW_CRC8PRF_1U8: crc = crc8->crctab[crc ^ crc8->profile_data[0]]; break; case CGW_CRC8PRF_16U8: crc = crc8->crctab[crc ^ crc8->profile_data[cf->data[1] & 0xF]]; break; case CGW_CRC8PRF_SFFID_XOR: crc = crc8->crctab[crc ^ (cf->can_id & 0xFF) ^ (cf->can_id >> 8 & 0xFF)]; break; } cf->data[crc8->result_idx] = crc ^ crc8->final_xor_val; } static void cgw_csum_crc8_neg(struct canfd_frame *cf, struct cgw_csum_crc8 *crc8) { u8 crc = crc8->init_crc_val; int i; for (i = crc8->from_idx; i >= crc8->to_idx; i--) crc = crc8->crctab[crc ^ cf->data[i]]; switch (crc8->profile) { case CGW_CRC8PRF_1U8: crc = crc8->crctab[crc ^ crc8->profile_data[0]]; break; case CGW_CRC8PRF_16U8: crc = crc8->crctab[crc ^ crc8->profile_data[cf->data[1] & 0xF]]; break; case CGW_CRC8PRF_SFFID_XOR: crc = crc8->crctab[crc ^ (cf->can_id & 0xFF) ^ (cf->can_id >> 8 & 0xFF)]; break; } cf->data[crc8->result_idx] = crc ^ crc8->final_xor_val; } /* the receive & process & send function */ static void can_can_gw_rcv(struct sk_buff *skb, void *data) { struct cgw_job *gwj = (struct cgw_job *)data; struct canfd_frame *cf; struct sk_buff *nskb; int modidx = 0; /* process strictly Classic CAN or CAN FD frames */ if (gwj->flags & CGW_FLAGS_CAN_FD) { if (!can_is_canfd_skb(skb)) return; } else { if (!can_is_can_skb(skb)) return; } /* Do not handle CAN frames routed more than 'max_hops' times. * In general we should never catch this delimiter which is intended * to cover a misconfiguration protection (e.g. circular CAN routes). * * The Controller Area Network controllers only accept CAN frames with * correct CRCs - which are not visible in the controller registers. * According to skbuff.h documentation the csum_start element for IP * checksums is undefined/unused when ip_summed == CHECKSUM_UNNECESSARY. * Only CAN skbs can be processed here which already have this property. */ #define cgw_hops(skb) ((skb)->csum_start) BUG_ON(skb->ip_summed != CHECKSUM_UNNECESSARY); if (cgw_hops(skb) >= max_hops) { /* indicate deleted frames due to misconfiguration */ gwj->deleted_frames++; return; } if (!(gwj->dst.dev->flags & IFF_UP)) { gwj->dropped_frames++; return; } /* is sending the skb back to the incoming interface not allowed? */ if (!(gwj->flags & CGW_FLAGS_CAN_IIF_TX_OK) && can_skb_prv(skb)->ifindex == gwj->dst.dev->ifindex) return; /* clone the given skb, which has not been done in can_rcv() * * When there is at least one modification function activated, * we need to copy the skb as we want to modify skb->data. */ if (gwj->mod.modfunc[0]) nskb = skb_copy(skb, GFP_ATOMIC); else nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) { gwj->dropped_frames++; return; } /* put the incremented hop counter in the cloned skb */ cgw_hops(nskb) = cgw_hops(skb) + 1; /* first processing of this CAN frame -> adjust to private hop limit */ if (gwj->limit_hops && cgw_hops(nskb) == 1) cgw_hops(nskb) = max_hops - gwj->limit_hops + 1; nskb->dev = gwj->dst.dev; /* pointer to modifiable CAN frame */ cf = (struct canfd_frame *)nskb->data; /* perform preprocessed modification functions if there are any */ while (modidx < MAX_MODFUNCTIONS && gwj->mod.modfunc[modidx]) (*gwj->mod.modfunc[modidx++])(cf, &gwj->mod); /* Has the CAN frame been modified? */ if (modidx) { /* get available space for the processed CAN frame type */ int max_len = nskb->len - offsetof(struct canfd_frame, data); /* dlc may have changed, make sure it fits to the CAN frame */ if (cf->len > max_len) { /* delete frame due to misconfiguration */ gwj->deleted_frames++; kfree_skb(nskb); return; } /* check for checksum updates */ if (gwj->mod.csumfunc.crc8) (*gwj->mod.csumfunc.crc8)(cf, &gwj->mod.csum.crc8); if (gwj->mod.csumfunc.xor) (*gwj->mod.csumfunc.xor)(cf, &gwj->mod.csum.xor); } /* clear the skb timestamp if not configured the other way */ if (!(gwj->flags & CGW_FLAGS_CAN_SRC_TSTAMP)) nskb->tstamp = 0; /* send to netdevice */ if (can_send(nskb, gwj->flags & CGW_FLAGS_CAN_ECHO)) gwj->dropped_frames++; else gwj->handled_frames++; } static inline int cgw_register_filter(struct net *net, struct cgw_job *gwj) { return can_rx_register(net, gwj->src.dev, gwj->ccgw.filter.can_id, gwj->ccgw.filter.can_mask, can_can_gw_rcv, gwj, "gw", NULL); } static inline void cgw_unregister_filter(struct net *net, struct cgw_job *gwj) { can_rx_unregister(net, gwj->src.dev, gwj->ccgw.filter.can_id, gwj->ccgw.filter.can_mask, can_can_gw_rcv, gwj); } static void cgw_job_free_rcu(struct rcu_head *rcu_head) { struct cgw_job *gwj = container_of(rcu_head, struct cgw_job, rcu); kmem_cache_free(cgw_cache, gwj); } static int cgw_notifier(struct notifier_block *nb, unsigned long msg, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); if (dev->type != ARPHRD_CAN) return NOTIFY_DONE; if (msg == NETDEV_UNREGISTER) { struct cgw_job *gwj = NULL; struct hlist_node *nx; ASSERT_RTNL(); hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) { if (gwj->src.dev == dev || gwj->dst.dev == dev) { hlist_del(&gwj->list); cgw_unregister_filter(net, gwj); call_rcu(&gwj->rcu, cgw_job_free_rcu); } } } return NOTIFY_DONE; } static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type, u32 pid, u32 seq, int flags) { struct rtcanmsg *rtcan; struct nlmsghdr *nlh; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*rtcan), flags); if (!nlh) return -EMSGSIZE; rtcan = nlmsg_data(nlh); rtcan->can_family = AF_CAN; rtcan->gwtype = gwj->gwtype; rtcan->flags = gwj->flags; /* add statistics if available */ if (gwj->handled_frames) { if (nla_put_u32(skb, CGW_HANDLED, gwj->handled_frames) < 0) goto cancel; } if (gwj->dropped_frames) { if (nla_put_u32(skb, CGW_DROPPED, gwj->dropped_frames) < 0) goto cancel; } if (gwj->deleted_frames) { if (nla_put_u32(skb, CGW_DELETED, gwj->deleted_frames) < 0) goto cancel; } /* check non default settings of attributes */ if (gwj->limit_hops) { if (nla_put_u8(skb, CGW_LIM_HOPS, gwj->limit_hops) < 0) goto cancel; } if (gwj->flags & CGW_FLAGS_CAN_FD) { struct cgw_fdframe_mod mb; if (gwj->mod.modtype.and) { memcpy(&mb.cf, &gwj->mod.modframe.and, sizeof(mb.cf)); mb.modtype = gwj->mod.modtype.and; if (nla_put(skb, CGW_FDMOD_AND, sizeof(mb), &mb) < 0) goto cancel; } if (gwj->mod.modtype.or) { memcpy(&mb.cf, &gwj->mod.modframe.or, sizeof(mb.cf)); mb.modtype = gwj->mod.modtype.or; if (nla_put(skb, CGW_FDMOD_OR, sizeof(mb), &mb) < 0) goto cancel; } if (gwj->mod.modtype.xor) { memcpy(&mb.cf, &gwj->mod.modframe.xor, sizeof(mb.cf)); mb.modtype = gwj->mod.modtype.xor; if (nla_put(skb, CGW_FDMOD_XOR, sizeof(mb), &mb) < 0) goto cancel; } if (gwj->mod.modtype.set) { memcpy(&mb.cf, &gwj->mod.modframe.set, sizeof(mb.cf)); mb.modtype = gwj->mod.modtype.set; if (nla_put(skb, CGW_FDMOD_SET, sizeof(mb), &mb) < 0) goto cancel; } } else { struct cgw_frame_mod mb; if (gwj->mod.modtype.and) { memcpy(&mb.cf, &gwj->mod.modframe.and, sizeof(mb.cf)); mb.modtype = gwj->mod.modtype.and; if (nla_put(skb, CGW_MOD_AND, sizeof(mb), &mb) < 0) goto cancel; } if (gwj->mod.modtype.or) { memcpy(&mb.cf, &gwj->mod.modframe.or, sizeof(mb.cf)); mb.modtype = gwj->mod.modtype.or; if (nla_put(skb, CGW_MOD_OR, sizeof(mb), &mb) < 0) goto cancel; } if (gwj->mod.modtype.xor) { memcpy(&mb.cf, &gwj->mod.modframe.xor, sizeof(mb.cf)); mb.modtype = gwj->mod.modtype.xor; if (nla_put(skb, CGW_MOD_XOR, sizeof(mb), &mb) < 0) goto cancel; } if (gwj->mod.modtype.set) { memcpy(&mb.cf, &gwj->mod.modframe.set, sizeof(mb.cf)); mb.modtype = gwj->mod.modtype.set; if (nla_put(skb, CGW_MOD_SET, sizeof(mb), &mb) < 0) goto cancel; } } if (gwj->mod.uid) { if (nla_put_u32(skb, CGW_MOD_UID, gwj->mod.uid) < 0) goto cancel; } if (gwj->mod.csumfunc.crc8) { if (nla_put(skb, CGW_CS_CRC8, CGW_CS_CRC8_LEN, &gwj->mod.csum.crc8) < 0) goto cancel; } if (gwj->mod.csumfunc.xor) { if (nla_put(skb, CGW_CS_XOR, CGW_CS_XOR_LEN, &gwj->mod.csum.xor) < 0) goto cancel; } if (gwj->gwtype == CGW_TYPE_CAN_CAN) { if (gwj->ccgw.filter.can_id || gwj->ccgw.filter.can_mask) { if (nla_put(skb, CGW_FILTER, sizeof(struct can_filter), &gwj->ccgw.filter) < 0) goto cancel; } if (nla_put_u32(skb, CGW_SRC_IF, gwj->ccgw.src_idx) < 0) goto cancel; if (nla_put_u32(skb, CGW_DST_IF, gwj->ccgw.dst_idx) < 0) goto cancel; } nlmsg_end(skb, nlh); return 0; cancel: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } /* Dump information about all CAN gateway jobs, in response to RTM_GETROUTE */ static int cgw_dump_jobs(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct cgw_job *gwj = NULL; int idx = 0; int s_idx = cb->args[0]; rcu_read_lock(); hlist_for_each_entry_rcu(gwj, &net->can.cgw_list, list) { if (idx < s_idx) goto cont; if (cgw_put_job(skb, gwj, RTM_NEWROUTE, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI) < 0) break; cont: idx++; } rcu_read_unlock(); cb->args[0] = idx; return skb->len; } static const struct nla_policy cgw_policy[CGW_MAX + 1] = { [CGW_MOD_AND] = { .len = sizeof(struct cgw_frame_mod) }, [CGW_MOD_OR] = { .len = sizeof(struct cgw_frame_mod) }, [CGW_MOD_XOR] = { .len = sizeof(struct cgw_frame_mod) }, [CGW_MOD_SET] = { .len = sizeof(struct cgw_frame_mod) }, [CGW_CS_XOR] = { .len = sizeof(struct cgw_csum_xor) }, [CGW_CS_CRC8] = { .len = sizeof(struct cgw_csum_crc8) }, [CGW_SRC_IF] = { .type = NLA_U32 }, [CGW_DST_IF] = { .type = NLA_U32 }, [CGW_FILTER] = { .len = sizeof(struct can_filter) }, [CGW_LIM_HOPS] = { .type = NLA_U8 }, [CGW_MOD_UID] = { .type = NLA_U32 }, [CGW_FDMOD_AND] = { .len = sizeof(struct cgw_fdframe_mod) }, [CGW_FDMOD_OR] = { .len = sizeof(struct cgw_fdframe_mod) }, [CGW_FDMOD_XOR] = { .len = sizeof(struct cgw_fdframe_mod) }, [CGW_FDMOD_SET] = { .len = sizeof(struct cgw_fdframe_mod) }, }; /* check for common and gwtype specific attributes */ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod, u8 gwtype, void *gwtypeattr, u8 *limhops) { struct nlattr *tb[CGW_MAX + 1]; struct rtcanmsg *r = nlmsg_data(nlh); int modidx = 0; int err = 0; /* initialize modification & checksum data space */ memset(mod, 0, sizeof(*mod)); err = nlmsg_parse_deprecated(nlh, sizeof(struct rtcanmsg), tb, CGW_MAX, cgw_policy, NULL); if (err < 0) return err; if (tb[CGW_LIM_HOPS]) { *limhops = nla_get_u8(tb[CGW_LIM_HOPS]); if (*limhops < 1 || *limhops > max_hops) return -EINVAL; } /* check for AND/OR/XOR/SET modifications */ if (r->flags & CGW_FLAGS_CAN_FD) { struct cgw_fdframe_mod mb; if (tb[CGW_FDMOD_AND]) { nla_memcpy(&mb, tb[CGW_FDMOD_AND], CGW_FDMODATTR_LEN); canfdframecpy(&mod->modframe.and, &mb.cf); mod->modtype.and = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_and_id; if (mb.modtype & CGW_MOD_LEN) mod->modfunc[modidx++] = mod_and_len; if (mb.modtype & CGW_MOD_FLAGS) mod->modfunc[modidx++] = mod_and_flags; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_and_fddata; } if (tb[CGW_FDMOD_OR]) { nla_memcpy(&mb, tb[CGW_FDMOD_OR], CGW_FDMODATTR_LEN); canfdframecpy(&mod->modframe.or, &mb.cf); mod->modtype.or = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_or_id; if (mb.modtype & CGW_MOD_LEN) mod->modfunc[modidx++] = mod_or_len; if (mb.modtype & CGW_MOD_FLAGS) mod->modfunc[modidx++] = mod_or_flags; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_or_fddata; } if (tb[CGW_FDMOD_XOR]) { nla_memcpy(&mb, tb[CGW_FDMOD_XOR], CGW_FDMODATTR_LEN); canfdframecpy(&mod->modframe.xor, &mb.cf); mod->modtype.xor = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_xor_id; if (mb.modtype & CGW_MOD_LEN) mod->modfunc[modidx++] = mod_xor_len; if (mb.modtype & CGW_MOD_FLAGS) mod->modfunc[modidx++] = mod_xor_flags; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_xor_fddata; } if (tb[CGW_FDMOD_SET]) { nla_memcpy(&mb, tb[CGW_FDMOD_SET], CGW_FDMODATTR_LEN); canfdframecpy(&mod->modframe.set, &mb.cf); mod->modtype.set = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_set_id; if (mb.modtype & CGW_MOD_LEN) mod->modfunc[modidx++] = mod_set_len; if (mb.modtype & CGW_MOD_FLAGS) mod->modfunc[modidx++] = mod_set_flags; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_set_fddata; } } else { struct cgw_frame_mod mb; if (tb[CGW_MOD_AND]) { nla_memcpy(&mb, tb[CGW_MOD_AND], CGW_MODATTR_LEN); canframecpy(&mod->modframe.and, &mb.cf); mod->modtype.and = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_and_id; if (mb.modtype & CGW_MOD_DLC) mod->modfunc[modidx++] = mod_and_ccdlc; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_and_data; } if (tb[CGW_MOD_OR]) { nla_memcpy(&mb, tb[CGW_MOD_OR], CGW_MODATTR_LEN); canframecpy(&mod->modframe.or, &mb.cf); mod->modtype.or = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_or_id; if (mb.modtype & CGW_MOD_DLC) mod->modfunc[modidx++] = mod_or_ccdlc; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_or_data; } if (tb[CGW_MOD_XOR]) { nla_memcpy(&mb, tb[CGW_MOD_XOR], CGW_MODATTR_LEN); canframecpy(&mod->modframe.xor, &mb.cf); mod->modtype.xor = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_xor_id; if (mb.modtype & CGW_MOD_DLC) mod->modfunc[modidx++] = mod_xor_ccdlc; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_xor_data; } if (tb[CGW_MOD_SET]) { nla_memcpy(&mb, tb[CGW_MOD_SET], CGW_MODATTR_LEN); canframecpy(&mod->modframe.set, &mb.cf); mod->modtype.set = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_set_id; if (mb.modtype & CGW_MOD_DLC) mod->modfunc[modidx++] = mod_set_ccdlc; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_set_data; } } /* check for checksum operations after CAN frame modifications */ if (modidx) { if (tb[CGW_CS_CRC8]) { struct cgw_csum_crc8 *c = nla_data(tb[CGW_CS_CRC8]); err = cgw_chk_csum_parms(c->from_idx, c->to_idx, c->result_idx, r); if (err) return err; nla_memcpy(&mod->csum.crc8, tb[CGW_CS_CRC8], CGW_CS_CRC8_LEN); /* select dedicated processing function to reduce * runtime operations in receive hot path. */ if (c->from_idx < 0 || c->to_idx < 0 || c->result_idx < 0) mod->csumfunc.crc8 = cgw_csum_crc8_rel; else if (c->from_idx <= c->to_idx) mod->csumfunc.crc8 = cgw_csum_crc8_pos; else mod->csumfunc.crc8 = cgw_csum_crc8_neg; } if (tb[CGW_CS_XOR]) { struct cgw_csum_xor *c = nla_data(tb[CGW_CS_XOR]); err = cgw_chk_csum_parms(c->from_idx, c->to_idx, c->result_idx, r); if (err) return err; nla_memcpy(&mod->csum.xor, tb[CGW_CS_XOR], CGW_CS_XOR_LEN); /* select dedicated processing function to reduce * runtime operations in receive hot path. */ if (c->from_idx < 0 || c->to_idx < 0 || c->result_idx < 0) mod->csumfunc.xor = cgw_csum_xor_rel; else if (c->from_idx <= c->to_idx) mod->csumfunc.xor = cgw_csum_xor_pos; else mod->csumfunc.xor = cgw_csum_xor_neg; } if (tb[CGW_MOD_UID]) nla_memcpy(&mod->uid, tb[CGW_MOD_UID], sizeof(u32)); } if (gwtype == CGW_TYPE_CAN_CAN) { /* check CGW_TYPE_CAN_CAN specific attributes */ struct can_can_gw *ccgw = (struct can_can_gw *)gwtypeattr; memset(ccgw, 0, sizeof(*ccgw)); /* check for can_filter in attributes */ if (tb[CGW_FILTER]) nla_memcpy(&ccgw->filter, tb[CGW_FILTER], sizeof(struct can_filter)); err = -ENODEV; /* specifying two interfaces is mandatory */ if (!tb[CGW_SRC_IF] || !tb[CGW_DST_IF]) return err; ccgw->src_idx = nla_get_u32(tb[CGW_SRC_IF]); ccgw->dst_idx = nla_get_u32(tb[CGW_DST_IF]); /* both indices set to 0 for flushing all routing entries */ if (!ccgw->src_idx && !ccgw->dst_idx) return 0; /* only one index set to 0 is an error */ if (!ccgw->src_idx || !ccgw->dst_idx) return err; } /* add the checks for other gwtypes here */ return 0; } static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct rtcanmsg *r; struct cgw_job *gwj; struct cf_mod mod; struct can_can_gw ccgw; u8 limhops = 0; int err = 0; if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (nlmsg_len(nlh) < sizeof(*r)) return -EINVAL; r = nlmsg_data(nlh); if (r->can_family != AF_CAN) return -EPFNOSUPPORT; /* so far we only support CAN -> CAN routings */ if (r->gwtype != CGW_TYPE_CAN_CAN) return -EINVAL; err = cgw_parse_attr(nlh, &mod, CGW_TYPE_CAN_CAN, &ccgw, &limhops); if (err < 0) return err; if (mod.uid) { ASSERT_RTNL(); /* check for updating an existing job with identical uid */ hlist_for_each_entry(gwj, &net->can.cgw_list, list) { if (gwj->mod.uid != mod.uid) continue; /* interfaces & filters must be identical */ if (memcmp(&gwj->ccgw, &ccgw, sizeof(ccgw))) return -EINVAL; /* update modifications with disabled softirq & quit */ local_bh_disable(); memcpy(&gwj->mod, &mod, sizeof(mod)); local_bh_enable(); return 0; } } /* ifindex == 0 is not allowed for job creation */ if (!ccgw.src_idx || !ccgw.dst_idx) return -ENODEV; gwj = kmem_cache_alloc(cgw_cache, GFP_KERNEL); if (!gwj) return -ENOMEM; gwj->handled_frames = 0; gwj->dropped_frames = 0; gwj->deleted_frames = 0; gwj->flags = r->flags; gwj->gwtype = r->gwtype; gwj->limit_hops = limhops; /* insert already parsed information */ memcpy(&gwj->mod, &mod, sizeof(mod)); memcpy(&gwj->ccgw, &ccgw, sizeof(ccgw)); err = -ENODEV; gwj->src.dev = __dev_get_by_index(net, gwj->ccgw.src_idx); if (!gwj->src.dev) goto out; if (gwj->src.dev->type != ARPHRD_CAN) goto out; gwj->dst.dev = __dev_get_by_index(net, gwj->ccgw.dst_idx); if (!gwj->dst.dev) goto out; if (gwj->dst.dev->type != ARPHRD_CAN) goto out; /* is sending the skb back to the incoming interface intended? */ if (gwj->src.dev == gwj->dst.dev && !(gwj->flags & CGW_FLAGS_CAN_IIF_TX_OK)) { err = -EINVAL; goto out; } ASSERT_RTNL(); err = cgw_register_filter(net, gwj); if (!err) hlist_add_head_rcu(&gwj->list, &net->can.cgw_list); out: if (err) kmem_cache_free(cgw_cache, gwj); return err; } static void cgw_remove_all_jobs(struct net *net) { struct cgw_job *gwj = NULL; struct hlist_node *nx; ASSERT_RTNL(); hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) { hlist_del(&gwj->list); cgw_unregister_filter(net, gwj); call_rcu(&gwj->rcu, cgw_job_free_rcu); } } static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct cgw_job *gwj = NULL; struct hlist_node *nx; struct rtcanmsg *r; struct cf_mod mod; struct can_can_gw ccgw; u8 limhops = 0; int err = 0; if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (nlmsg_len(nlh) < sizeof(*r)) return -EINVAL; r = nlmsg_data(nlh); if (r->can_family != AF_CAN) return -EPFNOSUPPORT; /* so far we only support CAN -> CAN routings */ if (r->gwtype != CGW_TYPE_CAN_CAN) return -EINVAL; err = cgw_parse_attr(nlh, &mod, CGW_TYPE_CAN_CAN, &ccgw, &limhops); if (err < 0) return err; /* two interface indices both set to 0 => remove all entries */ if (!ccgw.src_idx && !ccgw.dst_idx) { cgw_remove_all_jobs(net); return 0; } err = -EINVAL; ASSERT_RTNL(); /* remove only the first matching entry */ hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) { if (gwj->flags != r->flags) continue; if (gwj->limit_hops != limhops) continue; /* we have a match when uid is enabled and identical */ if (gwj->mod.uid || mod.uid) { if (gwj->mod.uid != mod.uid) continue; } else { /* no uid => check for identical modifications */ if (memcmp(&gwj->mod, &mod, sizeof(mod))) continue; } /* if (r->gwtype == CGW_TYPE_CAN_CAN) - is made sure here */ if (memcmp(&gwj->ccgw, &ccgw, sizeof(ccgw))) continue; hlist_del(&gwj->list); cgw_unregister_filter(net, gwj); call_rcu(&gwj->rcu, cgw_job_free_rcu); err = 0; break; } return err; } static int __net_init cangw_pernet_init(struct net *net) { INIT_HLIST_HEAD(&net->can.cgw_list); return 0; } static void __net_exit cangw_pernet_exit_batch(struct list_head *net_list) { struct net *net; rtnl_lock(); list_for_each_entry(net, net_list, exit_list) cgw_remove_all_jobs(net); rtnl_unlock(); } static struct pernet_operations cangw_pernet_ops = { .init = cangw_pernet_init, .exit_batch = cangw_pernet_exit_batch, }; static const struct rtnl_msg_handler cgw_rtnl_msg_handlers[] __initconst_or_module = { {.owner = THIS_MODULE, .protocol = PF_CAN, .msgtype = RTM_NEWROUTE, .doit = cgw_create_job}, {.owner = THIS_MODULE, .protocol = PF_CAN, .msgtype = RTM_DELROUTE, .doit = cgw_remove_job}, {.owner = THIS_MODULE, .protocol = PF_CAN, .msgtype = RTM_GETROUTE, .dumpit = cgw_dump_jobs}, }; static __init int cgw_module_init(void) { int ret; /* sanitize given module parameter */ max_hops = clamp_t(unsigned int, max_hops, CGW_MIN_HOPS, CGW_MAX_HOPS); pr_info("can: netlink gateway - max_hops=%d\n", max_hops); ret = register_pernet_subsys(&cangw_pernet_ops); if (ret) return ret; ret = -ENOMEM; cgw_cache = kmem_cache_create("can_gw", sizeof(struct cgw_job), 0, 0, NULL); if (!cgw_cache) goto out_cache_create; /* set notifier */ notifier.notifier_call = cgw_notifier; ret = register_netdevice_notifier(¬ifier); if (ret) goto out_register_notifier; ret = rtnl_register_many(cgw_rtnl_msg_handlers); if (ret) goto out_rtnl_register; return 0; out_rtnl_register: unregister_netdevice_notifier(¬ifier); out_register_notifier: kmem_cache_destroy(cgw_cache); out_cache_create: unregister_pernet_subsys(&cangw_pernet_ops); return ret; } static __exit void cgw_module_exit(void) { rtnl_unregister_all(PF_CAN); unregister_netdevice_notifier(¬ifier); unregister_pernet_subsys(&cangw_pernet_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ kmem_cache_destroy(cgw_cache); } module_init(cgw_module_init); module_exit(cgw_module_exit); |
| 311 311 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 | // SPDX-License-Identifier: GPL-2.0 /* * linux/mm/madvise.c * * Copyright (C) 1999 Linus Torvalds * Copyright (C) 2002 Christoph Hellwig */ #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/syscalls.h> #include <linux/mempolicy.h> #include <linux/page-isolation.h> #include <linux/page_idle.h> #include <linux/userfaultfd_k.h> #include <linux/hugetlb.h> #include <linux/falloc.h> #include <linux/fadvise.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/mm_inline.h> #include <linux/string.h> #include <linux/uio.h> #include <linux/ksm.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/pagewalk.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/shmem_fs.h> #include <linux/mmu_notifier.h> #include <asm/tlb.h> #include "internal.h" #include "swap.h" /* * Maximum number of attempts we make to install guard pages before we give up * and return -ERESTARTNOINTR to have userspace try again. */ #define MAX_MADVISE_GUARD_RETRIES 3 struct madvise_walk_private { struct mmu_gather *tlb; bool pageout; }; /* * Any behaviour which results in changes to the vma->vm_flags needs to * take mmap_lock for writing. Others, which simply traverse vmas, need * to only take it for reading. */ static int madvise_need_mmap_write(int behavior) { switch (behavior) { case MADV_REMOVE: case MADV_WILLNEED: case MADV_DONTNEED: case MADV_DONTNEED_LOCKED: case MADV_COLD: case MADV_PAGEOUT: case MADV_FREE: case MADV_POPULATE_READ: case MADV_POPULATE_WRITE: case MADV_COLLAPSE: case MADV_GUARD_INSTALL: case MADV_GUARD_REMOVE: return 0; default: /* be safe, default to 1. list exceptions explicitly */ return 1; } } #ifdef CONFIG_ANON_VMA_NAME struct anon_vma_name *anon_vma_name_alloc(const char *name) { struct anon_vma_name *anon_name; size_t count; /* Add 1 for NUL terminator at the end of the anon_name->name */ count = strlen(name) + 1; anon_name = kmalloc(struct_size(anon_name, name, count), GFP_KERNEL); if (anon_name) { kref_init(&anon_name->kref); memcpy(anon_name->name, name, count); } return anon_name; } void anon_vma_name_free(struct kref *kref) { struct anon_vma_name *anon_name = container_of(kref, struct anon_vma_name, kref); kfree(anon_name); } struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma) { mmap_assert_locked(vma->vm_mm); return vma->anon_name; } /* mmap_lock should be write-locked */ static int replace_anon_vma_name(struct vm_area_struct *vma, struct anon_vma_name *anon_name) { struct anon_vma_name *orig_name = anon_vma_name(vma); if (!anon_name) { vma->anon_name = NULL; anon_vma_name_put(orig_name); return 0; } if (anon_vma_name_eq(orig_name, anon_name)) return 0; vma->anon_name = anon_vma_name_reuse(anon_name); anon_vma_name_put(orig_name); return 0; } #else /* CONFIG_ANON_VMA_NAME */ static int replace_anon_vma_name(struct vm_area_struct *vma, struct anon_vma_name *anon_name) { if (anon_name) return -EINVAL; return 0; } #endif /* CONFIG_ANON_VMA_NAME */ /* * Update the vm_flags on region of a vma, splitting it or merging it as * necessary. Must be called with mmap_lock held for writing; * Caller should ensure anon_name stability by raising its refcount even when * anon_name belongs to a valid vma because this function might free that vma. */ static int madvise_update_vma(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, unsigned long new_flags, struct anon_vma_name *anon_name) { struct mm_struct *mm = vma->vm_mm; int error; VMA_ITERATOR(vmi, mm, start); if (new_flags == vma->vm_flags && anon_vma_name_eq(anon_vma_name(vma), anon_name)) { *prev = vma; return 0; } vma = vma_modify_flags_name(&vmi, *prev, vma, start, end, new_flags, anon_name); if (IS_ERR(vma)) return PTR_ERR(vma); *prev = vma; /* vm_flags is protected by the mmap_lock held in write mode. */ vma_start_write(vma); vm_flags_reset(vma, new_flags); if (!vma->vm_file || vma_is_anon_shmem(vma)) { error = replace_anon_vma_name(vma, anon_name); if (error) return error; } return 0; } #ifdef CONFIG_SWAP static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->private; struct swap_iocb *splug = NULL; pte_t *ptep = NULL; spinlock_t *ptl; unsigned long addr; for (addr = start; addr < end; addr += PAGE_SIZE) { pte_t pte; swp_entry_t entry; struct folio *folio; if (!ptep++) { ptep = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (!ptep) break; } pte = ptep_get(ptep); if (!is_swap_pte(pte)) continue; entry = pte_to_swp_entry(pte); if (unlikely(non_swap_entry(entry))) continue; pte_unmap_unlock(ptep, ptl); ptep = NULL; folio = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE, vma, addr, &splug); if (folio) folio_put(folio); } if (ptep) pte_unmap_unlock(ptep, ptl); swap_read_unplug(splug); cond_resched(); return 0; } static const struct mm_walk_ops swapin_walk_ops = { .pmd_entry = swapin_walk_pmd_entry, .walk_lock = PGWALK_RDLOCK, }; static void shmem_swapin_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct address_space *mapping) { XA_STATE(xas, &mapping->i_pages, linear_page_index(vma, start)); pgoff_t end_index = linear_page_index(vma, end) - 1; struct folio *folio; struct swap_iocb *splug = NULL; rcu_read_lock(); xas_for_each(&xas, folio, end_index) { unsigned long addr; swp_entry_t entry; if (!xa_is_value(folio)) continue; entry = radix_to_swp_entry(folio); /* There might be swapin error entries in shmem mapping. */ if (non_swap_entry(entry)) continue; addr = vma->vm_start + ((xas.xa_index - vma->vm_pgoff) << PAGE_SHIFT); xas_pause(&xas); rcu_read_unlock(); folio = read_swap_cache_async(entry, mapping_gfp_mask(mapping), vma, addr, &splug); if (folio) folio_put(folio); rcu_read_lock(); } rcu_read_unlock(); swap_read_unplug(splug); } #endif /* CONFIG_SWAP */ /* * Schedule all required I/O operations. Do not wait for completion. */ static long madvise_willneed(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end) { struct mm_struct *mm = vma->vm_mm; struct file *file = vma->vm_file; loff_t offset; *prev = vma; #ifdef CONFIG_SWAP if (!file) { walk_page_range(vma->vm_mm, start, end, &swapin_walk_ops, vma); lru_add_drain(); /* Push any new pages onto the LRU now */ return 0; } if (shmem_mapping(file->f_mapping)) { shmem_swapin_range(vma, start, end, file->f_mapping); lru_add_drain(); /* Push any new pages onto the LRU now */ return 0; } #else if (!file) return -EBADF; #endif if (IS_DAX(file_inode(file))) { /* no bad return value, but ignore advice */ return 0; } /* * Filesystem's fadvise may need to take various locks. We need to * explicitly grab a reference because the vma (and hence the * vma's reference to the file) can go away as soon as we drop * mmap_lock. */ *prev = NULL; /* tell sys_madvise we drop mmap_lock */ get_file(file); offset = (loff_t)(start - vma->vm_start) + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); mmap_read_unlock(mm); vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED); fput(file); mmap_read_lock(mm); return 0; } static inline bool can_do_file_pageout(struct vm_area_struct *vma) { if (!vma->vm_file) return false; /* * paging out pagecache only for non-anonymous mappings that correspond * to the files the calling process could (if tried) open for writing; * otherwise we'd be including shared non-exclusive mappings, which * opens a side channel. */ return inode_owner_or_capable(&nop_mnt_idmap, file_inode(vma->vm_file)) || file_permission(vma->vm_file, MAY_WRITE) == 0; } static inline int madvise_folio_pte_batch(unsigned long addr, unsigned long end, struct folio *folio, pte_t *ptep, pte_t pte, bool *any_young, bool *any_dirty) { const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY; int max_nr = (end - addr) / PAGE_SIZE; return folio_pte_batch(folio, addr, ptep, pte, max_nr, fpb_flags, NULL, any_young, any_dirty); } static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct madvise_walk_private *private = walk->private; struct mmu_gather *tlb = private->tlb; bool pageout = private->pageout; struct mm_struct *mm = tlb->mm; struct vm_area_struct *vma = walk->vma; pte_t *start_pte, *pte, ptent; spinlock_t *ptl; struct folio *folio = NULL; LIST_HEAD(folio_list); bool pageout_anon_only_filter; unsigned int batch_count = 0; int nr; if (fatal_signal_pending(current)) return -EINTR; pageout_anon_only_filter = pageout && !vma_is_anonymous(vma) && !can_do_file_pageout(vma); #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (pmd_trans_huge(*pmd)) { pmd_t orig_pmd; unsigned long next = pmd_addr_end(addr, end); tlb_change_page_size(tlb, HPAGE_PMD_SIZE); ptl = pmd_trans_huge_lock(pmd, vma); if (!ptl) return 0; orig_pmd = *pmd; if (is_huge_zero_pmd(orig_pmd)) goto huge_unlock; if (unlikely(!pmd_present(orig_pmd))) { VM_BUG_ON(thp_migration_supported() && !is_pmd_migration_entry(orig_pmd)); goto huge_unlock; } folio = pmd_folio(orig_pmd); /* Do not interfere with other mappings of this folio */ if (folio_likely_mapped_shared(folio)) goto huge_unlock; if (pageout_anon_only_filter && !folio_test_anon(folio)) goto huge_unlock; if (next - addr != HPAGE_PMD_SIZE) { int err; folio_get(folio); spin_unlock(ptl); folio_lock(folio); err = split_folio(folio); folio_unlock(folio); folio_put(folio); if (!err) goto regular_folio; return 0; } if (!pageout && pmd_young(orig_pmd)) { pmdp_invalidate(vma, addr, pmd); orig_pmd = pmd_mkold(orig_pmd); set_pmd_at(mm, addr, pmd, orig_pmd); tlb_remove_pmd_tlb_entry(tlb, pmd, addr); } folio_clear_referenced(folio); folio_test_clear_young(folio); if (folio_test_active(folio)) folio_set_workingset(folio); if (pageout) { if (folio_isolate_lru(folio)) { if (folio_test_unevictable(folio)) folio_putback_lru(folio); else list_add(&folio->lru, &folio_list); } } else folio_deactivate(folio); huge_unlock: spin_unlock(ptl); if (pageout) reclaim_pages(&folio_list); return 0; } regular_folio: #endif tlb_change_page_size(tlb, PAGE_SIZE); restart: start_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (!start_pte) return 0; flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); for (; addr < end; pte += nr, addr += nr * PAGE_SIZE) { nr = 1; ptent = ptep_get(pte); if (++batch_count == SWAP_CLUSTER_MAX) { batch_count = 0; if (need_resched()) { arch_leave_lazy_mmu_mode(); pte_unmap_unlock(start_pte, ptl); cond_resched(); goto restart; } } if (pte_none(ptent)) continue; if (!pte_present(ptent)) continue; folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; /* * If we encounter a large folio, only split it if it is not * fully mapped within the range we are operating on. Otherwise * leave it as is so that it can be swapped out whole. If we * fail to split a folio, leave it in place and advance to the * next pte in the range. */ if (folio_test_large(folio)) { bool any_young; nr = madvise_folio_pte_batch(addr, end, folio, pte, ptent, &any_young, NULL); if (any_young) ptent = pte_mkyoung(ptent); if (nr < folio_nr_pages(folio)) { int err; if (folio_likely_mapped_shared(folio)) continue; if (pageout_anon_only_filter && !folio_test_anon(folio)) continue; if (!folio_trylock(folio)) continue; folio_get(folio); arch_leave_lazy_mmu_mode(); pte_unmap_unlock(start_pte, ptl); start_pte = NULL; err = split_folio(folio); folio_unlock(folio); folio_put(folio); start_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl); if (!start_pte) break; arch_enter_lazy_mmu_mode(); if (!err) nr = 0; continue; } } /* * Do not interfere with other mappings of this folio and * non-LRU folio. If we have a large folio at this point, we * know it is fully mapped so if its mapcount is the same as its * number of pages, it must be exclusive. */ if (!folio_test_lru(folio) || folio_mapcount(folio) != folio_nr_pages(folio)) continue; if (pageout_anon_only_filter && !folio_test_anon(folio)) continue; if (!pageout && pte_young(ptent)) { clear_young_dirty_ptes(vma, addr, pte, nr, CYDP_CLEAR_YOUNG); tlb_remove_tlb_entries(tlb, pte, nr, addr); } /* * We are deactivating a folio for accelerating reclaiming. * VM couldn't reclaim the folio unless we clear PG_young. * As a side effect, it makes confuse idle-page tracking * because they will miss recent referenced history. */ folio_clear_referenced(folio); folio_test_clear_young(folio); if (folio_test_active(folio)) folio_set_workingset(folio); if (pageout) { if (folio_isolate_lru(folio)) { if (folio_test_unevictable(folio)) folio_putback_lru(folio); else list_add(&folio->lru, &folio_list); } } else folio_deactivate(folio); } if (start_pte) { arch_leave_lazy_mmu_mode(); pte_unmap_unlock(start_pte, ptl); } if (pageout) reclaim_pages(&folio_list); cond_resched(); return 0; } static const struct mm_walk_ops cold_walk_ops = { .pmd_entry = madvise_cold_or_pageout_pte_range, .walk_lock = PGWALK_RDLOCK, }; static void madvise_cold_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end) { struct madvise_walk_private walk_private = { .pageout = false, .tlb = tlb, }; tlb_start_vma(tlb, vma); walk_page_range(vma->vm_mm, addr, end, &cold_walk_ops, &walk_private); tlb_end_vma(tlb, vma); } static inline bool can_madv_lru_vma(struct vm_area_struct *vma) { return !(vma->vm_flags & (VM_LOCKED|VM_PFNMAP|VM_HUGETLB)); } static long madvise_cold(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start_addr, unsigned long end_addr) { struct mm_struct *mm = vma->vm_mm; struct mmu_gather tlb; *prev = vma; if (!can_madv_lru_vma(vma)) return -EINVAL; lru_add_drain(); tlb_gather_mmu(&tlb, mm); madvise_cold_page_range(&tlb, vma, start_addr, end_addr); tlb_finish_mmu(&tlb); return 0; } static void madvise_pageout_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end) { struct madvise_walk_private walk_private = { .pageout = true, .tlb = tlb, }; tlb_start_vma(tlb, vma); walk_page_range(vma->vm_mm, addr, end, &cold_walk_ops, &walk_private); tlb_end_vma(tlb, vma); } static long madvise_pageout(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start_addr, unsigned long end_addr) { struct mm_struct *mm = vma->vm_mm; struct mmu_gather tlb; *prev = vma; if (!can_madv_lru_vma(vma)) return -EINVAL; /* * If the VMA belongs to a private file mapping, there can be private * dirty pages which can be paged out if even this process is neither * owner nor write capable of the file. We allow private file mappings * further to pageout dirty anon pages. */ if (!vma_is_anonymous(vma) && (!can_do_file_pageout(vma) && (vma->vm_flags & VM_MAYSHARE))) return 0; lru_add_drain(); tlb_gather_mmu(&tlb, mm); madvise_pageout_page_range(&tlb, vma, start_addr, end_addr); tlb_finish_mmu(&tlb); return 0; } static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { const cydp_t cydp_flags = CYDP_CLEAR_YOUNG | CYDP_CLEAR_DIRTY; struct mmu_gather *tlb = walk->private; struct mm_struct *mm = tlb->mm; struct vm_area_struct *vma = walk->vma; spinlock_t *ptl; pte_t *start_pte, *pte, ptent; struct folio *folio; int nr_swap = 0; unsigned long next; int nr, max_nr; next = pmd_addr_end(addr, end); if (pmd_trans_huge(*pmd)) if (madvise_free_huge_pmd(tlb, vma, pmd, addr, next)) return 0; tlb_change_page_size(tlb, PAGE_SIZE); start_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl); if (!start_pte) return 0; flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); for (; addr != end; pte += nr, addr += PAGE_SIZE * nr) { nr = 1; ptent = ptep_get(pte); if (pte_none(ptent)) continue; /* * If the pte has swp_entry, just clear page table to * prevent swap-in which is more expensive rather than * (page allocation + zeroing). */ if (!pte_present(ptent)) { swp_entry_t entry; entry = pte_to_swp_entry(ptent); if (!non_swap_entry(entry)) { max_nr = (end - addr) / PAGE_SIZE; nr = swap_pte_batch(pte, max_nr, ptent); nr_swap -= nr; free_swap_and_cache_nr(entry, nr); clear_not_present_full_ptes(mm, addr, pte, nr, tlb->fullmm); } else if (is_hwpoison_entry(entry) || is_poisoned_swp_entry(entry)) { pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); } continue; } folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; /* * If we encounter a large folio, only split it if it is not * fully mapped within the range we are operating on. Otherwise * leave it as is so that it can be marked as lazyfree. If we * fail to split a folio, leave it in place and advance to the * next pte in the range. */ if (folio_test_large(folio)) { bool any_young, any_dirty; nr = madvise_folio_pte_batch(addr, end, folio, pte, ptent, &any_young, &any_dirty); if (nr < folio_nr_pages(folio)) { int err; if (folio_likely_mapped_shared(folio)) continue; if (!folio_trylock(folio)) continue; folio_get(folio); arch_leave_lazy_mmu_mode(); pte_unmap_unlock(start_pte, ptl); start_pte = NULL; err = split_folio(folio); folio_unlock(folio); folio_put(folio); pte = pte_offset_map_lock(mm, pmd, addr, &ptl); start_pte = pte; if (!start_pte) break; arch_enter_lazy_mmu_mode(); if (!err) nr = 0; continue; } if (any_young) ptent = pte_mkyoung(ptent); if (any_dirty) ptent = pte_mkdirty(ptent); } if (folio_test_swapcache(folio) || folio_test_dirty(folio)) { if (!folio_trylock(folio)) continue; /* * If we have a large folio at this point, we know it is * fully mapped so if its mapcount is the same as its * number of pages, it must be exclusive. */ if (folio_mapcount(folio) != folio_nr_pages(folio)) { folio_unlock(folio); continue; } if (folio_test_swapcache(folio) && !folio_free_swap(folio)) { folio_unlock(folio); continue; } folio_clear_dirty(folio); folio_unlock(folio); } if (pte_young(ptent) || pte_dirty(ptent)) { clear_young_dirty_ptes(vma, addr, pte, nr, cydp_flags); tlb_remove_tlb_entries(tlb, pte, nr, addr); } folio_mark_lazyfree(folio); } if (nr_swap) add_mm_counter(mm, MM_SWAPENTS, nr_swap); if (start_pte) { arch_leave_lazy_mmu_mode(); pte_unmap_unlock(start_pte, ptl); } cond_resched(); return 0; } static const struct mm_walk_ops madvise_free_walk_ops = { .pmd_entry = madvise_free_pte_range, .walk_lock = PGWALK_RDLOCK, }; static int madvise_free_single_vma(struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr) { struct mm_struct *mm = vma->vm_mm; struct mmu_notifier_range range; struct mmu_gather tlb; /* MADV_FREE works for only anon vma at the moment */ if (!vma_is_anonymous(vma)) return -EINVAL; range.start = max(vma->vm_start, start_addr); if (range.start >= vma->vm_end) return -EINVAL; range.end = min(vma->vm_end, end_addr); if (range.end <= vma->vm_start) return -EINVAL; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, range.start, range.end); lru_add_drain(); tlb_gather_mmu(&tlb, mm); update_hiwater_rss(mm); mmu_notifier_invalidate_range_start(&range); tlb_start_vma(&tlb, vma); walk_page_range(vma->vm_mm, range.start, range.end, &madvise_free_walk_ops, &tlb); tlb_end_vma(&tlb, vma); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb); return 0; } /* * Application no longer needs these pages. If the pages are dirty, * it's OK to just throw them away. The app will be more careful about * data it wants to keep. Be sure to free swap resources too. The * zap_page_range_single call sets things up for shrink_active_list to actually * free these pages later if no one else has touched them in the meantime, * although we could add these pages to a global reuse list for * shrink_active_list to pick up before reclaiming other pages. * * NB: This interface discards data rather than pushes it out to swap, * as some implementations do. This has performance implications for * applications like large transactional databases which want to discard * pages in anonymous maps after committing to backing store the data * that was kept in them. There is no reason to write this data out to * the swap area if the application is discarding it. * * An interface that causes the system to free clean pages and flush * dirty pages is already available as msync(MS_INVALIDATE). */ static long madvise_dontneed_single_vma(struct vm_area_struct *vma, unsigned long start, unsigned long end) { zap_page_range_single(vma, start, end - start, NULL); return 0; } static bool madvise_dontneed_free_valid_vma(struct vm_area_struct *vma, unsigned long start, unsigned long *end, int behavior) { if (!is_vm_hugetlb_page(vma)) { unsigned int forbidden = VM_PFNMAP; if (behavior != MADV_DONTNEED_LOCKED) forbidden |= VM_LOCKED; return !(vma->vm_flags & forbidden); } if (behavior != MADV_DONTNEED && behavior != MADV_DONTNEED_LOCKED) return false; if (start & ~huge_page_mask(hstate_vma(vma))) return false; /* * Madvise callers expect the length to be rounded up to PAGE_SIZE * boundaries, and may be unaware that this VMA uses huge pages. * Avoid unexpected data loss by rounding down the number of * huge pages freed. */ *end = ALIGN_DOWN(*end, huge_page_size(hstate_vma(vma))); return true; } static long madvise_dontneed_free(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, int behavior) { struct mm_struct *mm = vma->vm_mm; *prev = vma; if (!madvise_dontneed_free_valid_vma(vma, start, &end, behavior)) return -EINVAL; if (start == end) return 0; if (!userfaultfd_remove(vma, start, end)) { *prev = NULL; /* mmap_lock has been dropped, prev is stale */ mmap_read_lock(mm); vma = vma_lookup(mm, start); if (!vma) return -ENOMEM; /* * Potential end adjustment for hugetlb vma is OK as * the check below keeps end within vma. */ if (!madvise_dontneed_free_valid_vma(vma, start, &end, behavior)) return -EINVAL; if (end > vma->vm_end) { /* * Don't fail if end > vma->vm_end. If the old * vma was split while the mmap_lock was * released the effect of the concurrent * operation may not cause madvise() to * have an undefined result. There may be an * adjacent next vma that we'll walk * next. userfaultfd_remove() will generate an * UFFD_EVENT_REMOVE repetition on the * end-vma->vm_end range, but the manager can * handle a repetition fine. */ end = vma->vm_end; } VM_WARN_ON(start >= end); } if (behavior == MADV_DONTNEED || behavior == MADV_DONTNEED_LOCKED) return madvise_dontneed_single_vma(vma, start, end); else if (behavior == MADV_FREE) return madvise_free_single_vma(vma, start, end); else return -EINVAL; } static long madvise_populate(struct mm_struct *mm, unsigned long start, unsigned long end, int behavior) { const bool write = behavior == MADV_POPULATE_WRITE; int locked = 1; long pages; while (start < end) { /* Populate (prefault) page tables readable/writable. */ pages = faultin_page_range(mm, start, end, write, &locked); if (!locked) { mmap_read_lock(mm); locked = 1; } if (pages < 0) { switch (pages) { case -EINTR: return -EINTR; case -EINVAL: /* Incompatible mappings / permissions. */ return -EINVAL; case -EHWPOISON: return -EHWPOISON; case -EFAULT: /* VM_FAULT_SIGBUS or VM_FAULT_SIGSEGV */ return -EFAULT; default: pr_warn_once("%s: unhandled return value: %ld\n", __func__, pages); fallthrough; case -ENOMEM: /* No VMA or out of memory. */ return -ENOMEM; } } start += pages * PAGE_SIZE; } return 0; } /* * Application wants to free up the pages and associated backing store. * This is effectively punching a hole into the middle of a file. */ static long madvise_remove(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end) { loff_t offset; int error; struct file *f; struct mm_struct *mm = vma->vm_mm; *prev = NULL; /* tell sys_madvise we drop mmap_lock */ if (vma->vm_flags & VM_LOCKED) return -EINVAL; f = vma->vm_file; if (!f || !f->f_mapping || !f->f_mapping->host) { return -EINVAL; } if (!vma_is_shared_maywrite(vma)) return -EACCES; offset = (loff_t)(start - vma->vm_start) + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); /* * Filesystem's fallocate may need to take i_rwsem. We need to * explicitly grab a reference because the vma (and hence the * vma's reference to the file) can go away as soon as we drop * mmap_lock. */ get_file(f); if (userfaultfd_remove(vma, start, end)) { /* mmap_lock was not released by userfaultfd_remove() */ mmap_read_unlock(mm); } error = vfs_fallocate(f, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, offset, end - start); fput(f); mmap_read_lock(mm); return error; } static bool is_valid_guard_vma(struct vm_area_struct *vma, bool allow_locked) { vm_flags_t disallowed = VM_SPECIAL | VM_HUGETLB; /* * A user could lock after setting a guard range but that's fine, as * they'd not be able to fault in. The issue arises when we try to zap * existing locked VMAs. We don't want to do that. */ if (!allow_locked) disallowed |= VM_LOCKED; if (!vma_is_anonymous(vma)) return false; if ((vma->vm_flags & (VM_MAYWRITE | disallowed)) != VM_MAYWRITE) return false; return true; } static bool is_guard_pte_marker(pte_t ptent) { return is_pte_marker(ptent) && is_guard_swp_entry(pte_to_swp_entry(ptent)); } static int guard_install_pud_entry(pud_t *pud, unsigned long addr, unsigned long next, struct mm_walk *walk) { pud_t pudval = pudp_get(pud); /* If huge return >0 so we abort the operation + zap. */ return pud_trans_huge(pudval) || pud_devmap(pudval); } static int guard_install_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long next, struct mm_walk *walk) { pmd_t pmdval = pmdp_get(pmd); /* If huge return >0 so we abort the operation + zap. */ return pmd_trans_huge(pmdval) || pmd_devmap(pmdval); } static int guard_install_pte_entry(pte_t *pte, unsigned long addr, unsigned long next, struct mm_walk *walk) { pte_t pteval = ptep_get(pte); unsigned long *nr_pages = (unsigned long *)walk->private; /* If there is already a guard page marker, we have nothing to do. */ if (is_guard_pte_marker(pteval)) { (*nr_pages)++; return 0; } /* If populated return >0 so we abort the operation + zap. */ return 1; } static int guard_install_set_pte(unsigned long addr, unsigned long next, pte_t *ptep, struct mm_walk *walk) { unsigned long *nr_pages = (unsigned long *)walk->private; /* Simply install a PTE marker, this causes segfault on access. */ *ptep = make_pte_marker(PTE_MARKER_GUARD); (*nr_pages)++; return 0; } static const struct mm_walk_ops guard_install_walk_ops = { .pud_entry = guard_install_pud_entry, .pmd_entry = guard_install_pmd_entry, .pte_entry = guard_install_pte_entry, .install_pte = guard_install_set_pte, .walk_lock = PGWALK_RDLOCK, }; static long madvise_guard_install(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end) { long err; int i; *prev = vma; if (!is_valid_guard_vma(vma, /* allow_locked = */false)) return -EINVAL; /* * If we install guard markers, then the range is no longer * empty from a page table perspective and therefore it's * appropriate to have an anon_vma. * * This ensures that on fork, we copy page tables correctly. */ err = anon_vma_prepare(vma); if (err) return err; /* * Optimistically try to install the guard marker pages first. If any * non-guard pages are encountered, give up and zap the range before * trying again. * * We try a few times before giving up and releasing back to userland to * loop around, releasing locks in the process to avoid contention. This * would only happen if there was a great many racing page faults. * * In most cases we should simply install the guard markers immediately * with no zap or looping. */ for (i = 0; i < MAX_MADVISE_GUARD_RETRIES; i++) { unsigned long nr_pages = 0; /* Returns < 0 on error, == 0 if success, > 0 if zap needed. */ err = walk_page_range_mm(vma->vm_mm, start, end, &guard_install_walk_ops, &nr_pages); if (err < 0) return err; if (err == 0) { unsigned long nr_expected_pages = PHYS_PFN(end - start); VM_WARN_ON(nr_pages != nr_expected_pages); return 0; } /* * OK some of the range have non-guard pages mapped, zap * them. This leaves existing guard pages in place. */ zap_page_range_single(vma, start, end - start, NULL); } /* * We were unable to install the guard pages due to being raced by page * faults. This should not happen ordinarily. We return to userspace and * immediately retry, relieving lock contention. */ return restart_syscall(); } static int guard_remove_pud_entry(pud_t *pud, unsigned long addr, unsigned long next, struct mm_walk *walk) { pud_t pudval = pudp_get(pud); /* If huge, cannot have guard pages present, so no-op - skip. */ if (pud_trans_huge(pudval) || pud_devmap(pudval)) walk->action = ACTION_CONTINUE; return 0; } static int guard_remove_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long next, struct mm_walk *walk) { pmd_t pmdval = pmdp_get(pmd); /* If huge, cannot have guard pages present, so no-op - skip. */ if (pmd_trans_huge(pmdval) || pmd_devmap(pmdval)) walk->action = ACTION_CONTINUE; return 0; } static int guard_remove_pte_entry(pte_t *pte, unsigned long addr, unsigned long next, struct mm_walk *walk) { pte_t ptent = ptep_get(pte); if (is_guard_pte_marker(ptent)) { /* Simply clear the PTE marker. */ pte_clear_not_present_full(walk->mm, addr, pte, false); update_mmu_cache(walk->vma, addr, pte); } return 0; } static const struct mm_walk_ops guard_remove_walk_ops = { .pud_entry = guard_remove_pud_entry, .pmd_entry = guard_remove_pmd_entry, .pte_entry = guard_remove_pte_entry, .walk_lock = PGWALK_RDLOCK, }; static long madvise_guard_remove(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end) { *prev = vma; /* * We're ok with removing guards in mlock()'d ranges, as this is a * non-destructive action. */ if (!is_valid_guard_vma(vma, /* allow_locked = */true)) return -EINVAL; return walk_page_range(vma->vm_mm, start, end, &guard_remove_walk_ops, NULL); } /* * Apply an madvise behavior to a region of a vma. madvise_update_vma * will handle splitting a vm area into separate areas, each area with its own * behavior. */ static int madvise_vma_behavior(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, unsigned long behavior) { int error; struct anon_vma_name *anon_name; unsigned long new_flags = vma->vm_flags; if (unlikely(!can_modify_vma_madv(vma, behavior))) return -EPERM; switch (behavior) { case MADV_REMOVE: return madvise_remove(vma, prev, start, end); case MADV_WILLNEED: return madvise_willneed(vma, prev, start, end); case MADV_COLD: return madvise_cold(vma, prev, start, end); case MADV_PAGEOUT: return madvise_pageout(vma, prev, start, end); case MADV_FREE: case MADV_DONTNEED: case MADV_DONTNEED_LOCKED: return madvise_dontneed_free(vma, prev, start, end, behavior); case MADV_NORMAL: new_flags = new_flags & ~VM_RAND_READ & ~VM_SEQ_READ; break; case MADV_SEQUENTIAL: new_flags = (new_flags & ~VM_RAND_READ) | VM_SEQ_READ; break; case MADV_RANDOM: new_flags = (new_flags & ~VM_SEQ_READ) | VM_RAND_READ; break; case MADV_DONTFORK: new_flags |= VM_DONTCOPY; break; case MADV_DOFORK: if (vma->vm_flags & VM_IO) return -EINVAL; new_flags &= ~VM_DONTCOPY; break; case MADV_WIPEONFORK: /* MADV_WIPEONFORK is only supported on anonymous memory. */ if (vma->vm_file || vma->vm_flags & VM_SHARED) return -EINVAL; new_flags |= VM_WIPEONFORK; break; case MADV_KEEPONFORK: if (vma->vm_flags & VM_DROPPABLE) return -EINVAL; new_flags &= ~VM_WIPEONFORK; break; case MADV_DONTDUMP: new_flags |= VM_DONTDUMP; break; case MADV_DODUMP: if ((!is_vm_hugetlb_page(vma) && new_flags & VM_SPECIAL) || (vma->vm_flags & VM_DROPPABLE)) return -EINVAL; new_flags &= ~VM_DONTDUMP; break; case MADV_MERGEABLE: case MADV_UNMERGEABLE: error = ksm_madvise(vma, start, end, behavior, &new_flags); if (error) goto out; break; case MADV_HUGEPAGE: case MADV_NOHUGEPAGE: error = hugepage_madvise(vma, &new_flags, behavior); if (error) goto out; break; case MADV_COLLAPSE: return madvise_collapse(vma, prev, start, end); case MADV_GUARD_INSTALL: return madvise_guard_install(vma, prev, start, end); case MADV_GUARD_REMOVE: return madvise_guard_remove(vma, prev, start, end); } anon_name = anon_vma_name(vma); anon_vma_name_get(anon_name); error = madvise_update_vma(vma, prev, start, end, new_flags, anon_name); anon_vma_name_put(anon_name); out: /* * madvise() returns EAGAIN if kernel resources, such as * slab, are temporarily unavailable. */ if (error == -ENOMEM) error = -EAGAIN; return error; } #ifdef CONFIG_MEMORY_FAILURE /* * Error injection support for memory error handling. */ static int madvise_inject_error(int behavior, unsigned long start, unsigned long end) { unsigned long size; if (!capable(CAP_SYS_ADMIN)) return -EPERM; for (; start < end; start += size) { unsigned long pfn; struct page *page; int ret; ret = get_user_pages_fast(start, 1, 0, &page); if (ret != 1) return ret; pfn = page_to_pfn(page); /* * When soft offlining hugepages, after migrating the page * we dissolve it, therefore in the second loop "page" will * no longer be a compound page. */ size = page_size(compound_head(page)); if (behavior == MADV_SOFT_OFFLINE) { pr_info("Soft offlining pfn %#lx at process virtual address %#lx\n", pfn, start); ret = soft_offline_page(pfn, MF_COUNT_INCREASED); } else { pr_info("Injecting memory failure for pfn %#lx at process virtual address %#lx\n", pfn, start); ret = memory_failure(pfn, MF_ACTION_REQUIRED | MF_COUNT_INCREASED | MF_SW_SIMULATED); if (ret == -EOPNOTSUPP) ret = 0; } if (ret) return ret; } return 0; } #endif static bool madvise_behavior_valid(int behavior) { switch (behavior) { case MADV_DOFORK: case MADV_DONTFORK: case MADV_NORMAL: case MADV_SEQUENTIAL: case MADV_RANDOM: case MADV_REMOVE: case MADV_WILLNEED: case MADV_DONTNEED: case MADV_DONTNEED_LOCKED: case MADV_FREE: case MADV_COLD: case MADV_PAGEOUT: case MADV_POPULATE_READ: case MADV_POPULATE_WRITE: #ifdef CONFIG_KSM case MADV_MERGEABLE: case MADV_UNMERGEABLE: #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE case MADV_HUGEPAGE: case MADV_NOHUGEPAGE: case MADV_COLLAPSE: #endif case MADV_DONTDUMP: case MADV_DODUMP: case MADV_WIPEONFORK: case MADV_KEEPONFORK: case MADV_GUARD_INSTALL: case MADV_GUARD_REMOVE: #ifdef CONFIG_MEMORY_FAILURE case MADV_SOFT_OFFLINE: case MADV_HWPOISON: #endif return true; default: return false; } } /* Can we invoke process_madvise() on a remote mm for the specified behavior? */ static bool process_madvise_remote_valid(int behavior) { switch (behavior) { case MADV_COLD: case MADV_PAGEOUT: case MADV_WILLNEED: case MADV_COLLAPSE: return true; default: return false; } } /* * Walk the vmas in range [start,end), and call the visit function on each one. * The visit function will get start and end parameters that cover the overlap * between the current vma and the original range. Any unmapped regions in the * original range will result in this function returning -ENOMEM while still * calling the visit function on all of the existing vmas in the range. * Must be called with the mmap_lock held for reading or writing. */ static int madvise_walk_vmas(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned long arg, int (*visit)(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, unsigned long arg)) { struct vm_area_struct *vma; struct vm_area_struct *prev; unsigned long tmp; int unmapped_error = 0; /* * If the interval [start,end) covers some unmapped address * ranges, just ignore them, but return -ENOMEM at the end. * - different from the way of handling in mlock etc. */ vma = find_vma_prev(mm, start, &prev); if (vma && start > vma->vm_start) prev = vma; for (;;) { int error; /* Still start < end. */ if (!vma) return -ENOMEM; /* Here start < (end|vma->vm_end). */ if (start < vma->vm_start) { unmapped_error = -ENOMEM; start = vma->vm_start; if (start >= end) break; } /* Here vma->vm_start <= start < (end|vma->vm_end) */ tmp = vma->vm_end; if (end < tmp) tmp = end; /* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */ error = visit(vma, &prev, start, tmp, arg); if (error) return error; start = tmp; if (prev && start < prev->vm_end) start = prev->vm_end; if (start >= end) break; if (prev) vma = find_vma(mm, prev->vm_end); else /* madvise_remove dropped mmap_lock */ vma = find_vma(mm, start); } return unmapped_error; } #ifdef CONFIG_ANON_VMA_NAME static int madvise_vma_anon_name(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, unsigned long anon_name) { int error; /* Only anonymous mappings can be named */ if (vma->vm_file && !vma_is_anon_shmem(vma)) return -EBADF; error = madvise_update_vma(vma, prev, start, end, vma->vm_flags, (struct anon_vma_name *)anon_name); /* * madvise() returns EAGAIN if kernel resources, such as * slab, are temporarily unavailable. */ if (error == -ENOMEM) error = -EAGAIN; return error; } int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, unsigned long len_in, struct anon_vma_name *anon_name) { unsigned long end; unsigned long len; if (start & ~PAGE_MASK) return -EINVAL; len = (len_in + ~PAGE_MASK) & PAGE_MASK; /* Check to see whether len was rounded up from small -ve to zero */ if (len_in && !len) return -EINVAL; end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; return madvise_walk_vmas(mm, start, end, (unsigned long)anon_name, madvise_vma_anon_name); } #endif /* CONFIG_ANON_VMA_NAME */ /* * The madvise(2) system call. * * Applications can use madvise() to advise the kernel how it should * handle paging I/O in this VM area. The idea is to help the kernel * use appropriate read-ahead and caching techniques. The information * provided is advisory only, and can be safely disregarded by the * kernel without affecting the correct operation of the application. * * behavior values: * MADV_NORMAL - the default behavior is to read clusters. This * results in some read-ahead and read-behind. * MADV_RANDOM - the system should read the minimum amount of data * on any access, since it is unlikely that the appli- * cation will need more than what it asks for. * MADV_SEQUENTIAL - pages in the given range will probably be accessed * once, so they can be aggressively read ahead, and * can be freed soon after they are accessed. * MADV_WILLNEED - the application is notifying the system to read * some pages ahead. * MADV_DONTNEED - the application is finished with the given range, * so the kernel can free resources associated with it. * MADV_FREE - the application marks pages in the given range as lazy free, * where actual purges are postponed until memory pressure happens. * MADV_REMOVE - the application wants to free up the given range of * pages and associated backing store. * MADV_DONTFORK - omit this area from child's address space when forking: * typically, to avoid COWing pages pinned by get_user_pages(). * MADV_DOFORK - cancel MADV_DONTFORK: no longer omit this area when forking. * MADV_WIPEONFORK - present the child process with zero-filled memory in this * range after a fork. * MADV_KEEPONFORK - undo the effect of MADV_WIPEONFORK * MADV_HWPOISON - trigger memory error handler as if the given memory range * were corrupted by unrecoverable hardware memory failure. * MADV_SOFT_OFFLINE - try to soft-offline the given range of memory. * MADV_MERGEABLE - the application recommends that KSM try to merge pages in * this area with pages of identical content from other such areas. * MADV_UNMERGEABLE- cancel MADV_MERGEABLE: no longer merge pages with others. * MADV_HUGEPAGE - the application wants to back the given range by transparent * huge pages in the future. Existing pages might be coalesced and * new pages might be allocated as THP. * MADV_NOHUGEPAGE - mark the given range as not worth being backed by * transparent huge pages so the existing pages will not be * coalesced into THP and new pages will not be allocated as THP. * MADV_COLLAPSE - synchronously coalesce pages into new THP. * MADV_DONTDUMP - the application wants to prevent pages in the given range * from being included in its core dump. * MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump. * MADV_COLD - the application is not expected to use this memory soon, * deactivate pages in this range so that they can be reclaimed * easily if memory pressure happens. * MADV_PAGEOUT - the application is not expected to use this memory soon, * page out the pages in this range immediately. * MADV_POPULATE_READ - populate (prefault) page tables readable by * triggering read faults if required * MADV_POPULATE_WRITE - populate (prefault) page tables writable by * triggering write faults if required * * return values: * zero - success * -EINVAL - start + len < 0, start is not page-aligned, * "behavior" is not a valid value, or application * is attempting to release locked or shared pages, * or the specified address range includes file, Huge TLB, * MAP_SHARED or VMPFNMAP range. * -ENOMEM - addresses in the specified range are not currently * mapped, or are outside the AS of the process. * -EIO - an I/O error occurred while paging in data. * -EBADF - map exists, but area maps something that isn't a file. * -EAGAIN - a kernel resource was temporarily unavailable. * -EPERM - memory is sealed. */ int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior) { unsigned long end; int error; int write; size_t len; struct blk_plug plug; if (!madvise_behavior_valid(behavior)) return -EINVAL; if (!PAGE_ALIGNED(start)) return -EINVAL; len = PAGE_ALIGN(len_in); /* Check to see whether len was rounded up from small -ve to zero */ if (len_in && !len) return -EINVAL; end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; #ifdef CONFIG_MEMORY_FAILURE if (behavior == MADV_HWPOISON || behavior == MADV_SOFT_OFFLINE) return madvise_inject_error(behavior, start, start + len_in); #endif write = madvise_need_mmap_write(behavior); if (write) { if (mmap_write_lock_killable(mm)) return -EINTR; } else { mmap_read_lock(mm); } start = untagged_addr_remote(mm, start); end = start + len; blk_start_plug(&plug); switch (behavior) { case MADV_POPULATE_READ: case MADV_POPULATE_WRITE: error = madvise_populate(mm, start, end, behavior); break; default: error = madvise_walk_vmas(mm, start, end, behavior, madvise_vma_behavior); break; } blk_finish_plug(&plug); if (write) mmap_write_unlock(mm); else mmap_read_unlock(mm); return error; } SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) { return do_madvise(current->mm, start, len_in, behavior); } /* Perform an madvise operation over a vector of addresses and lengths. */ static ssize_t vector_madvise(struct mm_struct *mm, struct iov_iter *iter, int behavior) { ssize_t ret = 0; size_t total_len; total_len = iov_iter_count(iter); while (iov_iter_count(iter)) { ret = do_madvise(mm, (unsigned long)iter_iov_addr(iter), iter_iov_len(iter), behavior); /* * An madvise operation is attempting to restart the syscall, * but we cannot proceed as it would not be correct to repeat * the operation in aggregate, and would be surprising to the * user. * * As we have already dropped locks, it is safe to just loop and * try again. We check for fatal signals in case we need exit * early anyway. */ if (ret == -ERESTARTNOINTR) { if (fatal_signal_pending(current)) { ret = -EINTR; break; } continue; } if (ret < 0) break; iov_iter_advance(iter, iter_iov_len(iter)); } ret = (total_len - iov_iter_count(iter)) ? : ret; return ret; } SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec, size_t, vlen, int, behavior, unsigned int, flags) { ssize_t ret; struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; struct task_struct *task; struct mm_struct *mm; unsigned int f_flags; if (flags != 0) { ret = -EINVAL; goto out; } ret = import_iovec(ITER_DEST, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); if (ret < 0) goto out; task = pidfd_get_task(pidfd, &f_flags); if (IS_ERR(task)) { ret = PTR_ERR(task); goto free_iov; } /* Require PTRACE_MODE_READ to avoid leaking ASLR metadata. */ mm = mm_access(task, PTRACE_MODE_READ_FSCREDS); if (IS_ERR(mm)) { ret = PTR_ERR(mm); goto release_task; } /* * We need only perform this check if we are attempting to manipulate a * remote process's address space. */ if (mm != current->mm && !process_madvise_remote_valid(behavior)) { ret = -EINVAL; goto release_mm; } /* * Require CAP_SYS_NICE for influencing process performance. Note that * only non-destructive hints are currently supported for remote * processes. */ if (mm != current->mm && !capable(CAP_SYS_NICE)) { ret = -EPERM; goto release_mm; } ret = vector_madvise(mm, &iter, behavior); release_mm: mmput(mm); release_task: put_task_struct(task); free_iov: kfree(iov); out: return ret; } |
| 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kdebug.h> #include <linux/kprobes.h> #include <linux/export.h> #include <linux/notifier.h> #include <linux/rcupdate.h> #include <linux/vmalloc.h> #define CREATE_TRACE_POINTS #include <trace/events/notifier.h> /* * Notifier chain core routines. The exported routines below * are layered on top of these, with appropriate locking added. */ static int notifier_chain_register(struct notifier_block **nl, struct notifier_block *n, bool unique_priority) { while ((*nl) != NULL) { if (unlikely((*nl) == n)) { WARN(1, "notifier callback %ps already registered", n->notifier_call); return -EEXIST; } if (n->priority > (*nl)->priority) break; if (n->priority == (*nl)->priority && unique_priority) return -EBUSY; nl = &((*nl)->next); } n->next = *nl; rcu_assign_pointer(*nl, n); trace_notifier_register((void *)n->notifier_call); return 0; } static int notifier_chain_unregister(struct notifier_block **nl, struct notifier_block *n) { while ((*nl) != NULL) { if ((*nl) == n) { rcu_assign_pointer(*nl, n->next); trace_notifier_unregister((void *)n->notifier_call); return 0; } nl = &((*nl)->next); } return -ENOENT; } /** * notifier_call_chain - Informs the registered notifiers about an event. * @nl: Pointer to head of the blocking notifier chain * @val: Value passed unmodified to notifier function * @v: Pointer passed unmodified to notifier function * @nr_to_call: Number of notifier functions to be called. Don't care * value of this parameter is -1. * @nr_calls: Records the number of notifications sent. Don't care * value of this field is NULL. * Return: notifier_call_chain returns the value returned by the * last notifier function called. */ static int notifier_call_chain(struct notifier_block **nl, unsigned long val, void *v, int nr_to_call, int *nr_calls) { int ret = NOTIFY_DONE; struct notifier_block *nb, *next_nb; nb = rcu_dereference_raw(*nl); while (nb && nr_to_call) { next_nb = rcu_dereference_raw(nb->next); #ifdef CONFIG_DEBUG_NOTIFIERS if (unlikely(!func_ptr_is_kernel_text(nb->notifier_call))) { WARN(1, "Invalid notifier called!"); nb = next_nb; continue; } #endif trace_notifier_run((void *)nb->notifier_call); ret = nb->notifier_call(nb, val, v); if (nr_calls) (*nr_calls)++; if (ret & NOTIFY_STOP_MASK) break; nb = next_nb; nr_to_call--; } return ret; } NOKPROBE_SYMBOL(notifier_call_chain); /** * notifier_call_chain_robust - Inform the registered notifiers about an event * and rollback on error. * @nl: Pointer to head of the blocking notifier chain * @val_up: Value passed unmodified to the notifier function * @val_down: Value passed unmodified to the notifier function when recovering * from an error on @val_up * @v: Pointer passed unmodified to the notifier function * * NOTE: It is important the @nl chain doesn't change between the two * invocations of notifier_call_chain() such that we visit the * exact same notifier callbacks; this rules out any RCU usage. * * Return: the return value of the @val_up call. */ static int notifier_call_chain_robust(struct notifier_block **nl, unsigned long val_up, unsigned long val_down, void *v) { int ret, nr = 0; ret = notifier_call_chain(nl, val_up, v, -1, &nr); if (ret & NOTIFY_STOP_MASK) notifier_call_chain(nl, val_down, v, nr-1, NULL); return ret; } /* * Atomic notifier chain routines. Registration and unregistration * use a spinlock, and call_chain is synchronized by RCU (no locks). */ /** * atomic_notifier_chain_register - Add notifier to an atomic notifier chain * @nh: Pointer to head of the atomic notifier chain * @n: New entry in notifier chain * * Adds a notifier to an atomic notifier chain. * * Returns 0 on success, %-EEXIST on error. */ int atomic_notifier_chain_register(struct atomic_notifier_head *nh, struct notifier_block *n) { unsigned long flags; int ret; spin_lock_irqsave(&nh->lock, flags); ret = notifier_chain_register(&nh->head, n, false); spin_unlock_irqrestore(&nh->lock, flags); return ret; } EXPORT_SYMBOL_GPL(atomic_notifier_chain_register); /** * atomic_notifier_chain_register_unique_prio - Add notifier to an atomic notifier chain * @nh: Pointer to head of the atomic notifier chain * @n: New entry in notifier chain * * Adds a notifier to an atomic notifier chain if there is no other * notifier registered using the same priority. * * Returns 0 on success, %-EEXIST or %-EBUSY on error. */ int atomic_notifier_chain_register_unique_prio(struct atomic_notifier_head *nh, struct notifier_block *n) { unsigned long flags; int ret; spin_lock_irqsave(&nh->lock, flags); ret = notifier_chain_register(&nh->head, n, true); spin_unlock_irqrestore(&nh->lock, flags); return ret; } EXPORT_SYMBOL_GPL(atomic_notifier_chain_register_unique_prio); /** * atomic_notifier_chain_unregister - Remove notifier from an atomic notifier chain * @nh: Pointer to head of the atomic notifier chain * @n: Entry to remove from notifier chain * * Removes a notifier from an atomic notifier chain. * * Returns zero on success or %-ENOENT on failure. */ int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh, struct notifier_block *n) { unsigned long flags; int ret; spin_lock_irqsave(&nh->lock, flags); ret = notifier_chain_unregister(&nh->head, n); spin_unlock_irqrestore(&nh->lock, flags); synchronize_rcu(); return ret; } EXPORT_SYMBOL_GPL(atomic_notifier_chain_unregister); /** * atomic_notifier_call_chain - Call functions in an atomic notifier chain * @nh: Pointer to head of the atomic notifier chain * @val: Value passed unmodified to notifier function * @v: Pointer passed unmodified to notifier function * * Calls each function in a notifier chain in turn. The functions * run in an atomic context, so they must not block. * This routine uses RCU to synchronize with changes to the chain. * * If the return value of the notifier can be and'ed * with %NOTIFY_STOP_MASK then atomic_notifier_call_chain() * will return immediately, with the return value of * the notifier function which halted execution. * Otherwise the return value is the return value * of the last notifier function called. */ int atomic_notifier_call_chain(struct atomic_notifier_head *nh, unsigned long val, void *v) { int ret; rcu_read_lock(); ret = notifier_call_chain(&nh->head, val, v, -1, NULL); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(atomic_notifier_call_chain); NOKPROBE_SYMBOL(atomic_notifier_call_chain); /** * atomic_notifier_call_chain_is_empty - Check whether notifier chain is empty * @nh: Pointer to head of the atomic notifier chain * * Checks whether notifier chain is empty. * * Returns true is notifier chain is empty, false otherwise. */ bool atomic_notifier_call_chain_is_empty(struct atomic_notifier_head *nh) { return !rcu_access_pointer(nh->head); } /* * Blocking notifier chain routines. All access to the chain is * synchronized by an rwsem. */ static int __blocking_notifier_chain_register(struct blocking_notifier_head *nh, struct notifier_block *n, bool unique_priority) { int ret; /* * This code gets used during boot-up, when task switching is * not yet working and interrupts must remain disabled. At * such times we must not call down_write(). */ if (unlikely(system_state == SYSTEM_BOOTING)) return notifier_chain_register(&nh->head, n, unique_priority); down_write(&nh->rwsem); ret = notifier_chain_register(&nh->head, n, unique_priority); up_write(&nh->rwsem); return ret; } /** * blocking_notifier_chain_register - Add notifier to a blocking notifier chain * @nh: Pointer to head of the blocking notifier chain * @n: New entry in notifier chain * * Adds a notifier to a blocking notifier chain. * Must be called in process context. * * Returns 0 on success, %-EEXIST on error. */ int blocking_notifier_chain_register(struct blocking_notifier_head *nh, struct notifier_block *n) { return __blocking_notifier_chain_register(nh, n, false); } EXPORT_SYMBOL_GPL(blocking_notifier_chain_register); /** * blocking_notifier_chain_register_unique_prio - Add notifier to a blocking notifier chain * @nh: Pointer to head of the blocking notifier chain * @n: New entry in notifier chain * * Adds a notifier to an blocking notifier chain if there is no other * notifier registered using the same priority. * * Returns 0 on success, %-EEXIST or %-EBUSY on error. */ int blocking_notifier_chain_register_unique_prio(struct blocking_notifier_head *nh, struct notifier_block *n) { return __blocking_notifier_chain_register(nh, n, true); } EXPORT_SYMBOL_GPL(blocking_notifier_chain_register_unique_prio); /** * blocking_notifier_chain_unregister - Remove notifier from a blocking notifier chain * @nh: Pointer to head of the blocking notifier chain * @n: Entry to remove from notifier chain * * Removes a notifier from a blocking notifier chain. * Must be called from process context. * * Returns zero on success or %-ENOENT on failure. */ int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh, struct notifier_block *n) { int ret; /* * This code gets used during boot-up, when task switching is * not yet working and interrupts must remain disabled. At * such times we must not call down_write(). */ if (unlikely(system_state == SYSTEM_BOOTING)) return notifier_chain_unregister(&nh->head, n); down_write(&nh->rwsem); ret = notifier_chain_unregister(&nh->head, n); up_write(&nh->rwsem); return ret; } EXPORT_SYMBOL_GPL(blocking_notifier_chain_unregister); int blocking_notifier_call_chain_robust(struct blocking_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v) { int ret = NOTIFY_DONE; /* * We check the head outside the lock, but if this access is * racy then it does not matter what the result of the test * is, we re-check the list after having taken the lock anyway: */ if (rcu_access_pointer(nh->head)) { down_read(&nh->rwsem); ret = notifier_call_chain_robust(&nh->head, val_up, val_down, v); up_read(&nh->rwsem); } return ret; } EXPORT_SYMBOL_GPL(blocking_notifier_call_chain_robust); /** * blocking_notifier_call_chain - Call functions in a blocking notifier chain * @nh: Pointer to head of the blocking notifier chain * @val: Value passed unmodified to notifier function * @v: Pointer passed unmodified to notifier function * * Calls each function in a notifier chain in turn. The functions * run in a process context, so they are allowed to block. * * If the return value of the notifier can be and'ed * with %NOTIFY_STOP_MASK then blocking_notifier_call_chain() * will return immediately, with the return value of * the notifier function which halted execution. * Otherwise the return value is the return value * of the last notifier function called. */ int blocking_notifier_call_chain(struct blocking_notifier_head *nh, unsigned long val, void *v) { int ret = NOTIFY_DONE; /* * We check the head outside the lock, but if this access is * racy then it does not matter what the result of the test * is, we re-check the list after having taken the lock anyway: */ if (rcu_access_pointer(nh->head)) { down_read(&nh->rwsem); ret = notifier_call_chain(&nh->head, val, v, -1, NULL); up_read(&nh->rwsem); } return ret; } EXPORT_SYMBOL_GPL(blocking_notifier_call_chain); /* * Raw notifier chain routines. There is no protection; * the caller must provide it. Use at your own risk! */ /** * raw_notifier_chain_register - Add notifier to a raw notifier chain * @nh: Pointer to head of the raw notifier chain * @n: New entry in notifier chain * * Adds a notifier to a raw notifier chain. * All locking must be provided by the caller. * * Returns 0 on success, %-EEXIST on error. */ int raw_notifier_chain_register(struct raw_notifier_head *nh, struct notifier_block *n) { return notifier_chain_register(&nh->head, n, false); } EXPORT_SYMBOL_GPL(raw_notifier_chain_register); /** * raw_notifier_chain_unregister - Remove notifier from a raw notifier chain * @nh: Pointer to head of the raw notifier chain * @n: Entry to remove from notifier chain * * Removes a notifier from a raw notifier chain. * All locking must be provided by the caller. * * Returns zero on success or %-ENOENT on failure. */ int raw_notifier_chain_unregister(struct raw_notifier_head *nh, struct notifier_block *n) { return notifier_chain_unregister(&nh->head, n); } EXPORT_SYMBOL_GPL(raw_notifier_chain_unregister); int raw_notifier_call_chain_robust(struct raw_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v) { return notifier_call_chain_robust(&nh->head, val_up, val_down, v); } EXPORT_SYMBOL_GPL(raw_notifier_call_chain_robust); /** * raw_notifier_call_chain - Call functions in a raw notifier chain * @nh: Pointer to head of the raw notifier chain * @val: Value passed unmodified to notifier function * @v: Pointer passed unmodified to notifier function * * Calls each function in a notifier chain in turn. The functions * run in an undefined context. * All locking must be provided by the caller. * * If the return value of the notifier can be and'ed * with %NOTIFY_STOP_MASK then raw_notifier_call_chain() * will return immediately, with the return value of * the notifier function which halted execution. * Otherwise the return value is the return value * of the last notifier function called. */ int raw_notifier_call_chain(struct raw_notifier_head *nh, unsigned long val, void *v) { return notifier_call_chain(&nh->head, val, v, -1, NULL); } EXPORT_SYMBOL_GPL(raw_notifier_call_chain); /* * SRCU notifier chain routines. Registration and unregistration * use a mutex, and call_chain is synchronized by SRCU (no locks). */ /** * srcu_notifier_chain_register - Add notifier to an SRCU notifier chain * @nh: Pointer to head of the SRCU notifier chain * @n: New entry in notifier chain * * Adds a notifier to an SRCU notifier chain. * Must be called in process context. * * Returns 0 on success, %-EEXIST on error. */ int srcu_notifier_chain_register(struct srcu_notifier_head *nh, struct notifier_block *n) { int ret; /* * This code gets used during boot-up, when task switching is * not yet working and interrupts must remain disabled. At * such times we must not call mutex_lock(). */ if (unlikely(system_state == SYSTEM_BOOTING)) return notifier_chain_register(&nh->head, n, false); mutex_lock(&nh->mutex); ret = notifier_chain_register(&nh->head, n, false); mutex_unlock(&nh->mutex); return ret; } EXPORT_SYMBOL_GPL(srcu_notifier_chain_register); /** * srcu_notifier_chain_unregister - Remove notifier from an SRCU notifier chain * @nh: Pointer to head of the SRCU notifier chain * @n: Entry to remove from notifier chain * * Removes a notifier from an SRCU notifier chain. * Must be called from process context. * * Returns zero on success or %-ENOENT on failure. */ int srcu_notifier_chain_unregister(struct srcu_notifier_head *nh, struct notifier_block *n) { int ret; /* * This code gets used during boot-up, when task switching is * not yet working and interrupts must remain disabled. At * such times we must not call mutex_lock(). */ if (unlikely(system_state == SYSTEM_BOOTING)) return notifier_chain_unregister(&nh->head, n); mutex_lock(&nh->mutex); ret = notifier_chain_unregister(&nh->head, n); mutex_unlock(&nh->mutex); synchronize_srcu(&nh->srcu); return ret; } EXPORT_SYMBOL_GPL(srcu_notifier_chain_unregister); /** * srcu_notifier_call_chain - Call functions in an SRCU notifier chain * @nh: Pointer to head of the SRCU notifier chain * @val: Value passed unmodified to notifier function * @v: Pointer passed unmodified to notifier function * * Calls each function in a notifier chain in turn. The functions * run in a process context, so they are allowed to block. * * If the return value of the notifier can be and'ed * with %NOTIFY_STOP_MASK then srcu_notifier_call_chain() * will return immediately, with the return value of * the notifier function which halted execution. * Otherwise the return value is the return value * of the last notifier function called. */ int srcu_notifier_call_chain(struct srcu_notifier_head *nh, unsigned long val, void *v) { int ret; int idx; idx = srcu_read_lock(&nh->srcu); ret = notifier_call_chain(&nh->head, val, v, -1, NULL); srcu_read_unlock(&nh->srcu, idx); return ret; } EXPORT_SYMBOL_GPL(srcu_notifier_call_chain); /** * srcu_init_notifier_head - Initialize an SRCU notifier head * @nh: Pointer to head of the srcu notifier chain * * Unlike other sorts of notifier heads, SRCU notifier heads require * dynamic initialization. Be sure to call this routine before * calling any of the other SRCU notifier routines for this head. * * If an SRCU notifier head is deallocated, it must first be cleaned * up by calling srcu_cleanup_notifier_head(). Otherwise the head's * per-cpu data (used by the SRCU mechanism) will leak. */ void srcu_init_notifier_head(struct srcu_notifier_head *nh) { mutex_init(&nh->mutex); if (init_srcu_struct(&nh->srcu) < 0) BUG(); nh->head = NULL; } EXPORT_SYMBOL_GPL(srcu_init_notifier_head); static ATOMIC_NOTIFIER_HEAD(die_chain); int notrace notify_die(enum die_val val, const char *str, struct pt_regs *regs, long err, int trap, int sig) { struct die_args args = { .regs = regs, .str = str, .err = err, .trapnr = trap, .signr = sig, }; RCU_LOCKDEP_WARN(!rcu_is_watching(), "notify_die called but RCU thinks we're quiescent"); return atomic_notifier_call_chain(&die_chain, val, &args); } NOKPROBE_SYMBOL(notify_die); int register_die_notifier(struct notifier_block *nb) { return atomic_notifier_chain_register(&die_chain, nb); } EXPORT_SYMBOL_GPL(register_die_notifier); int unregister_die_notifier(struct notifier_block *nb) { return atomic_notifier_chain_unregister(&die_chain, nb); } EXPORT_SYMBOL_GPL(unregister_die_notifier); |
| 13 2 15 13 15 15 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/attr.c * * Copyright (C) 1991, 1992 Linus Torvalds * changes by Thomas Schoebel-Theuer */ #include <linux/export.h> #include <linux/time.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/sched/signal.h> #include <linux/capability.h> #include <linux/fsnotify.h> #include <linux/fcntl.h> #include <linux/filelock.h> #include <linux/security.h> /** * setattr_should_drop_sgid - determine whether the setgid bit needs to be * removed * @idmap: idmap of the mount @inode was found from * @inode: inode to check * * This function determines whether the setgid bit needs to be removed. * We retain backwards compatibility and require setgid bit to be removed * unconditionally if S_IXGRP is set. Otherwise we have the exact same * requirements as setattr_prepare() and setattr_copy(). * * Return: ATTR_KILL_SGID if setgid bit needs to be removed, 0 otherwise. */ int setattr_should_drop_sgid(struct mnt_idmap *idmap, const struct inode *inode) { umode_t mode = inode->i_mode; if (!(mode & S_ISGID)) return 0; if (mode & S_IXGRP) return ATTR_KILL_SGID; if (!in_group_or_capable(idmap, inode, i_gid_into_vfsgid(idmap, inode))) return ATTR_KILL_SGID; return 0; } EXPORT_SYMBOL(setattr_should_drop_sgid); /** * setattr_should_drop_suidgid - determine whether the set{g,u}id bit needs to * be dropped * @idmap: idmap of the mount @inode was found from * @inode: inode to check * * This function determines whether the set{g,u}id bits need to be removed. * If the setuid bit needs to be removed ATTR_KILL_SUID is returned. If the * setgid bit needs to be removed ATTR_KILL_SGID is returned. If both * set{g,u}id bits need to be removed the corresponding mask of both flags is * returned. * * Return: A mask of ATTR_KILL_S{G,U}ID indicating which - if any - setid bits * to remove, 0 otherwise. */ int setattr_should_drop_suidgid(struct mnt_idmap *idmap, struct inode *inode) { umode_t mode = inode->i_mode; int kill = 0; /* suid always must be killed */ if (unlikely(mode & S_ISUID)) kill = ATTR_KILL_SUID; kill |= setattr_should_drop_sgid(idmap, inode); if (unlikely(kill && !capable(CAP_FSETID) && S_ISREG(mode))) return kill; return 0; } EXPORT_SYMBOL(setattr_should_drop_suidgid); /** * chown_ok - verify permissions to chown inode * @idmap: idmap of the mount @inode was found from * @inode: inode to check permissions on * @ia_vfsuid: uid to chown @inode to * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. */ static bool chown_ok(struct mnt_idmap *idmap, const struct inode *inode, vfsuid_t ia_vfsuid) { vfsuid_t vfsuid = i_uid_into_vfsuid(idmap, inode); if (vfsuid_eq_kuid(vfsuid, current_fsuid()) && vfsuid_eq(ia_vfsuid, vfsuid)) return true; if (capable_wrt_inode_uidgid(idmap, inode, CAP_CHOWN)) return true; if (!vfsuid_valid(vfsuid) && ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN)) return true; return false; } /** * chgrp_ok - verify permissions to chgrp inode * @idmap: idmap of the mount @inode was found from * @inode: inode to check permissions on * @ia_vfsgid: gid to chown @inode to * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. */ static bool chgrp_ok(struct mnt_idmap *idmap, const struct inode *inode, vfsgid_t ia_vfsgid) { vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode); vfsuid_t vfsuid = i_uid_into_vfsuid(idmap, inode); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) { if (vfsgid_eq(ia_vfsgid, vfsgid)) return true; if (vfsgid_in_group_p(ia_vfsgid)) return true; } if (capable_wrt_inode_uidgid(idmap, inode, CAP_CHOWN)) return true; if (!vfsgid_valid(vfsgid) && ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN)) return true; return false; } /** * setattr_prepare - check if attribute changes to a dentry are allowed * @idmap: idmap of the mount the inode was found from * @dentry: dentry to check * @attr: attributes to change * * Check if we are allowed to change the attributes contained in @attr * in the given dentry. This includes the normal unix access permission * checks, as well as checks for rlimits and others. The function also clears * SGID bit from mode if user is not allowed to set it. Also file capabilities * and IMA extended attributes are cleared if ATTR_KILL_PRIV is set. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. * * Should be called as the first thing in ->setattr implementations, * possibly after taking additional locks. */ int setattr_prepare(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); unsigned int ia_valid = attr->ia_valid; /* * First check size constraints. These can't be overriden using * ATTR_FORCE. */ if (ia_valid & ATTR_SIZE) { int error = inode_newsize_ok(inode, attr->ia_size); if (error) return error; } /* If force is set do it anyway. */ if (ia_valid & ATTR_FORCE) goto kill_priv; /* Make sure a caller can chown. */ if ((ia_valid & ATTR_UID) && !chown_ok(idmap, inode, attr->ia_vfsuid)) return -EPERM; /* Make sure caller can chgrp. */ if ((ia_valid & ATTR_GID) && !chgrp_ok(idmap, inode, attr->ia_vfsgid)) return -EPERM; /* Make sure a caller can chmod. */ if (ia_valid & ATTR_MODE) { vfsgid_t vfsgid; if (!inode_owner_or_capable(idmap, inode)) return -EPERM; if (ia_valid & ATTR_GID) vfsgid = attr->ia_vfsgid; else vfsgid = i_gid_into_vfsgid(idmap, inode); /* Also check the setgid bit! */ if (!in_group_or_capable(idmap, inode, vfsgid)) attr->ia_mode &= ~S_ISGID; } /* Check for setting the inode time. */ if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET)) { if (!inode_owner_or_capable(idmap, inode)) return -EPERM; } kill_priv: /* User has permission for the change */ if (ia_valid & ATTR_KILL_PRIV) { int error; error = security_inode_killpriv(idmap, dentry); if (error) return error; } return 0; } EXPORT_SYMBOL(setattr_prepare); /** * inode_newsize_ok - may this inode be truncated to a given size * @inode: the inode to be truncated * @offset: the new size to assign to the inode * * inode_newsize_ok must be called with i_mutex held. * * inode_newsize_ok will check filesystem limits and ulimits to check that the * new inode size is within limits. inode_newsize_ok will also send SIGXFSZ * when necessary. Caller must not proceed with inode size change if failure is * returned. @inode must be a file (not directory), with appropriate * permissions to allow truncate (inode_newsize_ok does NOT check these * conditions). * * Return: 0 on success, -ve errno on failure */ int inode_newsize_ok(const struct inode *inode, loff_t offset) { if (offset < 0) return -EINVAL; if (inode->i_size < offset) { unsigned long limit; limit = rlimit(RLIMIT_FSIZE); if (limit != RLIM_INFINITY && offset > limit) goto out_sig; if (offset > inode->i_sb->s_maxbytes) goto out_big; } else { /* * truncation of in-use swapfiles is disallowed - it would * cause subsequent swapout to scribble on the now-freed * blocks. */ if (IS_SWAPFILE(inode)) return -ETXTBSY; } return 0; out_sig: send_sig(SIGXFSZ, current, 0); out_big: return -EFBIG; } EXPORT_SYMBOL(inode_newsize_ok); /** * setattr_copy_mgtime - update timestamps for mgtime inodes * @inode: inode timestamps to be updated * @attr: attrs for the update * * With multigrain timestamps, take more care to prevent races when * updating the ctime. Always update the ctime to the very latest using * the standard mechanism, and use that to populate the atime and mtime * appropriately (unless those are being set to specific values). */ static void setattr_copy_mgtime(struct inode *inode, const struct iattr *attr) { unsigned int ia_valid = attr->ia_valid; struct timespec64 now; if (ia_valid & ATTR_CTIME) { /* * In the case of an update for a write delegation, we must respect * the value in ia_ctime and not use the current time. */ if (ia_valid & ATTR_DELEG) now = inode_set_ctime_deleg(inode, attr->ia_ctime); else now = inode_set_ctime_current(inode); } else { /* If ATTR_CTIME isn't set, then ATTR_MTIME shouldn't be either. */ WARN_ON_ONCE(ia_valid & ATTR_MTIME); now = current_time(inode); } if (ia_valid & ATTR_ATIME_SET) inode_set_atime_to_ts(inode, attr->ia_atime); else if (ia_valid & ATTR_ATIME) inode_set_atime_to_ts(inode, now); if (ia_valid & ATTR_MTIME_SET) inode_set_mtime_to_ts(inode, attr->ia_mtime); else if (ia_valid & ATTR_MTIME) inode_set_mtime_to_ts(inode, now); } /** * setattr_copy - copy simple metadata updates into the generic inode * @idmap: idmap of the mount the inode was found from * @inode: the inode to be updated * @attr: the new attributes * * setattr_copy must be called with i_mutex held. * * setattr_copy updates the inode's metadata with that specified * in attr on idmapped mounts. Necessary permission checks to determine * whether or not the S_ISGID property needs to be removed are performed with * the correct idmapped mount permission helpers. * Noticeably missing is inode size update, which is more complex * as it requires pagecache updates. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. * * The inode is not marked as dirty after this operation. The rationale is * that for "simple" filesystems, the struct inode is the inode storage. * The caller is free to mark the inode dirty afterwards if needed. */ void setattr_copy(struct mnt_idmap *idmap, struct inode *inode, const struct iattr *attr) { unsigned int ia_valid = attr->ia_valid; i_uid_update(idmap, attr, inode); i_gid_update(idmap, attr, inode); if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; if (!in_group_or_capable(idmap, inode, i_gid_into_vfsgid(idmap, inode))) mode &= ~S_ISGID; inode->i_mode = mode; } if (is_mgtime(inode)) return setattr_copy_mgtime(inode, attr); if (ia_valid & ATTR_ATIME) inode_set_atime_to_ts(inode, attr->ia_atime); if (ia_valid & ATTR_MTIME) inode_set_mtime_to_ts(inode, attr->ia_mtime); if (ia_valid & ATTR_CTIME) { if (ia_valid & ATTR_DELEG) inode_set_ctime_deleg(inode, attr->ia_ctime); else inode_set_ctime_to_ts(inode, attr->ia_ctime); } } EXPORT_SYMBOL(setattr_copy); int may_setattr(struct mnt_idmap *idmap, struct inode *inode, unsigned int ia_valid) { int error; if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) { if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) return -EPERM; } /* * If utimes(2) and friends are called with times == NULL (or both * times are UTIME_NOW), then we need to check for write permission */ if (ia_valid & ATTR_TOUCH) { if (IS_IMMUTABLE(inode)) return -EPERM; if (!inode_owner_or_capable(idmap, inode)) { error = inode_permission(idmap, inode, MAY_WRITE); if (error) return error; } } return 0; } EXPORT_SYMBOL(may_setattr); /** * notify_change - modify attributes of a filesystem object * @idmap: idmap of the mount the inode was found from * @dentry: object affected * @attr: new attributes * @delegated_inode: returns inode, if the inode is delegated * * The caller must hold the i_mutex on the affected object. * * If notify_change discovers a delegation in need of breaking, * it will return -EWOULDBLOCK and return a reference to the inode in * delegated_inode. The caller should then break the delegation and * retry. Because breaking a delegation may take a long time, the * caller should drop the i_mutex before doing so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. Also, passing NULL is fine for callers holding * the file open for write, as there can be no conflicting delegation in * that case. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. */ int notify_change(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr, struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; umode_t mode = inode->i_mode; int error; struct timespec64 now; unsigned int ia_valid = attr->ia_valid; WARN_ON_ONCE(!inode_is_locked(inode)); error = may_setattr(idmap, inode, ia_valid); if (error) return error; if ((ia_valid & ATTR_MODE)) { /* * Don't allow changing the mode of symlinks: * * (1) The vfs doesn't take the mode of symlinks into account * during permission checking. * (2) This has never worked correctly. Most major filesystems * did return EOPNOTSUPP due to interactions with POSIX ACLs * but did still updated the mode of the symlink. * This inconsistency led system call wrapper providers such * as libc to block changing the mode of symlinks with * EOPNOTSUPP already. * (3) To even do this in the first place one would have to use * specific file descriptors and quite some effort. */ if (S_ISLNK(inode->i_mode)) return -EOPNOTSUPP; /* Flag setting protected by i_mutex */ if (is_sxid(attr->ia_mode)) inode->i_flags &= ~S_NOSEC; } now = current_time(inode); attr->ia_ctime = now; if (!(ia_valid & ATTR_ATIME_SET)) attr->ia_atime = now; else attr->ia_atime = timestamp_truncate(attr->ia_atime, inode); if (!(ia_valid & ATTR_MTIME_SET)) attr->ia_mtime = now; else attr->ia_mtime = timestamp_truncate(attr->ia_mtime, inode); if (ia_valid & ATTR_KILL_PRIV) { error = security_inode_need_killpriv(dentry); if (error < 0) return error; if (error == 0) ia_valid = attr->ia_valid &= ~ATTR_KILL_PRIV; } /* * We now pass ATTR_KILL_S*ID to the lower level setattr function so * that the function has the ability to reinterpret a mode change * that's due to these bits. This adds an implicit restriction that * no function will ever call notify_change with both ATTR_MODE and * ATTR_KILL_S*ID set. */ if ((ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) && (ia_valid & ATTR_MODE)) BUG(); if (ia_valid & ATTR_KILL_SUID) { if (mode & S_ISUID) { ia_valid = attr->ia_valid |= ATTR_MODE; attr->ia_mode = (inode->i_mode & ~S_ISUID); } } if (ia_valid & ATTR_KILL_SGID) { if (mode & S_ISGID) { if (!(ia_valid & ATTR_MODE)) { ia_valid = attr->ia_valid |= ATTR_MODE; attr->ia_mode = inode->i_mode; } attr->ia_mode &= ~S_ISGID; } } if (!(attr->ia_valid & ~(ATTR_KILL_SUID | ATTR_KILL_SGID))) return 0; /* * Verify that uid/gid changes are valid in the target * namespace of the superblock. */ if (ia_valid & ATTR_UID && !vfsuid_has_fsmapping(idmap, inode->i_sb->s_user_ns, attr->ia_vfsuid)) return -EOVERFLOW; if (ia_valid & ATTR_GID && !vfsgid_has_fsmapping(idmap, inode->i_sb->s_user_ns, attr->ia_vfsgid)) return -EOVERFLOW; /* Don't allow modifications of files with invalid uids or * gids unless those uids & gids are being made valid. */ if (!(ia_valid & ATTR_UID) && !vfsuid_valid(i_uid_into_vfsuid(idmap, inode))) return -EOVERFLOW; if (!(ia_valid & ATTR_GID) && !vfsgid_valid(i_gid_into_vfsgid(idmap, inode))) return -EOVERFLOW; error = security_inode_setattr(idmap, dentry, attr); if (error) return error; /* * If ATTR_DELEG is set, then these attributes are being set on * behalf of the holder of a write delegation. We want to avoid * breaking the delegation in this case. */ if (!(ia_valid & ATTR_DELEG)) { error = try_break_deleg(inode, delegated_inode); if (error) return error; } if (inode->i_op->setattr) error = inode->i_op->setattr(idmap, dentry, attr); else error = simple_setattr(idmap, dentry, attr); if (!error) { fsnotify_change(dentry, ia_valid); security_inode_post_setattr(idmap, dentry, ia_valid); } return error; } EXPORT_SYMBOL(notify_change); |
| 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> */ #include <linux/arm-smccc.h> #include <linux/preempt.h> #include <linux/kvm_host.h> #include <linux/uaccess.h> #include <linux/wait.h> #include <asm/cputype.h> #include <asm/kvm_emulate.h> #include <kvm/arm_psci.h> #include <kvm/arm_hypercalls.h> /* * This is an implementation of the Power State Coordination Interface * as described in ARM document number ARM DEN 0022A. */ #define AFFINITY_MASK(level) ~((0x1UL << ((level) * MPIDR_LEVEL_BITS)) - 1) static unsigned long psci_affinity_mask(unsigned long affinity_level) { if (affinity_level <= 3) return MPIDR_HWID_BITMASK & AFFINITY_MASK(affinity_level); return 0; } static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu) { /* * NOTE: For simplicity, we make VCPU suspend emulation to be * same-as WFI (Wait-for-interrupt) emulation. * * This means for KVM the wakeup events are interrupts and * this is consistent with intended use of StateID as described * in section 5.4.1 of PSCI v0.2 specification (ARM DEN 0022A). * * Further, we also treat power-down request to be same as * stand-by request as-per section 5.4.2 clause 3 of PSCI v0.2 * specification (ARM DEN 0022A). This means all suspend states * for KVM will preserve the register state. */ kvm_vcpu_wfi(vcpu); return PSCI_RET_SUCCESS; } static inline bool kvm_psci_valid_affinity(struct kvm_vcpu *vcpu, unsigned long affinity) { return !(affinity & ~MPIDR_HWID_BITMASK); } static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) { struct vcpu_reset_state *reset_state; struct kvm *kvm = source_vcpu->kvm; struct kvm_vcpu *vcpu = NULL; int ret = PSCI_RET_SUCCESS; unsigned long cpu_id; cpu_id = smccc_get_arg1(source_vcpu); if (!kvm_psci_valid_affinity(source_vcpu, cpu_id)) return PSCI_RET_INVALID_PARAMS; vcpu = kvm_mpidr_to_vcpu(kvm, cpu_id); /* * Make sure the caller requested a valid CPU and that the CPU is * turned off. */ if (!vcpu) return PSCI_RET_INVALID_PARAMS; spin_lock(&vcpu->arch.mp_state_lock); if (!kvm_arm_vcpu_stopped(vcpu)) { if (kvm_psci_version(source_vcpu) != KVM_ARM_PSCI_0_1) ret = PSCI_RET_ALREADY_ON; else ret = PSCI_RET_INVALID_PARAMS; goto out_unlock; } reset_state = &vcpu->arch.reset_state; reset_state->pc = smccc_get_arg2(source_vcpu); /* Propagate caller endianness */ reset_state->be = kvm_vcpu_is_be(source_vcpu); /* * NOTE: We always update r0 (or x0) because for PSCI v0.1 * the general purpose registers are undefined upon CPU_ON. */ reset_state->r0 = smccc_get_arg3(source_vcpu); reset_state->reset = true; kvm_make_request(KVM_REQ_VCPU_RESET, vcpu); /* * Make sure the reset request is observed if the RUNNABLE mp_state is * observed. */ smp_wmb(); WRITE_ONCE(vcpu->arch.mp_state.mp_state, KVM_MP_STATE_RUNNABLE); kvm_vcpu_wake_up(vcpu); out_unlock: spin_unlock(&vcpu->arch.mp_state_lock); return ret; } static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu) { int matching_cpus = 0; unsigned long i, mpidr; unsigned long target_affinity; unsigned long target_affinity_mask; unsigned long lowest_affinity_level; struct kvm *kvm = vcpu->kvm; struct kvm_vcpu *tmp; target_affinity = smccc_get_arg1(vcpu); lowest_affinity_level = smccc_get_arg2(vcpu); if (!kvm_psci_valid_affinity(vcpu, target_affinity)) return PSCI_RET_INVALID_PARAMS; /* Determine target affinity mask */ target_affinity_mask = psci_affinity_mask(lowest_affinity_level); if (!target_affinity_mask) return PSCI_RET_INVALID_PARAMS; /* Ignore other bits of target affinity */ target_affinity &= target_affinity_mask; /* * If one or more VCPU matching target affinity are running * then ON else OFF */ kvm_for_each_vcpu(i, tmp, kvm) { mpidr = kvm_vcpu_get_mpidr_aff(tmp); if ((mpidr & target_affinity_mask) == target_affinity) { matching_cpus++; if (!kvm_arm_vcpu_stopped(tmp)) return PSCI_0_2_AFFINITY_LEVEL_ON; } } if (!matching_cpus) return PSCI_RET_INVALID_PARAMS; return PSCI_0_2_AFFINITY_LEVEL_OFF; } static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type, u64 flags) { unsigned long i; struct kvm_vcpu *tmp; /* * The KVM ABI specifies that a system event exit may call KVM_RUN * again and may perform shutdown/reboot at a later time that when the * actual request is made. Since we are implementing PSCI and a * caller of PSCI reboot and shutdown expects that the system shuts * down or reboots immediately, let's make sure that VCPUs are not run * after this call is handled and before the VCPUs have been * re-initialized. */ kvm_for_each_vcpu(i, tmp, vcpu->kvm) { spin_lock(&tmp->arch.mp_state_lock); WRITE_ONCE(tmp->arch.mp_state.mp_state, KVM_MP_STATE_STOPPED); spin_unlock(&tmp->arch.mp_state_lock); } kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_SLEEP); memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event)); vcpu->run->system_event.type = type; vcpu->run->system_event.ndata = 1; vcpu->run->system_event.data[0] = flags; vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; } static void kvm_psci_system_off(struct kvm_vcpu *vcpu) { kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_SHUTDOWN, 0); } static void kvm_psci_system_off2(struct kvm_vcpu *vcpu) { kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_SHUTDOWN, KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2); } static void kvm_psci_system_reset(struct kvm_vcpu *vcpu) { kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET, 0); } static void kvm_psci_system_reset2(struct kvm_vcpu *vcpu) { kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET, KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2); } static void kvm_psci_system_suspend(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; memset(&run->system_event, 0, sizeof(vcpu->run->system_event)); run->system_event.type = KVM_SYSTEM_EVENT_SUSPEND; run->exit_reason = KVM_EXIT_SYSTEM_EVENT; } static void kvm_psci_narrow_to_32bit(struct kvm_vcpu *vcpu) { int i; /* * Zero the input registers' upper 32 bits. They will be fully * zeroed on exit, so we're fine changing them in place. */ for (i = 1; i < 4; i++) vcpu_set_reg(vcpu, i, lower_32_bits(vcpu_get_reg(vcpu, i))); } static unsigned long kvm_psci_check_allowed_function(struct kvm_vcpu *vcpu, u32 fn) { /* * Prevent 32 bit guests from calling 64 bit PSCI functions. */ if ((fn & PSCI_0_2_64BIT) && vcpu_mode_is_32bit(vcpu)) return PSCI_RET_NOT_SUPPORTED; return 0; } static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) { u32 psci_fn = smccc_get_function(vcpu); unsigned long val; int ret = 1; switch (psci_fn) { case PSCI_0_2_FN_PSCI_VERSION: /* * Bits[31:16] = Major Version = 0 * Bits[15:0] = Minor Version = 2 */ val = KVM_ARM_PSCI_0_2; break; case PSCI_0_2_FN_CPU_SUSPEND: case PSCI_0_2_FN64_CPU_SUSPEND: val = kvm_psci_vcpu_suspend(vcpu); break; case PSCI_0_2_FN_CPU_OFF: kvm_arm_vcpu_power_off(vcpu); val = PSCI_RET_SUCCESS; break; case PSCI_0_2_FN_CPU_ON: kvm_psci_narrow_to_32bit(vcpu); fallthrough; case PSCI_0_2_FN64_CPU_ON: val = kvm_psci_vcpu_on(vcpu); break; case PSCI_0_2_FN_AFFINITY_INFO: kvm_psci_narrow_to_32bit(vcpu); fallthrough; case PSCI_0_2_FN64_AFFINITY_INFO: val = kvm_psci_vcpu_affinity_info(vcpu); break; case PSCI_0_2_FN_MIGRATE_INFO_TYPE: /* * Trusted OS is MP hence does not require migration * or * Trusted OS is not present */ val = PSCI_0_2_TOS_MP; break; case PSCI_0_2_FN_SYSTEM_OFF: kvm_psci_system_off(vcpu); /* * We shouldn't be going back to guest VCPU after * receiving SYSTEM_OFF request. * * If user space accidentally/deliberately resumes * guest VCPU after SYSTEM_OFF request then guest * VCPU should see internal failure from PSCI return * value. To achieve this, we preload r0 (or x0) with * PSCI return value INTERNAL_FAILURE. */ val = PSCI_RET_INTERNAL_FAILURE; ret = 0; break; case PSCI_0_2_FN_SYSTEM_RESET: kvm_psci_system_reset(vcpu); /* * Same reason as SYSTEM_OFF for preloading r0 (or x0) * with PSCI return value INTERNAL_FAILURE. */ val = PSCI_RET_INTERNAL_FAILURE; ret = 0; break; default: val = PSCI_RET_NOT_SUPPORTED; break; } smccc_set_retval(vcpu, val, 0, 0, 0); return ret; } static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor) { unsigned long val = PSCI_RET_NOT_SUPPORTED; u32 psci_fn = smccc_get_function(vcpu); struct kvm *kvm = vcpu->kvm; u32 arg; int ret = 1; switch(psci_fn) { case PSCI_0_2_FN_PSCI_VERSION: val = PSCI_VERSION(1, minor); break; case PSCI_1_0_FN_PSCI_FEATURES: arg = smccc_get_arg1(vcpu); val = kvm_psci_check_allowed_function(vcpu, arg); if (val) break; val = PSCI_RET_NOT_SUPPORTED; switch(arg) { case PSCI_0_2_FN_PSCI_VERSION: case PSCI_0_2_FN_CPU_SUSPEND: case PSCI_0_2_FN64_CPU_SUSPEND: case PSCI_0_2_FN_CPU_OFF: case PSCI_0_2_FN_CPU_ON: case PSCI_0_2_FN64_CPU_ON: case PSCI_0_2_FN_AFFINITY_INFO: case PSCI_0_2_FN64_AFFINITY_INFO: case PSCI_0_2_FN_MIGRATE_INFO_TYPE: case PSCI_0_2_FN_SYSTEM_OFF: case PSCI_0_2_FN_SYSTEM_RESET: case PSCI_1_0_FN_PSCI_FEATURES: case ARM_SMCCC_VERSION_FUNC_ID: val = 0; break; case PSCI_1_0_FN_SYSTEM_SUSPEND: case PSCI_1_0_FN64_SYSTEM_SUSPEND: if (test_bit(KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED, &kvm->arch.flags)) val = 0; break; case PSCI_1_1_FN_SYSTEM_RESET2: case PSCI_1_1_FN64_SYSTEM_RESET2: if (minor >= 1) val = 0; break; case PSCI_1_3_FN_SYSTEM_OFF2: case PSCI_1_3_FN64_SYSTEM_OFF2: if (minor >= 3) val = PSCI_1_3_OFF_TYPE_HIBERNATE_OFF; break; } break; case PSCI_1_0_FN_SYSTEM_SUSPEND: kvm_psci_narrow_to_32bit(vcpu); fallthrough; case PSCI_1_0_FN64_SYSTEM_SUSPEND: /* * Return directly to userspace without changing the vCPU's * registers. Userspace depends on reading the SMCCC parameters * to implement SYSTEM_SUSPEND. */ if (test_bit(KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED, &kvm->arch.flags)) { kvm_psci_system_suspend(vcpu); return 0; } break; case PSCI_1_1_FN_SYSTEM_RESET2: kvm_psci_narrow_to_32bit(vcpu); fallthrough; case PSCI_1_1_FN64_SYSTEM_RESET2: if (minor >= 1) { arg = smccc_get_arg1(vcpu); if (arg <= PSCI_1_1_RESET_TYPE_SYSTEM_WARM_RESET || arg >= PSCI_1_1_RESET_TYPE_VENDOR_START) { kvm_psci_system_reset2(vcpu); vcpu_set_reg(vcpu, 0, PSCI_RET_INTERNAL_FAILURE); return 0; } val = PSCI_RET_INVALID_PARAMS; break; } break; case PSCI_1_3_FN_SYSTEM_OFF2: kvm_psci_narrow_to_32bit(vcpu); fallthrough; case PSCI_1_3_FN64_SYSTEM_OFF2: if (minor < 3) break; arg = smccc_get_arg1(vcpu); /* * SYSTEM_OFF2 defaults to HIBERNATE_OFF if arg1 is zero. arg2 * must be zero. */ if ((arg && arg != PSCI_1_3_OFF_TYPE_HIBERNATE_OFF) || smccc_get_arg2(vcpu) != 0) { val = PSCI_RET_INVALID_PARAMS; break; } kvm_psci_system_off2(vcpu); /* * We shouldn't be going back to the guest after receiving a * SYSTEM_OFF2 request. Preload a return value of * INTERNAL_FAILURE should userspace ignore the exit and resume * the vCPU. */ val = PSCI_RET_INTERNAL_FAILURE; ret = 0; break; default: return kvm_psci_0_2_call(vcpu); } smccc_set_retval(vcpu, val, 0, 0, 0); return ret; } static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu) { u32 psci_fn = smccc_get_function(vcpu); unsigned long val; switch (psci_fn) { case KVM_PSCI_FN_CPU_OFF: kvm_arm_vcpu_power_off(vcpu); val = PSCI_RET_SUCCESS; break; case KVM_PSCI_FN_CPU_ON: val = kvm_psci_vcpu_on(vcpu); break; default: val = PSCI_RET_NOT_SUPPORTED; break; } smccc_set_retval(vcpu, val, 0, 0, 0); return 1; } /** * kvm_psci_call - handle PSCI call if r0 value is in range * @vcpu: Pointer to the VCPU struct * * Handle PSCI calls from guests through traps from HVC instructions. * The calling convention is similar to SMC calls to the secure world * where the function number is placed in r0. * * This function returns: > 0 (success), 0 (success but exit to user * space), and < 0 (errors) * * Errors: * -EINVAL: Unrecognized PSCI function */ int kvm_psci_call(struct kvm_vcpu *vcpu) { u32 psci_fn = smccc_get_function(vcpu); int version = kvm_psci_version(vcpu); unsigned long val; val = kvm_psci_check_allowed_function(vcpu, psci_fn); if (val) { smccc_set_retval(vcpu, val, 0, 0, 0); return 1; } switch (version) { case KVM_ARM_PSCI_1_3: return kvm_psci_1_x_call(vcpu, 3); case KVM_ARM_PSCI_1_2: return kvm_psci_1_x_call(vcpu, 2); case KVM_ARM_PSCI_1_1: return kvm_psci_1_x_call(vcpu, 1); case KVM_ARM_PSCI_1_0: return kvm_psci_1_x_call(vcpu, 0); case KVM_ARM_PSCI_0_2: return kvm_psci_0_2_call(vcpu); case KVM_ARM_PSCI_0_1: return kvm_psci_0_1_call(vcpu); default: WARN_ONCE(1, "Unknown PSCI version %d", version); smccc_set_retval(vcpu, SMCCC_RET_NOT_SUPPORTED, 0, 0, 0); return 1; } } |
| 18 23 2 18 2 3 1 2 19 18 19 17 19 11 17 18 15 18 14 14 7 14 12 10 2 6 6 1 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/pipe.c * * Copyright (C) 1991, 1992, 1999 Linus Torvalds */ #include <linux/mm.h> #include <linux/file.h> #include <linux/poll.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/log2.h> #include <linux/mount.h> #include <linux/pseudo_fs.h> #include <linux/magic.h> #include <linux/pipe_fs_i.h> #include <linux/uio.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/audit.h> #include <linux/syscalls.h> #include <linux/fcntl.h> #include <linux/memcontrol.h> #include <linux/watch_queue.h> #include <linux/sysctl.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include "internal.h" /* * New pipe buffers will be restricted to this size while the user is exceeding * their pipe buffer quota. The general pipe use case needs at least two * buffers: one for data yet to be read, and one for new data. If this is less * than two, then a write to a non-empty pipe may block even if the pipe is not * full. This can occur with GNU make jobserver or similar uses of pipes as * semaphores: multiple processes may be waiting to write tokens back to the * pipe before reading tokens: https://lore.kernel.org/lkml/1628086770.5rn8p04n6j.none@localhost/. * * Users can reduce their pipe buffers with F_SETPIPE_SZ below this at their * own risk, namely: pipe writes to non-full pipes may block until the pipe is * emptied. */ #define PIPE_MIN_DEF_BUFFERS 2 /* * The max size that a non-root user is allowed to grow the pipe. Can * be set by root in /proc/sys/fs/pipe-max-size */ static unsigned int pipe_max_size = 1048576; /* Maximum allocatable pages per user. Hard limit is unset by default, soft * matches default values. */ static unsigned long pipe_user_pages_hard; static unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR; /* * We use head and tail indices that aren't masked off, except at the point of * dereference, but rather they're allowed to wrap naturally. This means there * isn't a dead spot in the buffer, but the ring has to be a power of two and * <= 2^31. * -- David Howells 2019-09-23. * * Reads with count = 0 should always return 0. * -- Julian Bradfield 1999-06-07. * * FIFOs and Pipes now generate SIGIO for both readers and writers. * -- Jeremy Elson <jelson@circlemud.org> 2001-08-16 * * pipe_read & write cleanup * -- Manfred Spraul <manfred@colorfullife.com> 2002-05-09 */ #define cmp_int(l, r) ((l > r) - (l < r)) #ifdef CONFIG_PROVE_LOCKING static int pipe_lock_cmp_fn(const struct lockdep_map *a, const struct lockdep_map *b) { return cmp_int((unsigned long) a, (unsigned long) b); } #endif void pipe_lock(struct pipe_inode_info *pipe) { if (pipe->files) mutex_lock(&pipe->mutex); } EXPORT_SYMBOL(pipe_lock); void pipe_unlock(struct pipe_inode_info *pipe) { if (pipe->files) mutex_unlock(&pipe->mutex); } EXPORT_SYMBOL(pipe_unlock); void pipe_double_lock(struct pipe_inode_info *pipe1, struct pipe_inode_info *pipe2) { BUG_ON(pipe1 == pipe2); if (pipe1 > pipe2) swap(pipe1, pipe2); pipe_lock(pipe1); pipe_lock(pipe2); } static void anon_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; /* * If nobody else uses this page, and we don't already have a * temporary page, let's keep track of it as a one-deep * allocation cache. (Otherwise just release our reference to it) */ if (page_count(page) == 1 && !pipe->tmp_page) pipe->tmp_page = page; else put_page(page); } static bool anon_pipe_buf_try_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; if (page_count(page) != 1) return false; memcg_kmem_uncharge_page(page, 0); __SetPageLocked(page); return true; } /** * generic_pipe_buf_try_steal - attempt to take ownership of a &pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to attempt to steal * * Description: * This function attempts to steal the &struct page attached to * @buf. If successful, this function returns 0 and returns with * the page locked. The caller may then reuse the page for whatever * he wishes; the typical use is insertion into a different file * page cache. */ bool generic_pipe_buf_try_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; /* * A reference of one is golden, that means that the owner of this * page is the only one holding a reference to it. lock the page * and return OK. */ if (page_count(page) == 1) { lock_page(page); return true; } return false; } EXPORT_SYMBOL(generic_pipe_buf_try_steal); /** * generic_pipe_buf_get - get a reference to a &struct pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to get a reference to * * Description: * This function grabs an extra reference to @buf. It's used in * the tee() system call, when we duplicate the buffers in one * pipe into another. */ bool generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { return try_get_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_get); /** * generic_pipe_buf_release - put a reference to a &struct pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to put a reference to * * Description: * This function releases a reference to @buf. */ void generic_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { put_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_release); static const struct pipe_buf_operations anon_pipe_buf_ops = { .release = anon_pipe_buf_release, .try_steal = anon_pipe_buf_try_steal, .get = generic_pipe_buf_get, }; /* Done while waiting without holding the pipe lock - thus the READ_ONCE() */ static inline bool pipe_readable(const struct pipe_inode_info *pipe) { unsigned int head = READ_ONCE(pipe->head); unsigned int tail = READ_ONCE(pipe->tail); unsigned int writers = READ_ONCE(pipe->writers); return !pipe_empty(head, tail) || !writers; } static inline unsigned int pipe_update_tail(struct pipe_inode_info *pipe, struct pipe_buffer *buf, unsigned int tail) { pipe_buf_release(pipe, buf); /* * If the pipe has a watch_queue, we need additional protection * by the spinlock because notifications get posted with only * this spinlock, no mutex */ if (pipe_has_watch_queue(pipe)) { spin_lock_irq(&pipe->rd_wait.lock); #ifdef CONFIG_WATCH_QUEUE if (buf->flags & PIPE_BUF_FLAG_LOSS) pipe->note_loss = true; #endif pipe->tail = ++tail; spin_unlock_irq(&pipe->rd_wait.lock); return tail; } /* * Without a watch_queue, we can simply increment the tail * without the spinlock - the mutex is enough. */ pipe->tail = ++tail; return tail; } static ssize_t pipe_read(struct kiocb *iocb, struct iov_iter *to) { size_t total_len = iov_iter_count(to); struct file *filp = iocb->ki_filp; struct pipe_inode_info *pipe = filp->private_data; bool was_full, wake_next_reader = false; ssize_t ret; /* Null read succeeds. */ if (unlikely(total_len == 0)) return 0; ret = 0; mutex_lock(&pipe->mutex); /* * We only wake up writers if the pipe was full when we started * reading in order to avoid unnecessary wakeups. * * But when we do wake up writers, we do so using a sync wakeup * (WF_SYNC), because we want them to get going and generate more * data for us. */ was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage); for (;;) { /* Read ->head with a barrier vs post_one_notification() */ unsigned int head = smp_load_acquire(&pipe->head); unsigned int tail = pipe->tail; unsigned int mask = pipe->ring_size - 1; #ifdef CONFIG_WATCH_QUEUE if (pipe->note_loss) { struct watch_notification n; if (total_len < 8) { if (ret == 0) ret = -ENOBUFS; break; } n.type = WATCH_TYPE_META; n.subtype = WATCH_META_LOSS_NOTIFICATION; n.info = watch_sizeof(n); if (copy_to_iter(&n, sizeof(n), to) != sizeof(n)) { if (ret == 0) ret = -EFAULT; break; } ret += sizeof(n); total_len -= sizeof(n); pipe->note_loss = false; } #endif if (!pipe_empty(head, tail)) { struct pipe_buffer *buf = &pipe->bufs[tail & mask]; size_t chars = buf->len; size_t written; int error; if (chars > total_len) { if (buf->flags & PIPE_BUF_FLAG_WHOLE) { if (ret == 0) ret = -ENOBUFS; break; } chars = total_len; } error = pipe_buf_confirm(pipe, buf); if (error) { if (!ret) ret = error; break; } written = copy_page_to_iter(buf->page, buf->offset, chars, to); if (unlikely(written < chars)) { if (!ret) ret = -EFAULT; break; } ret += chars; buf->offset += chars; buf->len -= chars; /* Was it a packet buffer? Clean up and exit */ if (buf->flags & PIPE_BUF_FLAG_PACKET) { total_len = chars; buf->len = 0; } if (!buf->len) tail = pipe_update_tail(pipe, buf, tail); total_len -= chars; if (!total_len) break; /* common path: read succeeded */ if (!pipe_empty(head, tail)) /* More to do? */ continue; } if (!pipe->writers) break; if (ret) break; if ((filp->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) { ret = -EAGAIN; break; } mutex_unlock(&pipe->mutex); /* * We only get here if we didn't actually read anything. * * However, we could have seen (and removed) a zero-sized * pipe buffer, and might have made space in the buffers * that way. * * You can't make zero-sized pipe buffers by doing an empty * write (not even in packet mode), but they can happen if * the writer gets an EFAULT when trying to fill a buffer * that already got allocated and inserted in the buffer * array. * * So we still need to wake up any pending writers in the * _very_ unlikely case that the pipe was full, but we got * no data. */ if (unlikely(was_full)) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); /* * But because we didn't read anything, at this point we can * just return directly with -ERESTARTSYS if we're interrupted, * since we've done any required wakeups and there's no need * to mark anything accessed. And we've dropped the lock. */ if (wait_event_interruptible_exclusive(pipe->rd_wait, pipe_readable(pipe)) < 0) return -ERESTARTSYS; mutex_lock(&pipe->mutex); was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage); wake_next_reader = true; } if (pipe_empty(pipe->head, pipe->tail)) wake_next_reader = false; mutex_unlock(&pipe->mutex); if (was_full) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); if (wake_next_reader) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); if (ret > 0) file_accessed(filp); return ret; } static inline int is_packetized(struct file *file) { return (file->f_flags & O_DIRECT) != 0; } /* Done while waiting without holding the pipe lock - thus the READ_ONCE() */ static inline bool pipe_writable(const struct pipe_inode_info *pipe) { unsigned int head = READ_ONCE(pipe->head); unsigned int tail = READ_ONCE(pipe->tail); unsigned int max_usage = READ_ONCE(pipe->max_usage); return !pipe_full(head, tail, max_usage) || !READ_ONCE(pipe->readers); } static ssize_t pipe_write(struct kiocb *iocb, struct iov_iter *from) { struct file *filp = iocb->ki_filp; struct pipe_inode_info *pipe = filp->private_data; unsigned int head; ssize_t ret = 0; size_t total_len = iov_iter_count(from); ssize_t chars; bool was_empty = false; bool wake_next_writer = false; /* * Reject writing to watch queue pipes before the point where we lock * the pipe. * Otherwise, lockdep would be unhappy if the caller already has another * pipe locked. * If we had to support locking a normal pipe and a notification pipe at * the same time, we could set up lockdep annotations for that, but * since we don't actually need that, it's simpler to just bail here. */ if (pipe_has_watch_queue(pipe)) return -EXDEV; /* Null write succeeds. */ if (unlikely(total_len == 0)) return 0; mutex_lock(&pipe->mutex); if (!pipe->readers) { send_sig(SIGPIPE, current, 0); ret = -EPIPE; goto out; } /* * If it wasn't empty we try to merge new data into * the last buffer. * * That naturally merges small writes, but it also * page-aligns the rest of the writes for large writes * spanning multiple pages. */ head = pipe->head; was_empty = pipe_empty(head, pipe->tail); chars = total_len & (PAGE_SIZE-1); if (chars && !was_empty) { unsigned int mask = pipe->ring_size - 1; struct pipe_buffer *buf = &pipe->bufs[(head - 1) & mask]; int offset = buf->offset + buf->len; if ((buf->flags & PIPE_BUF_FLAG_CAN_MERGE) && offset + chars <= PAGE_SIZE) { ret = pipe_buf_confirm(pipe, buf); if (ret) goto out; ret = copy_page_from_iter(buf->page, offset, chars, from); if (unlikely(ret < chars)) { ret = -EFAULT; goto out; } buf->len += ret; if (!iov_iter_count(from)) goto out; } } for (;;) { if (!pipe->readers) { send_sig(SIGPIPE, current, 0); if (!ret) ret = -EPIPE; break; } head = pipe->head; if (!pipe_full(head, pipe->tail, pipe->max_usage)) { unsigned int mask = pipe->ring_size - 1; struct pipe_buffer *buf; struct page *page = pipe->tmp_page; int copied; if (!page) { page = alloc_page(GFP_HIGHUSER | __GFP_ACCOUNT); if (unlikely(!page)) { ret = ret ? : -ENOMEM; break; } pipe->tmp_page = page; } /* Allocate a slot in the ring in advance and attach an * empty buffer. If we fault or otherwise fail to use * it, either the reader will consume it or it'll still * be there for the next write. */ pipe->head = head + 1; /* Insert it into the buffer array */ buf = &pipe->bufs[head & mask]; buf->page = page; buf->ops = &anon_pipe_buf_ops; buf->offset = 0; buf->len = 0; if (is_packetized(filp)) buf->flags = PIPE_BUF_FLAG_PACKET; else buf->flags = PIPE_BUF_FLAG_CAN_MERGE; pipe->tmp_page = NULL; copied = copy_page_from_iter(page, 0, PAGE_SIZE, from); if (unlikely(copied < PAGE_SIZE && iov_iter_count(from))) { if (!ret) ret = -EFAULT; break; } ret += copied; buf->len = copied; if (!iov_iter_count(from)) break; } if (!pipe_full(head, pipe->tail, pipe->max_usage)) continue; /* Wait for buffer space to become available. */ if ((filp->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) { if (!ret) ret = -EAGAIN; break; } if (signal_pending(current)) { if (!ret) ret = -ERESTARTSYS; break; } /* * We're going to release the pipe lock and wait for more * space. We wake up any readers if necessary, and then * after waiting we need to re-check whether the pipe * become empty while we dropped the lock. */ mutex_unlock(&pipe->mutex); if (was_empty) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); wait_event_interruptible_exclusive(pipe->wr_wait, pipe_writable(pipe)); mutex_lock(&pipe->mutex); was_empty = pipe_empty(pipe->head, pipe->tail); wake_next_writer = true; } out: if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) wake_next_writer = false; mutex_unlock(&pipe->mutex); /* * If we do do a wakeup event, we do a 'sync' wakeup, because we * want the reader to start processing things asap, rather than * leave the data pending. * * This is particularly important for small writes, because of * how (for example) the GNU make jobserver uses small writes to * wake up pending jobs * * Epoll nonsensically wants a wakeup whether the pipe * was already empty or not. */ if (was_empty || pipe->poll_usage) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); if (wake_next_writer) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); if (ret > 0 && sb_start_write_trylock(file_inode(filp)->i_sb)) { int err = file_update_time(filp); if (err) ret = err; sb_end_write(file_inode(filp)->i_sb); } return ret; } static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct pipe_inode_info *pipe = filp->private_data; unsigned int count, head, tail, mask; switch (cmd) { case FIONREAD: mutex_lock(&pipe->mutex); count = 0; head = pipe->head; tail = pipe->tail; mask = pipe->ring_size - 1; while (tail != head) { count += pipe->bufs[tail & mask].len; tail++; } mutex_unlock(&pipe->mutex); return put_user(count, (int __user *)arg); #ifdef CONFIG_WATCH_QUEUE case IOC_WATCH_QUEUE_SET_SIZE: { int ret; mutex_lock(&pipe->mutex); ret = watch_queue_set_size(pipe, arg); mutex_unlock(&pipe->mutex); return ret; } case IOC_WATCH_QUEUE_SET_FILTER: return watch_queue_set_filter( pipe, (struct watch_notification_filter __user *)arg); #endif default: return -ENOIOCTLCMD; } } /* No kernel lock held - fine */ static __poll_t pipe_poll(struct file *filp, poll_table *wait) { __poll_t mask; struct pipe_inode_info *pipe = filp->private_data; unsigned int head, tail; /* Epoll has some historical nasty semantics, this enables them */ WRITE_ONCE(pipe->poll_usage, true); /* * Reading pipe state only -- no need for acquiring the semaphore. * * But because this is racy, the code has to add the * entry to the poll table _first_ .. */ if (filp->f_mode & FMODE_READ) poll_wait(filp, &pipe->rd_wait, wait); if (filp->f_mode & FMODE_WRITE) poll_wait(filp, &pipe->wr_wait, wait); /* * .. and only then can you do the racy tests. That way, * if something changes and you got it wrong, the poll * table entry will wake you up and fix it. */ head = READ_ONCE(pipe->head); tail = READ_ONCE(pipe->tail); mask = 0; if (filp->f_mode & FMODE_READ) { if (!pipe_empty(head, tail)) mask |= EPOLLIN | EPOLLRDNORM; if (!pipe->writers && filp->f_pipe != pipe->w_counter) mask |= EPOLLHUP; } if (filp->f_mode & FMODE_WRITE) { if (!pipe_full(head, tail, pipe->max_usage)) mask |= EPOLLOUT | EPOLLWRNORM; /* * Most Unices do not set EPOLLERR for FIFOs but on Linux they * behave exactly like pipes for poll(). */ if (!pipe->readers) mask |= EPOLLERR; } return mask; } static void put_pipe_info(struct inode *inode, struct pipe_inode_info *pipe) { int kill = 0; spin_lock(&inode->i_lock); if (!--pipe->files) { inode->i_pipe = NULL; kill = 1; } spin_unlock(&inode->i_lock); if (kill) free_pipe_info(pipe); } static int pipe_release(struct inode *inode, struct file *file) { struct pipe_inode_info *pipe = file->private_data; mutex_lock(&pipe->mutex); if (file->f_mode & FMODE_READ) pipe->readers--; if (file->f_mode & FMODE_WRITE) pipe->writers--; /* Was that the last reader or writer, but not the other side? */ if (!pipe->readers != !pipe->writers) { wake_up_interruptible_all(&pipe->rd_wait); wake_up_interruptible_all(&pipe->wr_wait); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } mutex_unlock(&pipe->mutex); put_pipe_info(inode, pipe); return 0; } static int pipe_fasync(int fd, struct file *filp, int on) { struct pipe_inode_info *pipe = filp->private_data; int retval = 0; mutex_lock(&pipe->mutex); if (filp->f_mode & FMODE_READ) retval = fasync_helper(fd, filp, on, &pipe->fasync_readers); if ((filp->f_mode & FMODE_WRITE) && retval >= 0) { retval = fasync_helper(fd, filp, on, &pipe->fasync_writers); if (retval < 0 && (filp->f_mode & FMODE_READ)) /* this can happen only if on == T */ fasync_helper(-1, filp, 0, &pipe->fasync_readers); } mutex_unlock(&pipe->mutex); return retval; } unsigned long account_pipe_buffers(struct user_struct *user, unsigned long old, unsigned long new) { return atomic_long_add_return(new - old, &user->pipe_bufs); } bool too_many_pipe_buffers_soft(unsigned long user_bufs) { unsigned long soft_limit = READ_ONCE(pipe_user_pages_soft); return soft_limit && user_bufs > soft_limit; } bool too_many_pipe_buffers_hard(unsigned long user_bufs) { unsigned long hard_limit = READ_ONCE(pipe_user_pages_hard); return hard_limit && user_bufs > hard_limit; } bool pipe_is_unprivileged_user(void) { return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); } struct pipe_inode_info *alloc_pipe_info(void) { struct pipe_inode_info *pipe; unsigned long pipe_bufs = PIPE_DEF_BUFFERS; struct user_struct *user = get_current_user(); unsigned long user_bufs; unsigned int max_size = READ_ONCE(pipe_max_size); pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL_ACCOUNT); if (pipe == NULL) goto out_free_uid; if (pipe_bufs * PAGE_SIZE > max_size && !capable(CAP_SYS_RESOURCE)) pipe_bufs = max_size >> PAGE_SHIFT; user_bufs = account_pipe_buffers(user, 0, pipe_bufs); if (too_many_pipe_buffers_soft(user_bufs) && pipe_is_unprivileged_user()) { user_bufs = account_pipe_buffers(user, pipe_bufs, PIPE_MIN_DEF_BUFFERS); pipe_bufs = PIPE_MIN_DEF_BUFFERS; } if (too_many_pipe_buffers_hard(user_bufs) && pipe_is_unprivileged_user()) goto out_revert_acct; pipe->bufs = kcalloc(pipe_bufs, sizeof(struct pipe_buffer), GFP_KERNEL_ACCOUNT); if (pipe->bufs) { init_waitqueue_head(&pipe->rd_wait); init_waitqueue_head(&pipe->wr_wait); pipe->r_counter = pipe->w_counter = 1; pipe->max_usage = pipe_bufs; pipe->ring_size = pipe_bufs; pipe->nr_accounted = pipe_bufs; pipe->user = user; mutex_init(&pipe->mutex); lock_set_cmp_fn(&pipe->mutex, pipe_lock_cmp_fn, NULL); return pipe; } out_revert_acct: (void) account_pipe_buffers(user, pipe_bufs, 0); kfree(pipe); out_free_uid: free_uid(user); return NULL; } void free_pipe_info(struct pipe_inode_info *pipe) { unsigned int i; #ifdef CONFIG_WATCH_QUEUE if (pipe->watch_queue) watch_queue_clear(pipe->watch_queue); #endif (void) account_pipe_buffers(pipe->user, pipe->nr_accounted, 0); free_uid(pipe->user); for (i = 0; i < pipe->ring_size; i++) { struct pipe_buffer *buf = pipe->bufs + i; if (buf->ops) pipe_buf_release(pipe, buf); } #ifdef CONFIG_WATCH_QUEUE if (pipe->watch_queue) put_watch_queue(pipe->watch_queue); #endif if (pipe->tmp_page) __free_page(pipe->tmp_page); kfree(pipe->bufs); kfree(pipe); } static struct vfsmount *pipe_mnt __ro_after_init; /* * pipefs_dname() is called from d_path(). */ static char *pipefs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(buffer, buflen, "pipe:[%lu]", d_inode(dentry)->i_ino); } static const struct dentry_operations pipefs_dentry_operations = { .d_dname = pipefs_dname, }; static struct inode * get_pipe_inode(void) { struct inode *inode = new_inode_pseudo(pipe_mnt->mnt_sb); struct pipe_inode_info *pipe; if (!inode) goto fail_inode; inode->i_ino = get_next_ino(); pipe = alloc_pipe_info(); if (!pipe) goto fail_iput; inode->i_pipe = pipe; pipe->files = 2; pipe->readers = pipe->writers = 1; inode->i_fop = &pipefifo_fops; /* * Mark the inode dirty from the very beginning, * that way it will never be moved to the dirty * list because "mark_inode_dirty()" will think * that it already _is_ on the dirty list. */ inode->i_state = I_DIRTY; inode->i_mode = S_IFIFO | S_IRUSR | S_IWUSR; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); simple_inode_init_ts(inode); return inode; fail_iput: iput(inode); fail_inode: return NULL; } int create_pipe_files(struct file **res, int flags) { struct inode *inode = get_pipe_inode(); struct file *f; int error; if (!inode) return -ENFILE; if (flags & O_NOTIFICATION_PIPE) { error = watch_queue_init(inode->i_pipe); if (error) { free_pipe_info(inode->i_pipe); iput(inode); return error; } } f = alloc_file_pseudo(inode, pipe_mnt, "", O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)), &pipefifo_fops); if (IS_ERR(f)) { free_pipe_info(inode->i_pipe); iput(inode); return PTR_ERR(f); } f->private_data = inode->i_pipe; f->f_pipe = 0; res[0] = alloc_file_clone(f, O_RDONLY | (flags & O_NONBLOCK), &pipefifo_fops); if (IS_ERR(res[0])) { put_pipe_info(inode, inode->i_pipe); fput(f); return PTR_ERR(res[0]); } res[0]->private_data = inode->i_pipe; res[0]->f_pipe = 0; res[1] = f; stream_open(inode, res[0]); stream_open(inode, res[1]); return 0; } static int __do_pipe_flags(int *fd, struct file **files, int flags) { int error; int fdw, fdr; if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT | O_NOTIFICATION_PIPE)) return -EINVAL; error = create_pipe_files(files, flags); if (error) return error; error = get_unused_fd_flags(flags); if (error < 0) goto err_read_pipe; fdr = error; error = get_unused_fd_flags(flags); if (error < 0) goto err_fdr; fdw = error; audit_fd_pair(fdr, fdw); fd[0] = fdr; fd[1] = fdw; /* pipe groks IOCB_NOWAIT */ files[0]->f_mode |= FMODE_NOWAIT; files[1]->f_mode |= FMODE_NOWAIT; return 0; err_fdr: put_unused_fd(fdr); err_read_pipe: fput(files[0]); fput(files[1]); return error; } int do_pipe_flags(int *fd, int flags) { struct file *files[2]; int error = __do_pipe_flags(fd, files, flags); if (!error) { fd_install(fd[0], files[0]); fd_install(fd[1], files[1]); } return error; } /* * sys_pipe() is the normal C calling standard for creating * a pipe. It's not the way Unix traditionally does this, though. */ static int do_pipe2(int __user *fildes, int flags) { struct file *files[2]; int fd[2]; int error; error = __do_pipe_flags(fd, files, flags); if (!error) { if (unlikely(copy_to_user(fildes, fd, sizeof(fd)))) { fput(files[0]); fput(files[1]); put_unused_fd(fd[0]); put_unused_fd(fd[1]); error = -EFAULT; } else { fd_install(fd[0], files[0]); fd_install(fd[1], files[1]); } } return error; } SYSCALL_DEFINE2(pipe2, int __user *, fildes, int, flags) { return do_pipe2(fildes, flags); } SYSCALL_DEFINE1(pipe, int __user *, fildes) { return do_pipe2(fildes, 0); } /* * This is the stupid "wait for pipe to be readable or writable" * model. * * See pipe_read/write() for the proper kind of exclusive wait, * but that requires that we wake up any other readers/writers * if we then do not end up reading everything (ie the whole * "wake_next_reader/writer" logic in pipe_read/write()). */ void pipe_wait_readable(struct pipe_inode_info *pipe) { pipe_unlock(pipe); wait_event_interruptible(pipe->rd_wait, pipe_readable(pipe)); pipe_lock(pipe); } void pipe_wait_writable(struct pipe_inode_info *pipe) { pipe_unlock(pipe); wait_event_interruptible(pipe->wr_wait, pipe_writable(pipe)); pipe_lock(pipe); } /* * This depends on both the wait (here) and the wakeup (wake_up_partner) * holding the pipe lock, so "*cnt" is stable and we know a wakeup cannot * race with the count check and waitqueue prep. * * Normally in order to avoid races, you'd do the prepare_to_wait() first, * then check the condition you're waiting for, and only then sleep. But * because of the pipe lock, we can check the condition before being on * the wait queue. * * We use the 'rd_wait' waitqueue for pipe partner waiting. */ static int wait_for_partner(struct pipe_inode_info *pipe, unsigned int *cnt) { DEFINE_WAIT(rdwait); int cur = *cnt; while (cur == *cnt) { prepare_to_wait(&pipe->rd_wait, &rdwait, TASK_INTERRUPTIBLE); pipe_unlock(pipe); schedule(); finish_wait(&pipe->rd_wait, &rdwait); pipe_lock(pipe); if (signal_pending(current)) break; } return cur == *cnt ? -ERESTARTSYS : 0; } static void wake_up_partner(struct pipe_inode_info *pipe) { wake_up_interruptible_all(&pipe->rd_wait); } static int fifo_open(struct inode *inode, struct file *filp) { struct pipe_inode_info *pipe; bool is_pipe = inode->i_sb->s_magic == PIPEFS_MAGIC; int ret; filp->f_pipe = 0; spin_lock(&inode->i_lock); if (inode->i_pipe) { pipe = inode->i_pipe; pipe->files++; spin_unlock(&inode->i_lock); } else { spin_unlock(&inode->i_lock); pipe = alloc_pipe_info(); if (!pipe) return -ENOMEM; pipe->files = 1; spin_lock(&inode->i_lock); if (unlikely(inode->i_pipe)) { inode->i_pipe->files++; spin_unlock(&inode->i_lock); free_pipe_info(pipe); pipe = inode->i_pipe; } else { inode->i_pipe = pipe; spin_unlock(&inode->i_lock); } } filp->private_data = pipe; /* OK, we have a pipe and it's pinned down */ mutex_lock(&pipe->mutex); /* We can only do regular read/write on fifos */ stream_open(inode, filp); switch (filp->f_mode & (FMODE_READ | FMODE_WRITE)) { case FMODE_READ: /* * O_RDONLY * POSIX.1 says that O_NONBLOCK means return with the FIFO * opened, even when there is no process writing the FIFO. */ pipe->r_counter++; if (pipe->readers++ == 0) wake_up_partner(pipe); if (!is_pipe && !pipe->writers) { if ((filp->f_flags & O_NONBLOCK)) { /* suppress EPOLLHUP until we have * seen a writer */ filp->f_pipe = pipe->w_counter; } else { if (wait_for_partner(pipe, &pipe->w_counter)) goto err_rd; } } break; case FMODE_WRITE: /* * O_WRONLY * POSIX.1 says that O_NONBLOCK means return -1 with * errno=ENXIO when there is no process reading the FIFO. */ ret = -ENXIO; if (!is_pipe && (filp->f_flags & O_NONBLOCK) && !pipe->readers) goto err; pipe->w_counter++; if (!pipe->writers++) wake_up_partner(pipe); if (!is_pipe && !pipe->readers) { if (wait_for_partner(pipe, &pipe->r_counter)) goto err_wr; } break; case FMODE_READ | FMODE_WRITE: /* * O_RDWR * POSIX.1 leaves this case "undefined" when O_NONBLOCK is set. * This implementation will NEVER block on a O_RDWR open, since * the process can at least talk to itself. */ pipe->readers++; pipe->writers++; pipe->r_counter++; pipe->w_counter++; if (pipe->readers == 1 || pipe->writers == 1) wake_up_partner(pipe); break; default: ret = -EINVAL; goto err; } /* Ok! */ mutex_unlock(&pipe->mutex); return 0; err_rd: if (!--pipe->readers) wake_up_interruptible(&pipe->wr_wait); ret = -ERESTARTSYS; goto err; err_wr: if (!--pipe->writers) wake_up_interruptible_all(&pipe->rd_wait); ret = -ERESTARTSYS; goto err; err: mutex_unlock(&pipe->mutex); put_pipe_info(inode, pipe); return ret; } const struct file_operations pipefifo_fops = { .open = fifo_open, .read_iter = pipe_read, .write_iter = pipe_write, .poll = pipe_poll, .unlocked_ioctl = pipe_ioctl, .release = pipe_release, .fasync = pipe_fasync, .splice_write = iter_file_splice_write, }; /* * Currently we rely on the pipe array holding a power-of-2 number * of pages. Returns 0 on error. */ unsigned int round_pipe_size(unsigned int size) { if (size > (1U << 31)) return 0; /* Minimum pipe size, as required by POSIX */ if (size < PAGE_SIZE) return PAGE_SIZE; return roundup_pow_of_two(size); } /* * Resize the pipe ring to a number of slots. * * Note the pipe can be reduced in capacity, but only if the current * occupancy doesn't exceed nr_slots; if it does, EBUSY will be * returned instead. */ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) { struct pipe_buffer *bufs; unsigned int head, tail, mask, n; bufs = kcalloc(nr_slots, sizeof(*bufs), GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (unlikely(!bufs)) return -ENOMEM; spin_lock_irq(&pipe->rd_wait.lock); mask = pipe->ring_size - 1; head = pipe->head; tail = pipe->tail; n = pipe_occupancy(head, tail); if (nr_slots < n) { spin_unlock_irq(&pipe->rd_wait.lock); kfree(bufs); return -EBUSY; } /* * The pipe array wraps around, so just start the new one at zero * and adjust the indices. */ if (n > 0) { unsigned int h = head & mask; unsigned int t = tail & mask; if (h > t) { memcpy(bufs, pipe->bufs + t, n * sizeof(struct pipe_buffer)); } else { unsigned int tsize = pipe->ring_size - t; if (h > 0) memcpy(bufs + tsize, pipe->bufs, h * sizeof(struct pipe_buffer)); memcpy(bufs, pipe->bufs + t, tsize * sizeof(struct pipe_buffer)); } } head = n; tail = 0; kfree(pipe->bufs); pipe->bufs = bufs; pipe->ring_size = nr_slots; if (pipe->max_usage > nr_slots) pipe->max_usage = nr_slots; pipe->tail = tail; pipe->head = head; if (!pipe_has_watch_queue(pipe)) { pipe->max_usage = nr_slots; pipe->nr_accounted = nr_slots; } spin_unlock_irq(&pipe->rd_wait.lock); /* This might have made more room for writers */ wake_up_interruptible(&pipe->wr_wait); return 0; } /* * Allocate a new array of pipe buffers and copy the info over. Returns the * pipe size if successful, or return -ERROR on error. */ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned int arg) { unsigned long user_bufs; unsigned int nr_slots, size; long ret = 0; if (pipe_has_watch_queue(pipe)) return -EBUSY; size = round_pipe_size(arg); nr_slots = size >> PAGE_SHIFT; if (!nr_slots) return -EINVAL; /* * If trying to increase the pipe capacity, check that an * unprivileged user is not trying to exceed various limits * (soft limit check here, hard limit check just below). * Decreasing the pipe capacity is always permitted, even * if the user is currently over a limit. */ if (nr_slots > pipe->max_usage && size > pipe_max_size && !capable(CAP_SYS_RESOURCE)) return -EPERM; user_bufs = account_pipe_buffers(pipe->user, pipe->nr_accounted, nr_slots); if (nr_slots > pipe->max_usage && (too_many_pipe_buffers_hard(user_bufs) || too_many_pipe_buffers_soft(user_bufs)) && pipe_is_unprivileged_user()) { ret = -EPERM; goto out_revert_acct; } ret = pipe_resize_ring(pipe, nr_slots); if (ret < 0) goto out_revert_acct; return pipe->max_usage * PAGE_SIZE; out_revert_acct: (void) account_pipe_buffers(pipe->user, nr_slots, pipe->nr_accounted); return ret; } /* * Note that i_pipe and i_cdev share the same location, so checking ->i_pipe is * not enough to verify that this is a pipe. */ struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice) { struct pipe_inode_info *pipe = file->private_data; if (file->f_op != &pipefifo_fops || !pipe) return NULL; if (for_splice && pipe_has_watch_queue(pipe)) return NULL; return pipe; } long pipe_fcntl(struct file *file, unsigned int cmd, unsigned int arg) { struct pipe_inode_info *pipe; long ret; pipe = get_pipe_info(file, false); if (!pipe) return -EBADF; mutex_lock(&pipe->mutex); switch (cmd) { case F_SETPIPE_SZ: ret = pipe_set_size(pipe, arg); break; case F_GETPIPE_SZ: ret = pipe->max_usage * PAGE_SIZE; break; default: ret = -EINVAL; break; } mutex_unlock(&pipe->mutex); return ret; } static const struct super_operations pipefs_ops = { .destroy_inode = free_inode_nonrcu, .statfs = simple_statfs, }; /* * pipefs should _never_ be mounted by userland - too much of security hassle, * no real gain from having the whole file system mounted. So we don't need * any operations on the root directory. However, we need a non-trivial * d_name - pipe: will go nicely and kill the special-casing in procfs. */ static int pipefs_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx = init_pseudo(fc, PIPEFS_MAGIC); if (!ctx) return -ENOMEM; ctx->ops = &pipefs_ops; ctx->dops = &pipefs_dentry_operations; return 0; } static struct file_system_type pipe_fs_type = { .name = "pipefs", .init_fs_context = pipefs_init_fs_context, .kill_sb = kill_anon_super, }; #ifdef CONFIG_SYSCTL static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, unsigned int *valp, int write, void *data) { if (write) { unsigned int val; val = round_pipe_size(*lvalp); if (val == 0) return -EINVAL; *valp = val; } else { unsigned int val = *valp; *lvalp = (unsigned long) val; } return 0; } static int proc_dopipe_max_size(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return do_proc_douintvec(table, write, buffer, lenp, ppos, do_proc_dopipe_max_size_conv, NULL); } static struct ctl_table fs_pipe_sysctls[] = { { .procname = "pipe-max-size", .data = &pipe_max_size, .maxlen = sizeof(pipe_max_size), .mode = 0644, .proc_handler = proc_dopipe_max_size, }, { .procname = "pipe-user-pages-hard", .data = &pipe_user_pages_hard, .maxlen = sizeof(pipe_user_pages_hard), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "pipe-user-pages-soft", .data = &pipe_user_pages_soft, .maxlen = sizeof(pipe_user_pages_soft), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, }; #endif static int __init init_pipe_fs(void) { int err = register_filesystem(&pipe_fs_type); if (!err) { pipe_mnt = kern_mount(&pipe_fs_type); if (IS_ERR(pipe_mnt)) { err = PTR_ERR(pipe_mnt); unregister_filesystem(&pipe_fs_type); } } #ifdef CONFIG_SYSCTL register_sysctl_init("fs", fs_pipe_sysctls); #endif return err; } fs_initcall(init_pipe_fs); |
| 24 24 24 24 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 | // SPDX-License-Identifier: GPL-2.0-or-later /* * The "hash function" used as the core of the ChaCha stream cipher (RFC7539) * * Copyright (C) 2015 Martin Willi */ #include <linux/bug.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/bitops.h> #include <linux/string.h> #include <linux/unaligned.h> #include <crypto/chacha.h> static void chacha_permute(u32 *x, int nrounds) { int i; /* whitelist the allowed round counts */ WARN_ON_ONCE(nrounds != 20 && nrounds != 12); for (i = 0; i < nrounds; i += 2) { x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 16); x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 16); x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 16); x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 16); x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 12); x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 12); x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 12); x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 12); x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 8); x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 8); x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 8); x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 8); x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 7); x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 7); x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 7); x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 7); x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 16); x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 16); x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 16); x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 16); x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 12); x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 12); x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 12); x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 12); x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 8); x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 8); x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 8); x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 8); x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 7); x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 7); x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 7); x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 7); } } /** * chacha_block_generic - generate one keystream block and increment block counter * @state: input state matrix (16 32-bit words) * @stream: output keystream block (64 bytes) * @nrounds: number of rounds (20 or 12; 20 is recommended) * * This is the ChaCha core, a function from 64-byte strings to 64-byte strings. * The caller has already converted the endianness of the input. This function * also handles incrementing the block counter in the input matrix. */ void chacha_block_generic(u32 *state, u8 *stream, int nrounds) { u32 x[16]; int i; memcpy(x, state, 64); chacha_permute(x, nrounds); for (i = 0; i < ARRAY_SIZE(x); i++) put_unaligned_le32(x[i] + state[i], &stream[i * sizeof(u32)]); state[12]++; } EXPORT_SYMBOL(chacha_block_generic); /** * hchacha_block_generic - abbreviated ChaCha core, for XChaCha * @state: input state matrix (16 32-bit words) * @stream: output (8 32-bit words) * @nrounds: number of rounds (20 or 12; 20 is recommended) * * HChaCha is the ChaCha equivalent of HSalsa and is an intermediate step * towards XChaCha (see https://cr.yp.to/snuffle/xsalsa-20081128.pdf). HChaCha * skips the final addition of the initial state, and outputs only certain words * of the state. It should not be used for streaming directly. */ void hchacha_block_generic(const u32 *state, u32 *stream, int nrounds) { u32 x[16]; memcpy(x, state, 64); chacha_permute(x, nrounds); memcpy(&stream[0], &x[0], 16); memcpy(&stream[4], &x[12], 16); } EXPORT_SYMBOL(hchacha_block_generic); |
| 223 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM sock #if !defined(_TRACE_SOCK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SOCK_H #include <net/sock.h> #include <net/ipv6.h> #include <linux/tracepoint.h> #include <linux/ipv6.h> #include <linux/tcp.h> #include <trace/events/net_probe_common.h> #define family_names \ EM(AF_INET) \ EMe(AF_INET6) /* The protocol traced by inet_sock_set_state */ #define inet_protocol_names \ EM(IPPROTO_TCP) \ EM(IPPROTO_DCCP) \ EM(IPPROTO_SCTP) \ EMe(IPPROTO_MPTCP) #define tcp_state_names \ EM(TCP_ESTABLISHED) \ EM(TCP_SYN_SENT) \ EM(TCP_SYN_RECV) \ EM(TCP_FIN_WAIT1) \ EM(TCP_FIN_WAIT2) \ EM(TCP_TIME_WAIT) \ EM(TCP_CLOSE) \ EM(TCP_CLOSE_WAIT) \ EM(TCP_LAST_ACK) \ EM(TCP_LISTEN) \ EM(TCP_CLOSING) \ EMe(TCP_NEW_SYN_RECV) #define skmem_kind_names \ EM(SK_MEM_SEND) \ EMe(SK_MEM_RECV) /* enums need to be exported to user space */ #undef EM #undef EMe #define EM(a) TRACE_DEFINE_ENUM(a); #define EMe(a) TRACE_DEFINE_ENUM(a); family_names inet_protocol_names tcp_state_names skmem_kind_names #undef EM #undef EMe #define EM(a) { a, #a }, #define EMe(a) { a, #a } #define show_family_name(val) \ __print_symbolic(val, family_names) #define show_inet_protocol_name(val) \ __print_symbolic(val, inet_protocol_names) #define show_tcp_state_name(val) \ __print_symbolic(val, tcp_state_names) #define show_skmem_kind_names(val) \ __print_symbolic(val, skmem_kind_names) TRACE_EVENT(sock_rcvqueue_full, TP_PROTO(struct sock *sk, struct sk_buff *skb), TP_ARGS(sk, skb), TP_STRUCT__entry( __field(int, rmem_alloc) __field(unsigned int, truesize) __field(int, sk_rcvbuf) ), TP_fast_assign( __entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc); __entry->truesize = skb->truesize; __entry->sk_rcvbuf = READ_ONCE(sk->sk_rcvbuf); ), TP_printk("rmem_alloc=%d truesize=%u sk_rcvbuf=%d", __entry->rmem_alloc, __entry->truesize, __entry->sk_rcvbuf) ); TRACE_EVENT(sock_exceed_buf_limit, TP_PROTO(struct sock *sk, struct proto *prot, long allocated, int kind), TP_ARGS(sk, prot, allocated, kind), TP_STRUCT__entry( __array(char, name, 32) __array(long, sysctl_mem, 3) __field(long, allocated) __field(int, sysctl_rmem) __field(int, rmem_alloc) __field(int, sysctl_wmem) __field(int, wmem_alloc) __field(int, wmem_queued) __field(int, kind) ), TP_fast_assign( strscpy(__entry->name, prot->name, 32); __entry->sysctl_mem[0] = READ_ONCE(prot->sysctl_mem[0]); __entry->sysctl_mem[1] = READ_ONCE(prot->sysctl_mem[1]); __entry->sysctl_mem[2] = READ_ONCE(prot->sysctl_mem[2]); __entry->allocated = allocated; __entry->sysctl_rmem = sk_get_rmem0(sk, prot); __entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc); __entry->sysctl_wmem = sk_get_wmem0(sk, prot); __entry->wmem_alloc = refcount_read(&sk->sk_wmem_alloc); __entry->wmem_queued = READ_ONCE(sk->sk_wmem_queued); __entry->kind = kind; ), TP_printk("proto:%s sysctl_mem=%ld,%ld,%ld allocated=%ld sysctl_rmem=%d rmem_alloc=%d sysctl_wmem=%d wmem_alloc=%d wmem_queued=%d kind=%s", __entry->name, __entry->sysctl_mem[0], __entry->sysctl_mem[1], __entry->sysctl_mem[2], __entry->allocated, __entry->sysctl_rmem, __entry->rmem_alloc, __entry->sysctl_wmem, __entry->wmem_alloc, __entry->wmem_queued, show_skmem_kind_names(__entry->kind) ) ); TRACE_EVENT(inet_sock_set_state, TP_PROTO(const struct sock *sk, const int oldstate, const int newstate), TP_ARGS(sk, oldstate, newstate), TP_STRUCT__entry( __field(const void *, skaddr) __field(int, oldstate) __field(int, newstate) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __field(__u16, protocol) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) __array(__u8, daddr_v6, 16) ), TP_fast_assign( const struct inet_sock *inet = inet_sk(sk); __be32 *p32; __entry->skaddr = sk; __entry->oldstate = oldstate; __entry->newstate = newstate; __entry->family = sk->sk_family; __entry->protocol = sk->sk_protocol; __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); p32 = (__be32 *) __entry->saddr; *p32 = inet->inet_saddr; p32 = (__be32 *) __entry->daddr; *p32 = inet->inet_daddr; TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); ), TP_printk("family=%s protocol=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c oldstate=%s newstate=%s", show_family_name(__entry->family), show_inet_protocol_name(__entry->protocol), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, show_tcp_state_name(__entry->oldstate), show_tcp_state_name(__entry->newstate)) ); TRACE_EVENT(inet_sk_error_report, TP_PROTO(const struct sock *sk), TP_ARGS(sk), TP_STRUCT__entry( __field(int, error) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __field(__u16, protocol) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) __array(__u8, daddr_v6, 16) ), TP_fast_assign( const struct inet_sock *inet = inet_sk(sk); __be32 *p32; __entry->error = sk->sk_err; __entry->family = sk->sk_family; __entry->protocol = sk->sk_protocol; __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); p32 = (__be32 *) __entry->saddr; *p32 = inet->inet_saddr; p32 = (__be32 *) __entry->daddr; *p32 = inet->inet_daddr; TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); ), TP_printk("family=%s protocol=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c error=%d", show_family_name(__entry->family), show_inet_protocol_name(__entry->protocol), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, __entry->error) ); TRACE_EVENT(sk_data_ready, TP_PROTO(const struct sock *sk), TP_ARGS(sk), TP_STRUCT__entry( __field(const void *, skaddr) __field(__u16, family) __field(__u16, protocol) __field(unsigned long, ip) ), TP_fast_assign( __entry->skaddr = sk; __entry->family = sk->sk_family; __entry->protocol = sk->sk_protocol; __entry->ip = _RET_IP_; ), TP_printk("family=%u protocol=%u func=%ps", __entry->family, __entry->protocol, (void *)__entry->ip) ); /* * sock send/recv msg length */ DECLARE_EVENT_CLASS(sock_msg_length, TP_PROTO(struct sock *sk, int ret, int flags), TP_ARGS(sk, ret, flags), TP_STRUCT__entry( __field(void *, sk) __field(__u16, family) __field(__u16, protocol) __field(int, ret) __field(int, flags) ), TP_fast_assign( __entry->sk = sk; __entry->family = sk->sk_family; __entry->protocol = sk->sk_protocol; __entry->ret = ret; __entry->flags = flags; ), TP_printk("sk address = %p, family = %s protocol = %s, length = %d, error = %d, flags = 0x%x", __entry->sk, show_family_name(__entry->family), show_inet_protocol_name(__entry->protocol), !(__entry->flags & MSG_PEEK) ? (__entry->ret > 0 ? __entry->ret : 0) : 0, __entry->ret < 0 ? __entry->ret : 0, __entry->flags) ); DEFINE_EVENT(sock_msg_length, sock_send_length, TP_PROTO(struct sock *sk, int ret, int flags), TP_ARGS(sk, ret, flags) ); DEFINE_EVENT(sock_msg_length, sock_recv_length, TP_PROTO(struct sock *sk, int ret, int flags), TP_ARGS(sk, ret, flags) ); #endif /* _TRACE_SOCK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 185 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 | /* SPDX-License-Identifier: GPL-2.0 */ /* * A hash table (hashtab) maintains associations between * key values and datum values. The type of the key values * and the type of the datum values is arbitrary. The * functions for hash computation and key comparison are * provided by the creator of the table. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ #ifndef _SS_HASHTAB_H_ #define _SS_HASHTAB_H_ #include <linux/types.h> #include <linux/errno.h> #include <linux/sched.h> #define HASHTAB_MAX_NODES U32_MAX struct hashtab_key_params { u32 (*hash)(const void *key); /* hash func */ int (*cmp)(const void *key1, const void *key2); /* comparison func */ }; struct hashtab_node { void *key; void *datum; struct hashtab_node *next; }; struct hashtab { struct hashtab_node **htable; /* hash table */ u32 size; /* number of slots in hash table */ u32 nel; /* number of elements in hash table */ }; struct hashtab_info { u32 slots_used; u32 max_chain_len; u64 chain2_len_sum; }; /* * Initializes a new hash table with the specified characteristics. * * Returns -ENOMEM if insufficient space is available or 0 otherwise. */ int hashtab_init(struct hashtab *h, u32 nel_hint); int __hashtab_insert(struct hashtab *h, struct hashtab_node **dst, void *key, void *datum); /* * Inserts the specified (key, datum) pair into the specified hash table. * * Returns -ENOMEM on memory allocation error, * -EEXIST if there is already an entry with the same key, * -EINVAL for general errors or 0 otherwise. */ static inline int hashtab_insert(struct hashtab *h, void *key, void *datum, struct hashtab_key_params key_params) { u32 hvalue; struct hashtab_node *prev, *cur; cond_resched(); if (!h->size || h->nel == HASHTAB_MAX_NODES) return -EINVAL; hvalue = key_params.hash(key) & (h->size - 1); prev = NULL; cur = h->htable[hvalue]; while (cur) { int cmp = key_params.cmp(key, cur->key); if (cmp == 0) return -EEXIST; if (cmp < 0) break; prev = cur; cur = cur->next; } return __hashtab_insert(h, prev ? &prev->next : &h->htable[hvalue], key, datum); } /* * Searches for the entry with the specified key in the hash table. * * Returns NULL if no entry has the specified key or * the datum of the entry otherwise. */ static inline void *hashtab_search(struct hashtab *h, const void *key, struct hashtab_key_params key_params) { u32 hvalue; struct hashtab_node *cur; if (!h->size) return NULL; hvalue = key_params.hash(key) & (h->size - 1); cur = h->htable[hvalue]; while (cur) { int cmp = key_params.cmp(key, cur->key); if (cmp == 0) return cur->datum; if (cmp < 0) break; cur = cur->next; } return NULL; } /* * Destroys the specified hash table. */ void hashtab_destroy(struct hashtab *h); /* * Applies the specified apply function to (key,datum,args) * for each entry in the specified hash table. * * The order in which the function is applied to the entries * is dependent upon the internal structure of the hash table. * * If apply returns a non-zero status, then hashtab_map will cease * iterating through the hash table and will propagate the error * return to its caller. */ int hashtab_map(struct hashtab *h, int (*apply)(void *k, void *d, void *args), void *args); int hashtab_duplicate(struct hashtab *new, const struct hashtab *orig, int (*copy)(struct hashtab_node *new, const struct hashtab_node *orig, void *args), int (*destroy)(void *k, void *d, void *args), void *args); #ifdef CONFIG_SECURITY_SELINUX_DEBUG /* Fill info with some hash table statistics */ void hashtab_stat(struct hashtab *h, struct hashtab_info *info); #else static inline void hashtab_stat(struct hashtab *h, struct hashtab_info *info) { return; } #endif #endif /* _SS_HASHTAB_H */ |
| 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2002,2003 by Andreas Gruenbacher <a.gruenbacher@computer.org> * * Fixes from William Schumacher incorporated on 15 March 2001. * (Reported by Charles Bertsch, <CBertsch@microtest.com>). */ /* * This file contains generic functions for manipulating * POSIX 1003.1e draft standard 17 ACLs. */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/atomic.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/cred.h> #include <linux/posix_acl.h> #include <linux/posix_acl_xattr.h> #include <linux/xattr.h> #include <linux/export.h> #include <linux/user_namespace.h> #include <linux/namei.h> #include <linux/mnt_idmapping.h> #include <linux/iversion.h> #include <linux/security.h> #include <linux/fsnotify.h> #include <linux/filelock.h> #include "internal.h" static struct posix_acl **acl_by_type(struct inode *inode, int type) { switch (type) { case ACL_TYPE_ACCESS: return &inode->i_acl; case ACL_TYPE_DEFAULT: return &inode->i_default_acl; default: BUG(); } } struct posix_acl *get_cached_acl(struct inode *inode, int type) { struct posix_acl **p = acl_by_type(inode, type); struct posix_acl *acl; for (;;) { rcu_read_lock(); acl = rcu_dereference(*p); if (!acl || is_uncached_acl(acl) || refcount_inc_not_zero(&acl->a_refcount)) break; rcu_read_unlock(); cpu_relax(); } rcu_read_unlock(); return acl; } EXPORT_SYMBOL(get_cached_acl); struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type) { struct posix_acl *acl = rcu_dereference(*acl_by_type(inode, type)); if (acl == ACL_DONT_CACHE) { struct posix_acl *ret; ret = inode->i_op->get_inode_acl(inode, type, LOOKUP_RCU); if (!IS_ERR(ret)) acl = ret; } return acl; } EXPORT_SYMBOL(get_cached_acl_rcu); void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl) { struct posix_acl **p = acl_by_type(inode, type); struct posix_acl *old; old = xchg(p, posix_acl_dup(acl)); if (!is_uncached_acl(old)) posix_acl_release(old); } EXPORT_SYMBOL(set_cached_acl); static void __forget_cached_acl(struct posix_acl **p) { struct posix_acl *old; old = xchg(p, ACL_NOT_CACHED); if (!is_uncached_acl(old)) posix_acl_release(old); } void forget_cached_acl(struct inode *inode, int type) { __forget_cached_acl(acl_by_type(inode, type)); } EXPORT_SYMBOL(forget_cached_acl); void forget_all_cached_acls(struct inode *inode) { __forget_cached_acl(&inode->i_acl); __forget_cached_acl(&inode->i_default_acl); } EXPORT_SYMBOL(forget_all_cached_acls); static struct posix_acl *__get_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, int type) { struct posix_acl *sentinel; struct posix_acl **p; struct posix_acl *acl; /* * The sentinel is used to detect when another operation like * set_cached_acl() or forget_cached_acl() races with get_inode_acl(). * It is guaranteed that is_uncached_acl(sentinel) is true. */ acl = get_cached_acl(inode, type); if (!is_uncached_acl(acl)) return acl; if (!IS_POSIXACL(inode)) return NULL; sentinel = uncached_acl_sentinel(current); p = acl_by_type(inode, type); /* * If the ACL isn't being read yet, set our sentinel. Otherwise, the * current value of the ACL will not be ACL_NOT_CACHED and so our own * sentinel will not be set; another task will update the cache. We * could wait for that other task to complete its job, but it's easier * to just call ->get_inode_acl to fetch the ACL ourself. (This is * going to be an unlikely race.) */ cmpxchg(p, ACL_NOT_CACHED, sentinel); /* * Normally, the ACL returned by ->get{_inode}_acl will be cached. * A filesystem can prevent that by calling * forget_cached_acl(inode, type) in ->get{_inode}_acl. * * If the filesystem doesn't have a get{_inode}_ acl() function at all, * we'll just create the negative cache entry. */ if (dentry && inode->i_op->get_acl) { acl = inode->i_op->get_acl(idmap, dentry, type); } else if (inode->i_op->get_inode_acl) { acl = inode->i_op->get_inode_acl(inode, type, false); } else { set_cached_acl(inode, type, NULL); return NULL; } if (IS_ERR(acl)) { /* * Remove our sentinel so that we don't block future attempts * to cache the ACL. */ cmpxchg(p, sentinel, ACL_NOT_CACHED); return acl; } /* * Cache the result, but only if our sentinel is still in place. */ posix_acl_dup(acl); if (unlikely(!try_cmpxchg(p, &sentinel, acl))) posix_acl_release(acl); return acl; } struct posix_acl *get_inode_acl(struct inode *inode, int type) { return __get_acl(&nop_mnt_idmap, NULL, inode, type); } EXPORT_SYMBOL(get_inode_acl); /* * Init a fresh posix_acl */ void posix_acl_init(struct posix_acl *acl, int count) { refcount_set(&acl->a_refcount, 1); acl->a_count = count; } EXPORT_SYMBOL(posix_acl_init); /* * Allocate a new ACL with the specified number of entries. */ struct posix_acl * posix_acl_alloc(unsigned int count, gfp_t flags) { struct posix_acl *acl; acl = kmalloc(struct_size(acl, a_entries, count), flags); if (acl) posix_acl_init(acl, count); return acl; } EXPORT_SYMBOL(posix_acl_alloc); /* * Clone an ACL. */ struct posix_acl * posix_acl_clone(const struct posix_acl *acl, gfp_t flags) { struct posix_acl *clone = NULL; if (acl) { clone = kmemdup(acl, struct_size(acl, a_entries, acl->a_count), flags); if (clone) refcount_set(&clone->a_refcount, 1); } return clone; } EXPORT_SYMBOL_GPL(posix_acl_clone); /* * Check if an acl is valid. Returns 0 if it is, or -E... otherwise. */ int posix_acl_valid(struct user_namespace *user_ns, const struct posix_acl *acl) { const struct posix_acl_entry *pa, *pe; int state = ACL_USER_OBJ; int needs_mask = 0; FOREACH_ACL_ENTRY(pa, acl, pe) { if (pa->e_perm & ~(ACL_READ|ACL_WRITE|ACL_EXECUTE)) return -EINVAL; switch (pa->e_tag) { case ACL_USER_OBJ: if (state == ACL_USER_OBJ) { state = ACL_USER; break; } return -EINVAL; case ACL_USER: if (state != ACL_USER) return -EINVAL; if (!kuid_has_mapping(user_ns, pa->e_uid)) return -EINVAL; needs_mask = 1; break; case ACL_GROUP_OBJ: if (state == ACL_USER) { state = ACL_GROUP; break; } return -EINVAL; case ACL_GROUP: if (state != ACL_GROUP) return -EINVAL; if (!kgid_has_mapping(user_ns, pa->e_gid)) return -EINVAL; needs_mask = 1; break; case ACL_MASK: if (state != ACL_GROUP) return -EINVAL; state = ACL_OTHER; break; case ACL_OTHER: if (state == ACL_OTHER || (state == ACL_GROUP && !needs_mask)) { state = 0; break; } return -EINVAL; default: return -EINVAL; } } if (state == 0) return 0; return -EINVAL; } EXPORT_SYMBOL(posix_acl_valid); /* * Returns 0 if the acl can be exactly represented in the traditional * file mode permission bits, or else 1. Returns -E... on error. */ int posix_acl_equiv_mode(const struct posix_acl *acl, umode_t *mode_p) { const struct posix_acl_entry *pa, *pe; umode_t mode = 0; int not_equiv = 0; /* * A null ACL can always be presented as mode bits. */ if (!acl) return 0; FOREACH_ACL_ENTRY(pa, acl, pe) { switch (pa->e_tag) { case ACL_USER_OBJ: mode |= (pa->e_perm & S_IRWXO) << 6; break; case ACL_GROUP_OBJ: mode |= (pa->e_perm & S_IRWXO) << 3; break; case ACL_OTHER: mode |= pa->e_perm & S_IRWXO; break; case ACL_MASK: mode = (mode & ~S_IRWXG) | ((pa->e_perm & S_IRWXO) << 3); not_equiv = 1; break; case ACL_USER: case ACL_GROUP: not_equiv = 1; break; default: return -EINVAL; } } if (mode_p) *mode_p = (*mode_p & ~S_IRWXUGO) | mode; return not_equiv; } EXPORT_SYMBOL(posix_acl_equiv_mode); /* * Create an ACL representing the file mode permission bits of an inode. */ struct posix_acl * posix_acl_from_mode(umode_t mode, gfp_t flags) { struct posix_acl *acl = posix_acl_alloc(3, flags); if (!acl) return ERR_PTR(-ENOMEM); acl->a_entries[0].e_tag = ACL_USER_OBJ; acl->a_entries[0].e_perm = (mode & S_IRWXU) >> 6; acl->a_entries[1].e_tag = ACL_GROUP_OBJ; acl->a_entries[1].e_perm = (mode & S_IRWXG) >> 3; acl->a_entries[2].e_tag = ACL_OTHER; acl->a_entries[2].e_perm = (mode & S_IRWXO); return acl; } EXPORT_SYMBOL(posix_acl_from_mode); /* * Return 0 if current is granted want access to the inode * by the acl. Returns -E... otherwise. */ int posix_acl_permission(struct mnt_idmap *idmap, struct inode *inode, const struct posix_acl *acl, int want) { const struct posix_acl_entry *pa, *pe, *mask_obj; struct user_namespace *fs_userns = i_user_ns(inode); int found = 0; vfsuid_t vfsuid; vfsgid_t vfsgid; want &= MAY_READ | MAY_WRITE | MAY_EXEC; FOREACH_ACL_ENTRY(pa, acl, pe) { switch(pa->e_tag) { case ACL_USER_OBJ: /* (May have been checked already) */ vfsuid = i_uid_into_vfsuid(idmap, inode); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) goto check_perm; break; case ACL_USER: vfsuid = make_vfsuid(idmap, fs_userns, pa->e_uid); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) goto mask; break; case ACL_GROUP_OBJ: vfsgid = i_gid_into_vfsgid(idmap, inode); if (vfsgid_in_group_p(vfsgid)) { found = 1; if ((pa->e_perm & want) == want) goto mask; } break; case ACL_GROUP: vfsgid = make_vfsgid(idmap, fs_userns, pa->e_gid); if (vfsgid_in_group_p(vfsgid)) { found = 1; if ((pa->e_perm & want) == want) goto mask; } break; case ACL_MASK: break; case ACL_OTHER: if (found) return -EACCES; else goto check_perm; default: return -EIO; } } return -EIO; mask: for (mask_obj = pa+1; mask_obj != pe; mask_obj++) { if (mask_obj->e_tag == ACL_MASK) { if ((pa->e_perm & mask_obj->e_perm & want) == want) return 0; return -EACCES; } } check_perm: if ((pa->e_perm & want) == want) return 0; return -EACCES; } /* * Modify acl when creating a new inode. The caller must ensure the acl is * only referenced once. * * mode_p initially must contain the mode parameter to the open() / creat() * system calls. All permissions that are not granted by the acl are removed. * The permissions in the acl are changed to reflect the mode_p parameter. */ static int posix_acl_create_masq(struct posix_acl *acl, umode_t *mode_p) { struct posix_acl_entry *pa, *pe; struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL; umode_t mode = *mode_p; int not_equiv = 0; /* assert(atomic_read(acl->a_refcount) == 1); */ FOREACH_ACL_ENTRY(pa, acl, pe) { switch(pa->e_tag) { case ACL_USER_OBJ: pa->e_perm &= (mode >> 6) | ~S_IRWXO; mode &= (pa->e_perm << 6) | ~S_IRWXU; break; case ACL_USER: case ACL_GROUP: not_equiv = 1; break; case ACL_GROUP_OBJ: group_obj = pa; break; case ACL_OTHER: pa->e_perm &= mode | ~S_IRWXO; mode &= pa->e_perm | ~S_IRWXO; break; case ACL_MASK: mask_obj = pa; not_equiv = 1; break; default: return -EIO; } } if (mask_obj) { mask_obj->e_perm &= (mode >> 3) | ~S_IRWXO; mode &= (mask_obj->e_perm << 3) | ~S_IRWXG; } else { if (!group_obj) return -EIO; group_obj->e_perm &= (mode >> 3) | ~S_IRWXO; mode &= (group_obj->e_perm << 3) | ~S_IRWXG; } *mode_p = (*mode_p & ~S_IRWXUGO) | mode; return not_equiv; } /* * Modify the ACL for the chmod syscall. */ static int __posix_acl_chmod_masq(struct posix_acl *acl, umode_t mode) { struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL; struct posix_acl_entry *pa, *pe; /* assert(atomic_read(acl->a_refcount) == 1); */ FOREACH_ACL_ENTRY(pa, acl, pe) { switch(pa->e_tag) { case ACL_USER_OBJ: pa->e_perm = (mode & S_IRWXU) >> 6; break; case ACL_USER: case ACL_GROUP: break; case ACL_GROUP_OBJ: group_obj = pa; break; case ACL_MASK: mask_obj = pa; break; case ACL_OTHER: pa->e_perm = (mode & S_IRWXO); break; default: return -EIO; } } if (mask_obj) { mask_obj->e_perm = (mode & S_IRWXG) >> 3; } else { if (!group_obj) return -EIO; group_obj->e_perm = (mode & S_IRWXG) >> 3; } return 0; } int __posix_acl_create(struct posix_acl **acl, gfp_t gfp, umode_t *mode_p) { struct posix_acl *clone = posix_acl_clone(*acl, gfp); int err = -ENOMEM; if (clone) { err = posix_acl_create_masq(clone, mode_p); if (err < 0) { posix_acl_release(clone); clone = NULL; } } posix_acl_release(*acl); *acl = clone; return err; } EXPORT_SYMBOL(__posix_acl_create); int __posix_acl_chmod(struct posix_acl **acl, gfp_t gfp, umode_t mode) { struct posix_acl *clone = posix_acl_clone(*acl, gfp); int err = -ENOMEM; if (clone) { err = __posix_acl_chmod_masq(clone, mode); if (err) { posix_acl_release(clone); clone = NULL; } } posix_acl_release(*acl); *acl = clone; return err; } EXPORT_SYMBOL(__posix_acl_chmod); /** * posix_acl_chmod - chmod a posix acl * * @idmap: idmap of the mount @inode was found from * @dentry: dentry to check permissions on * @mode: the new mode of @inode * * If the dentry has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. */ int posix_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry, umode_t mode) { struct inode *inode = d_inode(dentry); struct posix_acl *acl; int ret = 0; if (!IS_POSIXACL(inode)) return 0; if (!inode->i_op->set_acl) return -EOPNOTSUPP; acl = get_inode_acl(inode, ACL_TYPE_ACCESS); if (IS_ERR_OR_NULL(acl)) { if (acl == ERR_PTR(-EOPNOTSUPP)) return 0; return PTR_ERR(acl); } ret = __posix_acl_chmod(&acl, GFP_KERNEL, mode); if (ret) return ret; ret = inode->i_op->set_acl(idmap, dentry, acl, ACL_TYPE_ACCESS); posix_acl_release(acl); return ret; } EXPORT_SYMBOL(posix_acl_chmod); int posix_acl_create(struct inode *dir, umode_t *mode, struct posix_acl **default_acl, struct posix_acl **acl) { struct posix_acl *p; struct posix_acl *clone; int ret; *acl = NULL; *default_acl = NULL; if (S_ISLNK(*mode) || !IS_POSIXACL(dir)) return 0; p = get_inode_acl(dir, ACL_TYPE_DEFAULT); if (!p || p == ERR_PTR(-EOPNOTSUPP)) { *mode &= ~current_umask(); return 0; } if (IS_ERR(p)) return PTR_ERR(p); ret = -ENOMEM; clone = posix_acl_clone(p, GFP_NOFS); if (!clone) goto err_release; ret = posix_acl_create_masq(clone, mode); if (ret < 0) goto err_release_clone; if (ret == 0) posix_acl_release(clone); else *acl = clone; if (!S_ISDIR(*mode)) posix_acl_release(p); else *default_acl = p; return 0; err_release_clone: posix_acl_release(clone); err_release: posix_acl_release(p); return ret; } EXPORT_SYMBOL_GPL(posix_acl_create); /** * posix_acl_update_mode - update mode in set_acl * @idmap: idmap of the mount @inode was found from * @inode: target inode * @mode_p: mode (pointer) for update * @acl: acl pointer * * Update the file mode when setting an ACL: compute the new file permission * bits based on the ACL. In addition, if the ACL is equivalent to the new * file mode, set *@acl to NULL to indicate that no ACL should be set. * * As with chmod, clear the setgid bit if the caller is not in the owning group * or capable of CAP_FSETID (see inode_change_ok). * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. * * Called from set_acl inode operations. */ int posix_acl_update_mode(struct mnt_idmap *idmap, struct inode *inode, umode_t *mode_p, struct posix_acl **acl) { umode_t mode = inode->i_mode; int error; error = posix_acl_equiv_mode(*acl, &mode); if (error < 0) return error; if (error == 0) *acl = NULL; if (!in_group_or_capable(idmap, inode, i_gid_into_vfsgid(idmap, inode))) mode &= ~S_ISGID; *mode_p = mode; return 0; } EXPORT_SYMBOL(posix_acl_update_mode); /* * Fix up the uids and gids in posix acl extended attributes in place. */ static int posix_acl_fix_xattr_common(const void *value, size_t size) { const struct posix_acl_xattr_header *header = value; int count; if (!header) return -EINVAL; if (size < sizeof(struct posix_acl_xattr_header)) return -EINVAL; if (header->a_version != cpu_to_le32(POSIX_ACL_XATTR_VERSION)) return -EOPNOTSUPP; count = posix_acl_xattr_count(size); if (count < 0) return -EINVAL; if (count == 0) return 0; return count; } /** * posix_acl_from_xattr - convert POSIX ACLs from backing store to VFS format * @userns: the filesystem's idmapping * @value: the uapi representation of POSIX ACLs * @size: the size of @void * * Filesystems that store POSIX ACLs in the unaltered uapi format should use * posix_acl_from_xattr() when reading them from the backing store and * converting them into the struct posix_acl VFS format. The helper is * specifically intended to be called from the acl inode operation. * * The posix_acl_from_xattr() function will map the raw {g,u}id values stored * in ACL_{GROUP,USER} entries into idmapping in @userns. * * Note that posix_acl_from_xattr() does not take idmapped mounts into account. * If it did it calling it from the get acl inode operation would return POSIX * ACLs mapped according to an idmapped mount which would mean that the value * couldn't be cached for the filesystem. Idmapped mounts are taken into * account on the fly during permission checking or right at the VFS - * userspace boundary before reporting them to the user. * * Return: Allocated struct posix_acl on success, NULL for a valid header but * without actual POSIX ACL entries, or ERR_PTR() encoded error code. */ struct posix_acl *posix_acl_from_xattr(struct user_namespace *userns, const void *value, size_t size) { const struct posix_acl_xattr_header *header = value; const struct posix_acl_xattr_entry *entry = (const void *)(header + 1), *end; int count; struct posix_acl *acl; struct posix_acl_entry *acl_e; count = posix_acl_fix_xattr_common(value, size); if (count < 0) return ERR_PTR(count); if (count == 0) return NULL; acl = posix_acl_alloc(count, GFP_NOFS); if (!acl) return ERR_PTR(-ENOMEM); acl_e = acl->a_entries; for (end = entry + count; entry != end; acl_e++, entry++) { acl_e->e_tag = le16_to_cpu(entry->e_tag); acl_e->e_perm = le16_to_cpu(entry->e_perm); switch(acl_e->e_tag) { case ACL_USER_OBJ: case ACL_GROUP_OBJ: case ACL_MASK: case ACL_OTHER: break; case ACL_USER: acl_e->e_uid = make_kuid(userns, le32_to_cpu(entry->e_id)); if (!uid_valid(acl_e->e_uid)) goto fail; break; case ACL_GROUP: acl_e->e_gid = make_kgid(userns, le32_to_cpu(entry->e_id)); if (!gid_valid(acl_e->e_gid)) goto fail; break; default: goto fail; } } return acl; fail: posix_acl_release(acl); return ERR_PTR(-EINVAL); } EXPORT_SYMBOL (posix_acl_from_xattr); /* * Convert from in-memory to extended attribute representation. */ int posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl, void *buffer, size_t size) { struct posix_acl_xattr_header *ext_acl = buffer; struct posix_acl_xattr_entry *ext_entry; int real_size, n; real_size = posix_acl_xattr_size(acl->a_count); if (!buffer) return real_size; if (real_size > size) return -ERANGE; ext_entry = (void *)(ext_acl + 1); ext_acl->a_version = cpu_to_le32(POSIX_ACL_XATTR_VERSION); for (n=0; n < acl->a_count; n++, ext_entry++) { const struct posix_acl_entry *acl_e = &acl->a_entries[n]; ext_entry->e_tag = cpu_to_le16(acl_e->e_tag); ext_entry->e_perm = cpu_to_le16(acl_e->e_perm); switch(acl_e->e_tag) { case ACL_USER: ext_entry->e_id = cpu_to_le32(from_kuid(user_ns, acl_e->e_uid)); break; case ACL_GROUP: ext_entry->e_id = cpu_to_le32(from_kgid(user_ns, acl_e->e_gid)); break; default: ext_entry->e_id = cpu_to_le32(ACL_UNDEFINED_ID); break; } } return real_size; } EXPORT_SYMBOL (posix_acl_to_xattr); /** * vfs_posix_acl_to_xattr - convert from kernel to userspace representation * @idmap: idmap of the mount * @inode: inode the posix acls are set on * @acl: the posix acls as represented by the vfs * @buffer: the buffer into which to convert @acl * @size: size of @buffer * * This converts @acl from the VFS representation in the filesystem idmapping * to the uapi form reportable to userspace. And mount and caller idmappings * are handled appropriately. * * Return: On success, the size of the stored uapi posix acls, on error a * negative errno. */ static ssize_t vfs_posix_acl_to_xattr(struct mnt_idmap *idmap, struct inode *inode, const struct posix_acl *acl, void *buffer, size_t size) { struct posix_acl_xattr_header *ext_acl = buffer; struct posix_acl_xattr_entry *ext_entry; struct user_namespace *fs_userns, *caller_userns; ssize_t real_size, n; vfsuid_t vfsuid; vfsgid_t vfsgid; real_size = posix_acl_xattr_size(acl->a_count); if (!buffer) return real_size; if (real_size > size) return -ERANGE; ext_entry = (void *)(ext_acl + 1); ext_acl->a_version = cpu_to_le32(POSIX_ACL_XATTR_VERSION); fs_userns = i_user_ns(inode); caller_userns = current_user_ns(); for (n=0; n < acl->a_count; n++, ext_entry++) { const struct posix_acl_entry *acl_e = &acl->a_entries[n]; ext_entry->e_tag = cpu_to_le16(acl_e->e_tag); ext_entry->e_perm = cpu_to_le16(acl_e->e_perm); switch(acl_e->e_tag) { case ACL_USER: vfsuid = make_vfsuid(idmap, fs_userns, acl_e->e_uid); ext_entry->e_id = cpu_to_le32(from_kuid( caller_userns, vfsuid_into_kuid(vfsuid))); break; case ACL_GROUP: vfsgid = make_vfsgid(idmap, fs_userns, acl_e->e_gid); ext_entry->e_id = cpu_to_le32(from_kgid( caller_userns, vfsgid_into_kgid(vfsgid))); break; default: ext_entry->e_id = cpu_to_le32(ACL_UNDEFINED_ID); break; } } return real_size; } int set_posix_acl(struct mnt_idmap *idmap, struct dentry *dentry, int type, struct posix_acl *acl) { struct inode *inode = d_inode(dentry); if (!IS_POSIXACL(inode)) return -EOPNOTSUPP; if (!inode->i_op->set_acl) return -EOPNOTSUPP; if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode)) return acl ? -EACCES : 0; if (!inode_owner_or_capable(idmap, inode)) return -EPERM; if (acl) { int ret = posix_acl_valid(inode->i_sb->s_user_ns, acl); if (ret) return ret; } return inode->i_op->set_acl(idmap, dentry, acl, type); } EXPORT_SYMBOL(set_posix_acl); int posix_acl_listxattr(struct inode *inode, char **buffer, ssize_t *remaining_size) { int err; if (!IS_POSIXACL(inode)) return 0; if (inode->i_acl) { err = xattr_list_one(buffer, remaining_size, XATTR_NAME_POSIX_ACL_ACCESS); if (err) return err; } if (inode->i_default_acl) { err = xattr_list_one(buffer, remaining_size, XATTR_NAME_POSIX_ACL_DEFAULT); if (err) return err; } return 0; } static bool posix_acl_xattr_list(struct dentry *dentry) { return IS_POSIXACL(d_backing_inode(dentry)); } /* * nop_posix_acl_access - legacy xattr handler for access POSIX ACLs * * This is the legacy POSIX ACL access xattr handler. It is used by some * filesystems to implement their ->listxattr() inode operation. New code * should never use them. */ const struct xattr_handler nop_posix_acl_access = { .name = XATTR_NAME_POSIX_ACL_ACCESS, .list = posix_acl_xattr_list, }; EXPORT_SYMBOL_GPL(nop_posix_acl_access); /* * nop_posix_acl_default - legacy xattr handler for default POSIX ACLs * * This is the legacy POSIX ACL default xattr handler. It is used by some * filesystems to implement their ->listxattr() inode operation. New code * should never use them. */ const struct xattr_handler nop_posix_acl_default = { .name = XATTR_NAME_POSIX_ACL_DEFAULT, .list = posix_acl_xattr_list, }; EXPORT_SYMBOL_GPL(nop_posix_acl_default); int simple_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { int error; struct inode *inode = d_inode(dentry); if (type == ACL_TYPE_ACCESS) { error = posix_acl_update_mode(idmap, inode, &inode->i_mode, &acl); if (error) return error; } inode_set_ctime_current(inode); if (IS_I_VERSION(inode)) inode_inc_iversion(inode); set_cached_acl(inode, type, acl); return 0; } int simple_acl_create(struct inode *dir, struct inode *inode) { struct posix_acl *default_acl, *acl; int error; error = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl); if (error) return error; set_cached_acl(inode, ACL_TYPE_DEFAULT, default_acl); set_cached_acl(inode, ACL_TYPE_ACCESS, acl); if (default_acl) posix_acl_release(default_acl); if (acl) posix_acl_release(acl); return 0; } static int vfs_set_acl_idmapped_mnt(struct mnt_idmap *idmap, struct user_namespace *fs_userns, struct posix_acl *acl) { for (int n = 0; n < acl->a_count; n++) { struct posix_acl_entry *acl_e = &acl->a_entries[n]; switch (acl_e->e_tag) { case ACL_USER: acl_e->e_uid = from_vfsuid(idmap, fs_userns, VFSUIDT_INIT(acl_e->e_uid)); break; case ACL_GROUP: acl_e->e_gid = from_vfsgid(idmap, fs_userns, VFSGIDT_INIT(acl_e->e_gid)); break; } } return 0; } /** * vfs_set_acl - set posix acls * @idmap: idmap of the mount * @dentry: the dentry based on which to set the posix acls * @acl_name: the name of the posix acl * @kacl: the posix acls in the appropriate VFS format * * This function sets @kacl. The caller must all posix_acl_release() on @kacl * afterwards. * * Return: On success 0, on error negative errno. */ int vfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { int acl_type; int error; struct inode *inode = d_inode(dentry); struct inode *delegated_inode = NULL; acl_type = posix_acl_type(acl_name); if (acl_type < 0) return -EINVAL; if (kacl) { /* * If we're on an idmapped mount translate from mount specific * vfs{g,u}id_t into global filesystem k{g,u}id_t. * Afterwards we can cache the POSIX ACLs filesystem wide and - * if this is a filesystem with a backing store - ultimately * translate them to backing store values. */ error = vfs_set_acl_idmapped_mnt(idmap, i_user_ns(inode), kacl); if (error) return error; } retry_deleg: inode_lock(inode); /* * We only care about restrictions the inode struct itself places upon * us otherwise POSIX ACLs aren't subject to any VFS restrictions. */ error = may_write_xattr(idmap, inode); if (error) goto out_inode_unlock; error = security_inode_set_acl(idmap, dentry, acl_name, kacl); if (error) goto out_inode_unlock; error = try_break_deleg(inode, &delegated_inode); if (error) goto out_inode_unlock; if (likely(!is_bad_inode(inode))) error = set_posix_acl(idmap, dentry, acl_type, kacl); else error = -EIO; if (!error) { fsnotify_xattr(dentry); security_inode_post_set_acl(dentry, acl_name, kacl); } out_inode_unlock: inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } return error; } EXPORT_SYMBOL_GPL(vfs_set_acl); /** * vfs_get_acl - get posix acls * @idmap: idmap of the mount * @dentry: the dentry based on which to retrieve the posix acls * @acl_name: the name of the posix acl * * This function retrieves @kacl from the filesystem. The caller must all * posix_acl_release() on @kacl. * * Return: On success POSIX ACLs in VFS format, on error negative errno. */ struct posix_acl *vfs_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { struct inode *inode = d_inode(dentry); struct posix_acl *acl; int acl_type, error; acl_type = posix_acl_type(acl_name); if (acl_type < 0) return ERR_PTR(-EINVAL); /* * The VFS has no restrictions on reading POSIX ACLs so calling * something like xattr_permission() isn't needed. Only LSMs get a say. */ error = security_inode_get_acl(idmap, dentry, acl_name); if (error) return ERR_PTR(error); if (!IS_POSIXACL(inode)) return ERR_PTR(-EOPNOTSUPP); if (S_ISLNK(inode->i_mode)) return ERR_PTR(-EOPNOTSUPP); acl = __get_acl(idmap, dentry, inode, acl_type); if (IS_ERR(acl)) return acl; if (!acl) return ERR_PTR(-ENODATA); return acl; } EXPORT_SYMBOL_GPL(vfs_get_acl); /** * vfs_remove_acl - remove posix acls * @idmap: idmap of the mount * @dentry: the dentry based on which to retrieve the posix acls * @acl_name: the name of the posix acl * * This function removes posix acls. * * Return: On success 0, on error negative errno. */ int vfs_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { int acl_type; int error; struct inode *inode = d_inode(dentry); struct inode *delegated_inode = NULL; acl_type = posix_acl_type(acl_name); if (acl_type < 0) return -EINVAL; retry_deleg: inode_lock(inode); /* * We only care about restrictions the inode struct itself places upon * us otherwise POSIX ACLs aren't subject to any VFS restrictions. */ error = may_write_xattr(idmap, inode); if (error) goto out_inode_unlock; error = security_inode_remove_acl(idmap, dentry, acl_name); if (error) goto out_inode_unlock; error = try_break_deleg(inode, &delegated_inode); if (error) goto out_inode_unlock; if (likely(!is_bad_inode(inode))) error = set_posix_acl(idmap, dentry, acl_type, NULL); else error = -EIO; if (!error) { fsnotify_xattr(dentry); security_inode_post_remove_acl(idmap, dentry, acl_name); } out_inode_unlock: inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } return error; } EXPORT_SYMBOL_GPL(vfs_remove_acl); int do_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, const void *kvalue, size_t size) { int error; struct posix_acl *acl = NULL; if (size) { /* * Note that posix_acl_from_xattr() uses GFP_NOFS when it * probably doesn't need to here. */ acl = posix_acl_from_xattr(current_user_ns(), kvalue, size); if (IS_ERR(acl)) return PTR_ERR(acl); } error = vfs_set_acl(idmap, dentry, acl_name, acl); posix_acl_release(acl); return error; } ssize_t do_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, void *kvalue, size_t size) { ssize_t error; struct posix_acl *acl; acl = vfs_get_acl(idmap, dentry, acl_name); if (IS_ERR(acl)) return PTR_ERR(acl); error = vfs_posix_acl_to_xattr(idmap, d_inode(dentry), acl, kvalue, size); posix_acl_release(acl); return error; } |
| 83 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_ENTRYKVM_H #define __LINUX_ENTRYKVM_H #include <linux/static_call_types.h> #include <linux/resume_user_mode.h> #include <linux/syscalls.h> #include <linux/seccomp.h> #include <linux/sched.h> #include <linux/tick.h> /* Transfer to guest mode work */ #ifdef CONFIG_KVM_XFER_TO_GUEST_WORK #ifndef ARCH_XFER_TO_GUEST_MODE_WORK # define ARCH_XFER_TO_GUEST_MODE_WORK (0) #endif #define XFER_TO_GUEST_MODE_WORK \ (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY | _TIF_SIGPENDING | \ _TIF_NOTIFY_SIGNAL | _TIF_NOTIFY_RESUME | \ ARCH_XFER_TO_GUEST_MODE_WORK) struct kvm_vcpu; /** * arch_xfer_to_guest_mode_handle_work - Architecture specific xfer to guest * mode work handling function. * @vcpu: Pointer to current's VCPU data * @ti_work: Cached TIF flags gathered in xfer_to_guest_mode_handle_work() * * Invoked from xfer_to_guest_mode_handle_work(). Defaults to NOOP. Can be * replaced by architecture specific code. */ static inline int arch_xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu, unsigned long ti_work); #ifndef arch_xfer_to_guest_mode_work static inline int arch_xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu, unsigned long ti_work) { return 0; } #endif /** * xfer_to_guest_mode_handle_work - Check and handle pending work which needs * to be handled before going to guest mode * @vcpu: Pointer to current's VCPU data * * Returns: 0 or an error code */ int xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu); /** * xfer_to_guest_mode_prepare - Perform last minute preparation work that * need to be handled while IRQs are disabled * upon entering to guest. * * Has to be invoked with interrupts disabled before the last call * to xfer_to_guest_mode_work_pending(). */ static inline void xfer_to_guest_mode_prepare(void) { lockdep_assert_irqs_disabled(); tick_nohz_user_enter_prepare(); } /** * __xfer_to_guest_mode_work_pending - Check if work is pending * * Returns: True if work pending, False otherwise. * * Bare variant of xfer_to_guest_mode_work_pending(). Can be called from * interrupt enabled code for racy quick checks with care. */ static inline bool __xfer_to_guest_mode_work_pending(void) { unsigned long ti_work = read_thread_flags(); return !!(ti_work & XFER_TO_GUEST_MODE_WORK); } /** * xfer_to_guest_mode_work_pending - Check if work is pending which needs to be * handled before returning to guest mode * * Returns: True if work pending, False otherwise. * * Has to be invoked with interrupts disabled before the transition to * guest mode. */ static inline bool xfer_to_guest_mode_work_pending(void) { lockdep_assert_irqs_disabled(); return __xfer_to_guest_mode_work_pending(); } #endif /* CONFIG_KVM_XFER_TO_GUEST_WORK */ #endif |
| 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Multicast support for IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Based on linux/ipv4/igmp.c and linux/ipv4/ip_sockglue.c */ /* Changes: * * yoshfuji : fix format of router-alert option * YOSHIFUJI Hideaki @USAGI: * Fixed source address for MLD message based on * <draft-ietf-magma-mld-source-05.txt>. * YOSHIFUJI Hideaki @USAGI: * - Ignore Queries for invalid addresses. * - MLD for link-local addresses. * David L Stevens <dlstevens@us.ibm.com>: * - MLDv2 support */ #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/jiffies.h> #include <linux/net.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/route.h> #include <linux/init.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/pkt_sched.h> #include <net/mld.h> #include <linux/workqueue.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/if_inet6.h> #include <net/ndisc.h> #include <net/addrconf.h> #include <net/ip6_route.h> #include <net/inet_common.h> #include <net/ip6_checksum.h> /* Ensure that we have struct in6_addr aligned on 32bit word. */ static int __mld2_query_bugs[] __attribute__((__unused__)) = { BUILD_BUG_ON_ZERO(offsetof(struct mld2_query, mld2q_srcs) % 4), BUILD_BUG_ON_ZERO(offsetof(struct mld2_report, mld2r_grec) % 4), BUILD_BUG_ON_ZERO(offsetof(struct mld2_grec, grec_mca) % 4) }; static struct workqueue_struct *mld_wq; static struct in6_addr mld2_all_mcr = MLD2_ALL_MCR_INIT; static void igmp6_join_group(struct ifmcaddr6 *ma); static void igmp6_leave_group(struct ifmcaddr6 *ma); static void mld_mca_work(struct work_struct *work); static void mld_ifc_event(struct inet6_dev *idev); static bool mld_in_v1_mode(const struct inet6_dev *idev); static int sf_setstate(struct ifmcaddr6 *pmc); static void sf_markstate(struct ifmcaddr6 *pmc); static void ip6_mc_clear_src(struct ifmcaddr6 *pmc); static int ip6_mc_del_src(struct inet6_dev *idev, const struct in6_addr *pmca, int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta); static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca, int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta); static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, struct inet6_dev *idev); static int __ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr, unsigned int mode); #define MLD_QRV_DEFAULT 2 /* RFC3810, 9.2. Query Interval */ #define MLD_QI_DEFAULT (125 * HZ) /* RFC3810, 9.3. Query Response Interval */ #define MLD_QRI_DEFAULT (10 * HZ) /* RFC3810, 8.1 Query Version Distinctions */ #define MLD_V1_QUERY_LEN 24 #define MLD_V2_QUERY_LEN_MIN 28 #define IPV6_MLD_MAX_MSF 64 int sysctl_mld_max_msf __read_mostly = IPV6_MLD_MAX_MSF; int sysctl_mld_qrv __read_mostly = MLD_QRV_DEFAULT; /* * socket join on multicast group */ #define mc_dereference(e, idev) \ rcu_dereference_protected(e, lockdep_is_held(&(idev)->mc_lock)) #define sock_dereference(e, sk) \ rcu_dereference_protected(e, lockdep_sock_is_held(sk)) #define for_each_pmc_socklock(np, sk, pmc) \ for (pmc = sock_dereference((np)->ipv6_mc_list, sk); \ pmc; \ pmc = sock_dereference(pmc->next, sk)) #define for_each_pmc_rcu(np, pmc) \ for (pmc = rcu_dereference((np)->ipv6_mc_list); \ pmc; \ pmc = rcu_dereference(pmc->next)) #define for_each_psf_mclock(mc, psf) \ for (psf = mc_dereference((mc)->mca_sources, mc->idev); \ psf; \ psf = mc_dereference(psf->sf_next, mc->idev)) #define for_each_psf_rcu(mc, psf) \ for (psf = rcu_dereference((mc)->mca_sources); \ psf; \ psf = rcu_dereference(psf->sf_next)) #define for_each_psf_tomb(mc, psf) \ for (psf = mc_dereference((mc)->mca_tomb, mc->idev); \ psf; \ psf = mc_dereference(psf->sf_next, mc->idev)) #define for_each_mc_mclock(idev, mc) \ for (mc = mc_dereference((idev)->mc_list, idev); \ mc; \ mc = mc_dereference(mc->next, idev)) #define for_each_mc_rcu(idev, mc) \ for (mc = rcu_dereference((idev)->mc_list); \ mc; \ mc = rcu_dereference(mc->next)) #define for_each_mc_tomb(idev, mc) \ for (mc = mc_dereference((idev)->mc_tomb, idev); \ mc; \ mc = mc_dereference(mc->next, idev)) static int unsolicited_report_interval(struct inet6_dev *idev) { int iv; if (mld_in_v1_mode(idev)) iv = READ_ONCE(idev->cnf.mldv1_unsolicited_report_interval); else iv = READ_ONCE(idev->cnf.mldv2_unsolicited_report_interval); return iv > 0 ? iv : 1; } static int __ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr, unsigned int mode) { struct net_device *dev = NULL; struct ipv6_mc_socklist *mc_lst; struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); int err; ASSERT_RTNL(); if (!ipv6_addr_is_multicast(addr)) return -EINVAL; for_each_pmc_socklock(np, sk, mc_lst) { if ((ifindex == 0 || mc_lst->ifindex == ifindex) && ipv6_addr_equal(&mc_lst->addr, addr)) return -EADDRINUSE; } mc_lst = sock_kmalloc(sk, sizeof(struct ipv6_mc_socklist), GFP_KERNEL); if (!mc_lst) return -ENOMEM; mc_lst->next = NULL; mc_lst->addr = *addr; if (ifindex == 0) { struct rt6_info *rt; rt = rt6_lookup(net, addr, NULL, 0, NULL, 0); if (rt) { dev = rt->dst.dev; ip6_rt_put(rt); } } else dev = __dev_get_by_index(net, ifindex); if (!dev) { sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return -ENODEV; } mc_lst->ifindex = dev->ifindex; mc_lst->sfmode = mode; RCU_INIT_POINTER(mc_lst->sflist, NULL); /* * now add/increase the group membership on the device */ err = __ipv6_dev_mc_inc(dev, addr, mode); if (err) { sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return err; } mc_lst->next = np->ipv6_mc_list; rcu_assign_pointer(np->ipv6_mc_list, mc_lst); return 0; } int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) { return __ipv6_sock_mc_join(sk, ifindex, addr, MCAST_EXCLUDE); } EXPORT_SYMBOL(ipv6_sock_mc_join); int ipv6_sock_mc_join_ssm(struct sock *sk, int ifindex, const struct in6_addr *addr, unsigned int mode) { return __ipv6_sock_mc_join(sk, ifindex, addr, mode); } /* * socket leave on multicast group */ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_mc_socklist *mc_lst; struct ipv6_mc_socklist __rcu **lnk; struct net *net = sock_net(sk); ASSERT_RTNL(); if (!ipv6_addr_is_multicast(addr)) return -EINVAL; for (lnk = &np->ipv6_mc_list; (mc_lst = sock_dereference(*lnk, sk)) != NULL; lnk = &mc_lst->next) { if ((ifindex == 0 || mc_lst->ifindex == ifindex) && ipv6_addr_equal(&mc_lst->addr, addr)) { struct net_device *dev; *lnk = mc_lst->next; dev = __dev_get_by_index(net, mc_lst->ifindex); if (dev) { struct inet6_dev *idev = __in6_dev_get(dev); ip6_mc_leave_src(sk, mc_lst, idev); if (idev) __ipv6_dev_mc_dec(idev, &mc_lst->addr); } else { ip6_mc_leave_src(sk, mc_lst, NULL); } atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); kfree_rcu(mc_lst, rcu); return 0; } } return -EADDRNOTAVAIL; } EXPORT_SYMBOL(ipv6_sock_mc_drop); static struct inet6_dev *ip6_mc_find_dev_rtnl(struct net *net, const struct in6_addr *group, int ifindex) { struct net_device *dev = NULL; struct inet6_dev *idev = NULL; if (ifindex == 0) { struct rt6_info *rt = rt6_lookup(net, group, NULL, 0, NULL, 0); if (rt) { dev = rt->dst.dev; ip6_rt_put(rt); } } else { dev = __dev_get_by_index(net, ifindex); } if (!dev) return NULL; idev = __in6_dev_get(dev); if (!idev) return NULL; if (idev->dead) return NULL; return idev; } void __ipv6_sock_mc_close(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_mc_socklist *mc_lst; struct net *net = sock_net(sk); ASSERT_RTNL(); while ((mc_lst = sock_dereference(np->ipv6_mc_list, sk)) != NULL) { struct net_device *dev; np->ipv6_mc_list = mc_lst->next; dev = __dev_get_by_index(net, mc_lst->ifindex); if (dev) { struct inet6_dev *idev = __in6_dev_get(dev); ip6_mc_leave_src(sk, mc_lst, idev); if (idev) __ipv6_dev_mc_dec(idev, &mc_lst->addr); } else { ip6_mc_leave_src(sk, mc_lst, NULL); } atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); kfree_rcu(mc_lst, rcu); } } void ipv6_sock_mc_close(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); if (!rcu_access_pointer(np->ipv6_mc_list)) return; rtnl_lock(); lock_sock(sk); __ipv6_sock_mc_close(sk); release_sock(sk); rtnl_unlock(); } int ip6_mc_source(int add, int omode, struct sock *sk, struct group_source_req *pgsr) { struct in6_addr *source, *group; struct ipv6_mc_socklist *pmc; struct inet6_dev *idev; struct ipv6_pinfo *inet6 = inet6_sk(sk); struct ip6_sf_socklist *psl; struct net *net = sock_net(sk); int i, j, rv; int leavegroup = 0; int err; source = &((struct sockaddr_in6 *)&pgsr->gsr_source)->sin6_addr; group = &((struct sockaddr_in6 *)&pgsr->gsr_group)->sin6_addr; if (!ipv6_addr_is_multicast(group)) return -EINVAL; idev = ip6_mc_find_dev_rtnl(net, group, pgsr->gsr_interface); if (!idev) return -ENODEV; err = -EADDRNOTAVAIL; mutex_lock(&idev->mc_lock); for_each_pmc_socklock(inet6, sk, pmc) { if (pgsr->gsr_interface && pmc->ifindex != pgsr->gsr_interface) continue; if (ipv6_addr_equal(&pmc->addr, group)) break; } if (!pmc) { /* must have a prior join */ err = -EINVAL; goto done; } /* if a source filter was set, must be the same mode as before */ if (rcu_access_pointer(pmc->sflist)) { if (pmc->sfmode != omode) { err = -EINVAL; goto done; } } else if (pmc->sfmode != omode) { /* allow mode switches for empty-set filters */ ip6_mc_add_src(idev, group, omode, 0, NULL, 0); ip6_mc_del_src(idev, group, pmc->sfmode, 0, NULL, 0); pmc->sfmode = omode; } psl = sock_dereference(pmc->sflist, sk); if (!add) { if (!psl) goto done; /* err = -EADDRNOTAVAIL */ rv = !0; for (i = 0; i < psl->sl_count; i++) { rv = !ipv6_addr_equal(&psl->sl_addr[i], source); if (rv == 0) break; } if (rv) /* source not found */ goto done; /* err = -EADDRNOTAVAIL */ /* special case - (INCLUDE, empty) == LEAVE_GROUP */ if (psl->sl_count == 1 && omode == MCAST_INCLUDE) { leavegroup = 1; goto done; } /* update the interface filter */ ip6_mc_del_src(idev, group, omode, 1, source, 1); for (j = i+1; j < psl->sl_count; j++) psl->sl_addr[j-1] = psl->sl_addr[j]; psl->sl_count--; err = 0; goto done; } /* else, add a new source to the filter */ if (psl && psl->sl_count >= sysctl_mld_max_msf) { err = -ENOBUFS; goto done; } if (!psl || psl->sl_count == psl->sl_max) { struct ip6_sf_socklist *newpsl; int count = IP6_SFBLOCK; if (psl) count += psl->sl_max; newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, count), GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; } newpsl->sl_max = count; newpsl->sl_count = count - IP6_SFBLOCK; if (psl) { for (i = 0; i < psl->sl_count; i++) newpsl->sl_addr[i] = psl->sl_addr[i]; atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); } rcu_assign_pointer(pmc->sflist, newpsl); kfree_rcu(psl, rcu); psl = newpsl; } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ for (i = 0; i < psl->sl_count; i++) { rv = !ipv6_addr_equal(&psl->sl_addr[i], source); if (rv == 0) /* There is an error in the address. */ goto done; } for (j = psl->sl_count-1; j >= i; j--) psl->sl_addr[j+1] = psl->sl_addr[j]; psl->sl_addr[i] = *source; psl->sl_count++; err = 0; /* update the interface list */ ip6_mc_add_src(idev, group, omode, 1, source, 1); done: mutex_unlock(&idev->mc_lock); if (leavegroup) err = ipv6_sock_mc_drop(sk, pgsr->gsr_interface, group); return err; } int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf, struct sockaddr_storage *list) { const struct in6_addr *group; struct ipv6_mc_socklist *pmc; struct inet6_dev *idev; struct ipv6_pinfo *inet6 = inet6_sk(sk); struct ip6_sf_socklist *newpsl, *psl; struct net *net = sock_net(sk); int leavegroup = 0; int i, err; group = &((struct sockaddr_in6 *)&gsf->gf_group)->sin6_addr; if (!ipv6_addr_is_multicast(group)) return -EINVAL; if (gsf->gf_fmode != MCAST_INCLUDE && gsf->gf_fmode != MCAST_EXCLUDE) return -EINVAL; idev = ip6_mc_find_dev_rtnl(net, group, gsf->gf_interface); if (!idev) return -ENODEV; err = 0; if (gsf->gf_fmode == MCAST_INCLUDE && gsf->gf_numsrc == 0) { leavegroup = 1; goto done; } for_each_pmc_socklock(inet6, sk, pmc) { if (pmc->ifindex != gsf->gf_interface) continue; if (ipv6_addr_equal(&pmc->addr, group)) break; } if (!pmc) { /* must have a prior join */ err = -EINVAL; goto done; } if (gsf->gf_numsrc) { newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, gsf->gf_numsrc), GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; } newpsl->sl_max = newpsl->sl_count = gsf->gf_numsrc; for (i = 0; i < newpsl->sl_count; ++i, ++list) { struct sockaddr_in6 *psin6; psin6 = (struct sockaddr_in6 *)list; newpsl->sl_addr[i] = psin6->sin6_addr; } mutex_lock(&idev->mc_lock); err = ip6_mc_add_src(idev, group, gsf->gf_fmode, newpsl->sl_count, newpsl->sl_addr, 0); if (err) { mutex_unlock(&idev->mc_lock); sock_kfree_s(sk, newpsl, struct_size(newpsl, sl_addr, newpsl->sl_max)); goto done; } mutex_unlock(&idev->mc_lock); } else { newpsl = NULL; mutex_lock(&idev->mc_lock); ip6_mc_add_src(idev, group, gsf->gf_fmode, 0, NULL, 0); mutex_unlock(&idev->mc_lock); } mutex_lock(&idev->mc_lock); psl = sock_dereference(pmc->sflist, sk); if (psl) { ip6_mc_del_src(idev, group, pmc->sfmode, psl->sl_count, psl->sl_addr, 0); atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); } else { ip6_mc_del_src(idev, group, pmc->sfmode, 0, NULL, 0); } rcu_assign_pointer(pmc->sflist, newpsl); mutex_unlock(&idev->mc_lock); kfree_rcu(psl, rcu); pmc->sfmode = gsf->gf_fmode; err = 0; done: if (leavegroup) err = ipv6_sock_mc_drop(sk, gsf->gf_interface, group); return err; } int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, sockptr_t optval, size_t ss_offset) { struct ipv6_pinfo *inet6 = inet6_sk(sk); const struct in6_addr *group; struct ipv6_mc_socklist *pmc; struct ip6_sf_socklist *psl; unsigned int count; int i, copycount; group = &((struct sockaddr_in6 *)&gsf->gf_group)->sin6_addr; if (!ipv6_addr_is_multicast(group)) return -EINVAL; /* changes to the ipv6_mc_list require the socket lock and * rtnl lock. We have the socket lock, so reading the list is safe. */ for_each_pmc_socklock(inet6, sk, pmc) { if (pmc->ifindex != gsf->gf_interface) continue; if (ipv6_addr_equal(group, &pmc->addr)) break; } if (!pmc) /* must have a prior join */ return -EADDRNOTAVAIL; gsf->gf_fmode = pmc->sfmode; psl = sock_dereference(pmc->sflist, sk); count = psl ? psl->sl_count : 0; copycount = min(count, gsf->gf_numsrc); gsf->gf_numsrc = count; for (i = 0; i < copycount; i++) { struct sockaddr_in6 *psin6; struct sockaddr_storage ss; psin6 = (struct sockaddr_in6 *)&ss; memset(&ss, 0, sizeof(ss)); psin6->sin6_family = AF_INET6; psin6->sin6_addr = psl->sl_addr[i]; if (copy_to_sockptr_offset(optval, ss_offset, &ss, sizeof(ss))) return -EFAULT; ss_offset += sizeof(ss); } return 0; } bool inet6_mc_check(const struct sock *sk, const struct in6_addr *mc_addr, const struct in6_addr *src_addr) { const struct ipv6_pinfo *np = inet6_sk(sk); const struct ipv6_mc_socklist *mc; const struct ip6_sf_socklist *psl; bool rv = true; rcu_read_lock(); for_each_pmc_rcu(np, mc) { if (ipv6_addr_equal(&mc->addr, mc_addr)) break; } if (!mc) { rcu_read_unlock(); return inet6_test_bit(MC6_ALL, sk); } psl = rcu_dereference(mc->sflist); if (!psl) { rv = mc->sfmode == MCAST_EXCLUDE; } else { int i; for (i = 0; i < psl->sl_count; i++) { if (ipv6_addr_equal(&psl->sl_addr[i], src_addr)) break; } if (mc->sfmode == MCAST_INCLUDE && i >= psl->sl_count) rv = false; if (mc->sfmode == MCAST_EXCLUDE && i < psl->sl_count) rv = false; } rcu_read_unlock(); return rv; } /* called with mc_lock */ static void igmp6_group_added(struct ifmcaddr6 *mc) { struct net_device *dev = mc->idev->dev; char buf[MAX_ADDR_LEN]; if (IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) return; if (!(mc->mca_flags&MAF_LOADED)) { mc->mca_flags |= MAF_LOADED; if (ndisc_mc_map(&mc->mca_addr, buf, dev, 0) == 0) dev_mc_add(dev, buf); } if (!(dev->flags & IFF_UP) || (mc->mca_flags & MAF_NOREPORT)) return; if (mld_in_v1_mode(mc->idev)) { igmp6_join_group(mc); return; } /* else v2 */ /* Based on RFC3810 6.1, for newly added INCLUDE SSM, we * should not send filter-mode change record as the mode * should be from IN() to IN(A). */ if (mc->mca_sfmode == MCAST_EXCLUDE) mc->mca_crcount = mc->idev->mc_qrv; mld_ifc_event(mc->idev); } /* called with mc_lock */ static void igmp6_group_dropped(struct ifmcaddr6 *mc) { struct net_device *dev = mc->idev->dev; char buf[MAX_ADDR_LEN]; if (IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) return; if (mc->mca_flags&MAF_LOADED) { mc->mca_flags &= ~MAF_LOADED; if (ndisc_mc_map(&mc->mca_addr, buf, dev, 0) == 0) dev_mc_del(dev, buf); } if (mc->mca_flags & MAF_NOREPORT) return; if (!mc->idev->dead) igmp6_leave_group(mc); if (cancel_delayed_work(&mc->mca_work)) refcount_dec(&mc->mca_refcnt); } /* * deleted ifmcaddr6 manipulation * called with mc_lock */ static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) { struct ifmcaddr6 *pmc; /* this is an "ifmcaddr6" for convenience; only the fields below * are actually used. In particular, the refcnt and users are not * used for management of the delete list. Using the same structure * for deleted items allows change reports to use common code with * non-deleted or query-response MCA's. */ pmc = kzalloc(sizeof(*pmc), GFP_KERNEL); if (!pmc) return; pmc->idev = im->idev; in6_dev_hold(idev); pmc->mca_addr = im->mca_addr; pmc->mca_crcount = idev->mc_qrv; pmc->mca_sfmode = im->mca_sfmode; if (pmc->mca_sfmode == MCAST_INCLUDE) { struct ip6_sf_list *psf; rcu_assign_pointer(pmc->mca_tomb, mc_dereference(im->mca_tomb, idev)); rcu_assign_pointer(pmc->mca_sources, mc_dereference(im->mca_sources, idev)); RCU_INIT_POINTER(im->mca_tomb, NULL); RCU_INIT_POINTER(im->mca_sources, NULL); for_each_psf_mclock(pmc, psf) psf->sf_crcount = pmc->mca_crcount; } rcu_assign_pointer(pmc->next, idev->mc_tomb); rcu_assign_pointer(idev->mc_tomb, pmc); } /* called with mc_lock */ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) { struct ip6_sf_list *psf, *sources, *tomb; struct in6_addr *pmca = &im->mca_addr; struct ifmcaddr6 *pmc, *pmc_prev; pmc_prev = NULL; for_each_mc_tomb(idev, pmc) { if (ipv6_addr_equal(&pmc->mca_addr, pmca)) break; pmc_prev = pmc; } if (pmc) { if (pmc_prev) rcu_assign_pointer(pmc_prev->next, pmc->next); else rcu_assign_pointer(idev->mc_tomb, pmc->next); } if (pmc) { im->idev = pmc->idev; if (im->mca_sfmode == MCAST_INCLUDE) { tomb = rcu_replace_pointer(im->mca_tomb, mc_dereference(pmc->mca_tomb, pmc->idev), lockdep_is_held(&im->idev->mc_lock)); rcu_assign_pointer(pmc->mca_tomb, tomb); sources = rcu_replace_pointer(im->mca_sources, mc_dereference(pmc->mca_sources, pmc->idev), lockdep_is_held(&im->idev->mc_lock)); rcu_assign_pointer(pmc->mca_sources, sources); for_each_psf_mclock(im, psf) psf->sf_crcount = idev->mc_qrv; } else { im->mca_crcount = idev->mc_qrv; } in6_dev_put(pmc->idev); ip6_mc_clear_src(pmc); kfree_rcu(pmc, rcu); } } /* called with mc_lock */ static void mld_clear_delrec(struct inet6_dev *idev) { struct ifmcaddr6 *pmc, *nextpmc; pmc = mc_dereference(idev->mc_tomb, idev); RCU_INIT_POINTER(idev->mc_tomb, NULL); for (; pmc; pmc = nextpmc) { nextpmc = mc_dereference(pmc->next, idev); ip6_mc_clear_src(pmc); in6_dev_put(pmc->idev); kfree_rcu(pmc, rcu); } /* clear dead sources, too */ for_each_mc_mclock(idev, pmc) { struct ip6_sf_list *psf, *psf_next; psf = mc_dereference(pmc->mca_tomb, idev); RCU_INIT_POINTER(pmc->mca_tomb, NULL); for (; psf; psf = psf_next) { psf_next = mc_dereference(psf->sf_next, idev); kfree_rcu(psf, rcu); } } } static void mld_clear_query(struct inet6_dev *idev) { struct sk_buff *skb; spin_lock_bh(&idev->mc_query_lock); while ((skb = __skb_dequeue(&idev->mc_query_queue))) kfree_skb(skb); spin_unlock_bh(&idev->mc_query_lock); } static void mld_clear_report(struct inet6_dev *idev) { struct sk_buff *skb; spin_lock_bh(&idev->mc_report_lock); while ((skb = __skb_dequeue(&idev->mc_report_queue))) kfree_skb(skb); spin_unlock_bh(&idev->mc_report_lock); } static void mca_get(struct ifmcaddr6 *mc) { refcount_inc(&mc->mca_refcnt); } static void ma_put(struct ifmcaddr6 *mc) { if (refcount_dec_and_test(&mc->mca_refcnt)) { in6_dev_put(mc->idev); kfree_rcu(mc, rcu); } } /* called with mc_lock */ static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev, const struct in6_addr *addr, unsigned int mode) { struct ifmcaddr6 *mc; mc = kzalloc(sizeof(*mc), GFP_KERNEL); if (!mc) return NULL; INIT_DELAYED_WORK(&mc->mca_work, mld_mca_work); mc->mca_addr = *addr; mc->idev = idev; /* reference taken by caller */ mc->mca_users = 1; /* mca_stamp should be updated upon changes */ mc->mca_cstamp = mc->mca_tstamp = jiffies; refcount_set(&mc->mca_refcnt, 1); mc->mca_sfmode = mode; mc->mca_sfcount[mode] = 1; if (ipv6_addr_is_ll_all_nodes(&mc->mca_addr) || IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) mc->mca_flags |= MAF_NOREPORT; return mc; } /* * device multicast group inc (add if not found) */ static int __ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr, unsigned int mode) { struct ifmcaddr6 *mc; struct inet6_dev *idev; ASSERT_RTNL(); /* we need to take a reference on idev */ idev = in6_dev_get(dev); if (!idev) return -EINVAL; if (idev->dead) { in6_dev_put(idev); return -ENODEV; } mutex_lock(&idev->mc_lock); for_each_mc_mclock(idev, mc) { if (ipv6_addr_equal(&mc->mca_addr, addr)) { mc->mca_users++; ip6_mc_add_src(idev, &mc->mca_addr, mode, 0, NULL, 0); mutex_unlock(&idev->mc_lock); in6_dev_put(idev); return 0; } } mc = mca_alloc(idev, addr, mode); if (!mc) { mutex_unlock(&idev->mc_lock); in6_dev_put(idev); return -ENOMEM; } rcu_assign_pointer(mc->next, idev->mc_list); rcu_assign_pointer(idev->mc_list, mc); mca_get(mc); mld_del_delrec(idev, mc); igmp6_group_added(mc); mutex_unlock(&idev->mc_lock); ma_put(mc); return 0; } int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) { return __ipv6_dev_mc_inc(dev, addr, MCAST_EXCLUDE); } EXPORT_SYMBOL(ipv6_dev_mc_inc); /* * device multicast group del */ int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifmcaddr6 *ma, __rcu **map; ASSERT_RTNL(); mutex_lock(&idev->mc_lock); for (map = &idev->mc_list; (ma = mc_dereference(*map, idev)); map = &ma->next) { if (ipv6_addr_equal(&ma->mca_addr, addr)) { if (--ma->mca_users == 0) { *map = ma->next; igmp6_group_dropped(ma); ip6_mc_clear_src(ma); mutex_unlock(&idev->mc_lock); ma_put(ma); return 0; } mutex_unlock(&idev->mc_lock); return 0; } } mutex_unlock(&idev->mc_lock); return -ENOENT; } int ipv6_dev_mc_dec(struct net_device *dev, const struct in6_addr *addr) { struct inet6_dev *idev; int err; ASSERT_RTNL(); idev = __in6_dev_get(dev); if (!idev) err = -ENODEV; else err = __ipv6_dev_mc_dec(idev, addr); return err; } EXPORT_SYMBOL(ipv6_dev_mc_dec); /* * check if the interface/address pair is valid */ bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, const struct in6_addr *src_addr) { struct inet6_dev *idev; struct ifmcaddr6 *mc; bool rv = false; rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) { for_each_mc_rcu(idev, mc) { if (ipv6_addr_equal(&mc->mca_addr, group)) break; } if (mc) { if (src_addr && !ipv6_addr_any(src_addr)) { struct ip6_sf_list *psf; for_each_psf_rcu(mc, psf) { if (ipv6_addr_equal(&psf->sf_addr, src_addr)) break; } if (psf) rv = psf->sf_count[MCAST_INCLUDE] || psf->sf_count[MCAST_EXCLUDE] != mc->mca_sfcount[MCAST_EXCLUDE]; else rv = mc->mca_sfcount[MCAST_EXCLUDE] != 0; } else rv = true; /* don't filter unspecified source */ } } rcu_read_unlock(); return rv; } /* called with mc_lock */ static void mld_gq_start_work(struct inet6_dev *idev) { unsigned long tv = get_random_u32_below(idev->mc_maxdelay); idev->mc_gq_running = 1; if (!mod_delayed_work(mld_wq, &idev->mc_gq_work, tv + 2)) in6_dev_hold(idev); } /* called with mc_lock */ static void mld_gq_stop_work(struct inet6_dev *idev) { idev->mc_gq_running = 0; if (cancel_delayed_work(&idev->mc_gq_work)) __in6_dev_put(idev); } /* called with mc_lock */ static void mld_ifc_start_work(struct inet6_dev *idev, unsigned long delay) { unsigned long tv = get_random_u32_below(delay); if (!mod_delayed_work(mld_wq, &idev->mc_ifc_work, tv + 2)) in6_dev_hold(idev); } /* called with mc_lock */ static void mld_ifc_stop_work(struct inet6_dev *idev) { idev->mc_ifc_count = 0; if (cancel_delayed_work(&idev->mc_ifc_work)) __in6_dev_put(idev); } /* called with mc_lock */ static void mld_dad_start_work(struct inet6_dev *idev, unsigned long delay) { unsigned long tv = get_random_u32_below(delay); if (!mod_delayed_work(mld_wq, &idev->mc_dad_work, tv + 2)) in6_dev_hold(idev); } static void mld_dad_stop_work(struct inet6_dev *idev) { if (cancel_delayed_work(&idev->mc_dad_work)) __in6_dev_put(idev); } static void mld_query_stop_work(struct inet6_dev *idev) { spin_lock_bh(&idev->mc_query_lock); if (cancel_delayed_work(&idev->mc_query_work)) __in6_dev_put(idev); spin_unlock_bh(&idev->mc_query_lock); } static void mld_report_stop_work(struct inet6_dev *idev) { if (cancel_delayed_work_sync(&idev->mc_report_work)) __in6_dev_put(idev); } /* * IGMP handling (alias multicast ICMPv6 messages) * called with mc_lock */ static void igmp6_group_queried(struct ifmcaddr6 *ma, unsigned long resptime) { unsigned long delay = resptime; /* Do not start work for these addresses */ if (ipv6_addr_is_ll_all_nodes(&ma->mca_addr) || IPV6_ADDR_MC_SCOPE(&ma->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) return; if (cancel_delayed_work(&ma->mca_work)) { refcount_dec(&ma->mca_refcnt); delay = ma->mca_work.timer.expires - jiffies; } if (delay >= resptime) delay = get_random_u32_below(resptime); if (!mod_delayed_work(mld_wq, &ma->mca_work, delay)) refcount_inc(&ma->mca_refcnt); ma->mca_flags |= MAF_TIMER_RUNNING; } /* mark EXCLUDE-mode sources * called with mc_lock */ static bool mld_xmarksources(struct ifmcaddr6 *pmc, int nsrcs, const struct in6_addr *srcs) { struct ip6_sf_list *psf; int i, scount; scount = 0; for_each_psf_mclock(pmc, psf) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) { /* skip inactive filters */ if (psf->sf_count[MCAST_INCLUDE] || pmc->mca_sfcount[MCAST_EXCLUDE] != psf->sf_count[MCAST_EXCLUDE]) break; if (ipv6_addr_equal(&srcs[i], &psf->sf_addr)) { scount++; break; } } } pmc->mca_flags &= ~MAF_GSQUERY; if (scount == nsrcs) /* all sources excluded */ return false; return true; } /* called with mc_lock */ static bool mld_marksources(struct ifmcaddr6 *pmc, int nsrcs, const struct in6_addr *srcs) { struct ip6_sf_list *psf; int i, scount; if (pmc->mca_sfmode == MCAST_EXCLUDE) return mld_xmarksources(pmc, nsrcs, srcs); /* mark INCLUDE-mode sources */ scount = 0; for_each_psf_mclock(pmc, psf) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) { if (ipv6_addr_equal(&srcs[i], &psf->sf_addr)) { psf->sf_gsresp = 1; scount++; break; } } } if (!scount) { pmc->mca_flags &= ~MAF_GSQUERY; return false; } pmc->mca_flags |= MAF_GSQUERY; return true; } static int mld_force_mld_version(const struct inet6_dev *idev) { const struct net *net = dev_net(idev->dev); int all_force; all_force = READ_ONCE(net->ipv6.devconf_all->force_mld_version); /* Normally, both are 0 here. If enforcement to a particular is * being used, individual device enforcement will have a lower * precedence over 'all' device (.../conf/all/force_mld_version). */ return all_force ?: READ_ONCE(idev->cnf.force_mld_version); } static bool mld_in_v2_mode_only(const struct inet6_dev *idev) { return mld_force_mld_version(idev) == 2; } static bool mld_in_v1_mode_only(const struct inet6_dev *idev) { return mld_force_mld_version(idev) == 1; } static bool mld_in_v1_mode(const struct inet6_dev *idev) { if (mld_in_v2_mode_only(idev)) return false; if (mld_in_v1_mode_only(idev)) return true; if (idev->mc_v1_seen && time_before(jiffies, idev->mc_v1_seen)) return true; return false; } static void mld_set_v1_mode(struct inet6_dev *idev) { /* RFC3810, relevant sections: * - 9.1. Robustness Variable * - 9.2. Query Interval * - 9.3. Query Response Interval * - 9.12. Older Version Querier Present Timeout */ unsigned long switchback; switchback = (idev->mc_qrv * idev->mc_qi) + idev->mc_qri; idev->mc_v1_seen = jiffies + switchback; } static void mld_update_qrv(struct inet6_dev *idev, const struct mld2_query *mlh2) { /* RFC3810, relevant sections: * - 5.1.8. QRV (Querier's Robustness Variable) * - 9.1. Robustness Variable */ /* The value of the Robustness Variable MUST NOT be zero, * and SHOULD NOT be one. Catch this here if we ever run * into such a case in future. */ const int min_qrv = min(MLD_QRV_DEFAULT, sysctl_mld_qrv); WARN_ON(idev->mc_qrv == 0); if (mlh2->mld2q_qrv > 0) idev->mc_qrv = mlh2->mld2q_qrv; if (unlikely(idev->mc_qrv < min_qrv)) { net_warn_ratelimited("IPv6: MLD: clamping QRV from %u to %u!\n", idev->mc_qrv, min_qrv); idev->mc_qrv = min_qrv; } } static void mld_update_qi(struct inet6_dev *idev, const struct mld2_query *mlh2) { /* RFC3810, relevant sections: * - 5.1.9. QQIC (Querier's Query Interval Code) * - 9.2. Query Interval * - 9.12. Older Version Querier Present Timeout * (the [Query Interval] in the last Query received) */ unsigned long mc_qqi; if (mlh2->mld2q_qqic < 128) { mc_qqi = mlh2->mld2q_qqic; } else { unsigned long mc_man, mc_exp; mc_exp = MLDV2_QQIC_EXP(mlh2->mld2q_qqic); mc_man = MLDV2_QQIC_MAN(mlh2->mld2q_qqic); mc_qqi = (mc_man | 0x10) << (mc_exp + 3); } idev->mc_qi = mc_qqi * HZ; } static void mld_update_qri(struct inet6_dev *idev, const struct mld2_query *mlh2) { /* RFC3810, relevant sections: * - 5.1.3. Maximum Response Code * - 9.3. Query Response Interval */ idev->mc_qri = msecs_to_jiffies(mldv2_mrc(mlh2)); } static int mld_process_v1(struct inet6_dev *idev, struct mld_msg *mld, unsigned long *max_delay, bool v1_query) { unsigned long mldv1_md; /* Ignore v1 queries */ if (mld_in_v2_mode_only(idev)) return -EINVAL; mldv1_md = ntohs(mld->mld_maxdelay); /* When in MLDv1 fallback and a MLDv2 router start-up being * unaware of current MLDv1 operation, the MRC == MRD mapping * only works when the exponential algorithm is not being * used (as MLDv1 is unaware of such things). * * According to the RFC author, the MLDv2 implementations * he's aware of all use a MRC < 32768 on start up queries. * * Thus, should we *ever* encounter something else larger * than that, just assume the maximum possible within our * reach. */ if (!v1_query) mldv1_md = min(mldv1_md, MLDV1_MRD_MAX_COMPAT); *max_delay = max(msecs_to_jiffies(mldv1_md), 1UL); /* MLDv1 router present: we need to go into v1 mode *only* * when an MLDv1 query is received as per section 9.12. of * RFC3810! And we know from RFC2710 section 3.7 that MLDv1 * queries MUST be of exactly 24 octets. */ if (v1_query) mld_set_v1_mode(idev); /* cancel MLDv2 report work */ mld_gq_stop_work(idev); /* cancel the interface change work */ mld_ifc_stop_work(idev); /* clear deleted report items */ mld_clear_delrec(idev); return 0; } static void mld_process_v2(struct inet6_dev *idev, struct mld2_query *mld, unsigned long *max_delay) { *max_delay = max(msecs_to_jiffies(mldv2_mrc(mld)), 1UL); mld_update_qrv(idev, mld); mld_update_qi(idev, mld); mld_update_qri(idev, mld); idev->mc_maxdelay = *max_delay; return; } /* called with rcu_read_lock() */ void igmp6_event_query(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); if (!idev || idev->dead) goto out; spin_lock_bh(&idev->mc_query_lock); if (skb_queue_len(&idev->mc_query_queue) < MLD_MAX_SKBS) { __skb_queue_tail(&idev->mc_query_queue, skb); if (!mod_delayed_work(mld_wq, &idev->mc_query_work, 0)) in6_dev_hold(idev); skb = NULL; } spin_unlock_bh(&idev->mc_query_lock); out: kfree_skb(skb); } static void __mld_query_work(struct sk_buff *skb) { struct mld2_query *mlh2 = NULL; const struct in6_addr *group; unsigned long max_delay; struct inet6_dev *idev; struct ifmcaddr6 *ma; struct mld_msg *mld; int group_type; int mark = 0; int len, err; if (!pskb_may_pull(skb, sizeof(struct in6_addr))) goto kfree_skb; /* compute payload length excluding extension headers */ len = ntohs(ipv6_hdr(skb)->payload_len) + sizeof(struct ipv6hdr); len -= skb_network_header_len(skb); /* RFC3810 6.2 * Upon reception of an MLD message that contains a Query, the node * checks if the source address of the message is a valid link-local * address, if the Hop Limit is set to 1, and if the Router Alert * option is present in the Hop-By-Hop Options header of the IPv6 * packet. If any of these checks fails, the packet is dropped. */ if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL) || ipv6_hdr(skb)->hop_limit != 1 || !(IP6CB(skb)->flags & IP6SKB_ROUTERALERT) || IP6CB(skb)->ra != htons(IPV6_OPT_ROUTERALERT_MLD)) goto kfree_skb; idev = in6_dev_get(skb->dev); if (!idev) goto kfree_skb; mld = (struct mld_msg *)icmp6_hdr(skb); group = &mld->mld_mca; group_type = ipv6_addr_type(group); if (group_type != IPV6_ADDR_ANY && !(group_type&IPV6_ADDR_MULTICAST)) goto out; if (len < MLD_V1_QUERY_LEN) { goto out; } else if (len == MLD_V1_QUERY_LEN || mld_in_v1_mode(idev)) { err = mld_process_v1(idev, mld, &max_delay, len == MLD_V1_QUERY_LEN); if (err < 0) goto out; } else if (len >= MLD_V2_QUERY_LEN_MIN) { int srcs_offset = sizeof(struct mld2_query) - sizeof(struct icmp6hdr); if (!pskb_may_pull(skb, srcs_offset)) goto out; mlh2 = (struct mld2_query *)skb_transport_header(skb); mld_process_v2(idev, mlh2, &max_delay); if (group_type == IPV6_ADDR_ANY) { /* general query */ if (mlh2->mld2q_nsrcs) goto out; /* no sources allowed */ mld_gq_start_work(idev); goto out; } /* mark sources to include, if group & source-specific */ if (mlh2->mld2q_nsrcs != 0) { if (!pskb_may_pull(skb, srcs_offset + ntohs(mlh2->mld2q_nsrcs) * sizeof(struct in6_addr))) goto out; mlh2 = (struct mld2_query *)skb_transport_header(skb); mark = 1; } } else { goto out; } if (group_type == IPV6_ADDR_ANY) { for_each_mc_mclock(idev, ma) { igmp6_group_queried(ma, max_delay); } } else { for_each_mc_mclock(idev, ma) { if (!ipv6_addr_equal(group, &ma->mca_addr)) continue; if (ma->mca_flags & MAF_TIMER_RUNNING) { /* gsquery <- gsquery && mark */ if (!mark) ma->mca_flags &= ~MAF_GSQUERY; } else { /* gsquery <- mark */ if (mark) ma->mca_flags |= MAF_GSQUERY; else ma->mca_flags &= ~MAF_GSQUERY; } if (!(ma->mca_flags & MAF_GSQUERY) || mld_marksources(ma, ntohs(mlh2->mld2q_nsrcs), mlh2->mld2q_srcs)) igmp6_group_queried(ma, max_delay); break; } } out: in6_dev_put(idev); kfree_skb: consume_skb(skb); } static void mld_query_work(struct work_struct *work) { struct inet6_dev *idev = container_of(to_delayed_work(work), struct inet6_dev, mc_query_work); struct sk_buff_head q; struct sk_buff *skb; bool rework = false; int cnt = 0; skb_queue_head_init(&q); spin_lock_bh(&idev->mc_query_lock); while ((skb = __skb_dequeue(&idev->mc_query_queue))) { __skb_queue_tail(&q, skb); if (++cnt >= MLD_MAX_QUEUE) { rework = true; break; } } spin_unlock_bh(&idev->mc_query_lock); mutex_lock(&idev->mc_lock); while ((skb = __skb_dequeue(&q))) __mld_query_work(skb); mutex_unlock(&idev->mc_lock); if (rework && queue_delayed_work(mld_wq, &idev->mc_query_work, 0)) return; in6_dev_put(idev); } /* called with rcu_read_lock() */ void igmp6_event_report(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); if (!idev || idev->dead) goto out; spin_lock_bh(&idev->mc_report_lock); if (skb_queue_len(&idev->mc_report_queue) < MLD_MAX_SKBS) { __skb_queue_tail(&idev->mc_report_queue, skb); if (!mod_delayed_work(mld_wq, &idev->mc_report_work, 0)) in6_dev_hold(idev); skb = NULL; } spin_unlock_bh(&idev->mc_report_lock); out: kfree_skb(skb); } static void __mld_report_work(struct sk_buff *skb) { struct inet6_dev *idev; struct ifmcaddr6 *ma; struct mld_msg *mld; int addr_type; /* Our own report looped back. Ignore it. */ if (skb->pkt_type == PACKET_LOOPBACK) goto kfree_skb; /* send our report if the MC router may not have heard this report */ if (skb->pkt_type != PACKET_MULTICAST && skb->pkt_type != PACKET_BROADCAST) goto kfree_skb; if (!pskb_may_pull(skb, sizeof(*mld) - sizeof(struct icmp6hdr))) goto kfree_skb; mld = (struct mld_msg *)icmp6_hdr(skb); /* Drop reports with not link local source */ addr_type = ipv6_addr_type(&ipv6_hdr(skb)->saddr); if (addr_type != IPV6_ADDR_ANY && !(addr_type&IPV6_ADDR_LINKLOCAL)) goto kfree_skb; idev = in6_dev_get(skb->dev); if (!idev) goto kfree_skb; /* * Cancel the work for this group */ for_each_mc_mclock(idev, ma) { if (ipv6_addr_equal(&ma->mca_addr, &mld->mld_mca)) { if (cancel_delayed_work(&ma->mca_work)) refcount_dec(&ma->mca_refcnt); ma->mca_flags &= ~(MAF_LAST_REPORTER | MAF_TIMER_RUNNING); break; } } in6_dev_put(idev); kfree_skb: consume_skb(skb); } static void mld_report_work(struct work_struct *work) { struct inet6_dev *idev = container_of(to_delayed_work(work), struct inet6_dev, mc_report_work); struct sk_buff_head q; struct sk_buff *skb; bool rework = false; int cnt = 0; skb_queue_head_init(&q); spin_lock_bh(&idev->mc_report_lock); while ((skb = __skb_dequeue(&idev->mc_report_queue))) { __skb_queue_tail(&q, skb); if (++cnt >= MLD_MAX_QUEUE) { rework = true; break; } } spin_unlock_bh(&idev->mc_report_lock); mutex_lock(&idev->mc_lock); while ((skb = __skb_dequeue(&q))) __mld_report_work(skb); mutex_unlock(&idev->mc_lock); if (rework && queue_delayed_work(mld_wq, &idev->mc_report_work, 0)) return; in6_dev_put(idev); } static bool is_in(struct ifmcaddr6 *pmc, struct ip6_sf_list *psf, int type, int gdeleted, int sdeleted) { switch (type) { case MLD2_MODE_IS_INCLUDE: case MLD2_MODE_IS_EXCLUDE: if (gdeleted || sdeleted) return false; if (!((pmc->mca_flags & MAF_GSQUERY) && !psf->sf_gsresp)) { if (pmc->mca_sfmode == MCAST_INCLUDE) return true; /* don't include if this source is excluded * in all filters */ if (psf->sf_count[MCAST_INCLUDE]) return type == MLD2_MODE_IS_INCLUDE; return pmc->mca_sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; } return false; case MLD2_CHANGE_TO_INCLUDE: if (gdeleted || sdeleted) return false; return psf->sf_count[MCAST_INCLUDE] != 0; case MLD2_CHANGE_TO_EXCLUDE: if (gdeleted || sdeleted) return false; if (pmc->mca_sfcount[MCAST_EXCLUDE] == 0 || psf->sf_count[MCAST_INCLUDE]) return false; return pmc->mca_sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; case MLD2_ALLOW_NEW_SOURCES: if (gdeleted || !psf->sf_crcount) return false; return (pmc->mca_sfmode == MCAST_INCLUDE) ^ sdeleted; case MLD2_BLOCK_OLD_SOURCES: if (pmc->mca_sfmode == MCAST_INCLUDE) return gdeleted || (psf->sf_crcount && sdeleted); return psf->sf_crcount && !gdeleted && !sdeleted; } return false; } static int mld_scount(struct ifmcaddr6 *pmc, int type, int gdeleted, int sdeleted) { struct ip6_sf_list *psf; int scount = 0; for_each_psf_mclock(pmc, psf) { if (!is_in(pmc, psf, type, gdeleted, sdeleted)) continue; scount++; } return scount; } static void ip6_mc_hdr(const struct sock *sk, struct sk_buff *skb, struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr, int proto, int len) { struct ipv6hdr *hdr; skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; skb_reset_network_header(skb); skb_put(skb, sizeof(struct ipv6hdr)); hdr = ipv6_hdr(skb); ip6_flow_hdr(hdr, 0, 0); hdr->payload_len = htons(len); hdr->nexthdr = proto; hdr->hop_limit = READ_ONCE(inet6_sk(sk)->hop_limit); hdr->saddr = *saddr; hdr->daddr = *daddr; } static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu) { u8 ra[8] = { IPPROTO_ICMPV6, 0, IPV6_TLV_ROUTERALERT, 2, 0, 0, IPV6_TLV_PADN, 0 }; struct net_device *dev = idev->dev; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; struct net *net = dev_net(dev); const struct in6_addr *saddr; struct in6_addr addr_buf; struct mld2_report *pmr; struct sk_buff *skb; unsigned int size; struct sock *sk; int err; sk = net->ipv6.igmp_sk; /* we assume size > sizeof(ra) here * Also try to not allocate high-order pages for big MTU */ size = min_t(int, mtu, PAGE_SIZE / 2) + hlen + tlen; skb = sock_alloc_send_skb(sk, size, 1, &err); if (!skb) return NULL; skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, hlen); skb_tailroom_reserve(skb, mtu, tlen); if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: * use unspecified address as the source address * when a valid link-local address is not available. */ saddr = &in6addr_any; } else saddr = &addr_buf; ip6_mc_hdr(sk, skb, dev, saddr, &mld2_all_mcr, NEXTHDR_HOP, 0); skb_put_data(skb, ra, sizeof(ra)); skb_set_transport_header(skb, skb_tail_pointer(skb) - skb->data); skb_put(skb, sizeof(*pmr)); pmr = (struct mld2_report *)skb_transport_header(skb); pmr->mld2r_type = ICMPV6_MLD2_REPORT; pmr->mld2r_resv1 = 0; pmr->mld2r_cksum = 0; pmr->mld2r_resv2 = 0; pmr->mld2r_ngrec = 0; return skb; } static void mld_sendpack(struct sk_buff *skb) { struct ipv6hdr *pip6 = ipv6_hdr(skb); struct mld2_report *pmr = (struct mld2_report *)skb_transport_header(skb); int payload_len, mldlen; struct inet6_dev *idev; struct net *net = dev_net(skb->dev); int err; struct flowi6 fl6; struct dst_entry *dst; rcu_read_lock(); idev = __in6_dev_get(skb->dev); IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); payload_len = (skb_tail_pointer(skb) - skb_network_header(skb)) - sizeof(*pip6); mldlen = skb_tail_pointer(skb) - skb_transport_header(skb); pip6->payload_len = htons(payload_len); pmr->mld2r_cksum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, mldlen, IPPROTO_ICMPV6, csum_partial(skb_transport_header(skb), mldlen, 0)); icmpv6_flow_init(net->ipv6.igmp_sk, &fl6, ICMPV6_MLD2_REPORT, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); dst = icmp6_dst_alloc(skb->dev, &fl6); err = 0; if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; } skb_dst_set(skb, dst); if (err) goto err_out; err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, net->ipv6.igmp_sk, skb, NULL, skb->dev, dst_output); out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } else { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); } rcu_read_unlock(); return; err_out: kfree_skb(skb); goto out; } static int grec_size(struct ifmcaddr6 *pmc, int type, int gdel, int sdel) { return sizeof(struct mld2_grec) + 16 * mld_scount(pmc,type,gdel,sdel); } static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc, int type, struct mld2_grec **ppgr, unsigned int mtu) { struct mld2_report *pmr; struct mld2_grec *pgr; if (!skb) { skb = mld_newpack(pmc->idev, mtu); if (!skb) return NULL; } pgr = skb_put(skb, sizeof(struct mld2_grec)); pgr->grec_type = type; pgr->grec_auxwords = 0; pgr->grec_nsrcs = 0; pgr->grec_mca = pmc->mca_addr; /* structure copy */ pmr = (struct mld2_report *)skb_transport_header(skb); pmr->mld2r_ngrec = htons(ntohs(pmr->mld2r_ngrec)+1); *ppgr = pgr; return skb; } #define AVAILABLE(skb) ((skb) ? skb_availroom(skb) : 0) /* called with mc_lock */ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, int type, int gdeleted, int sdeleted, int crsend) { struct ip6_sf_list *psf, *psf_prev, *psf_next; int scount, stotal, first, isquery, truncate; struct ip6_sf_list __rcu **psf_list; struct inet6_dev *idev = pmc->idev; struct net_device *dev = idev->dev; struct mld2_grec *pgr = NULL; struct mld2_report *pmr; unsigned int mtu; if (pmc->mca_flags & MAF_NOREPORT) return skb; mtu = READ_ONCE(dev->mtu); if (mtu < IPV6_MIN_MTU) return skb; isquery = type == MLD2_MODE_IS_INCLUDE || type == MLD2_MODE_IS_EXCLUDE; truncate = type == MLD2_MODE_IS_EXCLUDE || type == MLD2_CHANGE_TO_EXCLUDE; stotal = scount = 0; psf_list = sdeleted ? &pmc->mca_tomb : &pmc->mca_sources; if (!rcu_access_pointer(*psf_list)) goto empty_source; pmr = skb ? (struct mld2_report *)skb_transport_header(skb) : NULL; /* EX and TO_EX get a fresh packet, if needed */ if (truncate) { if (pmr && pmr->mld2r_ngrec && AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) { if (skb) mld_sendpack(skb); skb = mld_newpack(idev, mtu); } } first = 1; psf_prev = NULL; for (psf = mc_dereference(*psf_list, idev); psf; psf = psf_next) { struct in6_addr *psrc; psf_next = mc_dereference(psf->sf_next, idev); if (!is_in(pmc, psf, type, gdeleted, sdeleted) && !crsend) { psf_prev = psf; continue; } /* Based on RFC3810 6.1. Should not send source-list change * records when there is a filter mode change. */ if (((gdeleted && pmc->mca_sfmode == MCAST_EXCLUDE) || (!gdeleted && pmc->mca_crcount)) && (type == MLD2_ALLOW_NEW_SOURCES || type == MLD2_BLOCK_OLD_SOURCES) && psf->sf_crcount) goto decrease_sf_crcount; /* clear marks on query responses */ if (isquery) psf->sf_gsresp = 0; if (AVAILABLE(skb) < sizeof(*psrc) + first*sizeof(struct mld2_grec)) { if (truncate && !first) break; /* truncate these */ if (pgr) pgr->grec_nsrcs = htons(scount); if (skb) mld_sendpack(skb); skb = mld_newpack(idev, mtu); first = 1; scount = 0; } if (first) { skb = add_grhead(skb, pmc, type, &pgr, mtu); first = 0; } if (!skb) return NULL; psrc = skb_put(skb, sizeof(*psrc)); *psrc = psf->sf_addr; scount++; stotal++; if ((type == MLD2_ALLOW_NEW_SOURCES || type == MLD2_BLOCK_OLD_SOURCES) && psf->sf_crcount) { decrease_sf_crcount: psf->sf_crcount--; if ((sdeleted || gdeleted) && psf->sf_crcount == 0) { if (psf_prev) rcu_assign_pointer(psf_prev->sf_next, mc_dereference(psf->sf_next, idev)); else rcu_assign_pointer(*psf_list, mc_dereference(psf->sf_next, idev)); kfree_rcu(psf, rcu); continue; } } psf_prev = psf; } empty_source: if (!stotal) { if (type == MLD2_ALLOW_NEW_SOURCES || type == MLD2_BLOCK_OLD_SOURCES) return skb; if (pmc->mca_crcount || isquery || crsend) { /* make sure we have room for group header */ if (skb && AVAILABLE(skb) < sizeof(struct mld2_grec)) { mld_sendpack(skb); skb = NULL; /* add_grhead will get a new one */ } skb = add_grhead(skb, pmc, type, &pgr, mtu); } } if (pgr) pgr->grec_nsrcs = htons(scount); if (isquery) pmc->mca_flags &= ~MAF_GSQUERY; /* clear query state */ return skb; } /* called with mc_lock */ static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc) { struct sk_buff *skb = NULL; int type; if (!pmc) { for_each_mc_mclock(idev, pmc) { if (pmc->mca_flags & MAF_NOREPORT) continue; if (pmc->mca_sfcount[MCAST_EXCLUDE]) type = MLD2_MODE_IS_EXCLUDE; else type = MLD2_MODE_IS_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0, 0); } } else { if (pmc->mca_sfcount[MCAST_EXCLUDE]) type = MLD2_MODE_IS_EXCLUDE; else type = MLD2_MODE_IS_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0, 0); } if (skb) mld_sendpack(skb); } /* * remove zero-count source records from a source filter list * called with mc_lock */ static void mld_clear_zeros(struct ip6_sf_list __rcu **ppsf, struct inet6_dev *idev) { struct ip6_sf_list *psf_prev, *psf_next, *psf; psf_prev = NULL; for (psf = mc_dereference(*ppsf, idev); psf; psf = psf_next) { psf_next = mc_dereference(psf->sf_next, idev); if (psf->sf_crcount == 0) { if (psf_prev) rcu_assign_pointer(psf_prev->sf_next, mc_dereference(psf->sf_next, idev)); else rcu_assign_pointer(*ppsf, mc_dereference(psf->sf_next, idev)); kfree_rcu(psf, rcu); } else { psf_prev = psf; } } } /* called with mc_lock */ static void mld_send_cr(struct inet6_dev *idev) { struct ifmcaddr6 *pmc, *pmc_prev, *pmc_next; struct sk_buff *skb = NULL; int type, dtype; /* deleted MCA's */ pmc_prev = NULL; for (pmc = mc_dereference(idev->mc_tomb, idev); pmc; pmc = pmc_next) { pmc_next = mc_dereference(pmc->next, idev); if (pmc->mca_sfmode == MCAST_INCLUDE) { type = MLD2_BLOCK_OLD_SOURCES; dtype = MLD2_BLOCK_OLD_SOURCES; skb = add_grec(skb, pmc, type, 1, 0, 0); skb = add_grec(skb, pmc, dtype, 1, 1, 0); } if (pmc->mca_crcount) { if (pmc->mca_sfmode == MCAST_EXCLUDE) { type = MLD2_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 1, 0, 0); } pmc->mca_crcount--; if (pmc->mca_crcount == 0) { mld_clear_zeros(&pmc->mca_tomb, idev); mld_clear_zeros(&pmc->mca_sources, idev); } } if (pmc->mca_crcount == 0 && !rcu_access_pointer(pmc->mca_tomb) && !rcu_access_pointer(pmc->mca_sources)) { if (pmc_prev) rcu_assign_pointer(pmc_prev->next, pmc_next); else rcu_assign_pointer(idev->mc_tomb, pmc_next); in6_dev_put(pmc->idev); kfree_rcu(pmc, rcu); } else pmc_prev = pmc; } /* change recs */ for_each_mc_mclock(idev, pmc) { if (pmc->mca_sfcount[MCAST_EXCLUDE]) { type = MLD2_BLOCK_OLD_SOURCES; dtype = MLD2_ALLOW_NEW_SOURCES; } else { type = MLD2_ALLOW_NEW_SOURCES; dtype = MLD2_BLOCK_OLD_SOURCES; } skb = add_grec(skb, pmc, type, 0, 0, 0); skb = add_grec(skb, pmc, dtype, 0, 1, 0); /* deleted sources */ /* filter mode changes */ if (pmc->mca_crcount) { if (pmc->mca_sfmode == MCAST_EXCLUDE) type = MLD2_CHANGE_TO_EXCLUDE; else type = MLD2_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0, 0); pmc->mca_crcount--; } } if (!skb) return; (void) mld_sendpack(skb); } static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) { struct net *net = dev_net(dev); struct sock *sk = net->ipv6.igmp_sk; struct inet6_dev *idev; struct sk_buff *skb; struct mld_msg *hdr; const struct in6_addr *snd_addr, *saddr; struct in6_addr addr_buf; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; int err, len, payload_len, full_len; u8 ra[8] = { IPPROTO_ICMPV6, 0, IPV6_TLV_ROUTERALERT, 2, 0, 0, IPV6_TLV_PADN, 0 }; struct flowi6 fl6; struct dst_entry *dst; if (type == ICMPV6_MGM_REDUCTION) snd_addr = &in6addr_linklocal_allrouters; else snd_addr = addr; len = sizeof(struct icmp6hdr) + sizeof(struct in6_addr); payload_len = len + sizeof(ra); full_len = sizeof(struct ipv6hdr) + payload_len; rcu_read_lock(); IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_OUTREQUESTS); rcu_read_unlock(); skb = sock_alloc_send_skb(sk, hlen + tlen + full_len, 1, &err); if (!skb) { rcu_read_lock(); IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); return; } skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, hlen); if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: * use unspecified address as the source address * when a valid link-local address is not available. */ saddr = &in6addr_any; } else saddr = &addr_buf; ip6_mc_hdr(sk, skb, dev, saddr, snd_addr, NEXTHDR_HOP, payload_len); skb_put_data(skb, ra, sizeof(ra)); hdr = skb_put_zero(skb, sizeof(struct mld_msg)); hdr->mld_type = type; hdr->mld_mca = *addr; hdr->mld_cksum = csum_ipv6_magic(saddr, snd_addr, len, IPPROTO_ICMPV6, csum_partial(hdr, len, 0)); rcu_read_lock(); idev = __in6_dev_get(skb->dev); icmpv6_flow_init(sk, &fl6, type, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); dst = icmp6_dst_alloc(skb->dev, &fl6); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto err_out; } skb_dst_set(skb, dst); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb->dev, dst_output); out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } else IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); return; err_out: kfree_skb(skb); goto out; } /* called with mc_lock */ static void mld_send_initial_cr(struct inet6_dev *idev) { struct sk_buff *skb; struct ifmcaddr6 *pmc; int type; if (mld_in_v1_mode(idev)) return; skb = NULL; for_each_mc_mclock(idev, pmc) { if (pmc->mca_sfcount[MCAST_EXCLUDE]) type = MLD2_CHANGE_TO_EXCLUDE; else type = MLD2_ALLOW_NEW_SOURCES; skb = add_grec(skb, pmc, type, 0, 0, 1); } if (skb) mld_sendpack(skb); } void ipv6_mc_dad_complete(struct inet6_dev *idev) { mutex_lock(&idev->mc_lock); idev->mc_dad_count = idev->mc_qrv; if (idev->mc_dad_count) { mld_send_initial_cr(idev); idev->mc_dad_count--; if (idev->mc_dad_count) mld_dad_start_work(idev, unsolicited_report_interval(idev)); } mutex_unlock(&idev->mc_lock); } static void mld_dad_work(struct work_struct *work) { struct inet6_dev *idev = container_of(to_delayed_work(work), struct inet6_dev, mc_dad_work); mutex_lock(&idev->mc_lock); mld_send_initial_cr(idev); if (idev->mc_dad_count) { idev->mc_dad_count--; if (idev->mc_dad_count) mld_dad_start_work(idev, unsolicited_report_interval(idev)); } mutex_unlock(&idev->mc_lock); in6_dev_put(idev); } /* called with mc_lock */ static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode, const struct in6_addr *psfsrc) { struct ip6_sf_list *psf, *psf_prev; int rv = 0; psf_prev = NULL; for_each_psf_mclock(pmc, psf) { if (ipv6_addr_equal(&psf->sf_addr, psfsrc)) break; psf_prev = psf; } if (!psf || psf->sf_count[sfmode] == 0) { /* source filter not found, or count wrong => bug */ return -ESRCH; } psf->sf_count[sfmode]--; if (!psf->sf_count[MCAST_INCLUDE] && !psf->sf_count[MCAST_EXCLUDE]) { struct inet6_dev *idev = pmc->idev; /* no more filters for this source */ if (psf_prev) rcu_assign_pointer(psf_prev->sf_next, mc_dereference(psf->sf_next, idev)); else rcu_assign_pointer(pmc->mca_sources, mc_dereference(psf->sf_next, idev)); if (psf->sf_oldin && !(pmc->mca_flags & MAF_NOREPORT) && !mld_in_v1_mode(idev)) { psf->sf_crcount = idev->mc_qrv; rcu_assign_pointer(psf->sf_next, mc_dereference(pmc->mca_tomb, idev)); rcu_assign_pointer(pmc->mca_tomb, psf); rv = 1; } else { kfree_rcu(psf, rcu); } } return rv; } /* called with mc_lock */ static int ip6_mc_del_src(struct inet6_dev *idev, const struct in6_addr *pmca, int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta) { struct ifmcaddr6 *pmc; int changerec = 0; int i, err; if (!idev) return -ENODEV; for_each_mc_mclock(idev, pmc) { if (ipv6_addr_equal(pmca, &pmc->mca_addr)) break; } if (!pmc) return -ESRCH; sf_markstate(pmc); if (!delta) { if (!pmc->mca_sfcount[sfmode]) return -EINVAL; pmc->mca_sfcount[sfmode]--; } err = 0; for (i = 0; i < sfcount; i++) { int rv = ip6_mc_del1_src(pmc, sfmode, &psfsrc[i]); changerec |= rv > 0; if (!err && rv < 0) err = rv; } if (pmc->mca_sfmode == MCAST_EXCLUDE && pmc->mca_sfcount[MCAST_EXCLUDE] == 0 && pmc->mca_sfcount[MCAST_INCLUDE]) { struct ip6_sf_list *psf; /* filter mode change */ pmc->mca_sfmode = MCAST_INCLUDE; pmc->mca_crcount = idev->mc_qrv; idev->mc_ifc_count = pmc->mca_crcount; for_each_psf_mclock(pmc, psf) psf->sf_crcount = 0; mld_ifc_event(pmc->idev); } else if (sf_setstate(pmc) || changerec) { mld_ifc_event(pmc->idev); } return err; } /* * Add multicast single-source filter to the interface list * called with mc_lock */ static int ip6_mc_add1_src(struct ifmcaddr6 *pmc, int sfmode, const struct in6_addr *psfsrc) { struct ip6_sf_list *psf, *psf_prev; psf_prev = NULL; for_each_psf_mclock(pmc, psf) { if (ipv6_addr_equal(&psf->sf_addr, psfsrc)) break; psf_prev = psf; } if (!psf) { psf = kzalloc(sizeof(*psf), GFP_KERNEL); if (!psf) return -ENOBUFS; psf->sf_addr = *psfsrc; if (psf_prev) { rcu_assign_pointer(psf_prev->sf_next, psf); } else { rcu_assign_pointer(pmc->mca_sources, psf); } } psf->sf_count[sfmode]++; return 0; } /* called with mc_lock */ static void sf_markstate(struct ifmcaddr6 *pmc) { struct ip6_sf_list *psf; int mca_xcount = pmc->mca_sfcount[MCAST_EXCLUDE]; for_each_psf_mclock(pmc, psf) { if (pmc->mca_sfcount[MCAST_EXCLUDE]) { psf->sf_oldin = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; } else { psf->sf_oldin = psf->sf_count[MCAST_INCLUDE] != 0; } } } /* called with mc_lock */ static int sf_setstate(struct ifmcaddr6 *pmc) { struct ip6_sf_list *psf, *dpsf; int mca_xcount = pmc->mca_sfcount[MCAST_EXCLUDE]; int qrv = pmc->idev->mc_qrv; int new_in, rv; rv = 0; for_each_psf_mclock(pmc, psf) { if (pmc->mca_sfcount[MCAST_EXCLUDE]) { new_in = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; } else new_in = psf->sf_count[MCAST_INCLUDE] != 0; if (new_in) { if (!psf->sf_oldin) { struct ip6_sf_list *prev = NULL; for_each_psf_tomb(pmc, dpsf) { if (ipv6_addr_equal(&dpsf->sf_addr, &psf->sf_addr)) break; prev = dpsf; } if (dpsf) { if (prev) rcu_assign_pointer(prev->sf_next, mc_dereference(dpsf->sf_next, pmc->idev)); else rcu_assign_pointer(pmc->mca_tomb, mc_dereference(dpsf->sf_next, pmc->idev)); kfree_rcu(dpsf, rcu); } psf->sf_crcount = qrv; rv++; } } else if (psf->sf_oldin) { psf->sf_crcount = 0; /* * add or update "delete" records if an active filter * is now inactive */ for_each_psf_tomb(pmc, dpsf) if (ipv6_addr_equal(&dpsf->sf_addr, &psf->sf_addr)) break; if (!dpsf) { dpsf = kmalloc(sizeof(*dpsf), GFP_KERNEL); if (!dpsf) continue; *dpsf = *psf; rcu_assign_pointer(dpsf->sf_next, mc_dereference(pmc->mca_tomb, pmc->idev)); rcu_assign_pointer(pmc->mca_tomb, dpsf); } dpsf->sf_crcount = qrv; rv++; } } return rv; } /* * Add multicast source filter list to the interface list * called with mc_lock */ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca, int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta) { struct ifmcaddr6 *pmc; int isexclude; int i, err; if (!idev) return -ENODEV; for_each_mc_mclock(idev, pmc) { if (ipv6_addr_equal(pmca, &pmc->mca_addr)) break; } if (!pmc) return -ESRCH; sf_markstate(pmc); isexclude = pmc->mca_sfmode == MCAST_EXCLUDE; if (!delta) pmc->mca_sfcount[sfmode]++; err = 0; for (i = 0; i < sfcount; i++) { err = ip6_mc_add1_src(pmc, sfmode, &psfsrc[i]); if (err) break; } if (err) { int j; if (!delta) pmc->mca_sfcount[sfmode]--; for (j = 0; j < i; j++) ip6_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->mca_sfcount[MCAST_EXCLUDE] != 0)) { struct ip6_sf_list *psf; /* filter mode change */ if (pmc->mca_sfcount[MCAST_EXCLUDE]) pmc->mca_sfmode = MCAST_EXCLUDE; else if (pmc->mca_sfcount[MCAST_INCLUDE]) pmc->mca_sfmode = MCAST_INCLUDE; /* else no filters; keep old mode for reports */ pmc->mca_crcount = idev->mc_qrv; idev->mc_ifc_count = pmc->mca_crcount; for_each_psf_mclock(pmc, psf) psf->sf_crcount = 0; mld_ifc_event(idev); } else if (sf_setstate(pmc)) { mld_ifc_event(idev); } return err; } /* called with mc_lock */ static void ip6_mc_clear_src(struct ifmcaddr6 *pmc) { struct ip6_sf_list *psf, *nextpsf; for (psf = mc_dereference(pmc->mca_tomb, pmc->idev); psf; psf = nextpsf) { nextpsf = mc_dereference(psf->sf_next, pmc->idev); kfree_rcu(psf, rcu); } RCU_INIT_POINTER(pmc->mca_tomb, NULL); for (psf = mc_dereference(pmc->mca_sources, pmc->idev); psf; psf = nextpsf) { nextpsf = mc_dereference(psf->sf_next, pmc->idev); kfree_rcu(psf, rcu); } RCU_INIT_POINTER(pmc->mca_sources, NULL); pmc->mca_sfmode = MCAST_EXCLUDE; pmc->mca_sfcount[MCAST_INCLUDE] = 0; pmc->mca_sfcount[MCAST_EXCLUDE] = 1; } /* called with mc_lock */ static void igmp6_join_group(struct ifmcaddr6 *ma) { unsigned long delay; if (ma->mca_flags & MAF_NOREPORT) return; igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REPORT); delay = get_random_u32_below(unsolicited_report_interval(ma->idev)); if (cancel_delayed_work(&ma->mca_work)) { refcount_dec(&ma->mca_refcnt); delay = ma->mca_work.timer.expires - jiffies; } if (!mod_delayed_work(mld_wq, &ma->mca_work, delay)) refcount_inc(&ma->mca_refcnt); ma->mca_flags |= MAF_TIMER_RUNNING | MAF_LAST_REPORTER; } static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, struct inet6_dev *idev) { struct ip6_sf_socklist *psl; int err; psl = sock_dereference(iml->sflist, sk); if (idev) mutex_lock(&idev->mc_lock); if (!psl) { /* any-source empty exclude case */ err = ip6_mc_del_src(idev, &iml->addr, iml->sfmode, 0, NULL, 0); } else { err = ip6_mc_del_src(idev, &iml->addr, iml->sfmode, psl->sl_count, psl->sl_addr, 0); RCU_INIT_POINTER(iml->sflist, NULL); atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); kfree_rcu(psl, rcu); } if (idev) mutex_unlock(&idev->mc_lock); return err; } /* called with mc_lock */ static void igmp6_leave_group(struct ifmcaddr6 *ma) { if (mld_in_v1_mode(ma->idev)) { if (ma->mca_flags & MAF_LAST_REPORTER) { igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REDUCTION); } } else { mld_add_delrec(ma->idev, ma); mld_ifc_event(ma->idev); } } static void mld_gq_work(struct work_struct *work) { struct inet6_dev *idev = container_of(to_delayed_work(work), struct inet6_dev, mc_gq_work); mutex_lock(&idev->mc_lock); mld_send_report(idev, NULL); idev->mc_gq_running = 0; mutex_unlock(&idev->mc_lock); in6_dev_put(idev); } static void mld_ifc_work(struct work_struct *work) { struct inet6_dev *idev = container_of(to_delayed_work(work), struct inet6_dev, mc_ifc_work); mutex_lock(&idev->mc_lock); mld_send_cr(idev); if (idev->mc_ifc_count) { idev->mc_ifc_count--; if (idev->mc_ifc_count) mld_ifc_start_work(idev, unsolicited_report_interval(idev)); } mutex_unlock(&idev->mc_lock); in6_dev_put(idev); } /* called with mc_lock */ static void mld_ifc_event(struct inet6_dev *idev) { if (mld_in_v1_mode(idev)) return; idev->mc_ifc_count = idev->mc_qrv; mld_ifc_start_work(idev, 1); } static void mld_mca_work(struct work_struct *work) { struct ifmcaddr6 *ma = container_of(to_delayed_work(work), struct ifmcaddr6, mca_work); mutex_lock(&ma->idev->mc_lock); if (mld_in_v1_mode(ma->idev)) igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REPORT); else mld_send_report(ma->idev, ma); ma->mca_flags |= MAF_LAST_REPORTER; ma->mca_flags &= ~MAF_TIMER_RUNNING; mutex_unlock(&ma->idev->mc_lock); ma_put(ma); } /* Device changing type */ void ipv6_mc_unmap(struct inet6_dev *idev) { struct ifmcaddr6 *i; /* Install multicast list, except for all-nodes (already installed) */ mutex_lock(&idev->mc_lock); for_each_mc_mclock(idev, i) igmp6_group_dropped(i); mutex_unlock(&idev->mc_lock); } void ipv6_mc_remap(struct inet6_dev *idev) { ipv6_mc_up(idev); } /* Device going down */ void ipv6_mc_down(struct inet6_dev *idev) { struct ifmcaddr6 *i; mutex_lock(&idev->mc_lock); /* Withdraw multicast list */ for_each_mc_mclock(idev, i) igmp6_group_dropped(i); mutex_unlock(&idev->mc_lock); /* Should stop work after group drop. or we will * start work again in mld_ifc_event() */ mld_query_stop_work(idev); mld_report_stop_work(idev); mutex_lock(&idev->mc_lock); mld_ifc_stop_work(idev); mld_gq_stop_work(idev); mutex_unlock(&idev->mc_lock); mld_dad_stop_work(idev); } static void ipv6_mc_reset(struct inet6_dev *idev) { idev->mc_qrv = sysctl_mld_qrv; idev->mc_qi = MLD_QI_DEFAULT; idev->mc_qri = MLD_QRI_DEFAULT; idev->mc_v1_seen = 0; idev->mc_maxdelay = unsolicited_report_interval(idev); } /* Device going up */ void ipv6_mc_up(struct inet6_dev *idev) { struct ifmcaddr6 *i; /* Install multicast list, except for all-nodes (already installed) */ ipv6_mc_reset(idev); mutex_lock(&idev->mc_lock); for_each_mc_mclock(idev, i) { mld_del_delrec(idev, i); igmp6_group_added(i); } mutex_unlock(&idev->mc_lock); } /* IPv6 device initialization. */ void ipv6_mc_init_dev(struct inet6_dev *idev) { idev->mc_gq_running = 0; INIT_DELAYED_WORK(&idev->mc_gq_work, mld_gq_work); RCU_INIT_POINTER(idev->mc_tomb, NULL); idev->mc_ifc_count = 0; INIT_DELAYED_WORK(&idev->mc_ifc_work, mld_ifc_work); INIT_DELAYED_WORK(&idev->mc_dad_work, mld_dad_work); INIT_DELAYED_WORK(&idev->mc_query_work, mld_query_work); INIT_DELAYED_WORK(&idev->mc_report_work, mld_report_work); skb_queue_head_init(&idev->mc_query_queue); skb_queue_head_init(&idev->mc_report_queue); spin_lock_init(&idev->mc_query_lock); spin_lock_init(&idev->mc_report_lock); mutex_init(&idev->mc_lock); ipv6_mc_reset(idev); } /* * Device is about to be destroyed: clean up. */ void ipv6_mc_destroy_dev(struct inet6_dev *idev) { struct ifmcaddr6 *i; /* Deactivate works */ ipv6_mc_down(idev); mutex_lock(&idev->mc_lock); mld_clear_delrec(idev); mutex_unlock(&idev->mc_lock); mld_clear_query(idev); mld_clear_report(idev); /* Delete all-nodes address. */ /* We cannot call ipv6_dev_mc_dec() directly, our caller in * addrconf.c has NULL'd out dev->ip6_ptr so in6_dev_get() will * fail. */ __ipv6_dev_mc_dec(idev, &in6addr_linklocal_allnodes); if (idev->cnf.forwarding) __ipv6_dev_mc_dec(idev, &in6addr_linklocal_allrouters); mutex_lock(&idev->mc_lock); while ((i = mc_dereference(idev->mc_list, idev))) { rcu_assign_pointer(idev->mc_list, mc_dereference(i->next, idev)); ip6_mc_clear_src(i); ma_put(i); } mutex_unlock(&idev->mc_lock); } static void ipv6_mc_rejoin_groups(struct inet6_dev *idev) { struct ifmcaddr6 *pmc; ASSERT_RTNL(); mutex_lock(&idev->mc_lock); if (mld_in_v1_mode(idev)) { for_each_mc_mclock(idev, pmc) igmp6_join_group(pmc); } else { mld_send_report(idev, NULL); } mutex_unlock(&idev->mc_lock); } static int ipv6_mc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct inet6_dev *idev = __in6_dev_get(dev); switch (event) { case NETDEV_RESEND_IGMP: if (idev) ipv6_mc_rejoin_groups(idev); break; default: break; } return NOTIFY_DONE; } static struct notifier_block igmp6_netdev_notifier = { .notifier_call = ipv6_mc_netdev_event, }; #ifdef CONFIG_PROC_FS struct igmp6_mc_iter_state { struct seq_net_private p; struct net_device *dev; struct inet6_dev *idev; }; #define igmp6_mc_seq_private(seq) ((struct igmp6_mc_iter_state *)(seq)->private) static inline struct ifmcaddr6 *igmp6_mc_get_first(struct seq_file *seq) { struct ifmcaddr6 *im = NULL; struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); struct net *net = seq_file_net(seq); state->idev = NULL; for_each_netdev_rcu(net, state->dev) { struct inet6_dev *idev; idev = __in6_dev_get(state->dev); if (!idev) continue; im = rcu_dereference(idev->mc_list); if (im) { state->idev = idev; break; } } return im; } static struct ifmcaddr6 *igmp6_mc_get_next(struct seq_file *seq, struct ifmcaddr6 *im) { struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); im = rcu_dereference(im->next); while (!im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; break; } state->idev = __in6_dev_get(state->dev); if (!state->idev) continue; im = rcu_dereference(state->idev->mc_list); } return im; } static struct ifmcaddr6 *igmp6_mc_get_idx(struct seq_file *seq, loff_t pos) { struct ifmcaddr6 *im = igmp6_mc_get_first(seq); if (im) while (pos && (im = igmp6_mc_get_next(seq, im)) != NULL) --pos; return pos ? NULL : im; } static void *igmp6_mc_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); return igmp6_mc_get_idx(seq, *pos); } static void *igmp6_mc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ifmcaddr6 *im = igmp6_mc_get_next(seq, v); ++*pos; return im; } static void igmp6_mc_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); if (likely(state->idev)) state->idev = NULL; state->dev = NULL; rcu_read_unlock(); } static int igmp6_mc_seq_show(struct seq_file *seq, void *v) { struct ifmcaddr6 *im = (struct ifmcaddr6 *)v; struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); seq_printf(seq, "%-4d %-15s %pi6 %5d %08X %ld\n", state->dev->ifindex, state->dev->name, &im->mca_addr, im->mca_users, im->mca_flags, (im->mca_flags & MAF_TIMER_RUNNING) ? jiffies_to_clock_t(im->mca_work.timer.expires - jiffies) : 0); return 0; } static const struct seq_operations igmp6_mc_seq_ops = { .start = igmp6_mc_seq_start, .next = igmp6_mc_seq_next, .stop = igmp6_mc_seq_stop, .show = igmp6_mc_seq_show, }; struct igmp6_mcf_iter_state { struct seq_net_private p; struct net_device *dev; struct inet6_dev *idev; struct ifmcaddr6 *im; }; #define igmp6_mcf_seq_private(seq) ((struct igmp6_mcf_iter_state *)(seq)->private) static inline struct ip6_sf_list *igmp6_mcf_get_first(struct seq_file *seq) { struct ip6_sf_list *psf = NULL; struct ifmcaddr6 *im = NULL; struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); struct net *net = seq_file_net(seq); state->idev = NULL; state->im = NULL; for_each_netdev_rcu(net, state->dev) { struct inet6_dev *idev; idev = __in6_dev_get(state->dev); if (unlikely(idev == NULL)) continue; im = rcu_dereference(idev->mc_list); if (likely(im)) { psf = rcu_dereference(im->mca_sources); if (likely(psf)) { state->im = im; state->idev = idev; break; } } } return psf; } static struct ip6_sf_list *igmp6_mcf_get_next(struct seq_file *seq, struct ip6_sf_list *psf) { struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); psf = rcu_dereference(psf->sf_next); while (!psf) { state->im = rcu_dereference(state->im->next); while (!state->im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; goto out; } state->idev = __in6_dev_get(state->dev); if (!state->idev) continue; state->im = rcu_dereference(state->idev->mc_list); } psf = rcu_dereference(state->im->mca_sources); } out: return psf; } static struct ip6_sf_list *igmp6_mcf_get_idx(struct seq_file *seq, loff_t pos) { struct ip6_sf_list *psf = igmp6_mcf_get_first(seq); if (psf) while (pos && (psf = igmp6_mcf_get_next(seq, psf)) != NULL) --pos; return pos ? NULL : psf; } static void *igmp6_mcf_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); return *pos ? igmp6_mcf_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *igmp6_mcf_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip6_sf_list *psf; if (v == SEQ_START_TOKEN) psf = igmp6_mcf_get_first(seq); else psf = igmp6_mcf_get_next(seq, v); ++*pos; return psf; } static void igmp6_mcf_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); if (likely(state->im)) state->im = NULL; if (likely(state->idev)) state->idev = NULL; state->dev = NULL; rcu_read_unlock(); } static int igmp6_mcf_seq_show(struct seq_file *seq, void *v) { struct ip6_sf_list *psf = (struct ip6_sf_list *)v; struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); if (v == SEQ_START_TOKEN) { seq_puts(seq, "Idx Device Multicast Address Source Address INC EXC\n"); } else { seq_printf(seq, "%3d %6.6s %pi6 %pi6 %6lu %6lu\n", state->dev->ifindex, state->dev->name, &state->im->mca_addr, &psf->sf_addr, psf->sf_count[MCAST_INCLUDE], psf->sf_count[MCAST_EXCLUDE]); } return 0; } static const struct seq_operations igmp6_mcf_seq_ops = { .start = igmp6_mcf_seq_start, .next = igmp6_mcf_seq_next, .stop = igmp6_mcf_seq_stop, .show = igmp6_mcf_seq_show, }; static int __net_init igmp6_proc_init(struct net *net) { int err; err = -ENOMEM; if (!proc_create_net("igmp6", 0444, net->proc_net, &igmp6_mc_seq_ops, sizeof(struct igmp6_mc_iter_state))) goto out; if (!proc_create_net("mcfilter6", 0444, net->proc_net, &igmp6_mcf_seq_ops, sizeof(struct igmp6_mcf_iter_state))) goto out_proc_net_igmp6; err = 0; out: return err; out_proc_net_igmp6: remove_proc_entry("igmp6", net->proc_net); goto out; } static void __net_exit igmp6_proc_exit(struct net *net) { remove_proc_entry("mcfilter6", net->proc_net); remove_proc_entry("igmp6", net->proc_net); } #else static inline int igmp6_proc_init(struct net *net) { return 0; } static inline void igmp6_proc_exit(struct net *net) { } #endif static int __net_init igmp6_net_init(struct net *net) { int err; err = inet_ctl_sock_create(&net->ipv6.igmp_sk, PF_INET6, SOCK_RAW, IPPROTO_ICMPV6, net); if (err < 0) { pr_err("Failed to initialize the IGMP6 control socket (err %d)\n", err); goto out; } inet6_sk(net->ipv6.igmp_sk)->hop_limit = 1; net->ipv6.igmp_sk->sk_allocation = GFP_KERNEL; err = inet_ctl_sock_create(&net->ipv6.mc_autojoin_sk, PF_INET6, SOCK_RAW, IPPROTO_ICMPV6, net); if (err < 0) { pr_err("Failed to initialize the IGMP6 autojoin socket (err %d)\n", err); goto out_sock_create; } err = igmp6_proc_init(net); if (err) goto out_sock_create_autojoin; return 0; out_sock_create_autojoin: inet_ctl_sock_destroy(net->ipv6.mc_autojoin_sk); out_sock_create: inet_ctl_sock_destroy(net->ipv6.igmp_sk); out: return err; } static void __net_exit igmp6_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.igmp_sk); inet_ctl_sock_destroy(net->ipv6.mc_autojoin_sk); igmp6_proc_exit(net); } static struct pernet_operations igmp6_net_ops = { .init = igmp6_net_init, .exit = igmp6_net_exit, }; int __init igmp6_init(void) { int err; err = register_pernet_subsys(&igmp6_net_ops); if (err) return err; mld_wq = create_workqueue("mld"); if (!mld_wq) { unregister_pernet_subsys(&igmp6_net_ops); return -ENOMEM; } return err; } int __init igmp6_late_init(void) { return register_netdevice_notifier(&igmp6_netdev_notifier); } void igmp6_cleanup(void) { unregister_pernet_subsys(&igmp6_net_ops); destroy_workqueue(mld_wq); } void igmp6_late_cleanup(void) { unregister_netdevice_notifier(&igmp6_netdev_notifier); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIMEKEEPING_H #define _LINUX_TIMEKEEPING_H #include <linux/errno.h> #include <linux/clocksource_ids.h> #include <linux/ktime.h> /* Included from linux/ktime.h */ void timekeeping_init(void); extern int timekeeping_suspended; /* Architecture timer tick functions: */ extern void legacy_timer_tick(unsigned long ticks); /* * Get and set timeofday */ extern int do_settimeofday64(const struct timespec64 *ts); extern int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz); /* * ktime_get() family - read the current time in a multitude of ways. * * The default time reference is CLOCK_MONOTONIC, starting at * boot time but not counting the time spent in suspend. * For other references, use the functions with "real", "clocktai", * "boottime" and "raw" suffixes. * * To get the time in a different format, use the ones with * "ns", "ts64" and "seconds" suffix. * * See Documentation/core-api/timekeeping.rst for more details. */ /* * timespec64 based interfaces */ extern void ktime_get_raw_ts64(struct timespec64 *ts); extern void ktime_get_ts64(struct timespec64 *ts); extern void ktime_get_real_ts64(struct timespec64 *tv); extern void ktime_get_coarse_ts64(struct timespec64 *ts); extern void ktime_get_coarse_real_ts64(struct timespec64 *ts); /* Multigrain timestamp interfaces */ extern void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts); extern void ktime_get_real_ts64_mg(struct timespec64 *ts); extern unsigned long timekeeping_get_mg_floor_swaps(void); void getboottime64(struct timespec64 *ts); /* * time64_t base interfaces */ extern time64_t ktime_get_seconds(void); extern time64_t __ktime_get_real_seconds(void); extern time64_t ktime_get_real_seconds(void); /* * ktime_t based interfaces */ enum tk_offsets { TK_OFFS_REAL, TK_OFFS_BOOT, TK_OFFS_TAI, TK_OFFS_MAX, }; extern ktime_t ktime_get(void); extern ktime_t ktime_get_with_offset(enum tk_offsets offs); extern ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs); extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs); extern ktime_t ktime_get_raw(void); extern u32 ktime_get_resolution_ns(void); /** * ktime_get_real - get the real (wall-) time in ktime_t format * * Returns: real (wall) time in ktime_t format */ static inline ktime_t ktime_get_real(void) { return ktime_get_with_offset(TK_OFFS_REAL); } static inline ktime_t ktime_get_coarse_real(void) { return ktime_get_coarse_with_offset(TK_OFFS_REAL); } /** * ktime_get_boottime - Get monotonic time since boot in ktime_t format * * This is similar to CLOCK_MONTONIC/ktime_get, but also includes the * time spent in suspend. * * Returns: monotonic time since boot in ktime_t format */ static inline ktime_t ktime_get_boottime(void) { return ktime_get_with_offset(TK_OFFS_BOOT); } static inline ktime_t ktime_get_coarse_boottime(void) { return ktime_get_coarse_with_offset(TK_OFFS_BOOT); } /** * ktime_get_clocktai - Get the TAI time of day in ktime_t format * * Returns: the TAI time of day in ktime_t format */ static inline ktime_t ktime_get_clocktai(void) { return ktime_get_with_offset(TK_OFFS_TAI); } static inline ktime_t ktime_get_coarse_clocktai(void) { return ktime_get_coarse_with_offset(TK_OFFS_TAI); } static inline ktime_t ktime_get_coarse(void) { struct timespec64 ts; ktime_get_coarse_ts64(&ts); return timespec64_to_ktime(ts); } static inline u64 ktime_get_coarse_ns(void) { return ktime_to_ns(ktime_get_coarse()); } static inline u64 ktime_get_coarse_real_ns(void) { return ktime_to_ns(ktime_get_coarse_real()); } static inline u64 ktime_get_coarse_boottime_ns(void) { return ktime_to_ns(ktime_get_coarse_boottime()); } static inline u64 ktime_get_coarse_clocktai_ns(void) { return ktime_to_ns(ktime_get_coarse_clocktai()); } /** * ktime_mono_to_real - Convert monotonic time to clock realtime * @mono: monotonic time to convert * * Returns: time converted to realtime clock */ static inline ktime_t ktime_mono_to_real(ktime_t mono) { return ktime_mono_to_any(mono, TK_OFFS_REAL); } /** * ktime_get_ns - Get the current time in nanoseconds * * Returns: current time converted to nanoseconds */ static inline u64 ktime_get_ns(void) { return ktime_to_ns(ktime_get()); } /** * ktime_get_real_ns - Get the current real/wall time in nanoseconds * * Returns: current real time converted to nanoseconds */ static inline u64 ktime_get_real_ns(void) { return ktime_to_ns(ktime_get_real()); } /** * ktime_get_boottime_ns - Get the monotonic time since boot in nanoseconds * * Returns: current boottime converted to nanoseconds */ static inline u64 ktime_get_boottime_ns(void) { return ktime_to_ns(ktime_get_boottime()); } /** * ktime_get_clocktai_ns - Get the current TAI time of day in nanoseconds * * Returns: current TAI time converted to nanoseconds */ static inline u64 ktime_get_clocktai_ns(void) { return ktime_to_ns(ktime_get_clocktai()); } /** * ktime_get_raw_ns - Get the raw monotonic time in nanoseconds * * Returns: current raw monotonic time converted to nanoseconds */ static inline u64 ktime_get_raw_ns(void) { return ktime_to_ns(ktime_get_raw()); } extern u64 ktime_get_mono_fast_ns(void); extern u64 ktime_get_raw_fast_ns(void); extern u64 ktime_get_boot_fast_ns(void); extern u64 ktime_get_tai_fast_ns(void); extern u64 ktime_get_real_fast_ns(void); /* * timespec64/time64_t interfaces utilizing the ktime based ones * for API completeness, these could be implemented more efficiently * if needed. */ static inline void ktime_get_boottime_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_boottime()); } static inline void ktime_get_coarse_boottime_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_coarse_boottime()); } static inline time64_t ktime_get_boottime_seconds(void) { return ktime_divns(ktime_get_coarse_boottime(), NSEC_PER_SEC); } static inline void ktime_get_clocktai_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_clocktai()); } static inline void ktime_get_coarse_clocktai_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_coarse_clocktai()); } static inline time64_t ktime_get_clocktai_seconds(void) { return ktime_divns(ktime_get_coarse_clocktai(), NSEC_PER_SEC); } /* * RTC specific */ extern bool timekeeping_rtc_skipsuspend(void); extern bool timekeeping_rtc_skipresume(void); extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta); /** * struct ktime_timestamps - Simultaneous mono/boot/real timestamps * @mono: Monotonic timestamp * @boot: Boottime timestamp * @real: Realtime timestamp */ struct ktime_timestamps { u64 mono; u64 boot; u64 real; }; /** * struct system_time_snapshot - simultaneous raw/real time capture with * counter value * @cycles: Clocksource counter value to produce the system times * @real: Realtime system time * @boot: Boot time * @raw: Monotonic raw system time * @cs_id: Clocksource ID * @clock_was_set_seq: The sequence number of clock-was-set events * @cs_was_changed_seq: The sequence number of clocksource change events */ struct system_time_snapshot { u64 cycles; ktime_t real; ktime_t boot; ktime_t raw; enum clocksource_ids cs_id; unsigned int clock_was_set_seq; u8 cs_was_changed_seq; }; /** * struct system_device_crosststamp - system/device cross-timestamp * (synchronized capture) * @device: Device time * @sys_realtime: Realtime simultaneous with device time * @sys_monoraw: Monotonic raw simultaneous with device time */ struct system_device_crosststamp { ktime_t device; ktime_t sys_realtime; ktime_t sys_monoraw; }; /** * struct system_counterval_t - system counter value with the ID of the * corresponding clocksource * @cycles: System counter value * @cs_id: Clocksource ID corresponding to system counter value. Used by * timekeeping code to verify comparability of two cycle values. * The default ID, CSID_GENERIC, does not identify a specific * clocksource. * @use_nsecs: @cycles is in nanoseconds. */ struct system_counterval_t { u64 cycles; enum clocksource_ids cs_id; bool use_nsecs; }; extern bool ktime_real_to_base_clock(ktime_t treal, enum clocksource_ids base_id, u64 *cycles); extern bool timekeeping_clocksource_has_base(enum clocksource_ids id); /* * Get cross timestamp between system clock and device clock */ extern int get_device_system_crosststamp( int (*get_time_fn)(ktime_t *device_time, struct system_counterval_t *system_counterval, void *ctx), void *ctx, struct system_time_snapshot *history, struct system_device_crosststamp *xtstamp); /* * Simultaneously snapshot realtime and monotonic raw clocks */ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot); /* NMI safe mono/boot/realtime timestamps */ extern void ktime_get_fast_timestamps(struct ktime_timestamps *snap); /* * Persistent clock related interfaces */ extern int persistent_clock_is_local; extern void read_persistent_clock64(struct timespec64 *ts); void read_persistent_wall_and_boot_offset(struct timespec64 *wall_clock, struct timespec64 *boot_offset); #ifdef CONFIG_GENERIC_CMOS_UPDATE extern int update_persistent_clock64(struct timespec64 now); #endif #endif |
| 25 265 265 1 1 350 350 360 360 247 204 204 202 204 200 201 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PAGE_REF_H #define _LINUX_PAGE_REF_H #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/page-flags.h> #include <linux/tracepoint-defs.h> DECLARE_TRACEPOINT(page_ref_set); DECLARE_TRACEPOINT(page_ref_mod); DECLARE_TRACEPOINT(page_ref_mod_and_test); DECLARE_TRACEPOINT(page_ref_mod_and_return); DECLARE_TRACEPOINT(page_ref_mod_unless); DECLARE_TRACEPOINT(page_ref_freeze); DECLARE_TRACEPOINT(page_ref_unfreeze); #ifdef CONFIG_DEBUG_PAGE_REF /* * Ideally we would want to use the trace_<tracepoint>_enabled() helper * functions. But due to include header file issues, that is not * feasible. Instead we have to open code the static key functions. * * See trace_##name##_enabled(void) in include/linux/tracepoint.h */ #define page_ref_tracepoint_active(t) tracepoint_enabled(t) extern void __page_ref_set(struct page *page, int v); extern void __page_ref_mod(struct page *page, int v); extern void __page_ref_mod_and_test(struct page *page, int v, int ret); extern void __page_ref_mod_and_return(struct page *page, int v, int ret); extern void __page_ref_mod_unless(struct page *page, int v, int u); extern void __page_ref_freeze(struct page *page, int v, int ret); extern void __page_ref_unfreeze(struct page *page, int v); #else #define page_ref_tracepoint_active(t) false static inline void __page_ref_set(struct page *page, int v) { } static inline void __page_ref_mod(struct page *page, int v) { } static inline void __page_ref_mod_and_test(struct page *page, int v, int ret) { } static inline void __page_ref_mod_and_return(struct page *page, int v, int ret) { } static inline void __page_ref_mod_unless(struct page *page, int v, int u) { } static inline void __page_ref_freeze(struct page *page, int v, int ret) { } static inline void __page_ref_unfreeze(struct page *page, int v) { } #endif static inline int page_ref_count(const struct page *page) { return atomic_read(&page->_refcount); } /** * folio_ref_count - The reference count on this folio. * @folio: The folio. * * The refcount is usually incremented by calls to folio_get() and * decremented by calls to folio_put(). Some typical users of the * folio refcount: * * - Each reference from a page table * - The page cache * - Filesystem private data * - The LRU list * - Pipes * - Direct IO which references this page in the process address space * * Return: The number of references to this folio. */ static inline int folio_ref_count(const struct folio *folio) { return page_ref_count(&folio->page); } static inline int page_count(const struct page *page) { return folio_ref_count(page_folio(page)); } static inline void set_page_count(struct page *page, int v) { atomic_set(&page->_refcount, v); if (page_ref_tracepoint_active(page_ref_set)) __page_ref_set(page, v); } static inline void folio_set_count(struct folio *folio, int v) { set_page_count(&folio->page, v); } /* * Setup the page count before being freed into the page allocator for * the first time (boot or memory hotplug) */ static inline void init_page_count(struct page *page) { set_page_count(page, 1); } static inline void page_ref_add(struct page *page, int nr) { atomic_add(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, nr); } static inline void folio_ref_add(struct folio *folio, int nr) { page_ref_add(&folio->page, nr); } static inline void page_ref_sub(struct page *page, int nr) { atomic_sub(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, -nr); } static inline void folio_ref_sub(struct folio *folio, int nr) { page_ref_sub(&folio->page, nr); } static inline int folio_ref_sub_return(struct folio *folio, int nr) { int ret = atomic_sub_return(nr, &folio->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(&folio->page, -nr, ret); return ret; } static inline void page_ref_inc(struct page *page) { atomic_inc(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, 1); } static inline void folio_ref_inc(struct folio *folio) { page_ref_inc(&folio->page); } static inline void page_ref_dec(struct page *page) { atomic_dec(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, -1); } static inline void folio_ref_dec(struct folio *folio) { page_ref_dec(&folio->page); } static inline int page_ref_sub_and_test(struct page *page, int nr) { int ret = atomic_sub_and_test(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_test)) __page_ref_mod_and_test(page, -nr, ret); return ret; } static inline int folio_ref_sub_and_test(struct folio *folio, int nr) { return page_ref_sub_and_test(&folio->page, nr); } static inline int page_ref_inc_return(struct page *page) { int ret = atomic_inc_return(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(page, 1, ret); return ret; } static inline int folio_ref_inc_return(struct folio *folio) { return page_ref_inc_return(&folio->page); } static inline int page_ref_dec_and_test(struct page *page) { int ret = atomic_dec_and_test(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_test)) __page_ref_mod_and_test(page, -1, ret); return ret; } static inline int folio_ref_dec_and_test(struct folio *folio) { return page_ref_dec_and_test(&folio->page); } static inline int page_ref_dec_return(struct page *page) { int ret = atomic_dec_return(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(page, -1, ret); return ret; } static inline int folio_ref_dec_return(struct folio *folio) { return page_ref_dec_return(&folio->page); } static inline bool page_ref_add_unless(struct page *page, int nr, int u) { bool ret = false; rcu_read_lock(); /* avoid writing to the vmemmap area being remapped */ if (!page_is_fake_head(page) && page_ref_count(page) != u) ret = atomic_add_unless(&page->_refcount, nr, u); rcu_read_unlock(); if (page_ref_tracepoint_active(page_ref_mod_unless)) __page_ref_mod_unless(page, nr, ret); return ret; } static inline bool folio_ref_add_unless(struct folio *folio, int nr, int u) { return page_ref_add_unless(&folio->page, nr, u); } /** * folio_try_get - Attempt to increase the refcount on a folio. * @folio: The folio. * * If you do not already have a reference to a folio, you can attempt to * get one using this function. It may fail if, for example, the folio * has been freed since you found a pointer to it, or it is frozen for * the purposes of splitting or migration. * * Return: True if the reference count was successfully incremented. */ static inline bool folio_try_get(struct folio *folio) { return folio_ref_add_unless(folio, 1, 0); } static inline bool folio_ref_try_add(struct folio *folio, int count) { return folio_ref_add_unless(folio, count, 0); } static inline int page_ref_freeze(struct page *page, int count) { int ret = likely(atomic_cmpxchg(&page->_refcount, count, 0) == count); if (page_ref_tracepoint_active(page_ref_freeze)) __page_ref_freeze(page, count, ret); return ret; } static inline int folio_ref_freeze(struct folio *folio, int count) { return page_ref_freeze(&folio->page, count); } static inline void page_ref_unfreeze(struct page *page, int count) { VM_BUG_ON_PAGE(page_count(page) != 0, page); VM_BUG_ON(count == 0); atomic_set_release(&page->_refcount, count); if (page_ref_tracepoint_active(page_ref_unfreeze)) __page_ref_unfreeze(page, count); } static inline void folio_ref_unfreeze(struct folio *folio, int count) { page_ref_unfreeze(&folio->page, count); } #endif |
| 31 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 | // SPDX-License-Identifier: GPL-2.0-only /* * Guest PC manipulation helpers * * Copyright (C) 2012,2013 - ARM Ltd * Copyright (C) 2020 - Google LLC * Author: Marc Zyngier <maz@kernel.org> */ #ifndef __ARM64_KVM_HYP_ADJUST_PC_H__ #define __ARM64_KVM_HYP_ADJUST_PC_H__ #include <asm/kvm_emulate.h> #include <asm/kvm_host.h> static inline void kvm_skip_instr(struct kvm_vcpu *vcpu) { if (vcpu_mode_is_32bit(vcpu)) { kvm_skip_instr32(vcpu); } else { *vcpu_pc(vcpu) += 4; *vcpu_cpsr(vcpu) &= ~PSR_BTYPE_MASK; } /* advance the singlestep state machine */ *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; } /* * Skip an instruction which has been emulated at hyp while most guest sysregs * are live. */ static inline void __kvm_skip_instr(struct kvm_vcpu *vcpu) { *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); vcpu_gp_regs(vcpu)->pstate = read_sysreg_el2(SYS_SPSR); kvm_skip_instr(vcpu); write_sysreg_el2(vcpu_gp_regs(vcpu)->pstate, SYS_SPSR); write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR); } /* * Skip an instruction while host sysregs are live. * Assumes host is always 64-bit. */ static inline void kvm_skip_host_instr(void) { write_sysreg_el2(read_sysreg_el2(SYS_ELR) + 4, SYS_ELR); } #endif |
| 33 33 33 32 493 492 32 33 32 33 33 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved. * Authors: David Chinner and Glauber Costa * * Generic LRU infrastructure */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/list_lru.h> #include <linux/slab.h> #include <linux/mutex.h> #include <linux/memcontrol.h> #include "slab.h" #include "internal.h" #ifdef CONFIG_MEMCG static LIST_HEAD(memcg_list_lrus); static DEFINE_MUTEX(list_lrus_mutex); static inline bool list_lru_memcg_aware(struct list_lru *lru) { return lru->memcg_aware; } static void list_lru_register(struct list_lru *lru) { if (!list_lru_memcg_aware(lru)) return; mutex_lock(&list_lrus_mutex); list_add(&lru->list, &memcg_list_lrus); mutex_unlock(&list_lrus_mutex); } static void list_lru_unregister(struct list_lru *lru) { if (!list_lru_memcg_aware(lru)) return; mutex_lock(&list_lrus_mutex); list_del(&lru->list); mutex_unlock(&list_lrus_mutex); } static int lru_shrinker_id(struct list_lru *lru) { return lru->shrinker_id; } static inline struct list_lru_one * list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx) { if (list_lru_memcg_aware(lru) && idx >= 0) { struct list_lru_memcg *mlru = xa_load(&lru->xa, idx); return mlru ? &mlru->node[nid] : NULL; } return &lru->node[nid].lru; } static inline struct list_lru_one * lock_list_lru_of_memcg(struct list_lru *lru, int nid, struct mem_cgroup *memcg, bool irq, bool skip_empty) { struct list_lru_one *l; long nr_items; rcu_read_lock(); again: l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg)); if (likely(l)) { if (irq) spin_lock_irq(&l->lock); else spin_lock(&l->lock); nr_items = READ_ONCE(l->nr_items); if (likely(nr_items != LONG_MIN)) { WARN_ON(nr_items < 0); rcu_read_unlock(); return l; } if (irq) spin_unlock_irq(&l->lock); else spin_unlock(&l->lock); } /* * Caller may simply bail out if raced with reparenting or * may iterate through the list_lru and expect empty slots. */ if (skip_empty) { rcu_read_unlock(); return NULL; } VM_WARN_ON(!css_is_dying(&memcg->css)); memcg = parent_mem_cgroup(memcg); goto again; } static inline void unlock_list_lru(struct list_lru_one *l, bool irq_off) { if (irq_off) spin_unlock_irq(&l->lock); else spin_unlock(&l->lock); } #else static void list_lru_register(struct list_lru *lru) { } static void list_lru_unregister(struct list_lru *lru) { } static int lru_shrinker_id(struct list_lru *lru) { return -1; } static inline bool list_lru_memcg_aware(struct list_lru *lru) { return false; } static inline struct list_lru_one * list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx) { return &lru->node[nid].lru; } static inline struct list_lru_one * lock_list_lru_of_memcg(struct list_lru *lru, int nid, struct mem_cgroup *memcg, bool irq, bool skip_empty) { struct list_lru_one *l = &lru->node[nid].lru; if (irq) spin_lock_irq(&l->lock); else spin_lock(&l->lock); return l; } static inline void unlock_list_lru(struct list_lru_one *l, bool irq_off) { if (irq_off) spin_unlock_irq(&l->lock); else spin_unlock(&l->lock); } #endif /* CONFIG_MEMCG */ /* The caller must ensure the memcg lifetime. */ bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid, struct mem_cgroup *memcg) { struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l; l = lock_list_lru_of_memcg(lru, nid, memcg, false, false); if (!l) return false; if (list_empty(item)) { list_add_tail(item, &l->list); /* Set shrinker bit if the first element was added */ if (!l->nr_items++) set_shrinker_bit(memcg, nid, lru_shrinker_id(lru)); unlock_list_lru(l, false); atomic_long_inc(&nlru->nr_items); return true; } unlock_list_lru(l, false); return false; } bool list_lru_add_obj(struct list_lru *lru, struct list_head *item) { bool ret; int nid = page_to_nid(virt_to_page(item)); if (list_lru_memcg_aware(lru)) { rcu_read_lock(); ret = list_lru_add(lru, item, nid, mem_cgroup_from_slab_obj(item)); rcu_read_unlock(); } else { ret = list_lru_add(lru, item, nid, NULL); } return ret; } EXPORT_SYMBOL_GPL(list_lru_add_obj); /* The caller must ensure the memcg lifetime. */ bool list_lru_del(struct list_lru *lru, struct list_head *item, int nid, struct mem_cgroup *memcg) { struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l; l = lock_list_lru_of_memcg(lru, nid, memcg, false, false); if (!l) return false; if (!list_empty(item)) { list_del_init(item); l->nr_items--; unlock_list_lru(l, false); atomic_long_dec(&nlru->nr_items); return true; } unlock_list_lru(l, false); return false; } bool list_lru_del_obj(struct list_lru *lru, struct list_head *item) { bool ret; int nid = page_to_nid(virt_to_page(item)); if (list_lru_memcg_aware(lru)) { rcu_read_lock(); ret = list_lru_del(lru, item, nid, mem_cgroup_from_slab_obj(item)); rcu_read_unlock(); } else { ret = list_lru_del(lru, item, nid, NULL); } return ret; } EXPORT_SYMBOL_GPL(list_lru_del_obj); void list_lru_isolate(struct list_lru_one *list, struct list_head *item) { list_del_init(item); list->nr_items--; } EXPORT_SYMBOL_GPL(list_lru_isolate); void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item, struct list_head *head) { list_move(item, head); list->nr_items--; } EXPORT_SYMBOL_GPL(list_lru_isolate_move); unsigned long list_lru_count_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg) { struct list_lru_one *l; long count; rcu_read_lock(); l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg)); count = l ? READ_ONCE(l->nr_items) : 0; rcu_read_unlock(); if (unlikely(count < 0)) count = 0; return count; } EXPORT_SYMBOL_GPL(list_lru_count_one); unsigned long list_lru_count_node(struct list_lru *lru, int nid) { struct list_lru_node *nlru; nlru = &lru->node[nid]; return atomic_long_read(&nlru->nr_items); } EXPORT_SYMBOL_GPL(list_lru_count_node); static unsigned long __list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk, bool irq_off) { struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l = NULL; struct list_head *item, *n; unsigned long isolated = 0; restart: l = lock_list_lru_of_memcg(lru, nid, memcg, irq_off, true); if (!l) return isolated; list_for_each_safe(item, n, &l->list) { enum lru_status ret; /* * decrement nr_to_walk first so that we don't livelock if we * get stuck on large numbers of LRU_RETRY items */ if (!*nr_to_walk) break; --*nr_to_walk; ret = isolate(item, l, cb_arg); switch (ret) { /* * LRU_RETRY, LRU_REMOVED_RETRY and LRU_STOP will drop the lru * lock. List traversal will have to restart from scratch. */ case LRU_RETRY: goto restart; case LRU_REMOVED_RETRY: fallthrough; case LRU_REMOVED: isolated++; atomic_long_dec(&nlru->nr_items); if (ret == LRU_REMOVED_RETRY) goto restart; break; case LRU_ROTATE: list_move_tail(item, &l->list); break; case LRU_SKIP: break; case LRU_STOP: goto out; default: BUG(); } } unlock_list_lru(l, irq_off); out: return isolated; } unsigned long list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { return __list_lru_walk_one(lru, nid, memcg, isolate, cb_arg, nr_to_walk, false); } EXPORT_SYMBOL_GPL(list_lru_walk_one); unsigned long list_lru_walk_one_irq(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { return __list_lru_walk_one(lru, nid, memcg, isolate, cb_arg, nr_to_walk, true); } unsigned long list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { long isolated = 0; isolated += list_lru_walk_one(lru, nid, NULL, isolate, cb_arg, nr_to_walk); #ifdef CONFIG_MEMCG if (*nr_to_walk > 0 && list_lru_memcg_aware(lru)) { struct list_lru_memcg *mlru; struct mem_cgroup *memcg; unsigned long index; xa_for_each(&lru->xa, index, mlru) { rcu_read_lock(); memcg = mem_cgroup_from_id(index); if (!mem_cgroup_tryget(memcg)) { rcu_read_unlock(); continue; } rcu_read_unlock(); isolated += __list_lru_walk_one(lru, nid, memcg, isolate, cb_arg, nr_to_walk, false); mem_cgroup_put(memcg); if (*nr_to_walk <= 0) break; } } #endif return isolated; } EXPORT_SYMBOL_GPL(list_lru_walk_node); static void init_one_lru(struct list_lru *lru, struct list_lru_one *l) { INIT_LIST_HEAD(&l->list); spin_lock_init(&l->lock); l->nr_items = 0; #ifdef CONFIG_LOCKDEP if (lru->key) lockdep_set_class(&l->lock, lru->key); #endif } #ifdef CONFIG_MEMCG static struct list_lru_memcg *memcg_init_list_lru_one(struct list_lru *lru, gfp_t gfp) { int nid; struct list_lru_memcg *mlru; mlru = kmalloc(struct_size(mlru, node, nr_node_ids), gfp); if (!mlru) return NULL; for_each_node(nid) init_one_lru(lru, &mlru->node[nid]); return mlru; } static inline void memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) { if (memcg_aware) xa_init_flags(&lru->xa, XA_FLAGS_LOCK_IRQ); lru->memcg_aware = memcg_aware; } static void memcg_destroy_list_lru(struct list_lru *lru) { XA_STATE(xas, &lru->xa, 0); struct list_lru_memcg *mlru; if (!list_lru_memcg_aware(lru)) return; xas_lock_irq(&xas); xas_for_each(&xas, mlru, ULONG_MAX) { kfree(mlru); xas_store(&xas, NULL); } xas_unlock_irq(&xas); } static void memcg_reparent_list_lru_one(struct list_lru *lru, int nid, struct list_lru_one *src, struct mem_cgroup *dst_memcg) { int dst_idx = dst_memcg->kmemcg_id; struct list_lru_one *dst; spin_lock_irq(&src->lock); dst = list_lru_from_memcg_idx(lru, nid, dst_idx); spin_lock_nested(&dst->lock, SINGLE_DEPTH_NESTING); list_splice_init(&src->list, &dst->list); if (src->nr_items) { dst->nr_items += src->nr_items; set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru)); } /* Mark the list_lru_one dead */ src->nr_items = LONG_MIN; spin_unlock(&dst->lock); spin_unlock_irq(&src->lock); } void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *parent) { struct list_lru *lru; int i; mutex_lock(&list_lrus_mutex); list_for_each_entry(lru, &memcg_list_lrus, list) { struct list_lru_memcg *mlru; XA_STATE(xas, &lru->xa, memcg->kmemcg_id); /* * Lock the Xarray to ensure no on going list_lru_memcg * allocation and further allocation will see css_is_dying(). */ xas_lock_irq(&xas); mlru = xas_store(&xas, NULL); xas_unlock_irq(&xas); if (!mlru) continue; /* * With Xarray value set to NULL, holding the lru lock below * prevents list_lru_{add,del,isolate} from touching the lru, * safe to reparent. */ for_each_node(i) memcg_reparent_list_lru_one(lru, i, &mlru->node[i], parent); /* * Here all list_lrus corresponding to the cgroup are guaranteed * to remain empty, we can safely free this lru, any further * memcg_list_lru_alloc() call will simply bail out. */ kvfree_rcu(mlru, rcu); } mutex_unlock(&list_lrus_mutex); } static inline bool memcg_list_lru_allocated(struct mem_cgroup *memcg, struct list_lru *lru) { int idx = memcg->kmemcg_id; return idx < 0 || xa_load(&lru->xa, idx); } int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, gfp_t gfp) { unsigned long flags; struct list_lru_memcg *mlru; struct mem_cgroup *pos, *parent; XA_STATE(xas, &lru->xa, 0); if (!list_lru_memcg_aware(lru) || memcg_list_lru_allocated(memcg, lru)) return 0; gfp &= GFP_RECLAIM_MASK; /* * Because the list_lru can be reparented to the parent cgroup's * list_lru, we should make sure that this cgroup and all its * ancestors have allocated list_lru_memcg. */ do { /* * Keep finding the farest parent that wasn't populated * until found memcg itself. */ pos = memcg; parent = parent_mem_cgroup(pos); while (!memcg_list_lru_allocated(parent, lru)) { pos = parent; parent = parent_mem_cgroup(pos); } mlru = memcg_init_list_lru_one(lru, gfp); if (!mlru) return -ENOMEM; xas_set(&xas, pos->kmemcg_id); do { xas_lock_irqsave(&xas, flags); if (!xas_load(&xas) && !css_is_dying(&pos->css)) { xas_store(&xas, mlru); if (!xas_error(&xas)) mlru = NULL; } xas_unlock_irqrestore(&xas, flags); } while (xas_nomem(&xas, gfp)); if (mlru) kfree(mlru); } while (pos != memcg && !css_is_dying(&pos->css)); return xas_error(&xas); } #else static inline void memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) { } static void memcg_destroy_list_lru(struct list_lru *lru) { } #endif /* CONFIG_MEMCG */ int __list_lru_init(struct list_lru *lru, bool memcg_aware, struct shrinker *shrinker) { int i; #ifdef CONFIG_MEMCG if (shrinker) lru->shrinker_id = shrinker->id; else lru->shrinker_id = -1; if (mem_cgroup_kmem_disabled()) memcg_aware = false; #endif lru->node = kcalloc(nr_node_ids, sizeof(*lru->node), GFP_KERNEL); if (!lru->node) return -ENOMEM; for_each_node(i) init_one_lru(lru, &lru->node[i].lru); memcg_init_list_lru(lru, memcg_aware); list_lru_register(lru); return 0; } EXPORT_SYMBOL_GPL(__list_lru_init); void list_lru_destroy(struct list_lru *lru) { /* Already destroyed or not yet initialized? */ if (!lru->node) return; list_lru_unregister(lru); memcg_destroy_list_lru(lru); kfree(lru->node); lru->node = NULL; #ifdef CONFIG_MEMCG lru->shrinker_id = -1; #endif } EXPORT_SYMBOL_GPL(list_lru_destroy); |
| 47 4 43 43 43 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2023 ARM Ltd. */ #include <linux/mm.h> #include <linux/efi.h> #include <linux/export.h> #include <asm/tlbflush.h> static inline bool mm_is_user(struct mm_struct *mm) { /* * Don't attempt to apply the contig bit to kernel mappings, because * dynamically adding/removing the contig bit can cause page faults. * These racing faults are ok for user space, since they get serialized * on the PTL. But kernel mappings can't tolerate faults. */ if (unlikely(mm_is_efi(mm))) return false; return mm != &init_mm; } static inline pte_t *contpte_align_down(pte_t *ptep) { return PTR_ALIGN_DOWN(ptep, sizeof(*ptep) * CONT_PTES); } static void contpte_try_unfold_partial(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr) { /* * Unfold any partially covered contpte block at the beginning and end * of the range. */ if (ptep != contpte_align_down(ptep) || nr < CONT_PTES) contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); if (ptep + nr != contpte_align_down(ptep + nr)) { unsigned long last_addr = addr + PAGE_SIZE * (nr - 1); pte_t *last_ptep = ptep + nr - 1; contpte_try_unfold(mm, last_addr, last_ptep, __ptep_get(last_ptep)); } } static void contpte_convert(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); unsigned long start_addr; pte_t *start_ptep; int i; start_ptep = ptep = contpte_align_down(ptep); start_addr = addr = ALIGN_DOWN(addr, CONT_PTE_SIZE); pte = pfn_pte(ALIGN_DOWN(pte_pfn(pte), CONT_PTES), pte_pgprot(pte)); for (i = 0; i < CONT_PTES; i++, ptep++, addr += PAGE_SIZE) { pte_t ptent = __ptep_get_and_clear(mm, addr, ptep); if (pte_dirty(ptent)) pte = pte_mkdirty(pte); if (pte_young(ptent)) pte = pte_mkyoung(pte); } __flush_tlb_range(&vma, start_addr, addr, PAGE_SIZE, true, 3); __set_ptes(mm, start_addr, start_ptep, pte, CONT_PTES); } void __contpte_try_fold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { /* * We have already checked that the virtual and pysical addresses are * correctly aligned for a contpte mapping in contpte_try_fold() so the * remaining checks are to ensure that the contpte range is fully * covered by a single folio, and ensure that all the ptes are valid * with contiguous PFNs and matching prots. We ignore the state of the * access and dirty bits for the purpose of deciding if its a contiguous * range; the folding process will generate a single contpte entry which * has a single access and dirty bit. Those 2 bits are the logical OR of * their respective bits in the constituent pte entries. In order to * ensure the contpte range is covered by a single folio, we must * recover the folio from the pfn, but special mappings don't have a * folio backing them. Fortunately contpte_try_fold() already checked * that the pte is not special - we never try to fold special mappings. * Note we can't use vm_normal_page() for this since we don't have the * vma. */ unsigned long folio_start, folio_end; unsigned long cont_start, cont_end; pte_t expected_pte, subpte; struct folio *folio; struct page *page; unsigned long pfn; pte_t *orig_ptep; pgprot_t prot; int i; if (!mm_is_user(mm)) return; page = pte_page(pte); folio = page_folio(page); folio_start = addr - (page - &folio->page) * PAGE_SIZE; folio_end = folio_start + folio_nr_pages(folio) * PAGE_SIZE; cont_start = ALIGN_DOWN(addr, CONT_PTE_SIZE); cont_end = cont_start + CONT_PTE_SIZE; if (folio_start > cont_start || folio_end < cont_end) return; pfn = ALIGN_DOWN(pte_pfn(pte), CONT_PTES); prot = pte_pgprot(pte_mkold(pte_mkclean(pte))); expected_pte = pfn_pte(pfn, prot); orig_ptep = ptep; ptep = contpte_align_down(ptep); for (i = 0; i < CONT_PTES; i++) { subpte = pte_mkold(pte_mkclean(__ptep_get(ptep))); if (!pte_same(subpte, expected_pte)) return; expected_pte = pte_advance_pfn(expected_pte, 1); ptep++; } pte = pte_mkcont(pte); contpte_convert(mm, addr, orig_ptep, pte); } EXPORT_SYMBOL_GPL(__contpte_try_fold); void __contpte_try_unfold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { /* * We have already checked that the ptes are contiguous in * contpte_try_unfold(), so just check that the mm is user space. */ if (!mm_is_user(mm)) return; pte = pte_mknoncont(pte); contpte_convert(mm, addr, ptep, pte); } EXPORT_SYMBOL_GPL(__contpte_try_unfold); pte_t contpte_ptep_get(pte_t *ptep, pte_t orig_pte) { /* * Gather access/dirty bits, which may be populated in any of the ptes * of the contig range. We are guaranteed to be holding the PTL, so any * contiguous range cannot be unfolded or otherwise modified under our * feet. */ pte_t pte; int i; ptep = contpte_align_down(ptep); for (i = 0; i < CONT_PTES; i++, ptep++) { pte = __ptep_get(ptep); if (pte_dirty(pte)) orig_pte = pte_mkdirty(orig_pte); if (pte_young(pte)) orig_pte = pte_mkyoung(orig_pte); } return orig_pte; } EXPORT_SYMBOL_GPL(contpte_ptep_get); pte_t contpte_ptep_get_lockless(pte_t *orig_ptep) { /* * The ptep_get_lockless() API requires us to read and return *orig_ptep * so that it is self-consistent, without the PTL held, so we may be * racing with other threads modifying the pte. Usually a READ_ONCE() * would suffice, but for the contpte case, we also need to gather the * access and dirty bits from across all ptes in the contiguous block, * and we can't read all of those neighbouring ptes atomically, so any * contiguous range may be unfolded/modified/refolded under our feet. * Therefore we ensure we read a _consistent_ contpte range by checking * that all ptes in the range are valid and have CONT_PTE set, that all * pfns are contiguous and that all pgprots are the same (ignoring * access/dirty). If we find a pte that is not consistent, then we must * be racing with an update so start again. If the target pte does not * have CONT_PTE set then that is considered consistent on its own * because it is not part of a contpte range. */ pgprot_t orig_prot; unsigned long pfn; pte_t orig_pte; pgprot_t prot; pte_t *ptep; pte_t pte; int i; retry: orig_pte = __ptep_get(orig_ptep); if (!pte_valid_cont(orig_pte)) return orig_pte; orig_prot = pte_pgprot(pte_mkold(pte_mkclean(orig_pte))); ptep = contpte_align_down(orig_ptep); pfn = pte_pfn(orig_pte) - (orig_ptep - ptep); for (i = 0; i < CONT_PTES; i++, ptep++, pfn++) { pte = __ptep_get(ptep); prot = pte_pgprot(pte_mkold(pte_mkclean(pte))); if (!pte_valid_cont(pte) || pte_pfn(pte) != pfn || pgprot_val(prot) != pgprot_val(orig_prot)) goto retry; if (pte_dirty(pte)) orig_pte = pte_mkdirty(orig_pte); if (pte_young(pte)) orig_pte = pte_mkyoung(orig_pte); } return orig_pte; } EXPORT_SYMBOL_GPL(contpte_ptep_get_lockless); void contpte_set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned int nr) { unsigned long next; unsigned long end; unsigned long pfn; pgprot_t prot; /* * The set_ptes() spec guarantees that when nr > 1, the initial state of * all ptes is not-present. Therefore we never need to unfold or * otherwise invalidate a range before we set the new ptes. * contpte_set_ptes() should never be called for nr < 2. */ VM_WARN_ON(nr == 1); if (!mm_is_user(mm)) return __set_ptes(mm, addr, ptep, pte, nr); end = addr + (nr << PAGE_SHIFT); pfn = pte_pfn(pte); prot = pte_pgprot(pte); do { next = pte_cont_addr_end(addr, end); nr = (next - addr) >> PAGE_SHIFT; pte = pfn_pte(pfn, prot); if (((addr | next | (pfn << PAGE_SHIFT)) & ~CONT_PTE_MASK) == 0) pte = pte_mkcont(pte); else pte = pte_mknoncont(pte); __set_ptes(mm, addr, ptep, pte, nr); addr = next; ptep += nr; pfn += nr; } while (addr != end); } EXPORT_SYMBOL_GPL(contpte_set_ptes); void contpte_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { contpte_try_unfold_partial(mm, addr, ptep, nr); __clear_full_ptes(mm, addr, ptep, nr, full); } EXPORT_SYMBOL_GPL(contpte_clear_full_ptes); pte_t contpte_get_and_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { contpte_try_unfold_partial(mm, addr, ptep, nr); return __get_and_clear_full_ptes(mm, addr, ptep, nr, full); } EXPORT_SYMBOL_GPL(contpte_get_and_clear_full_ptes); int contpte_ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { /* * ptep_clear_flush_young() technically requires us to clear the access * flag for a _single_ pte. However, the core-mm code actually tracks * access/dirty per folio, not per page. And since we only create a * contig range when the range is covered by a single folio, we can get * away with clearing young for the whole contig range here, so we avoid * having to unfold. */ int young = 0; int i; ptep = contpte_align_down(ptep); addr = ALIGN_DOWN(addr, CONT_PTE_SIZE); for (i = 0; i < CONT_PTES; i++, ptep++, addr += PAGE_SIZE) young |= __ptep_test_and_clear_young(vma, addr, ptep); return young; } EXPORT_SYMBOL_GPL(contpte_ptep_test_and_clear_young); int contpte_ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { int young; young = contpte_ptep_test_and_clear_young(vma, addr, ptep); if (young) { /* * See comment in __ptep_clear_flush_young(); same rationale for * eliding the trailing DSB applies here. */ addr = ALIGN_DOWN(addr, CONT_PTE_SIZE); __flush_tlb_range_nosync(vma, addr, addr + CONT_PTE_SIZE, PAGE_SIZE, true, 3); } return young; } EXPORT_SYMBOL_GPL(contpte_ptep_clear_flush_young); void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr) { /* * If wrprotecting an entire contig range, we can avoid unfolding. Just * set wrprotect and wait for the later mmu_gather flush to invalidate * the tlb. Until the flush, the page may or may not be wrprotected. * After the flush, it is guaranteed wrprotected. If it's a partial * range though, we must unfold, because we can't have a case where * CONT_PTE is set but wrprotect applies to a subset of the PTEs; this * would cause it to continue to be unpredictable after the flush. */ contpte_try_unfold_partial(mm, addr, ptep, nr); __wrprotect_ptes(mm, addr, ptep, nr); } EXPORT_SYMBOL_GPL(contpte_wrprotect_ptes); void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr, cydp_t flags) { /* * We can safely clear access/dirty without needing to unfold from * the architectures perspective, even when contpte is set. If the * range starts or ends midway through a contpte block, we can just * expand to include the full contpte block. While this is not * exactly what the core-mm asked for, it tracks access/dirty per * folio, not per page. And since we only create a contpte block * when it is covered by a single folio, we can get away with * clearing access/dirty for the whole block. */ unsigned long start = addr; unsigned long end = start + nr * PAGE_SIZE; if (pte_cont(__ptep_get(ptep + nr - 1))) end = ALIGN(end, CONT_PTE_SIZE); if (pte_cont(__ptep_get(ptep))) { start = ALIGN_DOWN(start, CONT_PTE_SIZE); ptep = contpte_align_down(ptep); } __clear_young_dirty_ptes(vma, start, ptep, (end - start) / PAGE_SIZE, flags); } EXPORT_SYMBOL_GPL(contpte_clear_young_dirty_ptes); int contpte_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t entry, int dirty) { unsigned long start_addr; pte_t orig_pte; int i; /* * Gather the access/dirty bits for the contiguous range. If nothing has * changed, its a noop. */ orig_pte = pte_mknoncont(ptep_get(ptep)); if (pte_val(orig_pte) == pte_val(entry)) return 0; /* * We can fix up access/dirty bits without having to unfold the contig * range. But if the write bit is changing, we must unfold. */ if (pte_write(orig_pte) == pte_write(entry)) { /* * For HW access management, we technically only need to update * the flag on a single pte in the range. But for SW access * management, we need to update all the ptes to prevent extra * faults. Avoid per-page tlb flush in __ptep_set_access_flags() * and instead flush the whole range at the end. */ ptep = contpte_align_down(ptep); start_addr = addr = ALIGN_DOWN(addr, CONT_PTE_SIZE); /* * We are not advancing entry because __ptep_set_access_flags() * only consumes access flags from entry. And since we have checked * for the whole contpte block and returned early, pte_same() * within __ptep_set_access_flags() is likely false. */ for (i = 0; i < CONT_PTES; i++, ptep++, addr += PAGE_SIZE) __ptep_set_access_flags(vma, addr, ptep, entry, 0); if (dirty) __flush_tlb_range(vma, start_addr, addr, PAGE_SIZE, true, 3); } else { __contpte_try_unfold(vma->vm_mm, addr, ptep, orig_pte); __ptep_set_access_flags(vma, addr, ptep, entry, dirty); } return 1; } EXPORT_SYMBOL_GPL(contpte_ptep_set_access_flags); |
| 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_cbs.c Credit Based Shaper * * Authors: Vinicius Costa Gomes <vinicius.gomes@intel.com> */ /* Credit Based Shaper (CBS) * ========================= * * This is a simple rate-limiting shaper aimed at TSN applications on * systems with known traffic workloads. * * Its algorithm is defined by the IEEE 802.1Q-2014 Specification, * Section 8.6.8.2, and explained in more detail in the Annex L of the * same specification. * * There are four tunables to be considered: * * 'idleslope': Idleslope is the rate of credits that is * accumulated (in kilobits per second) when there is at least * one packet waiting for transmission. Packets are transmitted * when the current value of credits is equal or greater than * zero. When there is no packet to be transmitted the amount of * credits is set to zero. This is the main tunable of the CBS * algorithm. * * 'sendslope': * Sendslope is the rate of credits that is depleted (it should be a * negative number of kilobits per second) when a transmission is * ocurring. It can be calculated as follows, (IEEE 802.1Q-2014 Section * 8.6.8.2 item g): * * sendslope = idleslope - port_transmit_rate * * 'hicredit': Hicredit defines the maximum amount of credits (in * bytes) that can be accumulated. Hicredit depends on the * characteristics of interfering traffic, * 'max_interference_size' is the maximum size of any burst of * traffic that can delay the transmission of a frame that is * available for transmission for this traffic class, (IEEE * 802.1Q-2014 Annex L, Equation L-3): * * hicredit = max_interference_size * (idleslope / port_transmit_rate) * * 'locredit': Locredit is the minimum amount of credits that can * be reached. It is a function of the traffic flowing through * this qdisc (IEEE 802.1Q-2014 Annex L, Equation L-2): * * locredit = max_frame_size * (sendslope / port_transmit_rate) */ #include <linux/ethtool.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/units.h> #include <net/netevent.h> #include <net/netlink.h> #include <net/sch_generic.h> #include <net/pkt_sched.h> static LIST_HEAD(cbs_list); static DEFINE_SPINLOCK(cbs_list_lock); struct cbs_sched_data { bool offload; int queue; atomic64_t port_rate; /* in bytes/s */ s64 last; /* timestamp in ns */ s64 credits; /* in bytes */ s32 locredit; /* in bytes */ s32 hicredit; /* in bytes */ s64 sendslope; /* in bytes/s */ s64 idleslope; /* in bytes/s */ struct qdisc_watchdog watchdog; int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free); struct sk_buff *(*dequeue)(struct Qdisc *sch); struct Qdisc *qdisc; struct list_head cbs_list; }; static int cbs_child_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct Qdisc *child, struct sk_buff **to_free) { unsigned int len = qdisc_pkt_len(skb); int err; err = child->ops->enqueue(skb, child, to_free); if (err != NET_XMIT_SUCCESS) return err; sch->qstats.backlog += len; sch->q.qlen++; return NET_XMIT_SUCCESS; } static int cbs_enqueue_offload(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct cbs_sched_data *q = qdisc_priv(sch); struct Qdisc *qdisc = q->qdisc; return cbs_child_enqueue(skb, sch, qdisc, to_free); } static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct cbs_sched_data *q = qdisc_priv(sch); struct Qdisc *qdisc = q->qdisc; if (sch->q.qlen == 0 && q->credits > 0) { /* We need to stop accumulating credits when there's * no enqueued packets and q->credits is positive. */ q->credits = 0; q->last = ktime_get_ns(); } return cbs_child_enqueue(skb, sch, qdisc, to_free); } static int cbs_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct cbs_sched_data *q = qdisc_priv(sch); return q->enqueue(skb, sch, to_free); } /* timediff is in ns, slope is in bytes/s */ static s64 timediff_to_credits(s64 timediff, s64 slope) { return div64_s64(timediff * slope, NSEC_PER_SEC); } static s64 delay_from_credits(s64 credits, s64 slope) { if (unlikely(slope == 0)) return S64_MAX; return div64_s64(-credits * NSEC_PER_SEC, slope); } static s64 credits_from_len(unsigned int len, s64 slope, s64 port_rate) { if (unlikely(port_rate == 0)) return S64_MAX; return div64_s64(len * slope, port_rate); } static struct sk_buff *cbs_child_dequeue(struct Qdisc *sch, struct Qdisc *child) { struct sk_buff *skb; skb = child->ops->dequeue(child); if (!skb) return NULL; qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); sch->q.qlen--; return skb; } static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch) { struct cbs_sched_data *q = qdisc_priv(sch); struct Qdisc *qdisc = q->qdisc; s64 now = ktime_get_ns(); struct sk_buff *skb; s64 credits; int len; /* The previous packet is still being sent */ if (now < q->last) { qdisc_watchdog_schedule_ns(&q->watchdog, q->last); return NULL; } if (q->credits < 0) { credits = timediff_to_credits(now - q->last, q->idleslope); credits = q->credits + credits; q->credits = min_t(s64, credits, q->hicredit); if (q->credits < 0) { s64 delay; delay = delay_from_credits(q->credits, q->idleslope); qdisc_watchdog_schedule_ns(&q->watchdog, now + delay); q->last = now; return NULL; } } skb = cbs_child_dequeue(sch, qdisc); if (!skb) return NULL; len = qdisc_pkt_len(skb); /* As sendslope is a negative number, this will decrease the * amount of q->credits. */ credits = credits_from_len(len, q->sendslope, atomic64_read(&q->port_rate)); credits += q->credits; q->credits = max_t(s64, credits, q->locredit); /* Estimate of the transmission of the last byte of the packet in ns */ if (unlikely(atomic64_read(&q->port_rate) == 0)) q->last = now; else q->last = now + div64_s64(len * NSEC_PER_SEC, atomic64_read(&q->port_rate)); return skb; } static struct sk_buff *cbs_dequeue_offload(struct Qdisc *sch) { struct cbs_sched_data *q = qdisc_priv(sch); struct Qdisc *qdisc = q->qdisc; return cbs_child_dequeue(sch, qdisc); } static struct sk_buff *cbs_dequeue(struct Qdisc *sch) { struct cbs_sched_data *q = qdisc_priv(sch); return q->dequeue(sch); } static const struct nla_policy cbs_policy[TCA_CBS_MAX + 1] = { [TCA_CBS_PARMS] = { .len = sizeof(struct tc_cbs_qopt) }, }; static void cbs_disable_offload(struct net_device *dev, struct cbs_sched_data *q) { struct tc_cbs_qopt_offload cbs = { }; const struct net_device_ops *ops; int err; if (!q->offload) return; q->enqueue = cbs_enqueue_soft; q->dequeue = cbs_dequeue_soft; ops = dev->netdev_ops; if (!ops->ndo_setup_tc) return; cbs.queue = q->queue; cbs.enable = 0; err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_CBS, &cbs); if (err < 0) pr_warn("Couldn't disable CBS offload for queue %d\n", cbs.queue); } static int cbs_enable_offload(struct net_device *dev, struct cbs_sched_data *q, const struct tc_cbs_qopt *opt, struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; struct tc_cbs_qopt_offload cbs = { }; int err; if (!ops->ndo_setup_tc) { NL_SET_ERR_MSG(extack, "Specified device does not support cbs offload"); return -EOPNOTSUPP; } cbs.queue = q->queue; cbs.enable = 1; cbs.hicredit = opt->hicredit; cbs.locredit = opt->locredit; cbs.idleslope = opt->idleslope; cbs.sendslope = opt->sendslope; err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_CBS, &cbs); if (err < 0) { NL_SET_ERR_MSG(extack, "Specified device failed to setup cbs hardware offload"); return err; } q->enqueue = cbs_enqueue_offload; q->dequeue = cbs_dequeue_offload; return 0; } static void cbs_set_port_rate(struct net_device *dev, struct cbs_sched_data *q) { struct ethtool_link_ksettings ecmd; int speed = SPEED_10; s64 port_rate; int err; err = __ethtool_get_link_ksettings(dev, &ecmd); if (err < 0) goto skip; if (ecmd.base.speed && ecmd.base.speed != SPEED_UNKNOWN) speed = ecmd.base.speed; skip: port_rate = speed * 1000 * BYTES_PER_KBIT; atomic64_set(&q->port_rate, port_rate); netdev_dbg(dev, "cbs: set %s's port_rate to: %lld, linkspeed: %d\n", dev->name, (long long)atomic64_read(&q->port_rate), ecmd.base.speed); } static int cbs_dev_notifier(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct cbs_sched_data *q; struct net_device *qdev; bool found = false; ASSERT_RTNL(); if (event != NETDEV_UP && event != NETDEV_CHANGE) return NOTIFY_DONE; spin_lock(&cbs_list_lock); list_for_each_entry(q, &cbs_list, cbs_list) { qdev = qdisc_dev(q->qdisc); if (qdev == dev) { found = true; break; } } spin_unlock(&cbs_list_lock); if (found) cbs_set_port_rate(dev, q); return NOTIFY_DONE; } static int cbs_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct cbs_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); struct nlattr *tb[TCA_CBS_MAX + 1]; struct tc_cbs_qopt *qopt; int err; err = nla_parse_nested_deprecated(tb, TCA_CBS_MAX, opt, cbs_policy, extack); if (err < 0) return err; if (!tb[TCA_CBS_PARMS]) { NL_SET_ERR_MSG(extack, "Missing CBS parameter which are mandatory"); return -EINVAL; } qopt = nla_data(tb[TCA_CBS_PARMS]); if (!qopt->offload) { cbs_set_port_rate(dev, q); cbs_disable_offload(dev, q); } else { err = cbs_enable_offload(dev, q, qopt, extack); if (err < 0) return err; } /* Everything went OK, save the parameters used. */ WRITE_ONCE(q->hicredit, qopt->hicredit); WRITE_ONCE(q->locredit, qopt->locredit); WRITE_ONCE(q->idleslope, qopt->idleslope * BYTES_PER_KBIT); WRITE_ONCE(q->sendslope, qopt->sendslope * BYTES_PER_KBIT); WRITE_ONCE(q->offload, qopt->offload); return 0; } static int cbs_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct cbs_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); if (!opt) { NL_SET_ERR_MSG(extack, "Missing CBS qdisc options which are mandatory"); return -EINVAL; } q->qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle, extack); if (!q->qdisc) return -ENOMEM; spin_lock(&cbs_list_lock); list_add(&q->cbs_list, &cbs_list); spin_unlock(&cbs_list_lock); qdisc_hash_add(q->qdisc, false); q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0); q->enqueue = cbs_enqueue_soft; q->dequeue = cbs_dequeue_soft; qdisc_watchdog_init(&q->watchdog, sch); return cbs_change(sch, opt, extack); } static void cbs_destroy(struct Qdisc *sch) { struct cbs_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); /* Nothing to do if we couldn't create the underlying qdisc */ if (!q->qdisc) return; qdisc_watchdog_cancel(&q->watchdog); cbs_disable_offload(dev, q); spin_lock(&cbs_list_lock); list_del(&q->cbs_list); spin_unlock(&cbs_list_lock); qdisc_put(q->qdisc); } static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb) { struct cbs_sched_data *q = qdisc_priv(sch); struct tc_cbs_qopt opt = { }; struct nlattr *nest; nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (!nest) goto nla_put_failure; opt.hicredit = READ_ONCE(q->hicredit); opt.locredit = READ_ONCE(q->locredit); opt.sendslope = div64_s64(READ_ONCE(q->sendslope), BYTES_PER_KBIT); opt.idleslope = div64_s64(READ_ONCE(q->idleslope), BYTES_PER_KBIT); opt.offload = READ_ONCE(q->offload); if (nla_put(skb, TCA_CBS_PARMS, sizeof(opt), &opt)) goto nla_put_failure; return nla_nest_end(skb, nest); nla_put_failure: nla_nest_cancel(skb, nest); return -1; } static int cbs_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { struct cbs_sched_data *q = qdisc_priv(sch); if (cl != 1 || !q->qdisc) /* only one class */ return -ENOENT; tcm->tcm_handle |= TC_H_MIN(1); tcm->tcm_info = q->qdisc->handle; return 0; } static int cbs_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, struct Qdisc **old, struct netlink_ext_ack *extack) { struct cbs_sched_data *q = qdisc_priv(sch); if (!new) { new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle, NULL); if (!new) new = &noop_qdisc; } *old = qdisc_replace(sch, new, &q->qdisc); return 0; } static struct Qdisc *cbs_leaf(struct Qdisc *sch, unsigned long arg) { struct cbs_sched_data *q = qdisc_priv(sch); return q->qdisc; } static unsigned long cbs_find(struct Qdisc *sch, u32 classid) { return 1; } static void cbs_walk(struct Qdisc *sch, struct qdisc_walker *walker) { if (!walker->stop) { tc_qdisc_stats_dump(sch, 1, walker); } } static const struct Qdisc_class_ops cbs_class_ops = { .graft = cbs_graft, .leaf = cbs_leaf, .find = cbs_find, .walk = cbs_walk, .dump = cbs_dump_class, }; static struct Qdisc_ops cbs_qdisc_ops __read_mostly = { .id = "cbs", .cl_ops = &cbs_class_ops, .priv_size = sizeof(struct cbs_sched_data), .enqueue = cbs_enqueue, .dequeue = cbs_dequeue, .peek = qdisc_peek_dequeued, .init = cbs_init, .reset = qdisc_reset_queue, .destroy = cbs_destroy, .change = cbs_change, .dump = cbs_dump, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_SCH("cbs"); static struct notifier_block cbs_device_notifier = { .notifier_call = cbs_dev_notifier, }; static int __init cbs_module_init(void) { int err; err = register_netdevice_notifier(&cbs_device_notifier); if (err) return err; err = register_qdisc(&cbs_qdisc_ops); if (err) unregister_netdevice_notifier(&cbs_device_notifier); return err; } static void __exit cbs_module_exit(void) { unregister_qdisc(&cbs_qdisc_ops); unregister_netdevice_notifier(&cbs_device_notifier); } module_init(cbs_module_init) module_exit(cbs_module_exit) MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Credit Based shaper"); |
| 228 229 858 855 229 228 229 229 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 | // SPDX-License-Identifier: GPL-2.0 /* * Common Block IO controller cgroup interface * * Based on ideas and code from CFQ, CFS and BFQ: * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk> * * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it> * Paolo Valente <paolo.valente@unimore.it> * * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com> * Nauman Rafique <nauman@google.com> * * For policy-specific per-blkcg data: * Copyright (C) 2015 Paolo Valente <paolo.valente@unimore.it> * Arianna Avanzini <avanzini.arianna@gmail.com> */ #include <linux/ioprio.h> #include <linux/kdev_t.h> #include <linux/module.h> #include <linux/sched/signal.h> #include <linux/err.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/slab.h> #include <linux/delay.h> #include <linux/atomic.h> #include <linux/ctype.h> #include <linux/resume_user_mode.h> #include <linux/psi.h> #include <linux/part_stat.h> #include "blk.h" #include "blk-cgroup.h" #include "blk-ioprio.h" #include "blk-throttle.h" static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu); /* * blkcg_pol_mutex protects blkcg_policy[] and policy [de]activation. * blkcg_pol_register_mutex nests outside of it and synchronizes entire * policy [un]register operations including cgroup file additions / * removals. Putting cgroup file registration outside blkcg_pol_mutex * allows grabbing it from cgroup callbacks. */ static DEFINE_MUTEX(blkcg_pol_register_mutex); static DEFINE_MUTEX(blkcg_pol_mutex); struct blkcg blkcg_root; EXPORT_SYMBOL_GPL(blkcg_root); struct cgroup_subsys_state * const blkcg_root_css = &blkcg_root.css; EXPORT_SYMBOL_GPL(blkcg_root_css); static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS]; static LIST_HEAD(all_blkcgs); /* protected by blkcg_pol_mutex */ bool blkcg_debug_stats = false; static DEFINE_RAW_SPINLOCK(blkg_stat_lock); #define BLKG_DESTROY_BATCH_SIZE 64 /* * Lockless lists for tracking IO stats update * * New IO stats are stored in the percpu iostat_cpu within blkcg_gq (blkg). * There are multiple blkg's (one for each block device) attached to each * blkcg. The rstat code keeps track of which cpu has IO stats updated, * but it doesn't know which blkg has the updated stats. If there are many * block devices in a system, the cost of iterating all the blkg's to flush * out the IO stats can be high. To reduce such overhead, a set of percpu * lockless lists (lhead) per blkcg are used to track the set of recently * updated iostat_cpu's since the last flush. An iostat_cpu will be put * onto the lockless list on the update side [blk_cgroup_bio_start()] if * not there yet and then removed when being flushed [blkcg_rstat_flush()]. * References to blkg are gotten and then put back in the process to * protect against blkg removal. * * Return: 0 if successful or -ENOMEM if allocation fails. */ static int init_blkcg_llists(struct blkcg *blkcg) { int cpu; blkcg->lhead = alloc_percpu_gfp(struct llist_head, GFP_KERNEL); if (!blkcg->lhead) return -ENOMEM; for_each_possible_cpu(cpu) init_llist_head(per_cpu_ptr(blkcg->lhead, cpu)); return 0; } /** * blkcg_css - find the current css * * Find the css associated with either the kthread or the current task. * This may return a dying css, so it is up to the caller to use tryget logic * to confirm it is alive and well. */ static struct cgroup_subsys_state *blkcg_css(void) { struct cgroup_subsys_state *css; css = kthread_blkcg(); if (css) return css; return task_css(current, io_cgrp_id); } static bool blkcg_policy_enabled(struct request_queue *q, const struct blkcg_policy *pol) { return pol && test_bit(pol->plid, q->blkcg_pols); } static void blkg_free_workfn(struct work_struct *work) { struct blkcg_gq *blkg = container_of(work, struct blkcg_gq, free_work); struct request_queue *q = blkg->q; int i; /* * pd_free_fn() can also be called from blkcg_deactivate_policy(), * in order to make sure pd_free_fn() is called in order, the deletion * of the list blkg->q_node is delayed to here from blkg_destroy(), and * blkcg_mutex is used to synchronize blkg_free_workfn() and * blkcg_deactivate_policy(). */ mutex_lock(&q->blkcg_mutex); for (i = 0; i < BLKCG_MAX_POLS; i++) if (blkg->pd[i]) blkcg_policy[i]->pd_free_fn(blkg->pd[i]); if (blkg->parent) blkg_put(blkg->parent); spin_lock_irq(&q->queue_lock); list_del_init(&blkg->q_node); spin_unlock_irq(&q->queue_lock); mutex_unlock(&q->blkcg_mutex); blk_put_queue(q); free_percpu(blkg->iostat_cpu); percpu_ref_exit(&blkg->refcnt); kfree(blkg); } /** * blkg_free - free a blkg * @blkg: blkg to free * * Free @blkg which may be partially allocated. */ static void blkg_free(struct blkcg_gq *blkg) { if (!blkg) return; /* * Both ->pd_free_fn() and request queue's release handler may * sleep, so free us by scheduling one work func */ INIT_WORK(&blkg->free_work, blkg_free_workfn); schedule_work(&blkg->free_work); } static void __blkg_release(struct rcu_head *rcu) { struct blkcg_gq *blkg = container_of(rcu, struct blkcg_gq, rcu_head); struct blkcg *blkcg = blkg->blkcg; int cpu; #ifdef CONFIG_BLK_CGROUP_PUNT_BIO WARN_ON(!bio_list_empty(&blkg->async_bios)); #endif /* * Flush all the non-empty percpu lockless lists before releasing * us, given these stat belongs to us. * * blkg_stat_lock is for serializing blkg stat update */ for_each_possible_cpu(cpu) __blkcg_rstat_flush(blkcg, cpu); /* release the blkcg and parent blkg refs this blkg has been holding */ css_put(&blkg->blkcg->css); blkg_free(blkg); } /* * A group is RCU protected, but having an rcu lock does not mean that one * can access all the fields of blkg and assume these are valid. For * example, don't try to follow throtl_data and request queue links. * * Having a reference to blkg under an rcu allows accesses to only values * local to groups like group stats and group rate limits. */ static void blkg_release(struct percpu_ref *ref) { struct blkcg_gq *blkg = container_of(ref, struct blkcg_gq, refcnt); call_rcu(&blkg->rcu_head, __blkg_release); } #ifdef CONFIG_BLK_CGROUP_PUNT_BIO static struct workqueue_struct *blkcg_punt_bio_wq; static void blkg_async_bio_workfn(struct work_struct *work) { struct blkcg_gq *blkg = container_of(work, struct blkcg_gq, async_bio_work); struct bio_list bios = BIO_EMPTY_LIST; struct bio *bio; struct blk_plug plug; bool need_plug = false; /* as long as there are pending bios, @blkg can't go away */ spin_lock(&blkg->async_bio_lock); bio_list_merge_init(&bios, &blkg->async_bios); spin_unlock(&blkg->async_bio_lock); /* start plug only when bio_list contains at least 2 bios */ if (bios.head && bios.head->bi_next) { need_plug = true; blk_start_plug(&plug); } while ((bio = bio_list_pop(&bios))) submit_bio(bio); if (need_plug) blk_finish_plug(&plug); } /* * When a shared kthread issues a bio for a cgroup, doing so synchronously can * lead to priority inversions as the kthread can be trapped waiting for that * cgroup. Use this helper instead of submit_bio to punt the actual issuing to * a dedicated per-blkcg work item to avoid such priority inversions. */ void blkcg_punt_bio_submit(struct bio *bio) { struct blkcg_gq *blkg = bio->bi_blkg; if (blkg->parent) { spin_lock(&blkg->async_bio_lock); bio_list_add(&blkg->async_bios, bio); spin_unlock(&blkg->async_bio_lock); queue_work(blkcg_punt_bio_wq, &blkg->async_bio_work); } else { /* never bounce for the root cgroup */ submit_bio(bio); } } EXPORT_SYMBOL_GPL(blkcg_punt_bio_submit); static int __init blkcg_punt_bio_init(void) { blkcg_punt_bio_wq = alloc_workqueue("blkcg_punt_bio", WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND | WQ_SYSFS, 0); if (!blkcg_punt_bio_wq) return -ENOMEM; return 0; } subsys_initcall(blkcg_punt_bio_init); #endif /* CONFIG_BLK_CGROUP_PUNT_BIO */ /** * bio_blkcg_css - return the blkcg CSS associated with a bio * @bio: target bio * * This returns the CSS for the blkcg associated with a bio, or %NULL if not * associated. Callers are expected to either handle %NULL or know association * has been done prior to calling this. */ struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio) { if (!bio || !bio->bi_blkg) return NULL; return &bio->bi_blkg->blkcg->css; } EXPORT_SYMBOL_GPL(bio_blkcg_css); /** * blkcg_parent - get the parent of a blkcg * @blkcg: blkcg of interest * * Return the parent blkcg of @blkcg. Can be called anytime. */ static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) { return css_to_blkcg(blkcg->css.parent); } /** * blkg_alloc - allocate a blkg * @blkcg: block cgroup the new blkg is associated with * @disk: gendisk the new blkg is associated with * @gfp_mask: allocation mask to use * * Allocate a new blkg associating @blkcg and @disk. */ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk, gfp_t gfp_mask) { struct blkcg_gq *blkg; int i, cpu; /* alloc and init base part */ blkg = kzalloc_node(sizeof(*blkg), gfp_mask, disk->queue->node); if (!blkg) return NULL; if (percpu_ref_init(&blkg->refcnt, blkg_release, 0, gfp_mask)) goto out_free_blkg; blkg->iostat_cpu = alloc_percpu_gfp(struct blkg_iostat_set, gfp_mask); if (!blkg->iostat_cpu) goto out_exit_refcnt; if (!blk_get_queue(disk->queue)) goto out_free_iostat; blkg->q = disk->queue; INIT_LIST_HEAD(&blkg->q_node); blkg->blkcg = blkcg; blkg->iostat.blkg = blkg; #ifdef CONFIG_BLK_CGROUP_PUNT_BIO spin_lock_init(&blkg->async_bio_lock); bio_list_init(&blkg->async_bios); INIT_WORK(&blkg->async_bio_work, blkg_async_bio_workfn); #endif u64_stats_init(&blkg->iostat.sync); for_each_possible_cpu(cpu) { u64_stats_init(&per_cpu_ptr(blkg->iostat_cpu, cpu)->sync); per_cpu_ptr(blkg->iostat_cpu, cpu)->blkg = blkg; } for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; struct blkg_policy_data *pd; if (!blkcg_policy_enabled(disk->queue, pol)) continue; /* alloc per-policy data and attach it to blkg */ pd = pol->pd_alloc_fn(disk, blkcg, gfp_mask); if (!pd) goto out_free_pds; blkg->pd[i] = pd; pd->blkg = blkg; pd->plid = i; pd->online = false; } return blkg; out_free_pds: while (--i >= 0) if (blkg->pd[i]) blkcg_policy[i]->pd_free_fn(blkg->pd[i]); blk_put_queue(disk->queue); out_free_iostat: free_percpu(blkg->iostat_cpu); out_exit_refcnt: percpu_ref_exit(&blkg->refcnt); out_free_blkg: kfree(blkg); return NULL; } /* * If @new_blkg is %NULL, this function tries to allocate a new one as * necessary using %GFP_NOWAIT. @new_blkg is always consumed on return. */ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct gendisk *disk, struct blkcg_gq *new_blkg) { struct blkcg_gq *blkg; int i, ret; lockdep_assert_held(&disk->queue->queue_lock); /* request_queue is dying, do not create/recreate a blkg */ if (blk_queue_dying(disk->queue)) { ret = -ENODEV; goto err_free_blkg; } /* blkg holds a reference to blkcg */ if (!css_tryget_online(&blkcg->css)) { ret = -ENODEV; goto err_free_blkg; } /* allocate */ if (!new_blkg) { new_blkg = blkg_alloc(blkcg, disk, GFP_NOWAIT | __GFP_NOWARN); if (unlikely(!new_blkg)) { ret = -ENOMEM; goto err_put_css; } } blkg = new_blkg; /* link parent */ if (blkcg_parent(blkcg)) { blkg->parent = blkg_lookup(blkcg_parent(blkcg), disk->queue); if (WARN_ON_ONCE(!blkg->parent)) { ret = -ENODEV; goto err_put_css; } blkg_get(blkg->parent); } /* invoke per-policy init */ for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && pol->pd_init_fn) pol->pd_init_fn(blkg->pd[i]); } /* insert */ spin_lock(&blkcg->lock); ret = radix_tree_insert(&blkcg->blkg_tree, disk->queue->id, blkg); if (likely(!ret)) { hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list); list_add(&blkg->q_node, &disk->queue->blkg_list); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i]) { if (pol->pd_online_fn) pol->pd_online_fn(blkg->pd[i]); blkg->pd[i]->online = true; } } } blkg->online = true; spin_unlock(&blkcg->lock); if (!ret) return blkg; /* @blkg failed fully initialized, use the usual release path */ blkg_put(blkg); return ERR_PTR(ret); err_put_css: css_put(&blkcg->css); err_free_blkg: if (new_blkg) blkg_free(new_blkg); return ERR_PTR(ret); } /** * blkg_lookup_create - lookup blkg, try to create one if not there * @blkcg: blkcg of interest * @disk: gendisk of interest * * Lookup blkg for the @blkcg - @disk pair. If it doesn't exist, try to * create one. blkg creation is performed recursively from blkcg_root such * that all non-root blkg's have access to the parent blkg. This function * should be called under RCU read lock and takes @disk->queue->queue_lock. * * Returns the blkg or the closest blkg if blkg_create() fails as it walks * down from root. */ static struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, struct gendisk *disk) { struct request_queue *q = disk->queue; struct blkcg_gq *blkg; unsigned long flags; WARN_ON_ONCE(!rcu_read_lock_held()); blkg = blkg_lookup(blkcg, q); if (blkg) return blkg; spin_lock_irqsave(&q->queue_lock, flags); blkg = blkg_lookup(blkcg, q); if (blkg) { if (blkcg != &blkcg_root && blkg != rcu_dereference(blkcg->blkg_hint)) rcu_assign_pointer(blkcg->blkg_hint, blkg); goto found; } /* * Create blkgs walking down from blkcg_root to @blkcg, so that all * non-root blkgs have access to their parents. Returns the closest * blkg to the intended blkg should blkg_create() fail. */ while (true) { struct blkcg *pos = blkcg; struct blkcg *parent = blkcg_parent(blkcg); struct blkcg_gq *ret_blkg = q->root_blkg; while (parent) { blkg = blkg_lookup(parent, q); if (blkg) { /* remember closest blkg */ ret_blkg = blkg; break; } pos = parent; parent = blkcg_parent(parent); } blkg = blkg_create(pos, disk, NULL); if (IS_ERR(blkg)) { blkg = ret_blkg; break; } if (pos == blkcg) break; } found: spin_unlock_irqrestore(&q->queue_lock, flags); return blkg; } static void blkg_destroy(struct blkcg_gq *blkg) { struct blkcg *blkcg = blkg->blkcg; int i; lockdep_assert_held(&blkg->q->queue_lock); lockdep_assert_held(&blkcg->lock); /* * blkg stays on the queue list until blkg_free_workfn(), see details in * blkg_free_workfn(), hence this function can be called from * blkcg_destroy_blkgs() first and again from blkg_destroy_all() before * blkg_free_workfn(). */ if (hlist_unhashed(&blkg->blkcg_node)) return; for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && blkg->pd[i]->online) { blkg->pd[i]->online = false; if (pol->pd_offline_fn) pol->pd_offline_fn(blkg->pd[i]); } } blkg->online = false; radix_tree_delete(&blkcg->blkg_tree, blkg->q->id); hlist_del_init_rcu(&blkg->blkcg_node); /* * Both setting lookup hint to and clearing it from @blkg are done * under queue_lock. If it's not pointing to @blkg now, it never * will. Hint assignment itself can race safely. */ if (rcu_access_pointer(blkcg->blkg_hint) == blkg) rcu_assign_pointer(blkcg->blkg_hint, NULL); /* * Put the reference taken at the time of creation so that when all * queues are gone, group can be destroyed. */ percpu_ref_kill(&blkg->refcnt); } static void blkg_destroy_all(struct gendisk *disk) { struct request_queue *q = disk->queue; struct blkcg_gq *blkg; int count = BLKG_DESTROY_BATCH_SIZE; int i; restart: spin_lock_irq(&q->queue_lock); list_for_each_entry(blkg, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; if (hlist_unhashed(&blkg->blkcg_node)) continue; spin_lock(&blkcg->lock); blkg_destroy(blkg); spin_unlock(&blkcg->lock); /* * in order to avoid holding the spin lock for too long, release * it when a batch of blkgs are destroyed. */ if (!(--count)) { count = BLKG_DESTROY_BATCH_SIZE; spin_unlock_irq(&q->queue_lock); cond_resched(); goto restart; } } /* * Mark policy deactivated since policy offline has been done, and * the free is scheduled, so future blkcg_deactivate_policy() can * be bypassed */ for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (pol) __clear_bit(pol->plid, q->blkcg_pols); } q->root_blkg = NULL; spin_unlock_irq(&q->queue_lock); } static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src) { int i; for (i = 0; i < BLKG_IOSTAT_NR; i++) { dst->bytes[i] = src->bytes[i]; dst->ios[i] = src->ios[i]; } } static void __blkg_clear_stat(struct blkg_iostat_set *bis) { struct blkg_iostat cur = {0}; unsigned long flags; flags = u64_stats_update_begin_irqsave(&bis->sync); blkg_iostat_set(&bis->cur, &cur); blkg_iostat_set(&bis->last, &cur); u64_stats_update_end_irqrestore(&bis->sync, flags); } static void blkg_clear_stat(struct blkcg_gq *blkg) { int cpu; for_each_possible_cpu(cpu) { struct blkg_iostat_set *s = per_cpu_ptr(blkg->iostat_cpu, cpu); __blkg_clear_stat(s); } __blkg_clear_stat(&blkg->iostat); } static int blkcg_reset_stats(struct cgroup_subsys_state *css, struct cftype *cftype, u64 val) { struct blkcg *blkcg = css_to_blkcg(css); struct blkcg_gq *blkg; int i; mutex_lock(&blkcg_pol_mutex); spin_lock_irq(&blkcg->lock); /* * Note that stat reset is racy - it doesn't synchronize against * stat updates. This is a debug feature which shouldn't exist * anyway. If you get hit by a race, retry. */ hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { blkg_clear_stat(blkg); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && pol->pd_reset_stats_fn) pol->pd_reset_stats_fn(blkg->pd[i]); } } spin_unlock_irq(&blkcg->lock); mutex_unlock(&blkcg_pol_mutex); return 0; } const char *blkg_dev_name(struct blkcg_gq *blkg) { if (!blkg->q->disk) return NULL; return bdi_dev_name(blkg->q->disk->bdi); } /** * blkcg_print_blkgs - helper for printing per-blkg data * @sf: seq_file to print to * @blkcg: blkcg of interest * @prfill: fill function to print out a blkg * @pol: policy in question * @data: data to be passed to @prfill * @show_total: to print out sum of prfill return values or not * * This function invokes @prfill on each blkg of @blkcg if pd for the * policy specified by @pol exists. @prfill is invoked with @sf, the * policy data and @data and the matching queue lock held. If @show_total * is %true, the sum of the return values from @prfill is printed with * "Total" label at the end. * * This is to be used to construct print functions for * cftype->read_seq_string method. */ void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, u64 (*prfill)(struct seq_file *, struct blkg_policy_data *, int), const struct blkcg_policy *pol, int data, bool show_total) { struct blkcg_gq *blkg; u64 total = 0; rcu_read_lock(); hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { spin_lock_irq(&blkg->q->queue_lock); if (blkcg_policy_enabled(blkg->q, pol)) total += prfill(sf, blkg->pd[pol->plid], data); spin_unlock_irq(&blkg->q->queue_lock); } rcu_read_unlock(); if (show_total) seq_printf(sf, "Total %llu\n", (unsigned long long)total); } EXPORT_SYMBOL_GPL(blkcg_print_blkgs); /** * __blkg_prfill_u64 - prfill helper for a single u64 value * @sf: seq_file to print to * @pd: policy private data of interest * @v: value to print * * Print @v to @sf for the device associated with @pd. */ u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v) { const char *dname = blkg_dev_name(pd->blkg); if (!dname) return 0; seq_printf(sf, "%s %llu\n", dname, (unsigned long long)v); return v; } EXPORT_SYMBOL_GPL(__blkg_prfill_u64); /** * blkg_conf_init - initialize a blkg_conf_ctx * @ctx: blkg_conf_ctx to initialize * @input: input string * * Initialize @ctx which can be used to parse blkg config input string @input. * Once initialized, @ctx can be used with blkg_conf_open_bdev() and * blkg_conf_prep(), and must be cleaned up with blkg_conf_exit(). */ void blkg_conf_init(struct blkg_conf_ctx *ctx, char *input) { *ctx = (struct blkg_conf_ctx){ .input = input }; } EXPORT_SYMBOL_GPL(blkg_conf_init); /** * blkg_conf_open_bdev - parse and open bdev for per-blkg config update * @ctx: blkg_conf_ctx initialized with blkg_conf_init() * * Parse the device node prefix part, MAJ:MIN, of per-blkg config update from * @ctx->input and get and store the matching bdev in @ctx->bdev. @ctx->body is * set to point past the device node prefix. * * This function may be called multiple times on @ctx and the extra calls become * NOOPs. blkg_conf_prep() implicitly calls this function. Use this function * explicitly if bdev access is needed without resolving the blkcg / policy part * of @ctx->input. Returns -errno on error. */ int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx) { char *input = ctx->input; unsigned int major, minor; struct block_device *bdev; int key_len; if (ctx->bdev) return 0; if (sscanf(input, "%u:%u%n", &major, &minor, &key_len) != 2) return -EINVAL; input += key_len; if (!isspace(*input)) return -EINVAL; input = skip_spaces(input); bdev = blkdev_get_no_open(MKDEV(major, minor)); if (!bdev) return -ENODEV; if (bdev_is_partition(bdev)) { blkdev_put_no_open(bdev); return -ENODEV; } mutex_lock(&bdev->bd_queue->rq_qos_mutex); if (!disk_live(bdev->bd_disk)) { blkdev_put_no_open(bdev); mutex_unlock(&bdev->bd_queue->rq_qos_mutex); return -ENODEV; } ctx->body = input; ctx->bdev = bdev; return 0; } /** * blkg_conf_prep - parse and prepare for per-blkg config update * @blkcg: target block cgroup * @pol: target policy * @ctx: blkg_conf_ctx initialized with blkg_conf_init() * * Parse per-blkg config update from @ctx->input and initialize @ctx * accordingly. On success, @ctx->body points to the part of @ctx->input * following MAJ:MIN, @ctx->bdev points to the target block device and * @ctx->blkg to the blkg being configured. * * blkg_conf_open_bdev() may be called on @ctx beforehand. On success, this * function returns with queue lock held and must be followed by * blkg_conf_exit(). */ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, struct blkg_conf_ctx *ctx) __acquires(&bdev->bd_queue->queue_lock) { struct gendisk *disk; struct request_queue *q; struct blkcg_gq *blkg; int ret; ret = blkg_conf_open_bdev(ctx); if (ret) return ret; disk = ctx->bdev->bd_disk; q = disk->queue; /* * blkcg_deactivate_policy() requires queue to be frozen, we can grab * q_usage_counter to prevent concurrent with blkcg_deactivate_policy(). */ ret = blk_queue_enter(q, 0); if (ret) goto fail; spin_lock_irq(&q->queue_lock); if (!blkcg_policy_enabled(q, pol)) { ret = -EOPNOTSUPP; goto fail_unlock; } blkg = blkg_lookup(blkcg, q); if (blkg) goto success; /* * Create blkgs walking down from blkcg_root to @blkcg, so that all * non-root blkgs have access to their parents. */ while (true) { struct blkcg *pos = blkcg; struct blkcg *parent; struct blkcg_gq *new_blkg; parent = blkcg_parent(blkcg); while (parent && !blkg_lookup(parent, q)) { pos = parent; parent = blkcg_parent(parent); } /* Drop locks to do new blkg allocation with GFP_KERNEL. */ spin_unlock_irq(&q->queue_lock); new_blkg = blkg_alloc(pos, disk, GFP_KERNEL); if (unlikely(!new_blkg)) { ret = -ENOMEM; goto fail_exit_queue; } if (radix_tree_preload(GFP_KERNEL)) { blkg_free(new_blkg); ret = -ENOMEM; goto fail_exit_queue; } spin_lock_irq(&q->queue_lock); if (!blkcg_policy_enabled(q, pol)) { blkg_free(new_blkg); ret = -EOPNOTSUPP; goto fail_preloaded; } blkg = blkg_lookup(pos, q); if (blkg) { blkg_free(new_blkg); } else { blkg = blkg_create(pos, disk, new_blkg); if (IS_ERR(blkg)) { ret = PTR_ERR(blkg); goto fail_preloaded; } } radix_tree_preload_end(); if (pos == blkcg) goto success; } success: blk_queue_exit(q); ctx->blkg = blkg; return 0; fail_preloaded: radix_tree_preload_end(); fail_unlock: spin_unlock_irq(&q->queue_lock); fail_exit_queue: blk_queue_exit(q); fail: /* * If queue was bypassing, we should retry. Do so after a * short msleep(). It isn't strictly necessary but queue * can be bypassing for some time and it's always nice to * avoid busy looping. */ if (ret == -EBUSY) { msleep(10); ret = restart_syscall(); } return ret; } EXPORT_SYMBOL_GPL(blkg_conf_prep); /** * blkg_conf_exit - clean up per-blkg config update * @ctx: blkg_conf_ctx initialized with blkg_conf_init() * * Clean up after per-blkg config update. This function must be called on all * blkg_conf_ctx's initialized with blkg_conf_init(). */ void blkg_conf_exit(struct blkg_conf_ctx *ctx) __releases(&ctx->bdev->bd_queue->queue_lock) __releases(&ctx->bdev->bd_queue->rq_qos_mutex) { if (ctx->blkg) { spin_unlock_irq(&bdev_get_queue(ctx->bdev)->queue_lock); ctx->blkg = NULL; } if (ctx->bdev) { mutex_unlock(&ctx->bdev->bd_queue->rq_qos_mutex); blkdev_put_no_open(ctx->bdev); ctx->body = NULL; ctx->bdev = NULL; } } EXPORT_SYMBOL_GPL(blkg_conf_exit); static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src) { int i; for (i = 0; i < BLKG_IOSTAT_NR; i++) { dst->bytes[i] += src->bytes[i]; dst->ios[i] += src->ios[i]; } } static void blkg_iostat_sub(struct blkg_iostat *dst, struct blkg_iostat *src) { int i; for (i = 0; i < BLKG_IOSTAT_NR; i++) { dst->bytes[i] -= src->bytes[i]; dst->ios[i] -= src->ios[i]; } } static void blkcg_iostat_update(struct blkcg_gq *blkg, struct blkg_iostat *cur, struct blkg_iostat *last) { struct blkg_iostat delta; unsigned long flags; /* propagate percpu delta to global */ flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync); blkg_iostat_set(&delta, cur); blkg_iostat_sub(&delta, last); blkg_iostat_add(&blkg->iostat.cur, &delta); blkg_iostat_add(last, &delta); u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags); } static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu) { struct llist_head *lhead = per_cpu_ptr(blkcg->lhead, cpu); struct llist_node *lnode; struct blkg_iostat_set *bisc, *next_bisc; unsigned long flags; rcu_read_lock(); lnode = llist_del_all(lhead); if (!lnode) goto out; /* * For covering concurrent parent blkg update from blkg_release(). * * When flushing from cgroup, cgroup_rstat_lock is always held, so * this lock won't cause contention most of time. */ raw_spin_lock_irqsave(&blkg_stat_lock, flags); /* * Iterate only the iostat_cpu's queued in the lockless list. */ llist_for_each_entry_safe(bisc, next_bisc, lnode, lnode) { struct blkcg_gq *blkg = bisc->blkg; struct blkcg_gq *parent = blkg->parent; struct blkg_iostat cur; unsigned int seq; /* * Order assignment of `next_bisc` from `bisc->lnode.next` in * llist_for_each_entry_safe and clearing `bisc->lqueued` for * avoiding to assign `next_bisc` with new next pointer added * in blk_cgroup_bio_start() in case of re-ordering. * * The pair barrier is implied in llist_add() in blk_cgroup_bio_start(). */ smp_mb(); WRITE_ONCE(bisc->lqueued, false); if (bisc == &blkg->iostat) goto propagate_up; /* propagate up to parent only */ /* fetch the current per-cpu values */ do { seq = u64_stats_fetch_begin(&bisc->sync); blkg_iostat_set(&cur, &bisc->cur); } while (u64_stats_fetch_retry(&bisc->sync, seq)); blkcg_iostat_update(blkg, &cur, &bisc->last); propagate_up: /* propagate global delta to parent (unless that's root) */ if (parent && parent->parent) { blkcg_iostat_update(parent, &blkg->iostat.cur, &blkg->iostat.last); /* * Queue parent->iostat to its blkcg's lockless * list to propagate up to the grandparent if the * iostat hasn't been queued yet. */ if (!parent->iostat.lqueued) { struct llist_head *plhead; plhead = per_cpu_ptr(parent->blkcg->lhead, cpu); llist_add(&parent->iostat.lnode, plhead); parent->iostat.lqueued = true; } } } raw_spin_unlock_irqrestore(&blkg_stat_lock, flags); out: rcu_read_unlock(); } static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu) { /* Root-level stats are sourced from system-wide IO stats */ if (cgroup_parent(css->cgroup)) __blkcg_rstat_flush(css_to_blkcg(css), cpu); } /* * We source root cgroup stats from the system-wide stats to avoid * tracking the same information twice and incurring overhead when no * cgroups are defined. For that reason, cgroup_rstat_flush in * blkcg_print_stat does not actually fill out the iostat in the root * cgroup's blkcg_gq. * * However, we would like to re-use the printing code between the root and * non-root cgroups to the extent possible. For that reason, we simulate * flushing the root cgroup's stats by explicitly filling in the iostat * with disk level statistics. */ static void blkcg_fill_root_iostats(void) { struct class_dev_iter iter; struct device *dev; class_dev_iter_init(&iter, &block_class, NULL, &disk_type); while ((dev = class_dev_iter_next(&iter))) { struct block_device *bdev = dev_to_bdev(dev); struct blkcg_gq *blkg = bdev->bd_disk->queue->root_blkg; struct blkg_iostat tmp; int cpu; unsigned long flags; memset(&tmp, 0, sizeof(tmp)); for_each_possible_cpu(cpu) { struct disk_stats *cpu_dkstats; cpu_dkstats = per_cpu_ptr(bdev->bd_stats, cpu); tmp.ios[BLKG_IOSTAT_READ] += cpu_dkstats->ios[STAT_READ]; tmp.ios[BLKG_IOSTAT_WRITE] += cpu_dkstats->ios[STAT_WRITE]; tmp.ios[BLKG_IOSTAT_DISCARD] += cpu_dkstats->ios[STAT_DISCARD]; // convert sectors to bytes tmp.bytes[BLKG_IOSTAT_READ] += cpu_dkstats->sectors[STAT_READ] << 9; tmp.bytes[BLKG_IOSTAT_WRITE] += cpu_dkstats->sectors[STAT_WRITE] << 9; tmp.bytes[BLKG_IOSTAT_DISCARD] += cpu_dkstats->sectors[STAT_DISCARD] << 9; } flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync); blkg_iostat_set(&blkg->iostat.cur, &tmp); u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags); } } static void blkcg_print_one_stat(struct blkcg_gq *blkg, struct seq_file *s) { struct blkg_iostat_set *bis = &blkg->iostat; u64 rbytes, wbytes, rios, wios, dbytes, dios; const char *dname; unsigned seq; int i; if (!blkg->online) return; dname = blkg_dev_name(blkg); if (!dname) return; seq_printf(s, "%s ", dname); do { seq = u64_stats_fetch_begin(&bis->sync); rbytes = bis->cur.bytes[BLKG_IOSTAT_READ]; wbytes = bis->cur.bytes[BLKG_IOSTAT_WRITE]; dbytes = bis->cur.bytes[BLKG_IOSTAT_DISCARD]; rios = bis->cur.ios[BLKG_IOSTAT_READ]; wios = bis->cur.ios[BLKG_IOSTAT_WRITE]; dios = bis->cur.ios[BLKG_IOSTAT_DISCARD]; } while (u64_stats_fetch_retry(&bis->sync, seq)); if (rbytes || wbytes || rios || wios) { seq_printf(s, "rbytes=%llu wbytes=%llu rios=%llu wios=%llu dbytes=%llu dios=%llu", rbytes, wbytes, rios, wios, dbytes, dios); } if (blkcg_debug_stats && atomic_read(&blkg->use_delay)) { seq_printf(s, " use_delay=%d delay_nsec=%llu", atomic_read(&blkg->use_delay), atomic64_read(&blkg->delay_nsec)); } for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (!blkg->pd[i] || !pol->pd_stat_fn) continue; pol->pd_stat_fn(blkg->pd[i], s); } seq_puts(s, "\n"); } static int blkcg_print_stat(struct seq_file *sf, void *v) { struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); struct blkcg_gq *blkg; if (!seq_css(sf)->parent) blkcg_fill_root_iostats(); else cgroup_rstat_flush(blkcg->css.cgroup); rcu_read_lock(); hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { spin_lock_irq(&blkg->q->queue_lock); blkcg_print_one_stat(blkg, sf); spin_unlock_irq(&blkg->q->queue_lock); } rcu_read_unlock(); return 0; } static struct cftype blkcg_files[] = { { .name = "stat", .seq_show = blkcg_print_stat, }, { } /* terminate */ }; static struct cftype blkcg_legacy_files[] = { { .name = "reset_stats", .write_u64 = blkcg_reset_stats, }, { } /* terminate */ }; #ifdef CONFIG_CGROUP_WRITEBACK struct list_head *blkcg_get_cgwb_list(struct cgroup_subsys_state *css) { return &css_to_blkcg(css)->cgwb_list; } #endif /* * blkcg destruction is a three-stage process. * * 1. Destruction starts. The blkcg_css_offline() callback is invoked * which offlines writeback. Here we tie the next stage of blkg destruction * to the completion of writeback associated with the blkcg. This lets us * avoid punting potentially large amounts of outstanding writeback to root * while maintaining any ongoing policies. The next stage is triggered when * the nr_cgwbs count goes to zero. * * 2. When the nr_cgwbs count goes to zero, blkcg_destroy_blkgs() is called * and handles the destruction of blkgs. Here the css reference held by * the blkg is put back eventually allowing blkcg_css_free() to be called. * This work may occur in cgwb_release_workfn() on the cgwb_release * workqueue. Any submitted ios that fail to get the blkg ref will be * punted to the root_blkg. * * 3. Once the blkcg ref count goes to zero, blkcg_css_free() is called. * This finally frees the blkcg. */ /** * blkcg_destroy_blkgs - responsible for shooting down blkgs * @blkcg: blkcg of interest * * blkgs should be removed while holding both q and blkcg locks. As blkcg lock * is nested inside q lock, this function performs reverse double lock dancing. * Destroying the blkgs releases the reference held on the blkcg's css allowing * blkcg_css_free to eventually be called. * * This is the blkcg counterpart of ioc_release_fn(). */ static void blkcg_destroy_blkgs(struct blkcg *blkcg) { might_sleep(); spin_lock_irq(&blkcg->lock); while (!hlist_empty(&blkcg->blkg_list)) { struct blkcg_gq *blkg = hlist_entry(blkcg->blkg_list.first, struct blkcg_gq, blkcg_node); struct request_queue *q = blkg->q; if (need_resched() || !spin_trylock(&q->queue_lock)) { /* * Given that the system can accumulate a huge number * of blkgs in pathological cases, check to see if we * need to rescheduling to avoid softlockup. */ spin_unlock_irq(&blkcg->lock); cond_resched(); spin_lock_irq(&blkcg->lock); continue; } blkg_destroy(blkg); spin_unlock(&q->queue_lock); } spin_unlock_irq(&blkcg->lock); } /** * blkcg_pin_online - pin online state * @blkcg_css: blkcg of interest * * While pinned, a blkcg is kept online. This is primarily used to * impedance-match blkg and cgwb lifetimes so that blkg doesn't go offline * while an associated cgwb is still active. */ void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css) { refcount_inc(&css_to_blkcg(blkcg_css)->online_pin); } /** * blkcg_unpin_online - unpin online state * @blkcg_css: blkcg of interest * * This is primarily used to impedance-match blkg and cgwb lifetimes so * that blkg doesn't go offline while an associated cgwb is still active. * When this count goes to zero, all active cgwbs have finished so the * blkcg can continue destruction by calling blkcg_destroy_blkgs(). */ void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css) { struct blkcg *blkcg = css_to_blkcg(blkcg_css); do { struct blkcg *parent; if (!refcount_dec_and_test(&blkcg->online_pin)) break; parent = blkcg_parent(blkcg); blkcg_destroy_blkgs(blkcg); blkcg = parent; } while (blkcg); } /** * blkcg_css_offline - cgroup css_offline callback * @css: css of interest * * This function is called when @css is about to go away. Here the cgwbs are * offlined first and only once writeback associated with the blkcg has * finished do we start step 2 (see above). */ static void blkcg_css_offline(struct cgroup_subsys_state *css) { /* this prevents anyone from attaching or migrating to this blkcg */ wb_blkcg_offline(css); /* put the base online pin allowing step 2 to be triggered */ blkcg_unpin_online(css); } static void blkcg_css_free(struct cgroup_subsys_state *css) { struct blkcg *blkcg = css_to_blkcg(css); int i; mutex_lock(&blkcg_pol_mutex); list_del(&blkcg->all_blkcgs_node); for (i = 0; i < BLKCG_MAX_POLS; i++) if (blkcg->cpd[i]) blkcg_policy[i]->cpd_free_fn(blkcg->cpd[i]); mutex_unlock(&blkcg_pol_mutex); free_percpu(blkcg->lhead); kfree(blkcg); } static struct cgroup_subsys_state * blkcg_css_alloc(struct cgroup_subsys_state *parent_css) { struct blkcg *blkcg; int i; mutex_lock(&blkcg_pol_mutex); if (!parent_css) { blkcg = &blkcg_root; } else { blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL); if (!blkcg) goto unlock; } if (init_blkcg_llists(blkcg)) goto free_blkcg; for (i = 0; i < BLKCG_MAX_POLS ; i++) { struct blkcg_policy *pol = blkcg_policy[i]; struct blkcg_policy_data *cpd; /* * If the policy hasn't been attached yet, wait for it * to be attached before doing anything else. Otherwise, * check if the policy requires any specific per-cgroup * data: if it does, allocate and initialize it. */ if (!pol || !pol->cpd_alloc_fn) continue; cpd = pol->cpd_alloc_fn(GFP_KERNEL); if (!cpd) goto free_pd_blkcg; blkcg->cpd[i] = cpd; cpd->blkcg = blkcg; cpd->plid = i; } spin_lock_init(&blkcg->lock); refcount_set(&blkcg->online_pin, 1); INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_NOWAIT | __GFP_NOWARN); INIT_HLIST_HEAD(&blkcg->blkg_list); #ifdef CONFIG_CGROUP_WRITEBACK INIT_LIST_HEAD(&blkcg->cgwb_list); #endif list_add_tail(&blkcg->all_blkcgs_node, &all_blkcgs); mutex_unlock(&blkcg_pol_mutex); return &blkcg->css; free_pd_blkcg: for (i--; i >= 0; i--) if (blkcg->cpd[i]) blkcg_policy[i]->cpd_free_fn(blkcg->cpd[i]); free_percpu(blkcg->lhead); free_blkcg: if (blkcg != &blkcg_root) kfree(blkcg); unlock: mutex_unlock(&blkcg_pol_mutex); return ERR_PTR(-ENOMEM); } static int blkcg_css_online(struct cgroup_subsys_state *css) { struct blkcg *parent = blkcg_parent(css_to_blkcg(css)); /* * blkcg_pin_online() is used to delay blkcg offline so that blkgs * don't go offline while cgwbs are still active on them. Pin the * parent so that offline always happens towards the root. */ if (parent) blkcg_pin_online(&parent->css); return 0; } void blkg_init_queue(struct request_queue *q) { INIT_LIST_HEAD(&q->blkg_list); mutex_init(&q->blkcg_mutex); } int blkcg_init_disk(struct gendisk *disk) { struct request_queue *q = disk->queue; struct blkcg_gq *new_blkg, *blkg; bool preloaded; new_blkg = blkg_alloc(&blkcg_root, disk, GFP_KERNEL); if (!new_blkg) return -ENOMEM; preloaded = !radix_tree_preload(GFP_KERNEL); /* Make sure the root blkg exists. */ /* spin_lock_irq can serve as RCU read-side critical section. */ spin_lock_irq(&q->queue_lock); blkg = blkg_create(&blkcg_root, disk, new_blkg); if (IS_ERR(blkg)) goto err_unlock; q->root_blkg = blkg; spin_unlock_irq(&q->queue_lock); if (preloaded) radix_tree_preload_end(); return 0; err_unlock: spin_unlock_irq(&q->queue_lock); if (preloaded) radix_tree_preload_end(); return PTR_ERR(blkg); } void blkcg_exit_disk(struct gendisk *disk) { blkg_destroy_all(disk); blk_throtl_exit(disk); } static void blkcg_exit(struct task_struct *tsk) { if (tsk->throttle_disk) put_disk(tsk->throttle_disk); tsk->throttle_disk = NULL; } struct cgroup_subsys io_cgrp_subsys = { .css_alloc = blkcg_css_alloc, .css_online = blkcg_css_online, .css_offline = blkcg_css_offline, .css_free = blkcg_css_free, .css_rstat_flush = blkcg_rstat_flush, .dfl_cftypes = blkcg_files, .legacy_cftypes = blkcg_legacy_files, .legacy_name = "blkio", .exit = blkcg_exit, #ifdef CONFIG_MEMCG /* * This ensures that, if available, memcg is automatically enabled * together on the default hierarchy so that the owner cgroup can * be retrieved from writeback pages. */ .depends_on = 1 << memory_cgrp_id, #endif }; EXPORT_SYMBOL_GPL(io_cgrp_subsys); /** * blkcg_activate_policy - activate a blkcg policy on a gendisk * @disk: gendisk of interest * @pol: blkcg policy to activate * * Activate @pol on @disk. Requires %GFP_KERNEL context. @disk goes through * bypass mode to populate its blkgs with policy_data for @pol. * * Activation happens with @disk bypassed, so nobody would be accessing blkgs * from IO path. Update of each blkg is protected by both queue and blkcg * locks so that holding either lock and testing blkcg_policy_enabled() is * always enough for dereferencing policy data. * * The caller is responsible for synchronizing [de]activations and policy * [un]registerations. Returns 0 on success, -errno on failure. */ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol) { struct request_queue *q = disk->queue; struct blkg_policy_data *pd_prealloc = NULL; struct blkcg_gq *blkg, *pinned_blkg = NULL; int ret; if (blkcg_policy_enabled(q, pol)) return 0; /* * Policy is allowed to be registered without pd_alloc_fn/pd_free_fn, * for example, ioprio. Such policy will work on blkcg level, not disk * level, and don't need to be activated. */ if (WARN_ON_ONCE(!pol->pd_alloc_fn || !pol->pd_free_fn)) return -EINVAL; if (queue_is_mq(q)) blk_mq_freeze_queue(q); retry: spin_lock_irq(&q->queue_lock); /* blkg_list is pushed at the head, reverse walk to initialize parents first */ list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) { struct blkg_policy_data *pd; if (blkg->pd[pol->plid]) continue; /* If prealloc matches, use it; otherwise try GFP_NOWAIT */ if (blkg == pinned_blkg) { pd = pd_prealloc; pd_prealloc = NULL; } else { pd = pol->pd_alloc_fn(disk, blkg->blkcg, GFP_NOWAIT | __GFP_NOWARN); } if (!pd) { /* * GFP_NOWAIT failed. Free the existing one and * prealloc for @blkg w/ GFP_KERNEL. */ if (pinned_blkg) blkg_put(pinned_blkg); blkg_get(blkg); pinned_blkg = blkg; spin_unlock_irq(&q->queue_lock); if (pd_prealloc) pol->pd_free_fn(pd_prealloc); pd_prealloc = pol->pd_alloc_fn(disk, blkg->blkcg, GFP_KERNEL); if (pd_prealloc) goto retry; else goto enomem; } spin_lock(&blkg->blkcg->lock); pd->blkg = blkg; pd->plid = pol->plid; blkg->pd[pol->plid] = pd; if (pol->pd_init_fn) pol->pd_init_fn(pd); if (pol->pd_online_fn) pol->pd_online_fn(pd); pd->online = true; spin_unlock(&blkg->blkcg->lock); } __set_bit(pol->plid, q->blkcg_pols); ret = 0; spin_unlock_irq(&q->queue_lock); out: if (queue_is_mq(q)) blk_mq_unfreeze_queue(q); if (pinned_blkg) blkg_put(pinned_blkg); if (pd_prealloc) pol->pd_free_fn(pd_prealloc); return ret; enomem: /* alloc failed, take down everything */ spin_lock_irq(&q->queue_lock); list_for_each_entry(blkg, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; struct blkg_policy_data *pd; spin_lock(&blkcg->lock); pd = blkg->pd[pol->plid]; if (pd) { if (pd->online && pol->pd_offline_fn) pol->pd_offline_fn(pd); pd->online = false; pol->pd_free_fn(pd); blkg->pd[pol->plid] = NULL; } spin_unlock(&blkcg->lock); } spin_unlock_irq(&q->queue_lock); ret = -ENOMEM; goto out; } EXPORT_SYMBOL_GPL(blkcg_activate_policy); /** * blkcg_deactivate_policy - deactivate a blkcg policy on a gendisk * @disk: gendisk of interest * @pol: blkcg policy to deactivate * * Deactivate @pol on @disk. Follows the same synchronization rules as * blkcg_activate_policy(). */ void blkcg_deactivate_policy(struct gendisk *disk, const struct blkcg_policy *pol) { struct request_queue *q = disk->queue; struct blkcg_gq *blkg; if (!blkcg_policy_enabled(q, pol)) return; if (queue_is_mq(q)) blk_mq_freeze_queue(q); mutex_lock(&q->blkcg_mutex); spin_lock_irq(&q->queue_lock); __clear_bit(pol->plid, q->blkcg_pols); list_for_each_entry(blkg, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; spin_lock(&blkcg->lock); if (blkg->pd[pol->plid]) { if (blkg->pd[pol->plid]->online && pol->pd_offline_fn) pol->pd_offline_fn(blkg->pd[pol->plid]); pol->pd_free_fn(blkg->pd[pol->plid]); blkg->pd[pol->plid] = NULL; } spin_unlock(&blkcg->lock); } spin_unlock_irq(&q->queue_lock); mutex_unlock(&q->blkcg_mutex); if (queue_is_mq(q)) blk_mq_unfreeze_queue(q); } EXPORT_SYMBOL_GPL(blkcg_deactivate_policy); static void blkcg_free_all_cpd(struct blkcg_policy *pol) { struct blkcg *blkcg; list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { if (blkcg->cpd[pol->plid]) { pol->cpd_free_fn(blkcg->cpd[pol->plid]); blkcg->cpd[pol->plid] = NULL; } } } /** * blkcg_policy_register - register a blkcg policy * @pol: blkcg policy to register * * Register @pol with blkcg core. Might sleep and @pol may be modified on * successful registration. Returns 0 on success and -errno on failure. */ int blkcg_policy_register(struct blkcg_policy *pol) { struct blkcg *blkcg; int i, ret; mutex_lock(&blkcg_pol_register_mutex); mutex_lock(&blkcg_pol_mutex); /* find an empty slot */ ret = -ENOSPC; for (i = 0; i < BLKCG_MAX_POLS; i++) if (!blkcg_policy[i]) break; if (i >= BLKCG_MAX_POLS) { pr_warn("blkcg_policy_register: BLKCG_MAX_POLS too small\n"); goto err_unlock; } /* * Make sure cpd/pd_alloc_fn and cpd/pd_free_fn in pairs, and policy * without pd_alloc_fn/pd_free_fn can't be activated. */ if ((!pol->cpd_alloc_fn ^ !pol->cpd_free_fn) || (!pol->pd_alloc_fn ^ !pol->pd_free_fn)) goto err_unlock; /* register @pol */ pol->plid = i; blkcg_policy[pol->plid] = pol; /* allocate and install cpd's */ if (pol->cpd_alloc_fn) { list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { struct blkcg_policy_data *cpd; cpd = pol->cpd_alloc_fn(GFP_KERNEL); if (!cpd) goto err_free_cpds; blkcg->cpd[pol->plid] = cpd; cpd->blkcg = blkcg; cpd->plid = pol->plid; } } mutex_unlock(&blkcg_pol_mutex); /* everything is in place, add intf files for the new policy */ if (pol->dfl_cftypes) WARN_ON(cgroup_add_dfl_cftypes(&io_cgrp_subsys, pol->dfl_cftypes)); if (pol->legacy_cftypes) WARN_ON(cgroup_add_legacy_cftypes(&io_cgrp_subsys, pol->legacy_cftypes)); mutex_unlock(&blkcg_pol_register_mutex); return 0; err_free_cpds: if (pol->cpd_free_fn) blkcg_free_all_cpd(pol); blkcg_policy[pol->plid] = NULL; err_unlock: mutex_unlock(&blkcg_pol_mutex); mutex_unlock(&blkcg_pol_register_mutex); return ret; } EXPORT_SYMBOL_GPL(blkcg_policy_register); /** * blkcg_policy_unregister - unregister a blkcg policy * @pol: blkcg policy to unregister * * Undo blkcg_policy_register(@pol). Might sleep. */ void blkcg_policy_unregister(struct blkcg_policy *pol) { mutex_lock(&blkcg_pol_register_mutex); if (WARN_ON(blkcg_policy[pol->plid] != pol)) goto out_unlock; /* kill the intf files first */ if (pol->dfl_cftypes) cgroup_rm_cftypes(pol->dfl_cftypes); if (pol->legacy_cftypes) cgroup_rm_cftypes(pol->legacy_cftypes); /* remove cpds and unregister */ mutex_lock(&blkcg_pol_mutex); if (pol->cpd_free_fn) blkcg_free_all_cpd(pol); blkcg_policy[pol->plid] = NULL; mutex_unlock(&blkcg_pol_mutex); out_unlock: mutex_unlock(&blkcg_pol_register_mutex); } EXPORT_SYMBOL_GPL(blkcg_policy_unregister); /* * Scale the accumulated delay based on how long it has been since we updated * the delay. We only call this when we are adding delay, in case it's been a * while since we added delay, and when we are checking to see if we need to * delay a task, to account for any delays that may have occurred. */ static void blkcg_scale_delay(struct blkcg_gq *blkg, u64 now) { u64 old = atomic64_read(&blkg->delay_start); /* negative use_delay means no scaling, see blkcg_set_delay() */ if (atomic_read(&blkg->use_delay) < 0) return; /* * We only want to scale down every second. The idea here is that we * want to delay people for min(delay_nsec, NSEC_PER_SEC) in a certain * time window. We only want to throttle tasks for recent delay that * has occurred, in 1 second time windows since that's the maximum * things can be throttled. We save the current delay window in * blkg->last_delay so we know what amount is still left to be charged * to the blkg from this point onward. blkg->last_use keeps track of * the use_delay counter. The idea is if we're unthrottling the blkg we * are ok with whatever is happening now, and we can take away more of * the accumulated delay as we've already throttled enough that * everybody is happy with their IO latencies. */ if (time_before64(old + NSEC_PER_SEC, now) && atomic64_try_cmpxchg(&blkg->delay_start, &old, now)) { u64 cur = atomic64_read(&blkg->delay_nsec); u64 sub = min_t(u64, blkg->last_delay, now - old); int cur_use = atomic_read(&blkg->use_delay); /* * We've been unthrottled, subtract a larger chunk of our * accumulated delay. */ if (cur_use < blkg->last_use) sub = max_t(u64, sub, blkg->last_delay >> 1); /* * This shouldn't happen, but handle it anyway. Our delay_nsec * should only ever be growing except here where we subtract out * min(last_delay, 1 second), but lord knows bugs happen and I'd * rather not end up with negative numbers. */ if (unlikely(cur < sub)) { atomic64_set(&blkg->delay_nsec, 0); blkg->last_delay = 0; } else { atomic64_sub(sub, &blkg->delay_nsec); blkg->last_delay = cur - sub; } blkg->last_use = cur_use; } } /* * This is called when we want to actually walk up the hierarchy and check to * see if we need to throttle, and then actually throttle if there is some * accumulated delay. This should only be called upon return to user space so * we're not holding some lock that would induce a priority inversion. */ static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay) { unsigned long pflags; bool clamp; u64 now = blk_time_get_ns(); u64 exp; u64 delay_nsec = 0; int tok; while (blkg->parent) { int use_delay = atomic_read(&blkg->use_delay); if (use_delay) { u64 this_delay; blkcg_scale_delay(blkg, now); this_delay = atomic64_read(&blkg->delay_nsec); if (this_delay > delay_nsec) { delay_nsec = this_delay; clamp = use_delay > 0; } } blkg = blkg->parent; } if (!delay_nsec) return; /* * Let's not sleep for all eternity if we've amassed a huge delay. * Swapping or metadata IO can accumulate 10's of seconds worth of * delay, and we want userspace to be able to do _something_ so cap the * delays at 0.25s. If there's 10's of seconds worth of delay then the * tasks will be delayed for 0.25 second for every syscall. If * blkcg_set_delay() was used as indicated by negative use_delay, the * caller is responsible for regulating the range. */ if (clamp) delay_nsec = min_t(u64, delay_nsec, 250 * NSEC_PER_MSEC); if (use_memdelay) psi_memstall_enter(&pflags); exp = ktime_add_ns(now, delay_nsec); tok = io_schedule_prepare(); do { __set_current_state(TASK_KILLABLE); if (!schedule_hrtimeout(&exp, HRTIMER_MODE_ABS)) break; } while (!fatal_signal_pending(current)); io_schedule_finish(tok); if (use_memdelay) psi_memstall_leave(&pflags); } /** * blkcg_maybe_throttle_current - throttle the current task if it has been marked * * This is only called if we've been marked with set_notify_resume(). Obviously * we can be set_notify_resume() for reasons other than blkcg throttling, so we * check to see if current->throttle_disk is set and if not this doesn't do * anything. This should only ever be called by the resume code, it's not meant * to be called by people willy-nilly as it will actually do the work to * throttle the task if it is setup for throttling. */ void blkcg_maybe_throttle_current(void) { struct gendisk *disk = current->throttle_disk; struct blkcg *blkcg; struct blkcg_gq *blkg; bool use_memdelay = current->use_memdelay; if (!disk) return; current->throttle_disk = NULL; current->use_memdelay = false; rcu_read_lock(); blkcg = css_to_blkcg(blkcg_css()); if (!blkcg) goto out; blkg = blkg_lookup(blkcg, disk->queue); if (!blkg) goto out; if (!blkg_tryget(blkg)) goto out; rcu_read_unlock(); blkcg_maybe_throttle_blkg(blkg, use_memdelay); blkg_put(blkg); put_disk(disk); return; out: rcu_read_unlock(); } /** * blkcg_schedule_throttle - this task needs to check for throttling * @disk: disk to throttle * @use_memdelay: do we charge this to memory delay for PSI * * This is called by the IO controller when we know there's delay accumulated * for the blkg for this task. We do not pass the blkg because there are places * we call this that may not have that information, the swapping code for * instance will only have a block_device at that point. This set's the * notify_resume for the task to check and see if it requires throttling before * returning to user space. * * We will only schedule once per syscall. You can call this over and over * again and it will only do the check once upon return to user space, and only * throttle once. If the task needs to be throttled again it'll need to be * re-set at the next time we see the task. */ void blkcg_schedule_throttle(struct gendisk *disk, bool use_memdelay) { if (unlikely(current->flags & PF_KTHREAD)) return; if (current->throttle_disk != disk) { if (test_bit(GD_DEAD, &disk->state)) return; get_device(disk_to_dev(disk)); if (current->throttle_disk) put_disk(current->throttle_disk); current->throttle_disk = disk; } if (use_memdelay) current->use_memdelay = use_memdelay; set_notify_resume(current); } /** * blkcg_add_delay - add delay to this blkg * @blkg: blkg of interest * @now: the current time in nanoseconds * @delta: how many nanoseconds of delay to add * * Charge @delta to the blkg's current delay accumulation. This is used to * throttle tasks if an IO controller thinks we need more throttling. */ void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta) { if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0)) return; blkcg_scale_delay(blkg, now); atomic64_add(delta, &blkg->delay_nsec); } /** * blkg_tryget_closest - try and get a blkg ref on the closet blkg * @bio: target bio * @css: target css * * As the failure mode here is to walk up the blkg tree, this ensure that the * blkg->parent pointers are always valid. This returns the blkg that it ended * up taking a reference on or %NULL if no reference was taken. */ static inline struct blkcg_gq *blkg_tryget_closest(struct bio *bio, struct cgroup_subsys_state *css) { struct blkcg_gq *blkg, *ret_blkg = NULL; rcu_read_lock(); blkg = blkg_lookup_create(css_to_blkcg(css), bio->bi_bdev->bd_disk); while (blkg) { if (blkg_tryget(blkg)) { ret_blkg = blkg; break; } blkg = blkg->parent; } rcu_read_unlock(); return ret_blkg; } /** * bio_associate_blkg_from_css - associate a bio with a specified css * @bio: target bio * @css: target css * * Associate @bio with the blkg found by combining the css's blkg and the * request_queue of the @bio. An association failure is handled by walking up * the blkg tree. Therefore, the blkg associated can be anything between @blkg * and q->root_blkg. This situation only happens when a cgroup is dying and * then the remaining bios will spill to the closest alive blkg. * * A reference will be taken on the blkg and will be released when @bio is * freed. */ void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css) { if (bio->bi_blkg) blkg_put(bio->bi_blkg); if (css && css->parent) { bio->bi_blkg = blkg_tryget_closest(bio, css); } else { blkg_get(bdev_get_queue(bio->bi_bdev)->root_blkg); bio->bi_blkg = bdev_get_queue(bio->bi_bdev)->root_blkg; } } EXPORT_SYMBOL_GPL(bio_associate_blkg_from_css); /** * bio_associate_blkg - associate a bio with a blkg * @bio: target bio * * Associate @bio with the blkg found from the bio's css and request_queue. * If one is not found, bio_lookup_blkg() creates the blkg. If a blkg is * already associated, the css is reused and association redone as the * request_queue may have changed. */ void bio_associate_blkg(struct bio *bio) { struct cgroup_subsys_state *css; if (blk_op_is_passthrough(bio->bi_opf)) return; rcu_read_lock(); if (bio->bi_blkg) css = bio_blkcg_css(bio); else css = blkcg_css(); bio_associate_blkg_from_css(bio, css); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(bio_associate_blkg); /** * bio_clone_blkg_association - clone blkg association from src to dst bio * @dst: destination bio * @src: source bio */ void bio_clone_blkg_association(struct bio *dst, struct bio *src) { if (src->bi_blkg) bio_associate_blkg_from_css(dst, bio_blkcg_css(src)); } EXPORT_SYMBOL_GPL(bio_clone_blkg_association); static int blk_cgroup_io_type(struct bio *bio) { if (op_is_discard(bio->bi_opf)) return BLKG_IOSTAT_DISCARD; if (op_is_write(bio->bi_opf)) return BLKG_IOSTAT_WRITE; return BLKG_IOSTAT_READ; } void blk_cgroup_bio_start(struct bio *bio) { struct blkcg *blkcg = bio->bi_blkg->blkcg; int rwd = blk_cgroup_io_type(bio), cpu; struct blkg_iostat_set *bis; unsigned long flags; if (!cgroup_subsys_on_dfl(io_cgrp_subsys)) return; /* Root-level stats are sourced from system-wide IO stats */ if (!cgroup_parent(blkcg->css.cgroup)) return; cpu = get_cpu(); bis = per_cpu_ptr(bio->bi_blkg->iostat_cpu, cpu); flags = u64_stats_update_begin_irqsave(&bis->sync); /* * If the bio is flagged with BIO_CGROUP_ACCT it means this is a split * bio and we would have already accounted for the size of the bio. */ if (!bio_flagged(bio, BIO_CGROUP_ACCT)) { bio_set_flag(bio, BIO_CGROUP_ACCT); bis->cur.bytes[rwd] += bio->bi_iter.bi_size; } bis->cur.ios[rwd]++; /* * If the iostat_cpu isn't in a lockless list, put it into the * list to indicate that a stat update is pending. */ if (!READ_ONCE(bis->lqueued)) { struct llist_head *lhead = this_cpu_ptr(blkcg->lhead); llist_add(&bis->lnode, lhead); WRITE_ONCE(bis->lqueued, true); } u64_stats_update_end_irqrestore(&bis->sync, flags); cgroup_rstat_updated(blkcg->css.cgroup, cpu); put_cpu(); } bool blk_cgroup_congested(void) { struct blkcg *blkcg; bool ret = false; rcu_read_lock(); for (blkcg = css_to_blkcg(blkcg_css()); blkcg; blkcg = blkcg_parent(blkcg)) { if (atomic_read(&blkcg->congestion_count)) { ret = true; break; } } rcu_read_unlock(); return ret; } module_param(blkcg_debug_stats, bool, 0644); MODULE_PARM_DESC(blkcg_debug_stats, "True if you want debug stats, false if not"); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_UDP_TUNNEL_H #define __NET_UDP_TUNNEL_H #include <net/ip_tunnels.h> #include <net/udp.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> #include <net/ipv6_stubs.h> #endif struct udp_port_cfg { u8 family; /* Used only for kernel-created sockets */ union { struct in_addr local_ip; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr local_ip6; #endif }; union { struct in_addr peer_ip; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr peer_ip6; #endif }; __be16 local_udp_port; __be16 peer_udp_port; int bind_ifindex; unsigned int use_udp_checksums:1, use_udp6_tx_checksums:1, use_udp6_rx_checksums:1, ipv6_v6only:1; }; int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp); #if IS_ENABLED(CONFIG_IPV6) int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp); #else static inline int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { return 0; } #endif static inline int udp_sock_create(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { if (cfg->family == AF_INET) return udp_sock_create4(net, cfg, sockp); if (cfg->family == AF_INET6) return udp_sock_create6(net, cfg, sockp); return -EPFNOSUPPORT; } typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb); typedef int (*udp_tunnel_encap_err_lookup_t)(struct sock *sk, struct sk_buff *skb); typedef void (*udp_tunnel_encap_err_rcv_t)(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload); typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk); typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk, struct list_head *head, struct sk_buff *skb); typedef int (*udp_tunnel_gro_complete_t)(struct sock *sk, struct sk_buff *skb, int nhoff); struct udp_tunnel_sock_cfg { void *sk_user_data; /* user data used by encap_rcv call back */ /* Used for setting up udp_sock fields, see udp.h for details */ __u8 encap_type; udp_tunnel_encap_rcv_t encap_rcv; udp_tunnel_encap_err_lookup_t encap_err_lookup; udp_tunnel_encap_err_rcv_t encap_err_rcv; udp_tunnel_encap_destroy_t encap_destroy; udp_tunnel_gro_receive_t gro_receive; udp_tunnel_gro_complete_t gro_complete; }; /* Setup the given (UDP) sock to receive UDP encapsulated packets */ void setup_udp_tunnel_sock(struct net *net, struct socket *sock, struct udp_tunnel_sock_cfg *sock_cfg); /* -- List of parsable UDP tunnel types -- * * Adding to this list will result in serious debate. The main issue is * that this list is essentially a list of workarounds for either poorly * designed tunnels, or poorly designed device offloads. * * The parsing supported via these types should really be used for Rx * traffic only as the network stack will have already inserted offsets for * the location of the headers in the skb. In addition any ports that are * pushed should be kept within the namespace without leaking to other * devices such as VFs or other ports on the same device. * * It is strongly encouraged to use CHECKSUM_COMPLETE for Rx to avoid the * need to use this for Rx checksum offload. It should not be necessary to * call this function to perform Tx offloads on outgoing traffic. */ enum udp_parsable_tunnel_type { UDP_TUNNEL_TYPE_VXLAN = BIT(0), /* RFC 7348 */ UDP_TUNNEL_TYPE_GENEVE = BIT(1), /* draft-ietf-nvo3-geneve */ UDP_TUNNEL_TYPE_VXLAN_GPE = BIT(2), /* draft-ietf-nvo3-vxlan-gpe */ }; struct udp_tunnel_info { unsigned short type; sa_family_t sa_family; __be16 port; u8 hw_priv; }; /* Notify network devices of offloadable types */ void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock, unsigned short type); void udp_tunnel_drop_rx_port(struct net_device *dev, struct socket *sock, unsigned short type); void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type); void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type); static inline void udp_tunnel_get_rx_info(struct net_device *dev) { ASSERT_RTNL(); if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) return; call_netdevice_notifiers(NETDEV_UDP_TUNNEL_PUSH_INFO, dev); } static inline void udp_tunnel_drop_rx_info(struct net_device *dev) { ASSERT_RTNL(); if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) return; call_netdevice_notifiers(NETDEV_UDP_TUNNEL_DROP_INFO, dev); } /* Transmit the skb using UDP encapsulation. */ void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port, bool xnet, bool nocheck); int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr, __u8 prio, __u8 ttl, __be32 label, __be16 src_port, __be16 dst_port, bool nocheck); void udp_tunnel_sock_release(struct socket *sock); struct rtable *udp_tunnel_dst_lookup(struct sk_buff *skb, struct net_device *dev, struct net *net, int oif, __be32 *saddr, const struct ip_tunnel_key *key, __be16 sport, __be16 dport, u8 tos, struct dst_cache *dst_cache); struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb, struct net_device *dev, struct net *net, struct socket *sock, int oif, struct in6_addr *saddr, const struct ip_tunnel_key *key, __be16 sport, __be16 dport, u8 dsfield, struct dst_cache *dst_cache); struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, const unsigned long *flags, __be64 tunnel_id, int md_size); #ifdef CONFIG_INET static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum) { int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; return iptunnel_handle_offloads(skb, type); } #endif static inline void udp_tunnel_encap_enable(struct sock *sk) { if (udp_test_and_set_bit(ENCAP_ENABLED, sk)) return; #if IS_ENABLED(CONFIG_IPV6) if (READ_ONCE(sk->sk_family) == PF_INET6) ipv6_stub->udpv6_encap_enable(); #endif udp_encap_enable(); } #define UDP_TUNNEL_NIC_MAX_TABLES 4 enum udp_tunnel_nic_info_flags { /* Device callbacks may sleep */ UDP_TUNNEL_NIC_INFO_MAY_SLEEP = BIT(0), /* Device only supports offloads when it's open, all ports * will be removed before close and re-added after open. */ UDP_TUNNEL_NIC_INFO_OPEN_ONLY = BIT(1), /* Device supports only IPv4 tunnels */ UDP_TUNNEL_NIC_INFO_IPV4_ONLY = BIT(2), /* Device has hard-coded the IANA VXLAN port (4789) as VXLAN. * This port must not be counted towards n_entries of any table. * Driver will not receive any callback associated with port 4789. */ UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN = BIT(3), }; struct udp_tunnel_nic; #define UDP_TUNNEL_NIC_MAX_SHARING_DEVICES (U16_MAX / 2) struct udp_tunnel_nic_shared { struct udp_tunnel_nic *udp_tunnel_nic_info; struct list_head devices; }; struct udp_tunnel_nic_shared_node { struct net_device *dev; struct list_head list; }; /** * struct udp_tunnel_nic_info - driver UDP tunnel offload information * @set_port: callback for adding a new port * @unset_port: callback for removing a port * @sync_table: callback for syncing the entire port table at once * @shared: reference to device global state (optional) * @flags: device flags from enum udp_tunnel_nic_info_flags * @tables: UDP port tables this device has * @tables.n_entries: number of entries in this table * @tables.tunnel_types: types of tunnels this table accepts * * Drivers are expected to provide either @set_port and @unset_port callbacks * or the @sync_table callback. Callbacks are invoked with rtnl lock held. * * Devices which (misguidedly) share the UDP tunnel port table across multiple * netdevs should allocate an instance of struct udp_tunnel_nic_shared and * point @shared at it. * There must never be more than %UDP_TUNNEL_NIC_MAX_SHARING_DEVICES devices * sharing a table. * * Known limitations: * - UDP tunnel port notifications are fundamentally best-effort - * it is likely the driver will both see skbs which use a UDP tunnel port, * while not being a tunneled skb, and tunnel skbs from other ports - * drivers should only use these ports for non-critical RX-side offloads, * e.g. the checksum offload; * - none of the devices care about the socket family at present, so we don't * track it. Please extend this code if you care. */ struct udp_tunnel_nic_info { /* one-by-one */ int (*set_port)(struct net_device *dev, unsigned int table, unsigned int entry, struct udp_tunnel_info *ti); int (*unset_port)(struct net_device *dev, unsigned int table, unsigned int entry, struct udp_tunnel_info *ti); /* all at once */ int (*sync_table)(struct net_device *dev, unsigned int table); struct udp_tunnel_nic_shared *shared; unsigned int flags; struct udp_tunnel_nic_table_info { unsigned int n_entries; unsigned int tunnel_types; } tables[UDP_TUNNEL_NIC_MAX_TABLES]; }; /* UDP tunnel module dependencies * * Tunnel drivers are expected to have a hard dependency on the udp_tunnel * module. NIC drivers are not, they just attach their * struct udp_tunnel_nic_info to the netdev and wait for callbacks to come. * Loading a tunnel driver will cause the udp_tunnel module to be loaded * and only then will all the required state structures be allocated. * Since we want a weak dependency from the drivers and the core to udp_tunnel * we call things through the following stubs. */ struct udp_tunnel_nic_ops { void (*get_port)(struct net_device *dev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti); void (*set_port_priv)(struct net_device *dev, unsigned int table, unsigned int idx, u8 priv); void (*add_port)(struct net_device *dev, struct udp_tunnel_info *ti); void (*del_port)(struct net_device *dev, struct udp_tunnel_info *ti); void (*reset_ntf)(struct net_device *dev); size_t (*dump_size)(struct net_device *dev, unsigned int table); int (*dump_write)(struct net_device *dev, unsigned int table, struct sk_buff *skb); }; #ifdef CONFIG_INET extern const struct udp_tunnel_nic_ops *udp_tunnel_nic_ops; #else #define udp_tunnel_nic_ops ((struct udp_tunnel_nic_ops *)NULL) #endif static inline void udp_tunnel_nic_get_port(struct net_device *dev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti) { /* This helper is used from .sync_table, we indicate empty entries * by zero'ed @ti. Drivers which need to know the details of a port * when it gets deleted should use the .set_port / .unset_port * callbacks. * Zero out here, otherwise !CONFIG_INET causes uninitilized warnings. */ memset(ti, 0, sizeof(*ti)); if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->get_port(dev, table, idx, ti); } static inline void udp_tunnel_nic_set_port_priv(struct net_device *dev, unsigned int table, unsigned int idx, u8 priv) { if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->set_port_priv(dev, table, idx, priv); } static inline void udp_tunnel_nic_add_port(struct net_device *dev, struct udp_tunnel_info *ti) { if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) return; if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->add_port(dev, ti); } static inline void udp_tunnel_nic_del_port(struct net_device *dev, struct udp_tunnel_info *ti) { if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) return; if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->del_port(dev, ti); } /** * udp_tunnel_nic_reset_ntf() - device-originating reset notification * @dev: network interface device structure * * Called by the driver to inform the core that the entire UDP tunnel port * state has been lost, usually due to device reset. Core will assume device * forgot all the ports and issue .set_port and .sync_table callbacks as * necessary. * * This function must be called with rtnl lock held, and will issue all * the callbacks before returning. */ static inline void udp_tunnel_nic_reset_ntf(struct net_device *dev) { if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->reset_ntf(dev); } static inline size_t udp_tunnel_nic_dump_size(struct net_device *dev, unsigned int table) { if (!udp_tunnel_nic_ops) return 0; return udp_tunnel_nic_ops->dump_size(dev, table); } static inline int udp_tunnel_nic_dump_write(struct net_device *dev, unsigned int table, struct sk_buff *skb) { if (!udp_tunnel_nic_ops) return 0; return udp_tunnel_nic_ops->dump_write(dev, table, skb); } #endif |
| 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 | // SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* isotp.c - ISO 15765-2 CAN transport protocol for protocol family CAN * * This implementation does not provide ISO-TP specific return values to the * userspace. * * - RX path timeout of data reception leads to -ETIMEDOUT * - RX path SN mismatch leads to -EILSEQ * - RX path data reception with wrong padding leads to -EBADMSG * - TX path flowcontrol reception timeout leads to -ECOMM * - TX path flowcontrol reception overflow leads to -EMSGSIZE * - TX path flowcontrol reception with wrong layout/padding leads to -EBADMSG * - when a transfer (tx) is on the run the next write() blocks until it's done * - use CAN_ISOTP_WAIT_TX_DONE flag to block the caller until the PDU is sent * - as we have static buffers the check whether the PDU fits into the buffer * is done at FF reception time (no support for sending 'wait frames') * * Copyright (c) 2020 Volkswagen Group Electronic Research * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of Volkswagen nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * Alternatively, provided that this notice is retained in full, this * software may be distributed under the terms of the GNU General * Public License ("GPL") version 2, in which case the provisions of the * GPL apply INSTEAD OF those given above. * * The provided data structures and external interfaces from this code * are not restricted to be used by modules with a GPL compatible license. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. */ #include <linux/module.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/spinlock.h> #include <linux/hrtimer.h> #include <linux/wait.h> #include <linux/uio.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/socket.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/can.h> #include <linux/can/core.h> #include <linux/can/skb.h> #include <linux/can/isotp.h> #include <linux/slab.h> #include <net/sock.h> #include <net/net_namespace.h> MODULE_DESCRIPTION("PF_CAN ISO 15765-2 transport protocol"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Oliver Hartkopp <socketcan@hartkopp.net>"); MODULE_ALIAS("can-proto-6"); #define ISOTP_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_addr.tp) #define SINGLE_MASK(id) (((id) & CAN_EFF_FLAG) ? \ (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \ (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG)) /* Since ISO 15765-2:2016 the CAN isotp protocol supports more than 4095 * byte per ISO PDU as the FF_DL can take full 32 bit values (4 Gbyte). * We would need some good concept to handle this between user space and * kernel space. For now set the static buffer to something about 8 kbyte * to be able to test this new functionality. */ #define DEFAULT_MAX_PDU_SIZE 8300 /* maximum PDU size before ISO 15765-2:2016 extension was 4095 */ #define MAX_12BIT_PDU_SIZE 4095 /* limit the isotp pdu size from the optional module parameter to 1MByte */ #define MAX_PDU_SIZE (1025 * 1024U) static unsigned int max_pdu_size __read_mostly = DEFAULT_MAX_PDU_SIZE; module_param(max_pdu_size, uint, 0444); MODULE_PARM_DESC(max_pdu_size, "maximum isotp pdu size (default " __stringify(DEFAULT_MAX_PDU_SIZE) ")"); /* N_PCI type values in bits 7-4 of N_PCI bytes */ #define N_PCI_SF 0x00 /* single frame */ #define N_PCI_FF 0x10 /* first frame */ #define N_PCI_CF 0x20 /* consecutive frame */ #define N_PCI_FC 0x30 /* flow control */ #define N_PCI_SZ 1 /* size of the PCI byte #1 */ #define SF_PCI_SZ4 1 /* size of SingleFrame PCI including 4 bit SF_DL */ #define SF_PCI_SZ8 2 /* size of SingleFrame PCI including 8 bit SF_DL */ #define FF_PCI_SZ12 2 /* size of FirstFrame PCI including 12 bit FF_DL */ #define FF_PCI_SZ32 6 /* size of FirstFrame PCI including 32 bit FF_DL */ #define FC_CONTENT_SZ 3 /* flow control content size in byte (FS/BS/STmin) */ #define ISOTP_CHECK_PADDING (CAN_ISOTP_CHK_PAD_LEN | CAN_ISOTP_CHK_PAD_DATA) #define ISOTP_ALL_BC_FLAGS (CAN_ISOTP_SF_BROADCAST | CAN_ISOTP_CF_BROADCAST) /* Flow Status given in FC frame */ #define ISOTP_FC_CTS 0 /* clear to send */ #define ISOTP_FC_WT 1 /* wait */ #define ISOTP_FC_OVFLW 2 /* overflow */ #define ISOTP_FC_TIMEOUT 1 /* 1 sec */ #define ISOTP_ECHO_TIMEOUT 2 /* 2 secs */ enum { ISOTP_IDLE = 0, ISOTP_WAIT_FIRST_FC, ISOTP_WAIT_FC, ISOTP_WAIT_DATA, ISOTP_SENDING, ISOTP_SHUTDOWN, }; struct tpcon { u8 *buf; unsigned int buflen; unsigned int len; unsigned int idx; u32 state; u8 bs; u8 sn; u8 ll_dl; u8 sbuf[DEFAULT_MAX_PDU_SIZE]; }; struct isotp_sock { struct sock sk; int bound; int ifindex; canid_t txid; canid_t rxid; ktime_t tx_gap; ktime_t lastrxcf_tstamp; struct hrtimer rxtimer, txtimer, txfrtimer; struct can_isotp_options opt; struct can_isotp_fc_options rxfc, txfc; struct can_isotp_ll_options ll; u32 frame_txtime; u32 force_tx_stmin; u32 force_rx_stmin; u32 cfecho; /* consecutive frame echo tag */ struct tpcon rx, tx; struct list_head notifier; wait_queue_head_t wait; spinlock_t rx_lock; /* protect single thread state machine */ }; static LIST_HEAD(isotp_notifier_list); static DEFINE_SPINLOCK(isotp_notifier_lock); static struct isotp_sock *isotp_busy_notifier; static inline struct isotp_sock *isotp_sk(const struct sock *sk) { return (struct isotp_sock *)sk; } static u32 isotp_bc_flags(struct isotp_sock *so) { return so->opt.flags & ISOTP_ALL_BC_FLAGS; } static bool isotp_register_rxid(struct isotp_sock *so) { /* no broadcast modes => register rx_id for FC frame reception */ return (isotp_bc_flags(so) == 0); } static enum hrtimer_restart isotp_rx_timer_handler(struct hrtimer *hrtimer) { struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, rxtimer); struct sock *sk = &so->sk; if (so->rx.state == ISOTP_WAIT_DATA) { /* we did not get new data frames in time */ /* report 'connection timed out' */ sk->sk_err = ETIMEDOUT; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); /* reset rx state */ so->rx.state = ISOTP_IDLE; } return HRTIMER_NORESTART; } static int isotp_send_fc(struct sock *sk, int ae, u8 flowstatus) { struct net_device *dev; struct sk_buff *nskb; struct canfd_frame *ncf; struct isotp_sock *so = isotp_sk(sk); int can_send_ret; nskb = alloc_skb(so->ll.mtu + sizeof(struct can_skb_priv), gfp_any()); if (!nskb) return 1; dev = dev_get_by_index(sock_net(sk), so->ifindex); if (!dev) { kfree_skb(nskb); return 1; } can_skb_reserve(nskb); can_skb_prv(nskb)->ifindex = dev->ifindex; can_skb_prv(nskb)->skbcnt = 0; nskb->dev = dev; can_skb_set_owner(nskb, sk); ncf = (struct canfd_frame *)nskb->data; skb_put_zero(nskb, so->ll.mtu); /* create & send flow control reply */ ncf->can_id = so->txid; if (so->opt.flags & CAN_ISOTP_TX_PADDING) { memset(ncf->data, so->opt.txpad_content, CAN_MAX_DLEN); ncf->len = CAN_MAX_DLEN; } else { ncf->len = ae + FC_CONTENT_SZ; } ncf->data[ae] = N_PCI_FC | flowstatus; ncf->data[ae + 1] = so->rxfc.bs; ncf->data[ae + 2] = so->rxfc.stmin; if (ae) ncf->data[0] = so->opt.ext_address; ncf->flags = so->ll.tx_flags; can_send_ret = can_send(nskb, 1); if (can_send_ret) pr_notice_once("can-isotp: %s: can_send_ret %pe\n", __func__, ERR_PTR(can_send_ret)); dev_put(dev); /* reset blocksize counter */ so->rx.bs = 0; /* reset last CF frame rx timestamp for rx stmin enforcement */ so->lastrxcf_tstamp = ktime_set(0, 0); /* start rx timeout watchdog */ hrtimer_start(&so->rxtimer, ktime_set(ISOTP_FC_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); return 0; } static void isotp_rcv_skb(struct sk_buff *skb, struct sock *sk) { struct sockaddr_can *addr = (struct sockaddr_can *)skb->cb; BUILD_BUG_ON(sizeof(skb->cb) < sizeof(struct sockaddr_can)); memset(addr, 0, sizeof(*addr)); addr->can_family = AF_CAN; addr->can_ifindex = skb->dev->ifindex; if (sock_queue_rcv_skb(sk, skb) < 0) kfree_skb(skb); } static u8 padlen(u8 datalen) { static const u8 plen[] = { 8, 8, 8, 8, 8, 8, 8, 8, 8, /* 0 - 8 */ 12, 12, 12, 12, /* 9 - 12 */ 16, 16, 16, 16, /* 13 - 16 */ 20, 20, 20, 20, /* 17 - 20 */ 24, 24, 24, 24, /* 21 - 24 */ 32, 32, 32, 32, 32, 32, 32, 32, /* 25 - 32 */ 48, 48, 48, 48, 48, 48, 48, 48, /* 33 - 40 */ 48, 48, 48, 48, 48, 48, 48, 48 /* 41 - 48 */ }; if (datalen > 48) return 64; return plen[datalen]; } /* check for length optimization and return 1/true when the check fails */ static int check_optimized(struct canfd_frame *cf, int start_index) { /* for CAN_DL <= 8 the start_index is equal to the CAN_DL as the * padding would start at this point. E.g. if the padding would * start at cf.data[7] cf->len has to be 7 to be optimal. * Note: The data[] index starts with zero. */ if (cf->len <= CAN_MAX_DLEN) return (cf->len != start_index); /* This relation is also valid in the non-linear DLC range, where * we need to take care of the minimal next possible CAN_DL. * The correct check would be (padlen(cf->len) != padlen(start_index)). * But as cf->len can only take discrete values from 12, .., 64 at this * point the padlen(cf->len) is always equal to cf->len. */ return (cf->len != padlen(start_index)); } /* check padding and return 1/true when the check fails */ static int check_pad(struct isotp_sock *so, struct canfd_frame *cf, int start_index, u8 content) { int i; /* no RX_PADDING value => check length of optimized frame length */ if (!(so->opt.flags & CAN_ISOTP_RX_PADDING)) { if (so->opt.flags & CAN_ISOTP_CHK_PAD_LEN) return check_optimized(cf, start_index); /* no valid test against empty value => ignore frame */ return 1; } /* check datalength of correctly padded CAN frame */ if ((so->opt.flags & CAN_ISOTP_CHK_PAD_LEN) && cf->len != padlen(cf->len)) return 1; /* check padding content */ if (so->opt.flags & CAN_ISOTP_CHK_PAD_DATA) { for (i = start_index; i < cf->len; i++) if (cf->data[i] != content) return 1; } return 0; } static void isotp_send_cframe(struct isotp_sock *so); static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) { struct sock *sk = &so->sk; if (so->tx.state != ISOTP_WAIT_FC && so->tx.state != ISOTP_WAIT_FIRST_FC) return 0; hrtimer_cancel(&so->txtimer); if ((cf->len < ae + FC_CONTENT_SZ) || ((so->opt.flags & ISOTP_CHECK_PADDING) && check_pad(so, cf, ae + FC_CONTENT_SZ, so->opt.rxpad_content))) { /* malformed PDU - report 'not a data message' */ sk->sk_err = EBADMSG; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); so->tx.state = ISOTP_IDLE; wake_up_interruptible(&so->wait); return 1; } /* get static/dynamic communication params from first/every FC frame */ if (so->tx.state == ISOTP_WAIT_FIRST_FC || so->opt.flags & CAN_ISOTP_DYN_FC_PARMS) { so->txfc.bs = cf->data[ae + 1]; so->txfc.stmin = cf->data[ae + 2]; /* fix wrong STmin values according spec */ if (so->txfc.stmin > 0x7F && (so->txfc.stmin < 0xF1 || so->txfc.stmin > 0xF9)) so->txfc.stmin = 0x7F; so->tx_gap = ktime_set(0, 0); /* add transmission time for CAN frame N_As */ so->tx_gap = ktime_add_ns(so->tx_gap, so->frame_txtime); /* add waiting time for consecutive frames N_Cs */ if (so->opt.flags & CAN_ISOTP_FORCE_TXSTMIN) so->tx_gap = ktime_add_ns(so->tx_gap, so->force_tx_stmin); else if (so->txfc.stmin < 0x80) so->tx_gap = ktime_add_ns(so->tx_gap, so->txfc.stmin * 1000000); else so->tx_gap = ktime_add_ns(so->tx_gap, (so->txfc.stmin - 0xF0) * 100000); so->tx.state = ISOTP_WAIT_FC; } switch (cf->data[ae] & 0x0F) { case ISOTP_FC_CTS: so->tx.bs = 0; so->tx.state = ISOTP_SENDING; /* send CF frame and enable echo timeout handling */ hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); isotp_send_cframe(so); break; case ISOTP_FC_WT: /* start timer to wait for next FC frame */ hrtimer_start(&so->txtimer, ktime_set(ISOTP_FC_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); break; case ISOTP_FC_OVFLW: /* overflow on receiver side - report 'message too long' */ sk->sk_err = EMSGSIZE; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); fallthrough; default: /* stop this tx job */ so->tx.state = ISOTP_IDLE; wake_up_interruptible(&so->wait); } return 0; } static int isotp_rcv_sf(struct sock *sk, struct canfd_frame *cf, int pcilen, struct sk_buff *skb, int len) { struct isotp_sock *so = isotp_sk(sk); struct sk_buff *nskb; hrtimer_cancel(&so->rxtimer); so->rx.state = ISOTP_IDLE; if (!len || len > cf->len - pcilen) return 1; if ((so->opt.flags & ISOTP_CHECK_PADDING) && check_pad(so, cf, pcilen + len, so->opt.rxpad_content)) { /* malformed PDU - report 'not a data message' */ sk->sk_err = EBADMSG; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); return 1; } nskb = alloc_skb(len, gfp_any()); if (!nskb) return 1; memcpy(skb_put(nskb, len), &cf->data[pcilen], len); nskb->tstamp = skb->tstamp; nskb->dev = skb->dev; isotp_rcv_skb(nskb, sk); return 0; } static int isotp_rcv_ff(struct sock *sk, struct canfd_frame *cf, int ae) { struct isotp_sock *so = isotp_sk(sk); int i; int off; int ff_pci_sz; hrtimer_cancel(&so->rxtimer); so->rx.state = ISOTP_IDLE; /* get the used sender LL_DL from the (first) CAN frame data length */ so->rx.ll_dl = padlen(cf->len); /* the first frame has to use the entire frame up to LL_DL length */ if (cf->len != so->rx.ll_dl) return 1; /* get the FF_DL */ so->rx.len = (cf->data[ae] & 0x0F) << 8; so->rx.len += cf->data[ae + 1]; /* Check for FF_DL escape sequence supporting 32 bit PDU length */ if (so->rx.len) { ff_pci_sz = FF_PCI_SZ12; } else { /* FF_DL = 0 => get real length from next 4 bytes */ so->rx.len = cf->data[ae + 2] << 24; so->rx.len += cf->data[ae + 3] << 16; so->rx.len += cf->data[ae + 4] << 8; so->rx.len += cf->data[ae + 5]; ff_pci_sz = FF_PCI_SZ32; } /* take care of a potential SF_DL ESC offset for TX_DL > 8 */ off = (so->rx.ll_dl > CAN_MAX_DLEN) ? 1 : 0; if (so->rx.len + ae + off + ff_pci_sz < so->rx.ll_dl) return 1; /* PDU size > default => try max_pdu_size */ if (so->rx.len > so->rx.buflen && so->rx.buflen < max_pdu_size) { u8 *newbuf = kmalloc(max_pdu_size, GFP_ATOMIC); if (newbuf) { so->rx.buf = newbuf; so->rx.buflen = max_pdu_size; } } if (so->rx.len > so->rx.buflen) { /* send FC frame with overflow status */ isotp_send_fc(sk, ae, ISOTP_FC_OVFLW); return 1; } /* copy the first received data bytes */ so->rx.idx = 0; for (i = ae + ff_pci_sz; i < so->rx.ll_dl; i++) so->rx.buf[so->rx.idx++] = cf->data[i]; /* initial setup for this pdu reception */ so->rx.sn = 1; so->rx.state = ISOTP_WAIT_DATA; /* no creation of flow control frames */ if (so->opt.flags & CAN_ISOTP_LISTEN_MODE) return 0; /* send our first FC frame */ isotp_send_fc(sk, ae, ISOTP_FC_CTS); return 0; } static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae, struct sk_buff *skb) { struct isotp_sock *so = isotp_sk(sk); struct sk_buff *nskb; int i; if (so->rx.state != ISOTP_WAIT_DATA) return 0; /* drop if timestamp gap is less than force_rx_stmin nano secs */ if (so->opt.flags & CAN_ISOTP_FORCE_RXSTMIN) { if (ktime_to_ns(ktime_sub(skb->tstamp, so->lastrxcf_tstamp)) < so->force_rx_stmin) return 0; so->lastrxcf_tstamp = skb->tstamp; } hrtimer_cancel(&so->rxtimer); /* CFs are never longer than the FF */ if (cf->len > so->rx.ll_dl) return 1; /* CFs have usually the LL_DL length */ if (cf->len < so->rx.ll_dl) { /* this is only allowed for the last CF */ if (so->rx.len - so->rx.idx > so->rx.ll_dl - ae - N_PCI_SZ) return 1; } if ((cf->data[ae] & 0x0F) != so->rx.sn) { /* wrong sn detected - report 'illegal byte sequence' */ sk->sk_err = EILSEQ; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); /* reset rx state */ so->rx.state = ISOTP_IDLE; return 1; } so->rx.sn++; so->rx.sn %= 16; for (i = ae + N_PCI_SZ; i < cf->len; i++) { so->rx.buf[so->rx.idx++] = cf->data[i]; if (so->rx.idx >= so->rx.len) break; } if (so->rx.idx >= so->rx.len) { /* we are done */ so->rx.state = ISOTP_IDLE; if ((so->opt.flags & ISOTP_CHECK_PADDING) && check_pad(so, cf, i + 1, so->opt.rxpad_content)) { /* malformed PDU - report 'not a data message' */ sk->sk_err = EBADMSG; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); return 1; } nskb = alloc_skb(so->rx.len, gfp_any()); if (!nskb) return 1; memcpy(skb_put(nskb, so->rx.len), so->rx.buf, so->rx.len); nskb->tstamp = skb->tstamp; nskb->dev = skb->dev; isotp_rcv_skb(nskb, sk); return 0; } /* perform blocksize handling, if enabled */ if (!so->rxfc.bs || ++so->rx.bs < so->rxfc.bs) { /* start rx timeout watchdog */ hrtimer_start(&so->rxtimer, ktime_set(ISOTP_FC_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); return 0; } /* no creation of flow control frames */ if (so->opt.flags & CAN_ISOTP_LISTEN_MODE) return 0; /* we reached the specified blocksize so->rxfc.bs */ isotp_send_fc(sk, ae, ISOTP_FC_CTS); return 0; } static void isotp_rcv(struct sk_buff *skb, void *data) { struct sock *sk = (struct sock *)data; struct isotp_sock *so = isotp_sk(sk); struct canfd_frame *cf; int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0; u8 n_pci_type, sf_dl; /* Strictly receive only frames with the configured MTU size * => clear separation of CAN2.0 / CAN FD transport channels */ if (skb->len != so->ll.mtu) return; cf = (struct canfd_frame *)skb->data; /* if enabled: check reception of my configured extended address */ if (ae && cf->data[0] != so->opt.rx_ext_address) return; n_pci_type = cf->data[ae] & 0xF0; /* Make sure the state changes and data structures stay consistent at * CAN frame reception time. This locking is not needed in real world * use cases but the inconsistency can be triggered with syzkaller. */ spin_lock(&so->rx_lock); if (so->opt.flags & CAN_ISOTP_HALF_DUPLEX) { /* check rx/tx path half duplex expectations */ if ((so->tx.state != ISOTP_IDLE && n_pci_type != N_PCI_FC) || (so->rx.state != ISOTP_IDLE && n_pci_type == N_PCI_FC)) goto out_unlock; } switch (n_pci_type) { case N_PCI_FC: /* tx path: flow control frame containing the FC parameters */ isotp_rcv_fc(so, cf, ae); break; case N_PCI_SF: /* rx path: single frame * * As we do not have a rx.ll_dl configuration, we can only test * if the CAN frames payload length matches the LL_DL == 8 * requirements - no matter if it's CAN 2.0 or CAN FD */ /* get the SF_DL from the N_PCI byte */ sf_dl = cf->data[ae] & 0x0F; if (cf->len <= CAN_MAX_DLEN) { isotp_rcv_sf(sk, cf, SF_PCI_SZ4 + ae, skb, sf_dl); } else { if (can_is_canfd_skb(skb)) { /* We have a CAN FD frame and CAN_DL is greater than 8: * Only frames with the SF_DL == 0 ESC value are valid. * * If so take care of the increased SF PCI size * (SF_PCI_SZ8) to point to the message content behind * the extended SF PCI info and get the real SF_DL * length value from the formerly first data byte. */ if (sf_dl == 0) isotp_rcv_sf(sk, cf, SF_PCI_SZ8 + ae, skb, cf->data[SF_PCI_SZ4 + ae]); } } break; case N_PCI_FF: /* rx path: first frame */ isotp_rcv_ff(sk, cf, ae); break; case N_PCI_CF: /* rx path: consecutive frame */ isotp_rcv_cf(sk, cf, ae, skb); break; } out_unlock: spin_unlock(&so->rx_lock); } static void isotp_fill_dataframe(struct canfd_frame *cf, struct isotp_sock *so, int ae, int off) { int pcilen = N_PCI_SZ + ae + off; int space = so->tx.ll_dl - pcilen; int num = min_t(int, so->tx.len - so->tx.idx, space); int i; cf->can_id = so->txid; cf->len = num + pcilen; if (num < space) { if (so->opt.flags & CAN_ISOTP_TX_PADDING) { /* user requested padding */ cf->len = padlen(cf->len); memset(cf->data, so->opt.txpad_content, cf->len); } else if (cf->len > CAN_MAX_DLEN) { /* mandatory padding for CAN FD frames */ cf->len = padlen(cf->len); memset(cf->data, CAN_ISOTP_DEFAULT_PAD_CONTENT, cf->len); } } for (i = 0; i < num; i++) cf->data[pcilen + i] = so->tx.buf[so->tx.idx++]; if (ae) cf->data[0] = so->opt.ext_address; } static void isotp_send_cframe(struct isotp_sock *so) { struct sock *sk = &so->sk; struct sk_buff *skb; struct net_device *dev; struct canfd_frame *cf; int can_send_ret; int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0; dev = dev_get_by_index(sock_net(sk), so->ifindex); if (!dev) return; skb = alloc_skb(so->ll.mtu + sizeof(struct can_skb_priv), GFP_ATOMIC); if (!skb) { dev_put(dev); return; } can_skb_reserve(skb); can_skb_prv(skb)->ifindex = dev->ifindex; can_skb_prv(skb)->skbcnt = 0; cf = (struct canfd_frame *)skb->data; skb_put_zero(skb, so->ll.mtu); /* create consecutive frame */ isotp_fill_dataframe(cf, so, ae, 0); /* place consecutive frame N_PCI in appropriate index */ cf->data[ae] = N_PCI_CF | so->tx.sn++; so->tx.sn %= 16; so->tx.bs++; cf->flags = so->ll.tx_flags; skb->dev = dev; can_skb_set_owner(skb, sk); /* cfecho should have been zero'ed by init/isotp_rcv_echo() */ if (so->cfecho) pr_notice_once("can-isotp: cfecho is %08X != 0\n", so->cfecho); /* set consecutive frame echo tag */ so->cfecho = *(u32 *)cf->data; /* send frame with local echo enabled */ can_send_ret = can_send(skb, 1); if (can_send_ret) { pr_notice_once("can-isotp: %s: can_send_ret %pe\n", __func__, ERR_PTR(can_send_ret)); if (can_send_ret == -ENOBUFS) pr_notice_once("can-isotp: tx queue is full\n"); } dev_put(dev); } static void isotp_create_fframe(struct canfd_frame *cf, struct isotp_sock *so, int ae) { int i; int ff_pci_sz; cf->can_id = so->txid; cf->len = so->tx.ll_dl; if (ae) cf->data[0] = so->opt.ext_address; /* create N_PCI bytes with 12/32 bit FF_DL data length */ if (so->tx.len > MAX_12BIT_PDU_SIZE) { /* use 32 bit FF_DL notation */ cf->data[ae] = N_PCI_FF; cf->data[ae + 1] = 0; cf->data[ae + 2] = (u8)(so->tx.len >> 24) & 0xFFU; cf->data[ae + 3] = (u8)(so->tx.len >> 16) & 0xFFU; cf->data[ae + 4] = (u8)(so->tx.len >> 8) & 0xFFU; cf->data[ae + 5] = (u8)so->tx.len & 0xFFU; ff_pci_sz = FF_PCI_SZ32; } else { /* use 12 bit FF_DL notation */ cf->data[ae] = (u8)(so->tx.len >> 8) | N_PCI_FF; cf->data[ae + 1] = (u8)so->tx.len & 0xFFU; ff_pci_sz = FF_PCI_SZ12; } /* add first data bytes depending on ae */ for (i = ae + ff_pci_sz; i < so->tx.ll_dl; i++) cf->data[i] = so->tx.buf[so->tx.idx++]; so->tx.sn = 1; } static void isotp_rcv_echo(struct sk_buff *skb, void *data) { struct sock *sk = (struct sock *)data; struct isotp_sock *so = isotp_sk(sk); struct canfd_frame *cf = (struct canfd_frame *)skb->data; /* only handle my own local echo CF/SF skb's (no FF!) */ if (skb->sk != sk || so->cfecho != *(u32 *)cf->data) return; /* cancel local echo timeout */ hrtimer_cancel(&so->txtimer); /* local echo skb with consecutive frame has been consumed */ so->cfecho = 0; if (so->tx.idx >= so->tx.len) { /* we are done */ so->tx.state = ISOTP_IDLE; wake_up_interruptible(&so->wait); return; } if (so->txfc.bs && so->tx.bs >= so->txfc.bs) { /* stop and wait for FC with timeout */ so->tx.state = ISOTP_WAIT_FC; hrtimer_start(&so->txtimer, ktime_set(ISOTP_FC_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); return; } /* no gap between data frames needed => use burst mode */ if (!so->tx_gap) { /* enable echo timeout handling */ hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); isotp_send_cframe(so); return; } /* start timer to send next consecutive frame with correct delay */ hrtimer_start(&so->txfrtimer, so->tx_gap, HRTIMER_MODE_REL_SOFT); } static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) { struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, txtimer); struct sock *sk = &so->sk; /* don't handle timeouts in IDLE or SHUTDOWN state */ if (so->tx.state == ISOTP_IDLE || so->tx.state == ISOTP_SHUTDOWN) return HRTIMER_NORESTART; /* we did not get any flow control or echo frame in time */ /* report 'communication error on send' */ sk->sk_err = ECOMM; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); /* reset tx state */ so->tx.state = ISOTP_IDLE; wake_up_interruptible(&so->wait); return HRTIMER_NORESTART; } static enum hrtimer_restart isotp_txfr_timer_handler(struct hrtimer *hrtimer) { struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, txfrtimer); /* start echo timeout handling and cover below protocol error */ hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); /* cfecho should be consumed by isotp_rcv_echo() here */ if (so->tx.state == ISOTP_SENDING && !so->cfecho) isotp_send_cframe(so); return HRTIMER_NORESTART; } static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; struct isotp_sock *so = isotp_sk(sk); struct sk_buff *skb; struct net_device *dev; struct canfd_frame *cf; int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0; int wait_tx_done = (so->opt.flags & CAN_ISOTP_WAIT_TX_DONE) ? 1 : 0; s64 hrtimer_sec = ISOTP_ECHO_TIMEOUT; int off; int err; if (!so->bound || so->tx.state == ISOTP_SHUTDOWN) return -EADDRNOTAVAIL; while (cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SENDING) != ISOTP_IDLE) { /* we do not support multiple buffers - for now */ if (msg->msg_flags & MSG_DONTWAIT) return -EAGAIN; if (so->tx.state == ISOTP_SHUTDOWN) return -EADDRNOTAVAIL; /* wait for complete transmission of current pdu */ err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); if (err) goto err_event_drop; } /* PDU size > default => try max_pdu_size */ if (size > so->tx.buflen && so->tx.buflen < max_pdu_size) { u8 *newbuf = kmalloc(max_pdu_size, GFP_KERNEL); if (newbuf) { so->tx.buf = newbuf; so->tx.buflen = max_pdu_size; } } if (!size || size > so->tx.buflen) { err = -EINVAL; goto err_out_drop; } /* take care of a potential SF_DL ESC offset for TX_DL > 8 */ off = (so->tx.ll_dl > CAN_MAX_DLEN) ? 1 : 0; /* does the given data fit into a single frame for SF_BROADCAST? */ if ((isotp_bc_flags(so) == CAN_ISOTP_SF_BROADCAST) && (size > so->tx.ll_dl - SF_PCI_SZ4 - ae - off)) { err = -EINVAL; goto err_out_drop; } err = memcpy_from_msg(so->tx.buf, msg, size); if (err < 0) goto err_out_drop; dev = dev_get_by_index(sock_net(sk), so->ifindex); if (!dev) { err = -ENXIO; goto err_out_drop; } skb = sock_alloc_send_skb(sk, so->ll.mtu + sizeof(struct can_skb_priv), msg->msg_flags & MSG_DONTWAIT, &err); if (!skb) { dev_put(dev); goto err_out_drop; } can_skb_reserve(skb); can_skb_prv(skb)->ifindex = dev->ifindex; can_skb_prv(skb)->skbcnt = 0; so->tx.len = size; so->tx.idx = 0; cf = (struct canfd_frame *)skb->data; skb_put_zero(skb, so->ll.mtu); /* cfecho should have been zero'ed by init / former isotp_rcv_echo() */ if (so->cfecho) pr_notice_once("can-isotp: uninit cfecho %08X\n", so->cfecho); /* check for single frame transmission depending on TX_DL */ if (size <= so->tx.ll_dl - SF_PCI_SZ4 - ae - off) { /* The message size generally fits into a SingleFrame - good. * * SF_DL ESC offset optimization: * * When TX_DL is greater 8 but the message would still fit * into a 8 byte CAN frame, we can omit the offset. * This prevents a protocol caused length extension from * CAN_DL = 8 to CAN_DL = 12 due to the SF_SL ESC handling. */ if (size <= CAN_MAX_DLEN - SF_PCI_SZ4 - ae) off = 0; isotp_fill_dataframe(cf, so, ae, off); /* place single frame N_PCI w/o length in appropriate index */ cf->data[ae] = N_PCI_SF; /* place SF_DL size value depending on the SF_DL ESC offset */ if (off) cf->data[SF_PCI_SZ4 + ae] = size; else cf->data[ae] |= size; /* set CF echo tag for isotp_rcv_echo() (SF-mode) */ so->cfecho = *(u32 *)cf->data; } else { /* send first frame */ isotp_create_fframe(cf, so, ae); if (isotp_bc_flags(so) == CAN_ISOTP_CF_BROADCAST) { /* set timer for FC-less operation (STmin = 0) */ if (so->opt.flags & CAN_ISOTP_FORCE_TXSTMIN) so->tx_gap = ktime_set(0, so->force_tx_stmin); else so->tx_gap = ktime_set(0, so->frame_txtime); /* disable wait for FCs due to activated block size */ so->txfc.bs = 0; /* set CF echo tag for isotp_rcv_echo() (CF-mode) */ so->cfecho = *(u32 *)cf->data; } else { /* standard flow control check */ so->tx.state = ISOTP_WAIT_FIRST_FC; /* start timeout for FC */ hrtimer_sec = ISOTP_FC_TIMEOUT; /* no CF echo tag for isotp_rcv_echo() (FF-mode) */ so->cfecho = 0; } } hrtimer_start(&so->txtimer, ktime_set(hrtimer_sec, 0), HRTIMER_MODE_REL_SOFT); /* send the first or only CAN frame */ cf->flags = so->ll.tx_flags; skb->dev = dev; skb->sk = sk; err = can_send(skb, 1); dev_put(dev); if (err) { pr_notice_once("can-isotp: %s: can_send_ret %pe\n", __func__, ERR_PTR(err)); /* no transmission -> no timeout monitoring */ hrtimer_cancel(&so->txtimer); /* reset consecutive frame echo tag */ so->cfecho = 0; goto err_out_drop; } if (wait_tx_done) { /* wait for complete transmission of current pdu */ err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); if (err) goto err_event_drop; err = sock_error(sk); if (err) return err; } return size; err_event_drop: /* got signal: force tx state machine to be idle */ so->tx.state = ISOTP_IDLE; hrtimer_cancel(&so->txfrtimer); hrtimer_cancel(&so->txtimer); err_out_drop: /* drop this PDU and unlock a potential wait queue */ so->tx.state = ISOTP_IDLE; wake_up_interruptible(&so->wait); return err; } static int isotp_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; struct sk_buff *skb; struct isotp_sock *so = isotp_sk(sk); int ret = 0; if (flags & ~(MSG_DONTWAIT | MSG_TRUNC | MSG_PEEK | MSG_CMSG_COMPAT)) return -EINVAL; if (!so->bound) return -EADDRNOTAVAIL; skb = skb_recv_datagram(sk, flags, &ret); if (!skb) return ret; if (size < skb->len) msg->msg_flags |= MSG_TRUNC; else size = skb->len; ret = memcpy_to_msg(msg, skb->data, size); if (ret < 0) goto out_err; sock_recv_cmsgs(msg, sk, skb); if (msg->msg_name) { __sockaddr_check_size(ISOTP_MIN_NAMELEN); msg->msg_namelen = ISOTP_MIN_NAMELEN; memcpy(msg->msg_name, skb->cb, msg->msg_namelen); } /* set length of return value */ ret = (flags & MSG_TRUNC) ? skb->len : size; out_err: skb_free_datagram(sk, skb); return ret; } static int isotp_release(struct socket *sock) { struct sock *sk = sock->sk; struct isotp_sock *so; struct net *net; if (!sk) return 0; so = isotp_sk(sk); net = sock_net(sk); /* wait for complete transmission of current pdu */ while (wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE) == 0 && cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SHUTDOWN) != ISOTP_IDLE) ; /* force state machines to be idle also when a signal occurred */ so->tx.state = ISOTP_SHUTDOWN; so->rx.state = ISOTP_IDLE; spin_lock(&isotp_notifier_lock); while (isotp_busy_notifier == so) { spin_unlock(&isotp_notifier_lock); schedule_timeout_uninterruptible(1); spin_lock(&isotp_notifier_lock); } list_del(&so->notifier); spin_unlock(&isotp_notifier_lock); lock_sock(sk); /* remove current filters & unregister */ if (so->bound) { if (so->ifindex) { struct net_device *dev; dev = dev_get_by_index(net, so->ifindex); if (dev) { if (isotp_register_rxid(so)) can_rx_unregister(net, dev, so->rxid, SINGLE_MASK(so->rxid), isotp_rcv, sk); can_rx_unregister(net, dev, so->txid, SINGLE_MASK(so->txid), isotp_rcv_echo, sk); dev_put(dev); synchronize_rcu(); } } } hrtimer_cancel(&so->txfrtimer); hrtimer_cancel(&so->txtimer); hrtimer_cancel(&so->rxtimer); so->ifindex = 0; so->bound = 0; if (so->rx.buf != so->rx.sbuf) kfree(so->rx.buf); if (so->tx.buf != so->tx.sbuf) kfree(so->tx.buf); sock_orphan(sk); sock->sk = NULL; release_sock(sk); sock_put(sk); return 0; } static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct isotp_sock *so = isotp_sk(sk); struct net *net = sock_net(sk); int ifindex; struct net_device *dev; canid_t tx_id = addr->can_addr.tp.tx_id; canid_t rx_id = addr->can_addr.tp.rx_id; int err = 0; int notify_enetdown = 0; if (len < ISOTP_MIN_NAMELEN) return -EINVAL; if (addr->can_family != AF_CAN) return -EINVAL; /* sanitize tx CAN identifier */ if (tx_id & CAN_EFF_FLAG) tx_id &= (CAN_EFF_FLAG | CAN_EFF_MASK); else tx_id &= CAN_SFF_MASK; /* give feedback on wrong CAN-ID value */ if (tx_id != addr->can_addr.tp.tx_id) return -EINVAL; /* sanitize rx CAN identifier (if needed) */ if (isotp_register_rxid(so)) { if (rx_id & CAN_EFF_FLAG) rx_id &= (CAN_EFF_FLAG | CAN_EFF_MASK); else rx_id &= CAN_SFF_MASK; /* give feedback on wrong CAN-ID value */ if (rx_id != addr->can_addr.tp.rx_id) return -EINVAL; } if (!addr->can_ifindex) return -ENODEV; lock_sock(sk); if (so->bound) { err = -EINVAL; goto out; } /* ensure different CAN IDs when the rx_id is to be registered */ if (isotp_register_rxid(so) && rx_id == tx_id) { err = -EADDRNOTAVAIL; goto out; } dev = dev_get_by_index(net, addr->can_ifindex); if (!dev) { err = -ENODEV; goto out; } if (dev->type != ARPHRD_CAN) { dev_put(dev); err = -ENODEV; goto out; } if (dev->mtu < so->ll.mtu) { dev_put(dev); err = -EINVAL; goto out; } if (!(dev->flags & IFF_UP)) notify_enetdown = 1; ifindex = dev->ifindex; if (isotp_register_rxid(so)) can_rx_register(net, dev, rx_id, SINGLE_MASK(rx_id), isotp_rcv, sk, "isotp", sk); /* no consecutive frame echo skb in flight */ so->cfecho = 0; /* register for echo skb's */ can_rx_register(net, dev, tx_id, SINGLE_MASK(tx_id), isotp_rcv_echo, sk, "isotpe", sk); dev_put(dev); /* switch to new settings */ so->ifindex = ifindex; so->rxid = rx_id; so->txid = tx_id; so->bound = 1; out: release_sock(sk); if (notify_enetdown) { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } return err; } static int isotp_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct isotp_sock *so = isotp_sk(sk); if (peer) return -EOPNOTSUPP; memset(addr, 0, ISOTP_MIN_NAMELEN); addr->can_family = AF_CAN; addr->can_ifindex = so->ifindex; addr->can_addr.tp.rx_id = so->rxid; addr->can_addr.tp.tx_id = so->txid; return ISOTP_MIN_NAMELEN; } static int isotp_setsockopt_locked(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct isotp_sock *so = isotp_sk(sk); int ret = 0; if (so->bound) return -EISCONN; switch (optname) { case CAN_ISOTP_OPTS: if (optlen != sizeof(struct can_isotp_options)) return -EINVAL; if (copy_from_sockptr(&so->opt, optval, optlen)) return -EFAULT; /* no separate rx_ext_address is given => use ext_address */ if (!(so->opt.flags & CAN_ISOTP_RX_EXT_ADDR)) so->opt.rx_ext_address = so->opt.ext_address; /* these broadcast flags are not allowed together */ if (isotp_bc_flags(so) == ISOTP_ALL_BC_FLAGS) { /* CAN_ISOTP_SF_BROADCAST is prioritized */ so->opt.flags &= ~CAN_ISOTP_CF_BROADCAST; /* give user feedback on wrong config attempt */ ret = -EINVAL; } /* check for frame_txtime changes (0 => no changes) */ if (so->opt.frame_txtime) { if (so->opt.frame_txtime == CAN_ISOTP_FRAME_TXTIME_ZERO) so->frame_txtime = 0; else so->frame_txtime = so->opt.frame_txtime; } break; case CAN_ISOTP_RECV_FC: if (optlen != sizeof(struct can_isotp_fc_options)) return -EINVAL; if (copy_from_sockptr(&so->rxfc, optval, optlen)) return -EFAULT; break; case CAN_ISOTP_TX_STMIN: if (optlen != sizeof(u32)) return -EINVAL; if (copy_from_sockptr(&so->force_tx_stmin, optval, optlen)) return -EFAULT; break; case CAN_ISOTP_RX_STMIN: if (optlen != sizeof(u32)) return -EINVAL; if (copy_from_sockptr(&so->force_rx_stmin, optval, optlen)) return -EFAULT; break; case CAN_ISOTP_LL_OPTS: if (optlen == sizeof(struct can_isotp_ll_options)) { struct can_isotp_ll_options ll; if (copy_from_sockptr(&ll, optval, optlen)) return -EFAULT; /* check for correct ISO 11898-1 DLC data length */ if (ll.tx_dl != padlen(ll.tx_dl)) return -EINVAL; if (ll.mtu != CAN_MTU && ll.mtu != CANFD_MTU) return -EINVAL; if (ll.mtu == CAN_MTU && (ll.tx_dl > CAN_MAX_DLEN || ll.tx_flags != 0)) return -EINVAL; memcpy(&so->ll, &ll, sizeof(ll)); /* set ll_dl for tx path to similar place as for rx */ so->tx.ll_dl = ll.tx_dl; } else { return -EINVAL; } break; default: ret = -ENOPROTOOPT; } return ret; } static int isotp_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; int ret; if (level != SOL_CAN_ISOTP) return -EINVAL; lock_sock(sk); ret = isotp_setsockopt_locked(sock, level, optname, optval, optlen); release_sock(sk); return ret; } static int isotp_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct isotp_sock *so = isotp_sk(sk); int len; void *val; if (level != SOL_CAN_ISOTP) return -EINVAL; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; switch (optname) { case CAN_ISOTP_OPTS: len = min_t(int, len, sizeof(struct can_isotp_options)); val = &so->opt; break; case CAN_ISOTP_RECV_FC: len = min_t(int, len, sizeof(struct can_isotp_fc_options)); val = &so->rxfc; break; case CAN_ISOTP_TX_STMIN: len = min_t(int, len, sizeof(u32)); val = &so->force_tx_stmin; break; case CAN_ISOTP_RX_STMIN: len = min_t(int, len, sizeof(u32)); val = &so->force_rx_stmin; break; case CAN_ISOTP_LL_OPTS: len = min_t(int, len, sizeof(struct can_isotp_ll_options)); val = &so->ll; break; default: return -ENOPROTOOPT; } if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, val, len)) return -EFAULT; return 0; } static void isotp_notify(struct isotp_sock *so, unsigned long msg, struct net_device *dev) { struct sock *sk = &so->sk; if (!net_eq(dev_net(dev), sock_net(sk))) return; if (so->ifindex != dev->ifindex) return; switch (msg) { case NETDEV_UNREGISTER: lock_sock(sk); /* remove current filters & unregister */ if (so->bound) { if (isotp_register_rxid(so)) can_rx_unregister(dev_net(dev), dev, so->rxid, SINGLE_MASK(so->rxid), isotp_rcv, sk); can_rx_unregister(dev_net(dev), dev, so->txid, SINGLE_MASK(so->txid), isotp_rcv_echo, sk); } so->ifindex = 0; so->bound = 0; release_sock(sk); sk->sk_err = ENODEV; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); break; case NETDEV_DOWN: sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); break; } } static int isotp_notifier(struct notifier_block *nb, unsigned long msg, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (dev->type != ARPHRD_CAN) return NOTIFY_DONE; if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) return NOTIFY_DONE; if (unlikely(isotp_busy_notifier)) /* Check for reentrant bug. */ return NOTIFY_DONE; spin_lock(&isotp_notifier_lock); list_for_each_entry(isotp_busy_notifier, &isotp_notifier_list, notifier) { spin_unlock(&isotp_notifier_lock); isotp_notify(isotp_busy_notifier, msg, dev); spin_lock(&isotp_notifier_lock); } isotp_busy_notifier = NULL; spin_unlock(&isotp_notifier_lock); return NOTIFY_DONE; } static int isotp_init(struct sock *sk) { struct isotp_sock *so = isotp_sk(sk); so->ifindex = 0; so->bound = 0; so->opt.flags = CAN_ISOTP_DEFAULT_FLAGS; so->opt.ext_address = CAN_ISOTP_DEFAULT_EXT_ADDRESS; so->opt.rx_ext_address = CAN_ISOTP_DEFAULT_EXT_ADDRESS; so->opt.rxpad_content = CAN_ISOTP_DEFAULT_PAD_CONTENT; so->opt.txpad_content = CAN_ISOTP_DEFAULT_PAD_CONTENT; so->opt.frame_txtime = CAN_ISOTP_DEFAULT_FRAME_TXTIME; so->frame_txtime = CAN_ISOTP_DEFAULT_FRAME_TXTIME; so->rxfc.bs = CAN_ISOTP_DEFAULT_RECV_BS; so->rxfc.stmin = CAN_ISOTP_DEFAULT_RECV_STMIN; so->rxfc.wftmax = CAN_ISOTP_DEFAULT_RECV_WFTMAX; so->ll.mtu = CAN_ISOTP_DEFAULT_LL_MTU; so->ll.tx_dl = CAN_ISOTP_DEFAULT_LL_TX_DL; so->ll.tx_flags = CAN_ISOTP_DEFAULT_LL_TX_FLAGS; /* set ll_dl for tx path to similar place as for rx */ so->tx.ll_dl = so->ll.tx_dl; so->rx.state = ISOTP_IDLE; so->tx.state = ISOTP_IDLE; so->rx.buf = so->rx.sbuf; so->tx.buf = so->tx.sbuf; so->rx.buflen = ARRAY_SIZE(so->rx.sbuf); so->tx.buflen = ARRAY_SIZE(so->tx.sbuf); hrtimer_init(&so->rxtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); so->rxtimer.function = isotp_rx_timer_handler; hrtimer_init(&so->txtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); so->txtimer.function = isotp_tx_timer_handler; hrtimer_init(&so->txfrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); so->txfrtimer.function = isotp_txfr_timer_handler; init_waitqueue_head(&so->wait); spin_lock_init(&so->rx_lock); spin_lock(&isotp_notifier_lock); list_add_tail(&so->notifier, &isotp_notifier_list); spin_unlock(&isotp_notifier_lock); return 0; } static __poll_t isotp_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; struct isotp_sock *so = isotp_sk(sk); __poll_t mask = datagram_poll(file, sock, wait); poll_wait(file, &so->wait, wait); /* Check for false positives due to TX state */ if ((mask & EPOLLWRNORM) && (so->tx.state != ISOTP_IDLE)) mask &= ~(EPOLLOUT | EPOLLWRNORM); return mask; } static int isotp_sock_no_ioctlcmd(struct socket *sock, unsigned int cmd, unsigned long arg) { /* no ioctls for socket layer -> hand it down to NIC layer */ return -ENOIOCTLCMD; } static const struct proto_ops isotp_ops = { .family = PF_CAN, .release = isotp_release, .bind = isotp_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = isotp_getname, .poll = isotp_poll, .ioctl = isotp_sock_no_ioctlcmd, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = isotp_setsockopt, .getsockopt = isotp_getsockopt, .sendmsg = isotp_sendmsg, .recvmsg = isotp_recvmsg, .mmap = sock_no_mmap, }; static struct proto isotp_proto __read_mostly = { .name = "CAN_ISOTP", .owner = THIS_MODULE, .obj_size = sizeof(struct isotp_sock), .init = isotp_init, }; static const struct can_proto isotp_can_proto = { .type = SOCK_DGRAM, .protocol = CAN_ISOTP, .ops = &isotp_ops, .prot = &isotp_proto, }; static struct notifier_block canisotp_notifier = { .notifier_call = isotp_notifier }; static __init int isotp_module_init(void) { int err; max_pdu_size = max_t(unsigned int, max_pdu_size, MAX_12BIT_PDU_SIZE); max_pdu_size = min_t(unsigned int, max_pdu_size, MAX_PDU_SIZE); pr_info("can: isotp protocol (max_pdu_size %d)\n", max_pdu_size); err = can_proto_register(&isotp_can_proto); if (err < 0) pr_err("can: registration of isotp protocol failed %pe\n", ERR_PTR(err)); else register_netdevice_notifier(&canisotp_notifier); return err; } static __exit void isotp_module_exit(void) { can_proto_unregister(&isotp_can_proto); unregister_netdevice_notifier(&canisotp_notifier); } module_init(isotp_module_init); module_exit(isotp_module_exit); |
| 1197 1197 1194 1197 1193 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 | // SPDX-License-Identifier: GPL-2.0-only /* * arch/arm64/kernel/return_address.c * * Copyright (C) 2013 Linaro Limited * Author: AKASHI Takahiro <takahiro.akashi@linaro.org> */ #include <linux/export.h> #include <linux/ftrace.h> #include <linux/kprobes.h> #include <linux/stacktrace.h> #include <asm/stack_pointer.h> struct return_address_data { unsigned int level; void *addr; }; static bool save_return_addr(void *d, unsigned long pc) { struct return_address_data *data = d; if (!data->level) { data->addr = (void *)pc; return false; } else { --data->level; return true; } } NOKPROBE_SYMBOL(save_return_addr); void *return_address(unsigned int level) { struct return_address_data data; data.level = level + 2; data.addr = NULL; arch_stack_walk(save_return_addr, &data, current, NULL); if (!data.level) return data.addr; else return NULL; } EXPORT_SYMBOL_GPL(return_address); NOKPROBE_SYMBOL(return_address); |
| 485 483 485 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Procedures for maintaining information about logical memory blocks. * * Peter Bergner, IBM Corp. June 2001. * Copyright (C) 2001 Peter Bergner. */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/bitops.h> #include <linux/poison.h> #include <linux/pfn.h> #include <linux/debugfs.h> #include <linux/kmemleak.h> #include <linux/seq_file.h> #include <linux/memblock.h> #include <asm/sections.h> #include <linux/io.h> #include "internal.h" #define INIT_MEMBLOCK_REGIONS 128 #define INIT_PHYSMEM_REGIONS 4 #ifndef INIT_MEMBLOCK_RESERVED_REGIONS # define INIT_MEMBLOCK_RESERVED_REGIONS INIT_MEMBLOCK_REGIONS #endif #ifndef INIT_MEMBLOCK_MEMORY_REGIONS #define INIT_MEMBLOCK_MEMORY_REGIONS INIT_MEMBLOCK_REGIONS #endif /** * DOC: memblock overview * * Memblock is a method of managing memory regions during the early * boot period when the usual kernel memory allocators are not up and * running. * * Memblock views the system memory as collections of contiguous * regions. There are several types of these collections: * * * ``memory`` - describes the physical memory available to the * kernel; this may differ from the actual physical memory installed * in the system, for instance when the memory is restricted with * ``mem=`` command line parameter * * ``reserved`` - describes the regions that were allocated * * ``physmem`` - describes the actual physical memory available during * boot regardless of the possible restrictions and memory hot(un)plug; * the ``physmem`` type is only available on some architectures. * * Each region is represented by struct memblock_region that * defines the region extents, its attributes and NUMA node id on NUMA * systems. Every memory type is described by the struct memblock_type * which contains an array of memory regions along with * the allocator metadata. The "memory" and "reserved" types are nicely * wrapped with struct memblock. This structure is statically * initialized at build time. The region arrays are initially sized to * %INIT_MEMBLOCK_MEMORY_REGIONS for "memory" and * %INIT_MEMBLOCK_RESERVED_REGIONS for "reserved". The region array * for "physmem" is initially sized to %INIT_PHYSMEM_REGIONS. * The memblock_allow_resize() enables automatic resizing of the region * arrays during addition of new regions. This feature should be used * with care so that memory allocated for the region array will not * overlap with areas that should be reserved, for example initrd. * * The early architecture setup should tell memblock what the physical * memory layout is by using memblock_add() or memblock_add_node() * functions. The first function does not assign the region to a NUMA * node and it is appropriate for UMA systems. Yet, it is possible to * use it on NUMA systems as well and assign the region to a NUMA node * later in the setup process using memblock_set_node(). The * memblock_add_node() performs such an assignment directly. * * Once memblock is setup the memory can be allocated using one of the * API variants: * * * memblock_phys_alloc*() - these functions return the **physical** * address of the allocated memory * * memblock_alloc*() - these functions return the **virtual** address * of the allocated memory. * * Note, that both API variants use implicit assumptions about allowed * memory ranges and the fallback methods. Consult the documentation * of memblock_alloc_internal() and memblock_alloc_range_nid() * functions for more elaborate description. * * As the system boot progresses, the architecture specific mem_init() * function frees all the memory to the buddy page allocator. * * Unless an architecture enables %CONFIG_ARCH_KEEP_MEMBLOCK, the * memblock data structures (except "physmem") will be discarded after the * system initialization completes. */ #ifndef CONFIG_NUMA struct pglist_data __refdata contig_page_data; EXPORT_SYMBOL(contig_page_data); #endif unsigned long max_low_pfn; unsigned long min_low_pfn; unsigned long max_pfn; unsigned long long max_possible_pfn; static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_MEMORY_REGIONS] __initdata_memblock; static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_RESERVED_REGIONS] __initdata_memblock; #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP static struct memblock_region memblock_physmem_init_regions[INIT_PHYSMEM_REGIONS]; #endif struct memblock memblock __initdata_memblock = { .memory.regions = memblock_memory_init_regions, .memory.max = INIT_MEMBLOCK_MEMORY_REGIONS, .memory.name = "memory", .reserved.regions = memblock_reserved_init_regions, .reserved.max = INIT_MEMBLOCK_RESERVED_REGIONS, .reserved.name = "reserved", .bottom_up = false, .current_limit = MEMBLOCK_ALLOC_ANYWHERE, }; #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP struct memblock_type physmem = { .regions = memblock_physmem_init_regions, .max = INIT_PHYSMEM_REGIONS, .name = "physmem", }; #endif /* * keep a pointer to &memblock.memory in the text section to use it in * __next_mem_range() and its helpers. * For architectures that do not keep memblock data after init, this * pointer will be reset to NULL at memblock_discard() */ static __refdata struct memblock_type *memblock_memory = &memblock.memory; #define for_each_memblock_type(i, memblock_type, rgn) \ for (i = 0, rgn = &memblock_type->regions[0]; \ i < memblock_type->cnt; \ i++, rgn = &memblock_type->regions[i]) #define memblock_dbg(fmt, ...) \ do { \ if (memblock_debug) \ pr_info(fmt, ##__VA_ARGS__); \ } while (0) static int memblock_debug __initdata_memblock; static bool system_has_some_mirror __initdata_memblock; static int memblock_can_resize __initdata_memblock; static int memblock_memory_in_slab __initdata_memblock; static int memblock_reserved_in_slab __initdata_memblock; bool __init_memblock memblock_has_mirror(void) { return system_has_some_mirror; } static enum memblock_flags __init_memblock choose_memblock_flags(void) { return system_has_some_mirror ? MEMBLOCK_MIRROR : MEMBLOCK_NONE; } /* adjust *@size so that (@base + *@size) doesn't overflow, return new size */ static inline phys_addr_t memblock_cap_size(phys_addr_t base, phys_addr_t *size) { return *size = min(*size, PHYS_ADDR_MAX - base); } /* * Address comparison utilities */ unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1, phys_addr_t base2, phys_addr_t size2) { return ((base1 < (base2 + size2)) && (base2 < (base1 + size1))); } bool __init_memblock memblock_overlaps_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size) { unsigned long i; memblock_cap_size(base, &size); for (i = 0; i < type->cnt; i++) if (memblock_addrs_overlap(base, size, type->regions[i].base, type->regions[i].size)) return true; return false; } /** * __memblock_find_range_bottom_up - find free area utility in bottom-up * @start: start of candidate range * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or * %MEMBLOCK_ALLOC_ACCESSIBLE * @size: size of free area to find * @align: alignment of free area to find * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @flags: pick from blocks based on memory attributes * * Utility called from memblock_find_in_range_node(), find free area bottom-up. * * Return: * Found address on success, 0 on failure. */ static phys_addr_t __init_memblock __memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align, int nid, enum memblock_flags flags) { phys_addr_t this_start, this_end, cand; u64 i; for_each_free_mem_range(i, nid, flags, &this_start, &this_end, NULL) { this_start = clamp(this_start, start, end); this_end = clamp(this_end, start, end); cand = round_up(this_start, align); if (cand < this_end && this_end - cand >= size) return cand; } return 0; } /** * __memblock_find_range_top_down - find free area utility, in top-down * @start: start of candidate range * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or * %MEMBLOCK_ALLOC_ACCESSIBLE * @size: size of free area to find * @align: alignment of free area to find * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @flags: pick from blocks based on memory attributes * * Utility called from memblock_find_in_range_node(), find free area top-down. * * Return: * Found address on success, 0 on failure. */ static phys_addr_t __init_memblock __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align, int nid, enum memblock_flags flags) { phys_addr_t this_start, this_end, cand; u64 i; for_each_free_mem_range_reverse(i, nid, flags, &this_start, &this_end, NULL) { this_start = clamp(this_start, start, end); this_end = clamp(this_end, start, end); if (this_end < size) continue; cand = round_down(this_end - size, align); if (cand >= this_start) return cand; } return 0; } /** * memblock_find_in_range_node - find free area in given range and node * @size: size of free area to find * @align: alignment of free area to find * @start: start of candidate range * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or * %MEMBLOCK_ALLOC_ACCESSIBLE * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @flags: pick from blocks based on memory attributes * * Find @size free area aligned to @align in the specified range and node. * * Return: * Found address on success, 0 on failure. */ static phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, int nid, enum memblock_flags flags) { /* pump up @end */ if (end == MEMBLOCK_ALLOC_ACCESSIBLE || end == MEMBLOCK_ALLOC_NOLEAKTRACE) end = memblock.current_limit; /* avoid allocating the first page */ start = max_t(phys_addr_t, start, PAGE_SIZE); end = max(start, end); if (memblock_bottom_up()) return __memblock_find_range_bottom_up(start, end, size, align, nid, flags); else return __memblock_find_range_top_down(start, end, size, align, nid, flags); } /** * memblock_find_in_range - find free area in given range * @start: start of candidate range * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or * %MEMBLOCK_ALLOC_ACCESSIBLE * @size: size of free area to find * @align: alignment of free area to find * * Find @size free area aligned to @align in the specified range. * * Return: * Found address on success, 0 on failure. */ static phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align) { phys_addr_t ret; enum memblock_flags flags = choose_memblock_flags(); again: ret = memblock_find_in_range_node(size, align, start, end, NUMA_NO_NODE, flags); if (!ret && (flags & MEMBLOCK_MIRROR)) { pr_warn_ratelimited("Could not allocate %pap bytes of mirrored memory\n", &size); flags &= ~MEMBLOCK_MIRROR; goto again; } return ret; } static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r) { type->total_size -= type->regions[r].size; memmove(&type->regions[r], &type->regions[r + 1], (type->cnt - (r + 1)) * sizeof(type->regions[r])); type->cnt--; /* Special case for empty arrays */ if (type->cnt == 0) { WARN_ON(type->total_size != 0); type->regions[0].base = 0; type->regions[0].size = 0; type->regions[0].flags = 0; memblock_set_region_node(&type->regions[0], MAX_NUMNODES); } } #ifndef CONFIG_ARCH_KEEP_MEMBLOCK /** * memblock_discard - discard memory and reserved arrays if they were allocated */ void __init memblock_discard(void) { phys_addr_t addr, size; if (memblock.reserved.regions != memblock_reserved_init_regions) { addr = __pa(memblock.reserved.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.reserved.max); if (memblock_reserved_in_slab) kfree(memblock.reserved.regions); else memblock_free_late(addr, size); } if (memblock.memory.regions != memblock_memory_init_regions) { addr = __pa(memblock.memory.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.memory.max); if (memblock_memory_in_slab) kfree(memblock.memory.regions); else memblock_free_late(addr, size); } memblock_memory = NULL; } #endif /** * memblock_double_array - double the size of the memblock regions array * @type: memblock type of the regions array being doubled * @new_area_start: starting address of memory range to avoid overlap with * @new_area_size: size of memory range to avoid overlap with * * Double the size of the @type regions array. If memblock is being used to * allocate memory for a new reserved regions array and there is a previously * allocated memory range [@new_area_start, @new_area_start + @new_area_size] * waiting to be reserved, ensure the memory used by the new array does * not overlap. * * Return: * 0 on success, -1 on failure. */ static int __init_memblock memblock_double_array(struct memblock_type *type, phys_addr_t new_area_start, phys_addr_t new_area_size) { struct memblock_region *new_array, *old_array; phys_addr_t old_alloc_size, new_alloc_size; phys_addr_t old_size, new_size, addr, new_end; int use_slab = slab_is_available(); int *in_slab; /* We don't allow resizing until we know about the reserved regions * of memory that aren't suitable for allocation */ if (!memblock_can_resize) panic("memblock: cannot resize %s array\n", type->name); /* Calculate new doubled size */ old_size = type->max * sizeof(struct memblock_region); new_size = old_size << 1; /* * We need to allocated new one align to PAGE_SIZE, * so we can free them completely later. */ old_alloc_size = PAGE_ALIGN(old_size); new_alloc_size = PAGE_ALIGN(new_size); /* Retrieve the slab flag */ if (type == &memblock.memory) in_slab = &memblock_memory_in_slab; else in_slab = &memblock_reserved_in_slab; /* Try to find some space for it */ if (use_slab) { new_array = kmalloc(new_size, GFP_KERNEL); addr = new_array ? __pa(new_array) : 0; } else { /* only exclude range when trying to double reserved.regions */ if (type != &memblock.reserved) new_area_start = new_area_size = 0; addr = memblock_find_in_range(new_area_start + new_area_size, memblock.current_limit, new_alloc_size, PAGE_SIZE); if (!addr && new_area_size) addr = memblock_find_in_range(0, min(new_area_start, memblock.current_limit), new_alloc_size, PAGE_SIZE); new_array = addr ? __va(addr) : NULL; } if (!addr) { pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n", type->name, type->max, type->max * 2); return -1; } new_end = addr + new_size - 1; memblock_dbg("memblock: %s is doubled to %ld at [%pa-%pa]", type->name, type->max * 2, &addr, &new_end); /* * Found space, we now need to move the array over before we add the * reserved region since it may be our reserved array itself that is * full. */ memcpy(new_array, type->regions, old_size); memset(new_array + type->max, 0, old_size); old_array = type->regions; type->regions = new_array; type->max <<= 1; /* Free old array. We needn't free it if the array is the static one */ if (*in_slab) kfree(old_array); else if (old_array != memblock_memory_init_regions && old_array != memblock_reserved_init_regions) memblock_free(old_array, old_alloc_size); /* * Reserve the new array if that comes from the memblock. Otherwise, we * needn't do it */ if (!use_slab) BUG_ON(memblock_reserve(addr, new_alloc_size)); /* Update slab flag */ *in_slab = use_slab; return 0; } /** * memblock_merge_regions - merge neighboring compatible regions * @type: memblock type to scan * @start_rgn: start scanning from (@start_rgn - 1) * @end_rgn: end scanning at (@end_rgn - 1) * Scan @type and merge neighboring compatible regions in [@start_rgn - 1, @end_rgn) */ static void __init_memblock memblock_merge_regions(struct memblock_type *type, unsigned long start_rgn, unsigned long end_rgn) { int i = 0; if (start_rgn) i = start_rgn - 1; end_rgn = min(end_rgn, type->cnt - 1); while (i < end_rgn) { struct memblock_region *this = &type->regions[i]; struct memblock_region *next = &type->regions[i + 1]; if (this->base + this->size != next->base || memblock_get_region_node(this) != memblock_get_region_node(next) || this->flags != next->flags) { BUG_ON(this->base + this->size > next->base); i++; continue; } this->size += next->size; /* move forward from next + 1, index of which is i + 2 */ memmove(next, next + 1, (type->cnt - (i + 2)) * sizeof(*next)); type->cnt--; end_rgn--; } } /** * memblock_insert_region - insert new memblock region * @type: memblock type to insert into * @idx: index for the insertion point * @base: base address of the new region * @size: size of the new region * @nid: node id of the new region * @flags: flags of the new region * * Insert new memblock region [@base, @base + @size) into @type at @idx. * @type must already have extra room to accommodate the new region. */ static void __init_memblock memblock_insert_region(struct memblock_type *type, int idx, phys_addr_t base, phys_addr_t size, int nid, enum memblock_flags flags) { struct memblock_region *rgn = &type->regions[idx]; BUG_ON(type->cnt >= type->max); memmove(rgn + 1, rgn, (type->cnt - idx) * sizeof(*rgn)); rgn->base = base; rgn->size = size; rgn->flags = flags; memblock_set_region_node(rgn, nid); type->cnt++; type->total_size += size; } /** * memblock_add_range - add new memblock region * @type: memblock type to add new region into * @base: base address of the new region * @size: size of the new region * @nid: nid of the new region * @flags: flags of the new region * * Add new memblock region [@base, @base + @size) into @type. The new region * is allowed to overlap with existing ones - overlaps don't affect already * existing regions. @type is guaranteed to be minimal (all neighbouring * compatible regions are merged) after the addition. * * Return: * 0 on success, -errno on failure. */ static int __init_memblock memblock_add_range(struct memblock_type *type, phys_addr_t base, phys_addr_t size, int nid, enum memblock_flags flags) { bool insert = false; phys_addr_t obase = base; phys_addr_t end = base + memblock_cap_size(base, &size); int idx, nr_new, start_rgn = -1, end_rgn; struct memblock_region *rgn; if (!size) return 0; /* special case for empty array */ if (type->regions[0].size == 0) { WARN_ON(type->cnt != 0 || type->total_size); type->regions[0].base = base; type->regions[0].size = size; type->regions[0].flags = flags; memblock_set_region_node(&type->regions[0], nid); type->total_size = size; type->cnt = 1; return 0; } /* * The worst case is when new range overlaps all existing regions, * then we'll need type->cnt + 1 empty regions in @type. So if * type->cnt * 2 + 1 is less than or equal to type->max, we know * that there is enough empty regions in @type, and we can insert * regions directly. */ if (type->cnt * 2 + 1 <= type->max) insert = true; repeat: /* * The following is executed twice. Once with %false @insert and * then with %true. The first counts the number of regions needed * to accommodate the new area. The second actually inserts them. */ base = obase; nr_new = 0; for_each_memblock_type(idx, type, rgn) { phys_addr_t rbase = rgn->base; phys_addr_t rend = rbase + rgn->size; if (rbase >= end) break; if (rend <= base) continue; /* * @rgn overlaps. If it separates the lower part of new * area, insert that portion. */ if (rbase > base) { #ifdef CONFIG_NUMA WARN_ON(nid != memblock_get_region_node(rgn)); #endif WARN_ON(flags != rgn->flags); nr_new++; if (insert) { if (start_rgn == -1) start_rgn = idx; end_rgn = idx + 1; memblock_insert_region(type, idx++, base, rbase - base, nid, flags); } } /* area below @rend is dealt with, forget about it */ base = min(rend, end); } /* insert the remaining portion */ if (base < end) { nr_new++; if (insert) { if (start_rgn == -1) start_rgn = idx; end_rgn = idx + 1; memblock_insert_region(type, idx, base, end - base, nid, flags); } } if (!nr_new) return 0; /* * If this was the first round, resize array and repeat for actual * insertions; otherwise, merge and return. */ if (!insert) { while (type->cnt + nr_new > type->max) if (memblock_double_array(type, obase, size) < 0) return -ENOMEM; insert = true; goto repeat; } else { memblock_merge_regions(type, start_rgn, end_rgn); return 0; } } /** * memblock_add_node - add new memblock region within a NUMA node * @base: base address of the new region * @size: size of the new region * @nid: nid of the new region * @flags: flags of the new region * * Add new memblock region [@base, @base + @size) to the "memory" * type. See memblock_add_range() description for mode details * * Return: * 0 on success, -errno on failure. */ int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size, int nid, enum memblock_flags flags) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] nid=%d flags=%x %pS\n", __func__, &base, &end, nid, flags, (void *)_RET_IP_); return memblock_add_range(&memblock.memory, base, size, nid, flags); } /** * memblock_add - add new memblock region * @base: base address of the new region * @size: size of the new region * * Add new memblock region [@base, @base + @size) to the "memory" * type. See memblock_add_range() description for mode details * * Return: * 0 on success, -errno on failure. */ int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); return memblock_add_range(&memblock.memory, base, size, MAX_NUMNODES, 0); } /** * memblock_validate_numa_coverage - check if amount of memory with * no node ID assigned is less than a threshold * @threshold_bytes: maximal memory size that can have unassigned node * ID (in bytes). * * A buggy firmware may report memory that does not belong to any node. * Check if amount of such memory is below @threshold_bytes. * * Return: true on success, false on failure. */ bool __init_memblock memblock_validate_numa_coverage(unsigned long threshold_bytes) { unsigned long nr_pages = 0; unsigned long start_pfn, end_pfn, mem_size_mb; int nid, i; /* calculate lose page */ for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { if (!numa_valid_node(nid)) nr_pages += end_pfn - start_pfn; } if ((nr_pages << PAGE_SHIFT) > threshold_bytes) { mem_size_mb = memblock_phys_mem_size() >> 20; pr_err("NUMA: no nodes coverage for %luMB of %luMB RAM\n", (nr_pages << PAGE_SHIFT) >> 20, mem_size_mb); return false; } return true; } /** * memblock_isolate_range - isolate given range into disjoint memblocks * @type: memblock type to isolate range for * @base: base of range to isolate * @size: size of range to isolate * @start_rgn: out parameter for the start of isolated region * @end_rgn: out parameter for the end of isolated region * * Walk @type and ensure that regions don't cross the boundaries defined by * [@base, @base + @size). Crossing regions are split at the boundaries, * which may create at most two more regions. The index of the first * region inside the range is returned in *@start_rgn and the index of the * first region after the range is returned in *@end_rgn. * * Return: * 0 on success, -errno on failure. */ static int __init_memblock memblock_isolate_range(struct memblock_type *type, phys_addr_t base, phys_addr_t size, int *start_rgn, int *end_rgn) { phys_addr_t end = base + memblock_cap_size(base, &size); int idx; struct memblock_region *rgn; *start_rgn = *end_rgn = 0; if (!size) return 0; /* we'll create at most two more regions */ while (type->cnt + 2 > type->max) if (memblock_double_array(type, base, size) < 0) return -ENOMEM; for_each_memblock_type(idx, type, rgn) { phys_addr_t rbase = rgn->base; phys_addr_t rend = rbase + rgn->size; if (rbase >= end) break; if (rend <= base) continue; if (rbase < base) { /* * @rgn intersects from below. Split and continue * to process the next region - the new top half. */ rgn->base = base; rgn->size -= base - rbase; type->total_size -= base - rbase; memblock_insert_region(type, idx, rbase, base - rbase, memblock_get_region_node(rgn), rgn->flags); } else if (rend > end) { /* * @rgn intersects from above. Split and redo the * current region - the new bottom half. */ rgn->base = end; rgn->size -= end - rbase; type->total_size -= end - rbase; memblock_insert_region(type, idx--, rbase, end - rbase, memblock_get_region_node(rgn), rgn->flags); } else { /* @rgn is fully contained, record it */ if (!*end_rgn) *start_rgn = idx; *end_rgn = idx + 1; } } return 0; } static int __init_memblock memblock_remove_range(struct memblock_type *type, phys_addr_t base, phys_addr_t size) { int start_rgn, end_rgn; int i, ret; ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); if (ret) return ret; for (i = end_rgn - 1; i >= start_rgn; i--) memblock_remove_region(type, i); return 0; } int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); return memblock_remove_range(&memblock.memory, base, size); } /** * memblock_free - free boot memory allocation * @ptr: starting address of the boot memory allocation * @size: size of the boot memory block in bytes * * Free boot memory block previously allocated by memblock_alloc_xx() API. * The freeing memory will not be released to the buddy allocator. */ void __init_memblock memblock_free(void *ptr, size_t size) { if (ptr) memblock_phys_free(__pa(ptr), size); } /** * memblock_phys_free - free boot memory block * @base: phys starting address of the boot memory block * @size: size of the boot memory block in bytes * * Free boot memory block previously allocated by memblock_phys_alloc_xx() API. * The freeing memory will not be released to the buddy allocator. */ int __init_memblock memblock_phys_free(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); kmemleak_free_part_phys(base, size); return memblock_remove_range(&memblock.reserved, base, size); } int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); return memblock_add_range(&memblock.reserved, base, size, MAX_NUMNODES, 0); } #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP int __init_memblock memblock_physmem_add(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); return memblock_add_range(&physmem, base, size, MAX_NUMNODES, 0); } #endif /** * memblock_setclr_flag - set or clear flag for a memory region * @type: memblock type to set/clear flag for * @base: base address of the region * @size: size of the region * @set: set or clear the flag * @flag: the flag to update * * This function isolates region [@base, @base + @size), and sets/clears flag * * Return: 0 on success, -errno on failure. */ static int __init_memblock memblock_setclr_flag(struct memblock_type *type, phys_addr_t base, phys_addr_t size, int set, int flag) { int i, ret, start_rgn, end_rgn; ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); if (ret) return ret; for (i = start_rgn; i < end_rgn; i++) { struct memblock_region *r = &type->regions[i]; if (set) r->flags |= flag; else r->flags &= ~flag; } memblock_merge_regions(type, start_rgn, end_rgn); return 0; } /** * memblock_mark_hotplug - Mark hotpluggable memory with flag MEMBLOCK_HOTPLUG. * @base: the base phys addr of the region * @size: the size of the region * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size) { return memblock_setclr_flag(&memblock.memory, base, size, 1, MEMBLOCK_HOTPLUG); } /** * memblock_clear_hotplug - Clear flag MEMBLOCK_HOTPLUG for a specified region. * @base: the base phys addr of the region * @size: the size of the region * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size) { return memblock_setclr_flag(&memblock.memory, base, size, 0, MEMBLOCK_HOTPLUG); } /** * memblock_mark_mirror - Mark mirrored memory with flag MEMBLOCK_MIRROR. * @base: the base phys addr of the region * @size: the size of the region * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size) { if (!mirrored_kernelcore) return 0; system_has_some_mirror = true; return memblock_setclr_flag(&memblock.memory, base, size, 1, MEMBLOCK_MIRROR); } /** * memblock_mark_nomap - Mark a memory region with flag MEMBLOCK_NOMAP. * @base: the base phys addr of the region * @size: the size of the region * * The memory regions marked with %MEMBLOCK_NOMAP will not be added to the * direct mapping of the physical memory. These regions will still be * covered by the memory map. The struct page representing NOMAP memory * frames in the memory map will be PageReserved() * * Note: if the memory being marked %MEMBLOCK_NOMAP was allocated from * memblock, the caller must inform kmemleak to ignore that memory * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size) { return memblock_setclr_flag(&memblock.memory, base, size, 1, MEMBLOCK_NOMAP); } /** * memblock_clear_nomap - Clear flag MEMBLOCK_NOMAP for a specified region. * @base: the base phys addr of the region * @size: the size of the region * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size) { return memblock_setclr_flag(&memblock.memory, base, size, 0, MEMBLOCK_NOMAP); } /** * memblock_reserved_mark_noinit - Mark a reserved memory region with flag * MEMBLOCK_RSRV_NOINIT which results in the struct pages not being initialized * for this region. * @base: the base phys addr of the region * @size: the size of the region * * struct pages will not be initialized for reserved memory regions marked with * %MEMBLOCK_RSRV_NOINIT. * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_reserved_mark_noinit(phys_addr_t base, phys_addr_t size) { return memblock_setclr_flag(&memblock.reserved, base, size, 1, MEMBLOCK_RSRV_NOINIT); } static bool should_skip_region(struct memblock_type *type, struct memblock_region *m, int nid, int flags) { int m_nid = memblock_get_region_node(m); /* we never skip regions when iterating memblock.reserved or physmem */ if (type != memblock_memory) return false; /* only memory regions are associated with nodes, check it */ if (numa_valid_node(nid) && nid != m_nid) return true; /* skip hotpluggable memory regions if needed */ if (movable_node_is_enabled() && memblock_is_hotpluggable(m) && !(flags & MEMBLOCK_HOTPLUG)) return true; /* if we want mirror memory skip non-mirror memory regions */ if ((flags & MEMBLOCK_MIRROR) && !memblock_is_mirror(m)) return true; /* skip nomap memory unless we were asked for it explicitly */ if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m)) return true; /* skip driver-managed memory unless we were asked for it explicitly */ if (!(flags & MEMBLOCK_DRIVER_MANAGED) && memblock_is_driver_managed(m)) return true; return false; } /** * __next_mem_range - next function for for_each_free_mem_range() etc. * @idx: pointer to u64 loop variable * @nid: node selector, %NUMA_NO_NODE for all nodes * @flags: pick from blocks based on memory attributes * @type_a: pointer to memblock_type from where the range is taken * @type_b: pointer to memblock_type which excludes memory from being taken * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL * @out_nid: ptr to int for nid of the range, can be %NULL * * Find the first area from *@idx which matches @nid, fill the out * parameters, and update *@idx for the next iteration. The lower 32bit of * *@idx contains index into type_a and the upper 32bit indexes the * areas before each region in type_b. For example, if type_b regions * look like the following, * * 0:[0-16), 1:[32-48), 2:[128-130) * * The upper 32bit indexes the following regions. * * 0:[0-0), 1:[16-32), 2:[48-128), 3:[130-MAX) * * As both region arrays are sorted, the function advances the two indices * in lockstep and returns each intersection. */ void __next_mem_range(u64 *idx, int nid, enum memblock_flags flags, struct memblock_type *type_a, struct memblock_type *type_b, phys_addr_t *out_start, phys_addr_t *out_end, int *out_nid) { int idx_a = *idx & 0xffffffff; int idx_b = *idx >> 32; for (; idx_a < type_a->cnt; idx_a++) { struct memblock_region *m = &type_a->regions[idx_a]; phys_addr_t m_start = m->base; phys_addr_t m_end = m->base + m->size; int m_nid = memblock_get_region_node(m); if (should_skip_region(type_a, m, nid, flags)) continue; if (!type_b) { if (out_start) *out_start = m_start; if (out_end) *out_end = m_end; if (out_nid) *out_nid = m_nid; idx_a++; *idx = (u32)idx_a | (u64)idx_b << 32; return; } /* scan areas before each reservation */ for (; idx_b < type_b->cnt + 1; idx_b++) { struct memblock_region *r; phys_addr_t r_start; phys_addr_t r_end; r = &type_b->regions[idx_b]; r_start = idx_b ? r[-1].base + r[-1].size : 0; r_end = idx_b < type_b->cnt ? r->base : PHYS_ADDR_MAX; /* * if idx_b advanced past idx_a, * break out to advance idx_a */ if (r_start >= m_end) break; /* if the two regions intersect, we're done */ if (m_start < r_end) { if (out_start) *out_start = max(m_start, r_start); if (out_end) *out_end = min(m_end, r_end); if (out_nid) *out_nid = m_nid; /* * The region which ends first is * advanced for the next iteration. */ if (m_end <= r_end) idx_a++; else idx_b++; *idx = (u32)idx_a | (u64)idx_b << 32; return; } } } /* signal end of iteration */ *idx = ULLONG_MAX; } /** * __next_mem_range_rev - generic next function for for_each_*_range_rev() * * @idx: pointer to u64 loop variable * @nid: node selector, %NUMA_NO_NODE for all nodes * @flags: pick from blocks based on memory attributes * @type_a: pointer to memblock_type from where the range is taken * @type_b: pointer to memblock_type which excludes memory from being taken * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL * @out_nid: ptr to int for nid of the range, can be %NULL * * Finds the next range from type_a which is not marked as unsuitable * in type_b. * * Reverse of __next_mem_range(). */ void __init_memblock __next_mem_range_rev(u64 *idx, int nid, enum memblock_flags flags, struct memblock_type *type_a, struct memblock_type *type_b, phys_addr_t *out_start, phys_addr_t *out_end, int *out_nid) { int idx_a = *idx & 0xffffffff; int idx_b = *idx >> 32; if (*idx == (u64)ULLONG_MAX) { idx_a = type_a->cnt - 1; if (type_b != NULL) idx_b = type_b->cnt; else idx_b = 0; } for (; idx_a >= 0; idx_a--) { struct memblock_region *m = &type_a->regions[idx_a]; phys_addr_t m_start = m->base; phys_addr_t m_end = m->base + m->size; int m_nid = memblock_get_region_node(m); if (should_skip_region(type_a, m, nid, flags)) continue; if (!type_b) { if (out_start) *out_start = m_start; if (out_end) *out_end = m_end; if (out_nid) *out_nid = m_nid; idx_a--; *idx = (u32)idx_a | (u64)idx_b << 32; return; } /* scan areas before each reservation */ for (; idx_b >= 0; idx_b--) { struct memblock_region *r; phys_addr_t r_start; phys_addr_t r_end; r = &type_b->regions[idx_b]; r_start = idx_b ? r[-1].base + r[-1].size : 0; r_end = idx_b < type_b->cnt ? r->base : PHYS_ADDR_MAX; /* * if idx_b advanced past idx_a, * break out to advance idx_a */ if (r_end <= m_start) break; /* if the two regions intersect, we're done */ if (m_end > r_start) { if (out_start) *out_start = max(m_start, r_start); if (out_end) *out_end = min(m_end, r_end); if (out_nid) *out_nid = m_nid; if (m_start >= r_start) idx_a--; else idx_b--; *idx = (u32)idx_a | (u64)idx_b << 32; return; } } } /* signal end of iteration */ *idx = ULLONG_MAX; } /* * Common iterator interface used to define for_each_mem_pfn_range(). */ void __init_memblock __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, unsigned long *out_end_pfn, int *out_nid) { struct memblock_type *type = &memblock.memory; struct memblock_region *r; int r_nid; while (++*idx < type->cnt) { r = &type->regions[*idx]; r_nid = memblock_get_region_node(r); if (PFN_UP(r->base) >= PFN_DOWN(r->base + r->size)) continue; if (!numa_valid_node(nid) || nid == r_nid) break; } if (*idx >= type->cnt) { *idx = -1; return; } if (out_start_pfn) *out_start_pfn = PFN_UP(r->base); if (out_end_pfn) *out_end_pfn = PFN_DOWN(r->base + r->size); if (out_nid) *out_nid = r_nid; } /** * memblock_set_node - set node ID on memblock regions * @base: base of area to set node ID for * @size: size of area to set node ID for * @type: memblock type to set node ID for * @nid: node ID to set * * Set the nid of memblock @type regions in [@base, @base + @size) to @nid. * Regions which cross the area boundaries are split as necessary. * * Return: * 0 on success, -errno on failure. */ int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size, struct memblock_type *type, int nid) { #ifdef CONFIG_NUMA int start_rgn, end_rgn; int i, ret; ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); if (ret) return ret; for (i = start_rgn; i < end_rgn; i++) memblock_set_region_node(&type->regions[i], nid); memblock_merge_regions(type, start_rgn, end_rgn); #endif return 0; } #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /** * __next_mem_pfn_range_in_zone - iterator for for_each_*_range_in_zone() * * @idx: pointer to u64 loop variable * @zone: zone in which all of the memory blocks reside * @out_spfn: ptr to ulong for start pfn of the range, can be %NULL * @out_epfn: ptr to ulong for end pfn of the range, can be %NULL * * This function is meant to be a zone/pfn specific wrapper for the * for_each_mem_range type iterators. Specifically they are used in the * deferred memory init routines and as such we were duplicating much of * this logic throughout the code. So instead of having it in multiple * locations it seemed like it would make more sense to centralize this to * one new iterator that does everything they need. */ void __init_memblock __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, unsigned long *out_spfn, unsigned long *out_epfn) { int zone_nid = zone_to_nid(zone); phys_addr_t spa, epa; __next_mem_range(idx, zone_nid, MEMBLOCK_NONE, &memblock.memory, &memblock.reserved, &spa, &epa, NULL); while (*idx != U64_MAX) { unsigned long epfn = PFN_DOWN(epa); unsigned long spfn = PFN_UP(spa); /* * Verify the end is at least past the start of the zone and * that we have at least one PFN to initialize. */ if (zone->zone_start_pfn < epfn && spfn < epfn) { /* if we went too far just stop searching */ if (zone_end_pfn(zone) <= spfn) { *idx = U64_MAX; break; } if (out_spfn) *out_spfn = max(zone->zone_start_pfn, spfn); if (out_epfn) *out_epfn = min(zone_end_pfn(zone), epfn); return; } __next_mem_range(idx, zone_nid, MEMBLOCK_NONE, &memblock.memory, &memblock.reserved, &spa, &epa, NULL); } /* signal end of iteration */ if (out_spfn) *out_spfn = ULONG_MAX; if (out_epfn) *out_epfn = 0; } #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ /** * memblock_alloc_range_nid - allocate boot memory block * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @start: the lower bound of the memory region to allocate (phys address) * @end: the upper bound of the memory region to allocate (phys address) * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @exact_nid: control the allocation fall back to other nodes * * The allocation is performed from memory region limited by * memblock.current_limit if @end == %MEMBLOCK_ALLOC_ACCESSIBLE. * * If the specified node can not hold the requested memory and @exact_nid * is false, the allocation falls back to any node in the system. * * For systems with memory mirroring, the allocation is attempted first * from the regions with mirroring enabled and then retried from any * memory region. * * In addition, function using kmemleak_alloc_phys for allocated boot * memory block, it is never reported as leaks. * * Return: * Physical address of allocated memory block on success, %0 on failure. */ phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, int nid, bool exact_nid) { enum memblock_flags flags = choose_memblock_flags(); phys_addr_t found; /* * Detect any accidental use of these APIs after slab is ready, as at * this moment memblock may be deinitialized already and its * internal data may be destroyed (after execution of memblock_free_all) */ if (WARN_ON_ONCE(slab_is_available())) { void *vaddr = kzalloc_node(size, GFP_NOWAIT, nid); return vaddr ? virt_to_phys(vaddr) : 0; } if (!align) { /* Can't use WARNs this early in boot on powerpc */ dump_stack(); align = SMP_CACHE_BYTES; } again: found = memblock_find_in_range_node(size, align, start, end, nid, flags); if (found && !memblock_reserve(found, size)) goto done; if (numa_valid_node(nid) && !exact_nid) { found = memblock_find_in_range_node(size, align, start, end, NUMA_NO_NODE, flags); if (found && !memblock_reserve(found, size)) goto done; } if (flags & MEMBLOCK_MIRROR) { flags &= ~MEMBLOCK_MIRROR; pr_warn_ratelimited("Could not allocate %pap bytes of mirrored memory\n", &size); goto again; } return 0; done: /* * Skip kmemleak for those places like kasan_init() and * early_pgtable_alloc() due to high volume. */ if (end != MEMBLOCK_ALLOC_NOLEAKTRACE) /* * Memblock allocated blocks are never reported as * leaks. This is because many of these blocks are * only referred via the physical address which is * not looked up by kmemleak. */ kmemleak_alloc_phys(found, size, 0); /* * Some Virtual Machine platforms, such as Intel TDX or AMD SEV-SNP, * require memory to be accepted before it can be used by the * guest. * * Accept the memory of the allocated buffer. */ accept_memory(found, size); return found; } /** * memblock_phys_alloc_range - allocate a memory block inside specified range * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @start: the lower bound of the memory region to allocate (physical address) * @end: the upper bound of the memory region to allocate (physical address) * * Allocate @size bytes in the between @start and @end. * * Return: physical address of the allocated memory block on success, * %0 on failure. */ phys_addr_t __init memblock_phys_alloc_range(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end) { memblock_dbg("%s: %llu bytes align=0x%llx from=%pa max_addr=%pa %pS\n", __func__, (u64)size, (u64)align, &start, &end, (void *)_RET_IP_); return memblock_alloc_range_nid(size, align, start, end, NUMA_NO_NODE, false); } /** * memblock_phys_alloc_try_nid - allocate a memory block from specified NUMA node * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * * Allocates memory block from the specified NUMA node. If the node * has no available memory, attempts to allocated from any node in the * system. * * Return: physical address of the allocated memory block on success, * %0 on failure. */ phys_addr_t __init memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid) { return memblock_alloc_range_nid(size, align, 0, MEMBLOCK_ALLOC_ACCESSIBLE, nid, false); } /** * memblock_alloc_internal - allocate boot memory block * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region to allocate (phys address) * @max_addr: the upper bound of the memory region to allocate (phys address) * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @exact_nid: control the allocation fall back to other nodes * * Allocates memory block using memblock_alloc_range_nid() and * converts the returned physical address to virtual. * * The @min_addr limit is dropped if it can not be satisfied and the allocation * will fall back to memory below @min_addr. Other constraints, such * as node and mirrored memory will be handled again in * memblock_alloc_range_nid(). * * Return: * Virtual address of allocated memory block on success, NULL on failure. */ static void * __init memblock_alloc_internal( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid, bool exact_nid) { phys_addr_t alloc; if (max_addr > memblock.current_limit) max_addr = memblock.current_limit; alloc = memblock_alloc_range_nid(size, align, min_addr, max_addr, nid, exact_nid); /* retry allocation without lower limit */ if (!alloc && min_addr) alloc = memblock_alloc_range_nid(size, align, 0, max_addr, nid, exact_nid); if (!alloc) return NULL; return phys_to_virt(alloc); } /** * memblock_alloc_exact_nid_raw - allocate boot memory block on the exact node * without zeroing memory * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region from where the allocation * is preferred (phys address) * @max_addr: the upper bound of the memory region from where the allocation * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to * allocate only from memory limited by memblock.current_limit value * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * * Public function, provides additional debug information (including caller * info), if enabled. Does not zero allocated memory. * * Return: * Virtual address of allocated memory block on success, NULL on failure. */ void * __init memblock_alloc_exact_nid_raw( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) { memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n", __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); return memblock_alloc_internal(size, align, min_addr, max_addr, nid, true); } /** * memblock_alloc_try_nid_raw - allocate boot memory block without zeroing * memory and without panicking * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region from where the allocation * is preferred (phys address) * @max_addr: the upper bound of the memory region from where the allocation * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to * allocate only from memory limited by memblock.current_limit value * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * * Public function, provides additional debug information (including caller * info), if enabled. Does not zero allocated memory, does not panic if request * cannot be satisfied. * * Return: * Virtual address of allocated memory block on success, NULL on failure. */ void * __init memblock_alloc_try_nid_raw( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) { memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n", __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); return memblock_alloc_internal(size, align, min_addr, max_addr, nid, false); } /** * memblock_alloc_try_nid - allocate boot memory block * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region from where the allocation * is preferred (phys address) * @max_addr: the upper bound of the memory region from where the allocation * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to * allocate only from memory limited by memblock.current_limit value * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * * Public function, provides additional debug information (including caller * info), if enabled. This function zeroes the allocated memory. * * Return: * Virtual address of allocated memory block on success, NULL on failure. */ void * __init memblock_alloc_try_nid( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) { void *ptr; memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n", __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); ptr = memblock_alloc_internal(size, align, min_addr, max_addr, nid, false); if (ptr) memset(ptr, 0, size); return ptr; } /** * memblock_free_late - free pages directly to buddy allocator * @base: phys starting address of the boot memory block * @size: size of the boot memory block in bytes * * This is only useful when the memblock allocator has already been torn * down, but we are still initializing the system. Pages are released directly * to the buddy allocator. */ void __init memblock_free_late(phys_addr_t base, phys_addr_t size) { phys_addr_t cursor, end; end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); kmemleak_free_part_phys(base, size); cursor = PFN_UP(base); end = PFN_DOWN(base + size); for (; cursor < end; cursor++) { memblock_free_pages(pfn_to_page(cursor), cursor, 0); totalram_pages_inc(); } } /* * Remaining API functions */ phys_addr_t __init_memblock memblock_phys_mem_size(void) { return memblock.memory.total_size; } phys_addr_t __init_memblock memblock_reserved_size(void) { return memblock.reserved.total_size; } /** * memblock_estimated_nr_free_pages - return estimated number of free pages * from memblock point of view * * During bootup, subsystems might need a rough estimate of the number of free * pages in the whole system, before precise numbers are available from the * buddy. Especially with CONFIG_DEFERRED_STRUCT_PAGE_INIT, the numbers * obtained from the buddy might be very imprecise during bootup. * * Return: * An estimated number of free pages from memblock point of view. */ unsigned long __init memblock_estimated_nr_free_pages(void) { return PHYS_PFN(memblock_phys_mem_size() - memblock_reserved_size()); } /* lowest address */ phys_addr_t __init_memblock memblock_start_of_DRAM(void) { return memblock.memory.regions[0].base; } phys_addr_t __init_memblock memblock_end_of_DRAM(void) { int idx = memblock.memory.cnt - 1; return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size); } static phys_addr_t __init_memblock __find_max_addr(phys_addr_t limit) { phys_addr_t max_addr = PHYS_ADDR_MAX; struct memblock_region *r; /* * translate the memory @limit size into the max address within one of * the memory memblock regions, if the @limit exceeds the total size * of those regions, max_addr will keep original value PHYS_ADDR_MAX */ for_each_mem_region(r) { if (limit <= r->size) { max_addr = r->base + limit; break; } limit -= r->size; } return max_addr; } void __init memblock_enforce_memory_limit(phys_addr_t limit) { phys_addr_t max_addr; if (!limit) return; max_addr = __find_max_addr(limit); /* @limit exceeds the total size of the memory, do nothing */ if (max_addr == PHYS_ADDR_MAX) return; /* truncate both memory and reserved regions */ memblock_remove_range(&memblock.memory, max_addr, PHYS_ADDR_MAX); memblock_remove_range(&memblock.reserved, max_addr, PHYS_ADDR_MAX); } void __init memblock_cap_memory_range(phys_addr_t base, phys_addr_t size) { int start_rgn, end_rgn; int i, ret; if (!size) return; if (!memblock_memory->total_size) { pr_warn("%s: No memory registered yet\n", __func__); return; } ret = memblock_isolate_range(&memblock.memory, base, size, &start_rgn, &end_rgn); if (ret) return; /* remove all the MAP regions */ for (i = memblock.memory.cnt - 1; i >= end_rgn; i--) if (!memblock_is_nomap(&memblock.memory.regions[i])) memblock_remove_region(&memblock.memory, i); for (i = start_rgn - 1; i >= 0; i--) if (!memblock_is_nomap(&memblock.memory.regions[i])) memblock_remove_region(&memblock.memory, i); /* truncate the reserved regions */ memblock_remove_range(&memblock.reserved, 0, base); memblock_remove_range(&memblock.reserved, base + size, PHYS_ADDR_MAX); } void __init memblock_mem_limit_remove_map(phys_addr_t limit) { phys_addr_t max_addr; if (!limit) return; max_addr = __find_max_addr(limit); /* @limit exceeds the total size of the memory, do nothing */ if (max_addr == PHYS_ADDR_MAX) return; memblock_cap_memory_range(0, max_addr); } static int __init_memblock memblock_search(struct memblock_type *type, phys_addr_t addr) { unsigned int left = 0, right = type->cnt; do { unsigned int mid = (right + left) / 2; if (addr < type->regions[mid].base) right = mid; else if (addr >= (type->regions[mid].base + type->regions[mid].size)) left = mid + 1; else return mid; } while (left < right); return -1; } bool __init_memblock memblock_is_reserved(phys_addr_t addr) { return memblock_search(&memblock.reserved, addr) != -1; } bool __init_memblock memblock_is_memory(phys_addr_t addr) { return memblock_search(&memblock.memory, addr) != -1; } bool __init_memblock memblock_is_map_memory(phys_addr_t addr) { int i = memblock_search(&memblock.memory, addr); if (i == -1) return false; return !memblock_is_nomap(&memblock.memory.regions[i]); } int __init_memblock memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn) { struct memblock_type *type = &memblock.memory; int mid = memblock_search(type, PFN_PHYS(pfn)); if (mid == -1) return NUMA_NO_NODE; *start_pfn = PFN_DOWN(type->regions[mid].base); *end_pfn = PFN_DOWN(type->regions[mid].base + type->regions[mid].size); return memblock_get_region_node(&type->regions[mid]); } /** * memblock_is_region_memory - check if a region is a subset of memory * @base: base of region to check * @size: size of region to check * * Check if the region [@base, @base + @size) is a subset of a memory block. * * Return: * 0 if false, non-zero if true */ bool __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size) { int idx = memblock_search(&memblock.memory, base); phys_addr_t end = base + memblock_cap_size(base, &size); if (idx == -1) return false; return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size) >= end; } /** * memblock_is_region_reserved - check if a region intersects reserved memory * @base: base of region to check * @size: size of region to check * * Check if the region [@base, @base + @size) intersects a reserved * memory block. * * Return: * True if they intersect, false if not. */ bool __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size) { return memblock_overlaps_region(&memblock.reserved, base, size); } void __init_memblock memblock_trim_memory(phys_addr_t align) { phys_addr_t start, end, orig_start, orig_end; struct memblock_region *r; for_each_mem_region(r) { orig_start = r->base; orig_end = r->base + r->size; start = round_up(orig_start, align); end = round_down(orig_end, align); if (start == orig_start && end == orig_end) continue; if (start < end) { r->base = start; r->size = end - start; } else { memblock_remove_region(&memblock.memory, r - memblock.memory.regions); r--; } } } void __init_memblock memblock_set_current_limit(phys_addr_t limit) { memblock.current_limit = limit; } phys_addr_t __init_memblock memblock_get_current_limit(void) { return memblock.current_limit; } static void __init_memblock memblock_dump(struct memblock_type *type) { phys_addr_t base, end, size; enum memblock_flags flags; int idx; struct memblock_region *rgn; pr_info(" %s.cnt = 0x%lx\n", type->name, type->cnt); for_each_memblock_type(idx, type, rgn) { char nid_buf[32] = ""; base = rgn->base; size = rgn->size; end = base + size - 1; flags = rgn->flags; #ifdef CONFIG_NUMA if (numa_valid_node(memblock_get_region_node(rgn))) snprintf(nid_buf, sizeof(nid_buf), " on node %d", memblock_get_region_node(rgn)); #endif pr_info(" %s[%#x]\t[%pa-%pa], %pa bytes%s flags: %#x\n", type->name, idx, &base, &end, &size, nid_buf, flags); } } static void __init_memblock __memblock_dump_all(void) { pr_info("MEMBLOCK configuration:\n"); pr_info(" memory size = %pa reserved size = %pa\n", &memblock.memory.total_size, &memblock.reserved.total_size); memblock_dump(&memblock.memory); memblock_dump(&memblock.reserved); #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP memblock_dump(&physmem); #endif } void __init_memblock memblock_dump_all(void) { if (memblock_debug) __memblock_dump_all(); } void __init memblock_allow_resize(void) { memblock_can_resize = 1; } static int __init early_memblock(char *p) { if (p && strstr(p, "debug")) memblock_debug = 1; return 0; } early_param("memblock", early_memblock); static void __init free_memmap(unsigned long start_pfn, unsigned long end_pfn) { struct page *start_pg, *end_pg; phys_addr_t pg, pgend; /* * Convert start_pfn/end_pfn to a struct page pointer. */ start_pg = pfn_to_page(start_pfn - 1) + 1; end_pg = pfn_to_page(end_pfn - 1) + 1; /* * Convert to physical addresses, and round start upwards and end * downwards. */ pg = PAGE_ALIGN(__pa(start_pg)); pgend = PAGE_ALIGN_DOWN(__pa(end_pg)); /* * If there are free pages between these, free the section of the * memmap array. */ if (pg < pgend) memblock_phys_free(pg, pgend - pg); } /* * The mem_map array can get very big. Free the unused area of the memory map. */ static void __init free_unused_memmap(void) { unsigned long start, end, prev_end = 0; int i; if (!IS_ENABLED(CONFIG_HAVE_ARCH_PFN_VALID) || IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP)) return; /* * This relies on each bank being in address order. * The banks are sorted previously in bootmem_init(). */ for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, NULL) { #ifdef CONFIG_SPARSEMEM /* * Take care not to free memmap entries that don't exist * due to SPARSEMEM sections which aren't present. */ start = min(start, ALIGN(prev_end, PAGES_PER_SECTION)); #endif /* * Align down here since many operations in VM subsystem * presume that there are no holes in the memory map inside * a pageblock */ start = pageblock_start_pfn(start); /* * If we had a previous bank, and there is a space * between the current bank and the previous, free it. */ if (prev_end && prev_end < start) free_memmap(prev_end, start); /* * Align up here since many operations in VM subsystem * presume that there are no holes in the memory map inside * a pageblock */ prev_end = pageblock_align(end); } #ifdef CONFIG_SPARSEMEM if (!IS_ALIGNED(prev_end, PAGES_PER_SECTION)) { prev_end = pageblock_align(end); free_memmap(prev_end, ALIGN(prev_end, PAGES_PER_SECTION)); } #endif } static void __init __free_pages_memory(unsigned long start, unsigned long end) { int order; while (start < end) { /* * Free the pages in the largest chunks alignment allows. * * __ffs() behaviour is undefined for 0. start == 0 is * MAX_PAGE_ORDER-aligned, set order to MAX_PAGE_ORDER for * the case. */ if (start) order = min_t(int, MAX_PAGE_ORDER, __ffs(start)); else order = MAX_PAGE_ORDER; while (start + (1UL << order) > end) order--; memblock_free_pages(pfn_to_page(start), start, order); start += (1UL << order); } } static unsigned long __init __free_memory_core(phys_addr_t start, phys_addr_t end) { unsigned long start_pfn = PFN_UP(start); unsigned long end_pfn = min_t(unsigned long, PFN_DOWN(end), max_low_pfn); if (start_pfn >= end_pfn) return 0; __free_pages_memory(start_pfn, end_pfn); return end_pfn - start_pfn; } static void __init memmap_init_reserved_pages(void) { struct memblock_region *region; phys_addr_t start, end; int nid; /* * set nid on all reserved pages and also treat struct * pages for the NOMAP regions as PageReserved */ for_each_mem_region(region) { nid = memblock_get_region_node(region); start = region->base; end = start + region->size; if (memblock_is_nomap(region)) reserve_bootmem_region(start, end, nid); memblock_set_node(start, end, &memblock.reserved, nid); } /* * initialize struct pages for reserved regions that don't have * the MEMBLOCK_RSRV_NOINIT flag set */ for_each_reserved_mem_region(region) { if (!memblock_is_reserved_noinit(region)) { nid = memblock_get_region_node(region); start = region->base; end = start + region->size; if (!numa_valid_node(nid)) nid = early_pfn_to_nid(PFN_DOWN(start)); reserve_bootmem_region(start, end, nid); } } } static unsigned long __init free_low_memory_core_early(void) { unsigned long count = 0; phys_addr_t start, end; u64 i; memblock_clear_hotplug(0, -1); memmap_init_reserved_pages(); /* * We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id * because in some case like Node0 doesn't have RAM installed * low ram will be on Node1 */ for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, NULL) count += __free_memory_core(start, end); return count; } static int reset_managed_pages_done __initdata; static void __init reset_node_managed_pages(pg_data_t *pgdat) { struct zone *z; for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++) atomic_long_set(&z->managed_pages, 0); } void __init reset_all_zones_managed_pages(void) { struct pglist_data *pgdat; if (reset_managed_pages_done) return; for_each_online_pgdat(pgdat) reset_node_managed_pages(pgdat); reset_managed_pages_done = 1; } /** * memblock_free_all - release free pages to the buddy allocator */ void __init memblock_free_all(void) { unsigned long pages; free_unused_memmap(); reset_all_zones_managed_pages(); pages = free_low_memory_core_early(); totalram_pages_add(pages); } /* Keep a table to reserve named memory */ #define RESERVE_MEM_MAX_ENTRIES 8 #define RESERVE_MEM_NAME_SIZE 16 struct reserve_mem_table { char name[RESERVE_MEM_NAME_SIZE]; phys_addr_t start; phys_addr_t size; }; static struct reserve_mem_table reserved_mem_table[RESERVE_MEM_MAX_ENTRIES]; static int reserved_mem_count; /* Add wildcard region with a lookup name */ static void __init reserved_mem_add(phys_addr_t start, phys_addr_t size, const char *name) { struct reserve_mem_table *map; map = &reserved_mem_table[reserved_mem_count++]; map->start = start; map->size = size; strscpy(map->name, name); } /** * reserve_mem_find_by_name - Find reserved memory region with a given name * @name: The name that is attached to a reserved memory region * @start: If found, holds the start address * @size: If found, holds the size of the address. * * @start and @size are only updated if @name is found. * * Returns: 1 if found or 0 if not found. */ int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *size) { struct reserve_mem_table *map; int i; for (i = 0; i < reserved_mem_count; i++) { map = &reserved_mem_table[i]; if (!map->size) continue; if (strcmp(name, map->name) == 0) { *start = map->start; *size = map->size; return 1; } } return 0; } EXPORT_SYMBOL_GPL(reserve_mem_find_by_name); /* * Parse reserve_mem=nn:align:name */ static int __init reserve_mem(char *p) { phys_addr_t start, size, align, tmp; char *name; char *oldp; int len; if (!p) return -EINVAL; /* Check if there's room for more reserved memory */ if (reserved_mem_count >= RESERVE_MEM_MAX_ENTRIES) return -EBUSY; oldp = p; size = memparse(p, &p); if (!size || p == oldp) return -EINVAL; if (*p != ':') return -EINVAL; align = memparse(p+1, &p); if (*p != ':') return -EINVAL; /* * memblock_phys_alloc() doesn't like a zero size align, * but it is OK for this command to have it. */ if (align < SMP_CACHE_BYTES) align = SMP_CACHE_BYTES; name = p + 1; len = strlen(name); /* name needs to have length but not too big */ if (!len || len >= RESERVE_MEM_NAME_SIZE) return -EINVAL; /* Make sure that name has text */ for (p = name; *p; p++) { if (!isspace(*p)) break; } if (!*p) return -EINVAL; /* Make sure the name is not already used */ if (reserve_mem_find_by_name(name, &start, &tmp)) return -EBUSY; start = memblock_phys_alloc(size, align); if (!start) return -ENOMEM; reserved_mem_add(start, size, name); return 1; } __setup("reserve_mem=", reserve_mem); #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_ARCH_KEEP_MEMBLOCK) static const char * const flagname[] = { [ilog2(MEMBLOCK_HOTPLUG)] = "HOTPLUG", [ilog2(MEMBLOCK_MIRROR)] = "MIRROR", [ilog2(MEMBLOCK_NOMAP)] = "NOMAP", [ilog2(MEMBLOCK_DRIVER_MANAGED)] = "DRV_MNG", [ilog2(MEMBLOCK_RSRV_NOINIT)] = "RSV_NIT", }; static int memblock_debug_show(struct seq_file *m, void *private) { struct memblock_type *type = m->private; struct memblock_region *reg; int i, j, nid; unsigned int count = ARRAY_SIZE(flagname); phys_addr_t end; for (i = 0; i < type->cnt; i++) { reg = &type->regions[i]; end = reg->base + reg->size - 1; nid = memblock_get_region_node(reg); seq_printf(m, "%4d: ", i); seq_printf(m, "%pa..%pa ", ®->base, &end); if (numa_valid_node(nid)) seq_printf(m, "%4d ", nid); else seq_printf(m, "%4c ", 'x'); if (reg->flags) { for (j = 0; j < count; j++) { if (reg->flags & (1U << j)) { seq_printf(m, "%s\n", flagname[j]); break; } } if (j == count) seq_printf(m, "%s\n", "UNKNOWN"); } else { seq_printf(m, "%s\n", "NONE"); } } return 0; } DEFINE_SHOW_ATTRIBUTE(memblock_debug); static int __init memblock_init_debugfs(void) { struct dentry *root = debugfs_create_dir("memblock", NULL); debugfs_create_file("memory", 0444, root, &memblock.memory, &memblock_debug_fops); debugfs_create_file("reserved", 0444, root, &memblock.reserved, &memblock_debug_fops); #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP debugfs_create_file("physmem", 0444, root, &physmem, &memblock_debug_fops); #endif return 0; } __initcall(memblock_init_debugfs); #endif /* CONFIG_DEBUG_FS */ |
| 328 196 256 256 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2022 Christian Brauner <brauner@kernel.org> */ #include <linux/cred.h> #include <linux/fs.h> #include <linux/mnt_idmapping.h> #include <linux/slab.h> #include <linux/user_namespace.h> #include "internal.h" /* * Outside of this file vfs{g,u}id_t are always created from k{g,u}id_t, * never from raw values. These are just internal helpers. */ #define VFSUIDT_INIT_RAW(val) (vfsuid_t){ val } #define VFSGIDT_INIT_RAW(val) (vfsgid_t){ val } struct mnt_idmap { struct uid_gid_map uid_map; struct uid_gid_map gid_map; refcount_t count; }; /* * Carries the initial idmapping of 0:0:4294967295 which is an identity * mapping. This means that {g,u}id 0 is mapped to {g,u}id 0, {g,u}id 1 is * mapped to {g,u}id 1, [...], {g,u}id 1000 to {g,u}id 1000, [...]. */ struct mnt_idmap nop_mnt_idmap = { .count = REFCOUNT_INIT(1), }; EXPORT_SYMBOL_GPL(nop_mnt_idmap); /* * Carries the invalid idmapping of a full 0-4294967295 {g,u}id range. * This means that all {g,u}ids are mapped to INVALID_VFS{G,U}ID. */ struct mnt_idmap invalid_mnt_idmap = { .count = REFCOUNT_INIT(1), }; EXPORT_SYMBOL_GPL(invalid_mnt_idmap); /** * initial_idmapping - check whether this is the initial mapping * @ns: idmapping to check * * Check whether this is the initial mapping, mapping 0 to 0, 1 to 1, * [...], 1000 to 1000 [...]. * * Return: true if this is the initial mapping, false if not. */ static inline bool initial_idmapping(const struct user_namespace *ns) { return ns == &init_user_ns; } /** * make_vfsuid - map a filesystem kuid according to an idmapping * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * @kuid : kuid to be mapped * * Take a @kuid and remap it from @fs_userns into @idmap. Use this * function when preparing a @kuid to be reported to userspace. * * If initial_idmapping() determines that this is not an idmapped mount * we can simply return @kuid unchanged. * If initial_idmapping() tells us that the filesystem is not mounted with an * idmapping we know the value of @kuid won't change when calling * from_kuid() so we can simply retrieve the value via __kuid_val() * directly. * * Return: @kuid mapped according to @idmap. * If @kuid has no mapping in either @idmap or @fs_userns INVALID_UID is * returned. */ vfsuid_t make_vfsuid(struct mnt_idmap *idmap, struct user_namespace *fs_userns, kuid_t kuid) { uid_t uid; if (idmap == &nop_mnt_idmap) return VFSUIDT_INIT(kuid); if (idmap == &invalid_mnt_idmap) return INVALID_VFSUID; if (initial_idmapping(fs_userns)) uid = __kuid_val(kuid); else uid = from_kuid(fs_userns, kuid); if (uid == (uid_t)-1) return INVALID_VFSUID; return VFSUIDT_INIT_RAW(map_id_down(&idmap->uid_map, uid)); } EXPORT_SYMBOL_GPL(make_vfsuid); /** * make_vfsgid - map a filesystem kgid according to an idmapping * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * @kgid : kgid to be mapped * * Take a @kgid and remap it from @fs_userns into @idmap. Use this * function when preparing a @kgid to be reported to userspace. * * If initial_idmapping() determines that this is not an idmapped mount * we can simply return @kgid unchanged. * If initial_idmapping() tells us that the filesystem is not mounted with an * idmapping we know the value of @kgid won't change when calling * from_kgid() so we can simply retrieve the value via __kgid_val() * directly. * * Return: @kgid mapped according to @idmap. * If @kgid has no mapping in either @idmap or @fs_userns INVALID_GID is * returned. */ vfsgid_t make_vfsgid(struct mnt_idmap *idmap, struct user_namespace *fs_userns, kgid_t kgid) { gid_t gid; if (idmap == &nop_mnt_idmap) return VFSGIDT_INIT(kgid); if (idmap == &invalid_mnt_idmap) return INVALID_VFSGID; if (initial_idmapping(fs_userns)) gid = __kgid_val(kgid); else gid = from_kgid(fs_userns, kgid); if (gid == (gid_t)-1) return INVALID_VFSGID; return VFSGIDT_INIT_RAW(map_id_down(&idmap->gid_map, gid)); } EXPORT_SYMBOL_GPL(make_vfsgid); /** * from_vfsuid - map a vfsuid into the filesystem idmapping * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * @vfsuid : vfsuid to be mapped * * Map @vfsuid into the filesystem idmapping. This function has to be used in * order to e.g. write @vfsuid to inode->i_uid. * * Return: @vfsuid mapped into the filesystem idmapping */ kuid_t from_vfsuid(struct mnt_idmap *idmap, struct user_namespace *fs_userns, vfsuid_t vfsuid) { uid_t uid; if (idmap == &nop_mnt_idmap) return AS_KUIDT(vfsuid); if (idmap == &invalid_mnt_idmap) return INVALID_UID; uid = map_id_up(&idmap->uid_map, __vfsuid_val(vfsuid)); if (uid == (uid_t)-1) return INVALID_UID; if (initial_idmapping(fs_userns)) return KUIDT_INIT(uid); return make_kuid(fs_userns, uid); } EXPORT_SYMBOL_GPL(from_vfsuid); /** * from_vfsgid - map a vfsgid into the filesystem idmapping * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * @vfsgid : vfsgid to be mapped * * Map @vfsgid into the filesystem idmapping. This function has to be used in * order to e.g. write @vfsgid to inode->i_gid. * * Return: @vfsgid mapped into the filesystem idmapping */ kgid_t from_vfsgid(struct mnt_idmap *idmap, struct user_namespace *fs_userns, vfsgid_t vfsgid) { gid_t gid; if (idmap == &nop_mnt_idmap) return AS_KGIDT(vfsgid); if (idmap == &invalid_mnt_idmap) return INVALID_GID; gid = map_id_up(&idmap->gid_map, __vfsgid_val(vfsgid)); if (gid == (gid_t)-1) return INVALID_GID; if (initial_idmapping(fs_userns)) return KGIDT_INIT(gid); return make_kgid(fs_userns, gid); } EXPORT_SYMBOL_GPL(from_vfsgid); #ifdef CONFIG_MULTIUSER /** * vfsgid_in_group_p() - check whether a vfsuid matches the caller's groups * @vfsgid: the mnt gid to match * * This function can be used to determine whether @vfsuid matches any of the * caller's groups. * * Return: 1 if vfsuid matches caller's groups, 0 if not. */ int vfsgid_in_group_p(vfsgid_t vfsgid) { return in_group_p(AS_KGIDT(vfsgid)); } #else int vfsgid_in_group_p(vfsgid_t vfsgid) { return 1; } #endif EXPORT_SYMBOL_GPL(vfsgid_in_group_p); static int copy_mnt_idmap(struct uid_gid_map *map_from, struct uid_gid_map *map_to) { struct uid_gid_extent *forward, *reverse; u32 nr_extents = READ_ONCE(map_from->nr_extents); /* Pairs with smp_wmb() when writing the idmapping. */ smp_rmb(); /* * Don't blindly copy @map_to into @map_from if nr_extents is * smaller or equal to UID_GID_MAP_MAX_BASE_EXTENTS. Since we * read @nr_extents someone could have written an idmapping and * then we might end up with inconsistent data. So just don't do * anything at all. */ if (nr_extents == 0) return -EINVAL; /* * Here we know that nr_extents is greater than zero which means * a map has been written. Since idmappings can't be changed * once they have been written we know that we can safely copy * from @map_to into @map_from. */ if (nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) { *map_to = *map_from; return 0; } forward = kmemdup_array(map_from->forward, nr_extents, sizeof(struct uid_gid_extent), GFP_KERNEL_ACCOUNT); if (!forward) return -ENOMEM; reverse = kmemdup_array(map_from->reverse, nr_extents, sizeof(struct uid_gid_extent), GFP_KERNEL_ACCOUNT); if (!reverse) { kfree(forward); return -ENOMEM; } /* * The idmapping isn't exposed anywhere so we don't need to care * about ordering between extent pointers and @nr_extents * initialization. */ map_to->forward = forward; map_to->reverse = reverse; map_to->nr_extents = nr_extents; return 0; } static void free_mnt_idmap(struct mnt_idmap *idmap) { if (idmap->uid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(idmap->uid_map.forward); kfree(idmap->uid_map.reverse); } if (idmap->gid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(idmap->gid_map.forward); kfree(idmap->gid_map.reverse); } kfree(idmap); } struct mnt_idmap *alloc_mnt_idmap(struct user_namespace *mnt_userns) { struct mnt_idmap *idmap; int ret; idmap = kzalloc(sizeof(struct mnt_idmap), GFP_KERNEL_ACCOUNT); if (!idmap) return ERR_PTR(-ENOMEM); refcount_set(&idmap->count, 1); ret = copy_mnt_idmap(&mnt_userns->uid_map, &idmap->uid_map); if (!ret) ret = copy_mnt_idmap(&mnt_userns->gid_map, &idmap->gid_map); if (ret) { free_mnt_idmap(idmap); idmap = ERR_PTR(ret); } return idmap; } /** * mnt_idmap_get - get a reference to an idmapping * @idmap: the idmap to bump the reference on * * If @idmap is not the @nop_mnt_idmap bump the reference count. * * Return: @idmap with reference count bumped if @not_mnt_idmap isn't passed. */ struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap) { if (idmap != &nop_mnt_idmap && idmap != &invalid_mnt_idmap) refcount_inc(&idmap->count); return idmap; } EXPORT_SYMBOL_GPL(mnt_idmap_get); /** * mnt_idmap_put - put a reference to an idmapping * @idmap: the idmap to put the reference on * * If this is a non-initial idmapping, put the reference count when a mount is * released and free it if we're the last user. */ void mnt_idmap_put(struct mnt_idmap *idmap) { if (idmap != &nop_mnt_idmap && idmap != &invalid_mnt_idmap && refcount_dec_and_test(&idmap->count)) free_mnt_idmap(idmap); } EXPORT_SYMBOL_GPL(mnt_idmap_put); |
| 677 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Security-Enhanced Linux (SELinux) security module * * This file contains the SELinux security data structures for kernel objects. * * Author(s): Stephen Smalley, <stephen.smalley.work@gmail.com> * Chris Vance, <cvance@nai.com> * Wayne Salamon, <wsalamon@nai.com> * James Morris <jmorris@redhat.com> * * Copyright (C) 2001,2002 Networks Associates Technology, Inc. * Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com> * Copyright (C) 2016 Mellanox Technologies */ #ifndef _SELINUX_OBJSEC_H_ #define _SELINUX_OBJSEC_H_ #include <linux/list.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/binfmts.h> #include <linux/in.h> #include <linux/spinlock.h> #include <linux/lsm_hooks.h> #include <linux/msg.h> #include <net/net_namespace.h> #include "flask.h" #include "avc.h" struct task_security_struct { u32 osid; /* SID prior to last execve */ u32 sid; /* current SID */ u32 exec_sid; /* exec SID */ u32 create_sid; /* fscreate SID */ u32 keycreate_sid; /* keycreate SID */ u32 sockcreate_sid; /* fscreate SID */ } __randomize_layout; enum label_initialized { LABEL_INVALID, /* invalid or not initialized */ LABEL_INITIALIZED, /* initialized */ LABEL_PENDING }; struct inode_security_struct { struct inode *inode; /* back pointer to inode object */ struct list_head list; /* list of inode_security_struct */ u32 task_sid; /* SID of creating task */ u32 sid; /* SID of this object */ u16 sclass; /* security class of this object */ unsigned char initialized; /* initialization flag */ spinlock_t lock; }; struct file_security_struct { u32 sid; /* SID of open file description */ u32 fown_sid; /* SID of file owner (for SIGIO) */ u32 isid; /* SID of inode at the time of file open */ u32 pseqno; /* Policy seqno at the time of file open */ }; struct superblock_security_struct { u32 sid; /* SID of file system superblock */ u32 def_sid; /* default SID for labeling */ u32 mntpoint_sid; /* SECURITY_FS_USE_MNTPOINT context for files */ unsigned short behavior; /* labeling behavior */ unsigned short flags; /* which mount options were specified */ struct mutex lock; struct list_head isec_head; spinlock_t isec_lock; }; struct msg_security_struct { u32 sid; /* SID of message */ }; struct ipc_security_struct { u16 sclass; /* security class of this object */ u32 sid; /* SID of IPC resource */ }; struct netif_security_struct { struct net *ns; /* network namespace */ int ifindex; /* device index */ u32 sid; /* SID for this interface */ }; struct netnode_security_struct { union { __be32 ipv4; /* IPv4 node address */ struct in6_addr ipv6; /* IPv6 node address */ } addr; u32 sid; /* SID for this node */ u16 family; /* address family */ }; struct netport_security_struct { u32 sid; /* SID for this node */ u16 port; /* port number */ u8 protocol; /* transport protocol */ }; struct sk_security_struct { #ifdef CONFIG_NETLABEL enum { /* NetLabel state */ NLBL_UNSET = 0, NLBL_REQUIRE, NLBL_LABELED, NLBL_REQSKB, NLBL_CONNLABELED, } nlbl_state; struct netlbl_lsm_secattr *nlbl_secattr; /* NetLabel sec attributes */ #endif u32 sid; /* SID of this object */ u32 peer_sid; /* SID of peer */ u16 sclass; /* sock security class */ enum { /* SCTP association state */ SCTP_ASSOC_UNSET = 0, SCTP_ASSOC_SET, } sctp_assoc_state; }; struct tun_security_struct { u32 sid; /* SID for the tun device sockets */ }; struct key_security_struct { u32 sid; /* SID of key */ }; struct ib_security_struct { u32 sid; /* SID of the queue pair or MAD agent */ }; struct pkey_security_struct { u64 subnet_prefix; /* Port subnet prefix */ u16 pkey; /* PKey number */ u32 sid; /* SID of pkey */ }; struct bpf_security_struct { u32 sid; /* SID of bpf obj creator */ }; struct perf_event_security_struct { u32 sid; /* SID of perf_event obj creator */ }; extern struct lsm_blob_sizes selinux_blob_sizes; static inline struct task_security_struct *selinux_cred(const struct cred *cred) { return cred->security + selinux_blob_sizes.lbs_cred; } static inline struct file_security_struct *selinux_file(const struct file *file) { return file->f_security + selinux_blob_sizes.lbs_file; } static inline struct inode_security_struct * selinux_inode(const struct inode *inode) { if (unlikely(!inode->i_security)) return NULL; return inode->i_security + selinux_blob_sizes.lbs_inode; } static inline struct msg_security_struct * selinux_msg_msg(const struct msg_msg *msg_msg) { return msg_msg->security + selinux_blob_sizes.lbs_msg_msg; } static inline struct ipc_security_struct * selinux_ipc(const struct kern_ipc_perm *ipc) { return ipc->security + selinux_blob_sizes.lbs_ipc; } /* * get the subjective security ID of the current task */ static inline u32 current_sid(void) { const struct task_security_struct *tsec = selinux_cred(current_cred()); return tsec->sid; } static inline struct superblock_security_struct * selinux_superblock(const struct super_block *superblock) { return superblock->s_security + selinux_blob_sizes.lbs_superblock; } #ifdef CONFIG_KEYS static inline struct key_security_struct *selinux_key(const struct key *key) { return key->security + selinux_blob_sizes.lbs_key; } #endif /* CONFIG_KEYS */ static inline struct sk_security_struct *selinux_sock(const struct sock *sock) { return sock->sk_security + selinux_blob_sizes.lbs_sock; } static inline struct tun_security_struct *selinux_tun_dev(void *security) { return security + selinux_blob_sizes.lbs_tun_dev; } static inline struct ib_security_struct *selinux_ib(void *ib_sec) { return ib_sec + selinux_blob_sizes.lbs_ib; } static inline struct perf_event_security_struct * selinux_perf_event(void *perf_event) { return perf_event + selinux_blob_sizes.lbs_perf_event; } #endif /* _SELINUX_OBJSEC_H_ */ |
| 48 13 48 36 35 35 38 5 5 29 29 13 13 13 13 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/export.h> #include <linux/bvec.h> #include <linux/fault-inject-usercopy.h> #include <linux/uio.h> #include <linux/pagemap.h> #include <linux/highmem.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/splice.h> #include <linux/compat.h> #include <linux/scatterlist.h> #include <linux/instrumented.h> #include <linux/iov_iter.h> static __always_inline size_t copy_to_user_iter(void __user *iter_to, size_t progress, size_t len, void *from, void *priv2) { if (should_fail_usercopy()) return len; if (access_ok(iter_to, len)) { from += progress; instrument_copy_to_user(iter_to, from, len); len = raw_copy_to_user(iter_to, from, len); } return len; } static __always_inline size_t copy_to_user_iter_nofault(void __user *iter_to, size_t progress, size_t len, void *from, void *priv2) { ssize_t res; if (should_fail_usercopy()) return len; from += progress; res = copy_to_user_nofault(iter_to, from, len); return res < 0 ? len : res; } static __always_inline size_t copy_from_user_iter(void __user *iter_from, size_t progress, size_t len, void *to, void *priv2) { size_t res = len; if (should_fail_usercopy()) return len; if (access_ok(iter_from, len)) { to += progress; instrument_copy_from_user_before(to, iter_from, len); res = raw_copy_from_user(to, iter_from, len); instrument_copy_from_user_after(to, iter_from, len, res); } return res; } static __always_inline size_t memcpy_to_iter(void *iter_to, size_t progress, size_t len, void *from, void *priv2) { memcpy(iter_to, from + progress, len); return 0; } static __always_inline size_t memcpy_from_iter(void *iter_from, size_t progress, size_t len, void *to, void *priv2) { memcpy(to + progress, iter_from, len); return 0; } /* * fault_in_iov_iter_readable - fault in iov iterator for reading * @i: iterator * @size: maximum length * * Fault in one or more iovecs of the given iov_iter, to a maximum length of * @size. For each iovec, fault in each page that constitutes the iovec. * * Returns the number of bytes not faulted in (like copy_to_user() and * copy_from_user()). * * Always returns 0 for non-userspace iterators. */ size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t size) { if (iter_is_ubuf(i)) { size_t n = min(size, iov_iter_count(i)); n -= fault_in_readable(i->ubuf + i->iov_offset, n); return size - n; } else if (iter_is_iovec(i)) { size_t count = min(size, iov_iter_count(i)); const struct iovec *p; size_t skip; size -= count; for (p = iter_iov(i), skip = i->iov_offset; count; p++, skip = 0) { size_t len = min(count, p->iov_len - skip); size_t ret; if (unlikely(!len)) continue; ret = fault_in_readable(p->iov_base + skip, len); count -= len - ret; if (ret) break; } return count + size; } return 0; } EXPORT_SYMBOL(fault_in_iov_iter_readable); /* * fault_in_iov_iter_writeable - fault in iov iterator for writing * @i: iterator * @size: maximum length * * Faults in the iterator using get_user_pages(), i.e., without triggering * hardware page faults. This is primarily useful when we already know that * some or all of the pages in @i aren't in memory. * * Returns the number of bytes not faulted in, like copy_to_user() and * copy_from_user(). * * Always returns 0 for non-user-space iterators. */ size_t fault_in_iov_iter_writeable(const struct iov_iter *i, size_t size) { if (iter_is_ubuf(i)) { size_t n = min(size, iov_iter_count(i)); n -= fault_in_safe_writeable(i->ubuf + i->iov_offset, n); return size - n; } else if (iter_is_iovec(i)) { size_t count = min(size, iov_iter_count(i)); const struct iovec *p; size_t skip; size -= count; for (p = iter_iov(i), skip = i->iov_offset; count; p++, skip = 0) { size_t len = min(count, p->iov_len - skip); size_t ret; if (unlikely(!len)) continue; ret = fault_in_safe_writeable(p->iov_base + skip, len); count -= len - ret; if (ret) break; } return count + size; } return 0; } EXPORT_SYMBOL(fault_in_iov_iter_writeable); void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov, unsigned long nr_segs, size_t count) { WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter) { .iter_type = ITER_IOVEC, .nofault = false, .data_source = direction, .__iov = iov, .nr_segs = nr_segs, .iov_offset = 0, .count = count }; } EXPORT_SYMBOL(iov_iter_init); size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { if (WARN_ON_ONCE(i->data_source)) return 0; if (user_backed_iter(i)) might_fault(); return iterate_and_advance(i, bytes, (void *)addr, copy_to_user_iter, memcpy_to_iter); } EXPORT_SYMBOL(_copy_to_iter); #ifdef CONFIG_ARCH_HAS_COPY_MC static __always_inline size_t copy_to_user_iter_mc(void __user *iter_to, size_t progress, size_t len, void *from, void *priv2) { if (access_ok(iter_to, len)) { from += progress; instrument_copy_to_user(iter_to, from, len); len = copy_mc_to_user(iter_to, from, len); } return len; } static __always_inline size_t memcpy_to_iter_mc(void *iter_to, size_t progress, size_t len, void *from, void *priv2) { return copy_mc_to_kernel(iter_to, from + progress, len); } /** * _copy_mc_to_iter - copy to iter with source memory error exception handling * @addr: source kernel address * @bytes: total transfer length * @i: destination iterator * * The pmem driver deploys this for the dax operation * (dax_copy_to_iter()) for dax reads (bypass page-cache and the * block-layer). Upon #MC read(2) aborts and returns EIO or the bytes * successfully copied. * * The main differences between this and typical _copy_to_iter(). * * * Typical tail/residue handling after a fault retries the copy * byte-by-byte until the fault happens again. Re-triggering machine * checks is potentially fatal so the implementation uses source * alignment and poison alignment assumptions to avoid re-triggering * hardware exceptions. * * * ITER_KVEC and ITER_BVEC can return short copies. Compare to * copy_to_iter() where only ITER_IOVEC attempts might return a short copy. * * Return: number of bytes copied (may be %0) */ size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { if (WARN_ON_ONCE(i->data_source)) return 0; if (user_backed_iter(i)) might_fault(); return iterate_and_advance(i, bytes, (void *)addr, copy_to_user_iter_mc, memcpy_to_iter_mc); } EXPORT_SYMBOL_GPL(_copy_mc_to_iter); #endif /* CONFIG_ARCH_HAS_COPY_MC */ static __always_inline size_t __copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { return iterate_and_advance(i, bytes, addr, copy_from_user_iter, memcpy_from_iter); } size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { if (WARN_ON_ONCE(!i->data_source)) return 0; if (user_backed_iter(i)) might_fault(); return __copy_from_iter(addr, bytes, i); } EXPORT_SYMBOL(_copy_from_iter); static __always_inline size_t copy_from_user_iter_nocache(void __user *iter_from, size_t progress, size_t len, void *to, void *priv2) { return __copy_from_user_inatomic_nocache(to + progress, iter_from, len); } size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) { if (WARN_ON_ONCE(!i->data_source)) return 0; return iterate_and_advance(i, bytes, addr, copy_from_user_iter_nocache, memcpy_from_iter); } EXPORT_SYMBOL(_copy_from_iter_nocache); #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE static __always_inline size_t copy_from_user_iter_flushcache(void __user *iter_from, size_t progress, size_t len, void *to, void *priv2) { return __copy_from_user_flushcache(to + progress, iter_from, len); } static __always_inline size_t memcpy_from_iter_flushcache(void *iter_from, size_t progress, size_t len, void *to, void *priv2) { memcpy_flushcache(to + progress, iter_from, len); return 0; } /** * _copy_from_iter_flushcache - write destination through cpu cache * @addr: destination kernel address * @bytes: total transfer length * @i: source iterator * * The pmem driver arranges for filesystem-dax to use this facility via * dax_copy_from_iter() for ensuring that writes to persistent memory * are flushed through the CPU cache. It is differentiated from * _copy_from_iter_nocache() in that guarantees all data is flushed for * all iterator types. The _copy_from_iter_nocache() only attempts to * bypass the cache for the ITER_IOVEC case, and on some archs may use * instructions that strand dirty-data in the cache. * * Return: number of bytes copied (may be %0) */ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) { if (WARN_ON_ONCE(!i->data_source)) return 0; return iterate_and_advance(i, bytes, addr, copy_from_user_iter_flushcache, memcpy_from_iter_flushcache); } EXPORT_SYMBOL_GPL(_copy_from_iter_flushcache); #endif static inline bool page_copy_sane(struct page *page, size_t offset, size_t n) { struct page *head; size_t v = n + offset; /* * The general case needs to access the page order in order * to compute the page size. * However, we mostly deal with order-0 pages and thus can * avoid a possible cache line miss for requests that fit all * page orders. */ if (n <= v && v <= PAGE_SIZE) return true; head = compound_head(page); v += (page - head) << PAGE_SHIFT; if (WARN_ON(n > v || v > page_size(head))) return false; return true; } size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { size_t res = 0; if (!page_copy_sane(page, offset, bytes)) return 0; if (WARN_ON_ONCE(i->data_source)) return 0; page += offset / PAGE_SIZE; // first subpage offset %= PAGE_SIZE; while (1) { void *kaddr = kmap_local_page(page); size_t n = min(bytes, (size_t)PAGE_SIZE - offset); n = _copy_to_iter(kaddr + offset, n, i); kunmap_local(kaddr); res += n; bytes -= n; if (!bytes || !n) break; offset += n; if (offset == PAGE_SIZE) { page++; offset = 0; } } return res; } EXPORT_SYMBOL(copy_page_to_iter); size_t copy_page_to_iter_nofault(struct page *page, unsigned offset, size_t bytes, struct iov_iter *i) { size_t res = 0; if (!page_copy_sane(page, offset, bytes)) return 0; if (WARN_ON_ONCE(i->data_source)) return 0; page += offset / PAGE_SIZE; // first subpage offset %= PAGE_SIZE; while (1) { void *kaddr = kmap_local_page(page); size_t n = min(bytes, (size_t)PAGE_SIZE - offset); n = iterate_and_advance(i, n, kaddr + offset, copy_to_user_iter_nofault, memcpy_to_iter); kunmap_local(kaddr); res += n; bytes -= n; if (!bytes || !n) break; offset += n; if (offset == PAGE_SIZE) { page++; offset = 0; } } return res; } EXPORT_SYMBOL(copy_page_to_iter_nofault); size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { size_t res = 0; if (!page_copy_sane(page, offset, bytes)) return 0; page += offset / PAGE_SIZE; // first subpage offset %= PAGE_SIZE; while (1) { void *kaddr = kmap_local_page(page); size_t n = min(bytes, (size_t)PAGE_SIZE - offset); n = _copy_from_iter(kaddr + offset, n, i); kunmap_local(kaddr); res += n; bytes -= n; if (!bytes || !n) break; offset += n; if (offset == PAGE_SIZE) { page++; offset = 0; } } return res; } EXPORT_SYMBOL(copy_page_from_iter); static __always_inline size_t zero_to_user_iter(void __user *iter_to, size_t progress, size_t len, void *priv, void *priv2) { return clear_user(iter_to, len); } static __always_inline size_t zero_to_iter(void *iter_to, size_t progress, size_t len, void *priv, void *priv2) { memset(iter_to, 0, len); return 0; } size_t iov_iter_zero(size_t bytes, struct iov_iter *i) { return iterate_and_advance(i, bytes, NULL, zero_to_user_iter, zero_to_iter); } EXPORT_SYMBOL(iov_iter_zero); size_t copy_page_from_iter_atomic(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { size_t n, copied = 0; bool uses_kmap = IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP) || PageHighMem(page); if (!page_copy_sane(page, offset, bytes)) return 0; if (WARN_ON_ONCE(!i->data_source)) return 0; do { char *p; n = bytes - copied; if (uses_kmap) { page += offset / PAGE_SIZE; offset %= PAGE_SIZE; n = min_t(size_t, n, PAGE_SIZE - offset); } p = kmap_atomic(page) + offset; n = __copy_from_iter(p, n, i); kunmap_atomic(p); copied += n; offset += n; } while (uses_kmap && copied != bytes && n > 0); return copied; } EXPORT_SYMBOL(copy_page_from_iter_atomic); static void iov_iter_bvec_advance(struct iov_iter *i, size_t size) { const struct bio_vec *bvec, *end; if (!i->count) return; i->count -= size; size += i->iov_offset; for (bvec = i->bvec, end = bvec + i->nr_segs; bvec < end; bvec++) { if (likely(size < bvec->bv_len)) break; size -= bvec->bv_len; } i->iov_offset = size; i->nr_segs -= bvec - i->bvec; i->bvec = bvec; } static void iov_iter_iovec_advance(struct iov_iter *i, size_t size) { const struct iovec *iov, *end; if (!i->count) return; i->count -= size; size += i->iov_offset; // from beginning of current segment for (iov = iter_iov(i), end = iov + i->nr_segs; iov < end; iov++) { if (likely(size < iov->iov_len)) break; size -= iov->iov_len; } i->iov_offset = size; i->nr_segs -= iov - iter_iov(i); i->__iov = iov; } static void iov_iter_folioq_advance(struct iov_iter *i, size_t size) { const struct folio_queue *folioq = i->folioq; unsigned int slot = i->folioq_slot; if (!i->count) return; i->count -= size; if (slot >= folioq_nr_slots(folioq)) { folioq = folioq->next; slot = 0; } size += i->iov_offset; /* From beginning of current segment. */ do { size_t fsize = folioq_folio_size(folioq, slot); if (likely(size < fsize)) break; size -= fsize; slot++; if (slot >= folioq_nr_slots(folioq) && folioq->next) { folioq = folioq->next; slot = 0; } } while (size); i->iov_offset = size; i->folioq_slot = slot; i->folioq = folioq; } void iov_iter_advance(struct iov_iter *i, size_t size) { if (unlikely(i->count < size)) size = i->count; if (likely(iter_is_ubuf(i)) || unlikely(iov_iter_is_xarray(i))) { i->iov_offset += size; i->count -= size; } else if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i))) { /* iovec and kvec have identical layouts */ iov_iter_iovec_advance(i, size); } else if (iov_iter_is_bvec(i)) { iov_iter_bvec_advance(i, size); } else if (iov_iter_is_folioq(i)) { iov_iter_folioq_advance(i, size); } else if (iov_iter_is_discard(i)) { i->count -= size; } } EXPORT_SYMBOL(iov_iter_advance); static void iov_iter_folioq_revert(struct iov_iter *i, size_t unroll) { const struct folio_queue *folioq = i->folioq; unsigned int slot = i->folioq_slot; for (;;) { size_t fsize; if (slot == 0) { folioq = folioq->prev; slot = folioq_nr_slots(folioq); } slot--; fsize = folioq_folio_size(folioq, slot); if (unroll <= fsize) { i->iov_offset = fsize - unroll; break; } unroll -= fsize; } i->folioq_slot = slot; i->folioq = folioq; } void iov_iter_revert(struct iov_iter *i, size_t unroll) { if (!unroll) return; if (WARN_ON(unroll > MAX_RW_COUNT)) return; i->count += unroll; if (unlikely(iov_iter_is_discard(i))) return; if (unroll <= i->iov_offset) { i->iov_offset -= unroll; return; } unroll -= i->iov_offset; if (iov_iter_is_xarray(i) || iter_is_ubuf(i)) { BUG(); /* We should never go beyond the start of the specified * range since we might then be straying into pages that * aren't pinned. */ } else if (iov_iter_is_bvec(i)) { const struct bio_vec *bvec = i->bvec; while (1) { size_t n = (--bvec)->bv_len; i->nr_segs++; if (unroll <= n) { i->bvec = bvec; i->iov_offset = n - unroll; return; } unroll -= n; } } else if (iov_iter_is_folioq(i)) { i->iov_offset = 0; iov_iter_folioq_revert(i, unroll); } else { /* same logics for iovec and kvec */ const struct iovec *iov = iter_iov(i); while (1) { size_t n = (--iov)->iov_len; i->nr_segs++; if (unroll <= n) { i->__iov = iov; i->iov_offset = n - unroll; return; } unroll -= n; } } } EXPORT_SYMBOL(iov_iter_revert); /* * Return the count of just the current iov_iter segment. */ size_t iov_iter_single_seg_count(const struct iov_iter *i) { if (i->nr_segs > 1) { if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i))) return min(i->count, iter_iov(i)->iov_len - i->iov_offset); if (iov_iter_is_bvec(i)) return min(i->count, i->bvec->bv_len - i->iov_offset); } if (unlikely(iov_iter_is_folioq(i))) return !i->count ? 0 : umin(folioq_folio_size(i->folioq, i->folioq_slot), i->count); return i->count; } EXPORT_SYMBOL(iov_iter_single_seg_count); void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec *kvec, unsigned long nr_segs, size_t count) { WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter){ .iter_type = ITER_KVEC, .data_source = direction, .kvec = kvec, .nr_segs = nr_segs, .iov_offset = 0, .count = count }; } EXPORT_SYMBOL(iov_iter_kvec); void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count) { WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter){ .iter_type = ITER_BVEC, .data_source = direction, .bvec = bvec, .nr_segs = nr_segs, .iov_offset = 0, .count = count }; } EXPORT_SYMBOL(iov_iter_bvec); /** * iov_iter_folio_queue - Initialise an I/O iterator to use the folios in a folio queue * @i: The iterator to initialise. * @direction: The direction of the transfer. * @folioq: The starting point in the folio queue. * @first_slot: The first slot in the folio queue to use * @offset: The offset into the folio in the first slot to start at * @count: The size of the I/O buffer in bytes. * * Set up an I/O iterator to either draw data out of the pages attached to an * inode or to inject data into those pages. The pages *must* be prevented * from evaporation, either by taking a ref on them or locking them by the * caller. */ void iov_iter_folio_queue(struct iov_iter *i, unsigned int direction, const struct folio_queue *folioq, unsigned int first_slot, unsigned int offset, size_t count) { BUG_ON(direction & ~1); *i = (struct iov_iter) { .iter_type = ITER_FOLIOQ, .data_source = direction, .folioq = folioq, .folioq_slot = first_slot, .count = count, .iov_offset = offset, }; } EXPORT_SYMBOL(iov_iter_folio_queue); /** * iov_iter_xarray - Initialise an I/O iterator to use the pages in an xarray * @i: The iterator to initialise. * @direction: The direction of the transfer. * @xarray: The xarray to access. * @start: The start file position. * @count: The size of the I/O buffer in bytes. * * Set up an I/O iterator to either draw data out of the pages attached to an * inode or to inject data into those pages. The pages *must* be prevented * from evaporation, either by taking a ref on them or locking them by the * caller. */ void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *xarray, loff_t start, size_t count) { BUG_ON(direction & ~1); *i = (struct iov_iter) { .iter_type = ITER_XARRAY, .data_source = direction, .xarray = xarray, .xarray_start = start, .count = count, .iov_offset = 0 }; } EXPORT_SYMBOL(iov_iter_xarray); /** * iov_iter_discard - Initialise an I/O iterator that discards data * @i: The iterator to initialise. * @direction: The direction of the transfer. * @count: The size of the I/O buffer in bytes. * * Set up an I/O iterator that just discards everything that's written to it. * It's only available as a READ iterator. */ void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count) { BUG_ON(direction != READ); *i = (struct iov_iter){ .iter_type = ITER_DISCARD, .data_source = false, .count = count, .iov_offset = 0 }; } EXPORT_SYMBOL(iov_iter_discard); static bool iov_iter_aligned_iovec(const struct iov_iter *i, unsigned addr_mask, unsigned len_mask) { const struct iovec *iov = iter_iov(i); size_t size = i->count; size_t skip = i->iov_offset; do { size_t len = iov->iov_len - skip; if (len > size) len = size; if (len & len_mask) return false; if ((unsigned long)(iov->iov_base + skip) & addr_mask) return false; iov++; size -= len; skip = 0; } while (size); return true; } static bool iov_iter_aligned_bvec(const struct iov_iter *i, unsigned addr_mask, unsigned len_mask) { const struct bio_vec *bvec = i->bvec; unsigned skip = i->iov_offset; size_t size = i->count; do { size_t len = bvec->bv_len; if (len > size) len = size; if (len & len_mask) return false; if ((unsigned long)(bvec->bv_offset + skip) & addr_mask) return false; bvec++; size -= len; skip = 0; } while (size); return true; } /** * iov_iter_is_aligned() - Check if the addresses and lengths of each segments * are aligned to the parameters. * * @i: &struct iov_iter to restore * @addr_mask: bit mask to check against the iov element's addresses * @len_mask: bit mask to check against the iov element's lengths * * Return: false if any addresses or lengths intersect with the provided masks */ bool iov_iter_is_aligned(const struct iov_iter *i, unsigned addr_mask, unsigned len_mask) { if (likely(iter_is_ubuf(i))) { if (i->count & len_mask) return false; if ((unsigned long)(i->ubuf + i->iov_offset) & addr_mask) return false; return true; } if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i))) return iov_iter_aligned_iovec(i, addr_mask, len_mask); if (iov_iter_is_bvec(i)) return iov_iter_aligned_bvec(i, addr_mask, len_mask); /* With both xarray and folioq types, we're dealing with whole folios. */ if (iov_iter_is_xarray(i)) { if (i->count & len_mask) return false; if ((i->xarray_start + i->iov_offset) & addr_mask) return false; } if (iov_iter_is_folioq(i)) { if (i->count & len_mask) return false; if (i->iov_offset & addr_mask) return false; } return true; } EXPORT_SYMBOL_GPL(iov_iter_is_aligned); static unsigned long iov_iter_alignment_iovec(const struct iov_iter *i) { const struct iovec *iov = iter_iov(i); unsigned long res = 0; size_t size = i->count; size_t skip = i->iov_offset; do { size_t len = iov->iov_len - skip; if (len) { res |= (unsigned long)iov->iov_base + skip; if (len > size) len = size; res |= len; size -= len; } iov++; skip = 0; } while (size); return res; } static unsigned long iov_iter_alignment_bvec(const struct iov_iter *i) { const struct bio_vec *bvec = i->bvec; unsigned res = 0; size_t size = i->count; unsigned skip = i->iov_offset; do { size_t len = bvec->bv_len - skip; res |= (unsigned long)bvec->bv_offset + skip; if (len > size) len = size; res |= len; bvec++; size -= len; skip = 0; } while (size); return res; } unsigned long iov_iter_alignment(const struct iov_iter *i) { if (likely(iter_is_ubuf(i))) { size_t size = i->count; if (size) return ((unsigned long)i->ubuf + i->iov_offset) | size; return 0; } /* iovec and kvec have identical layouts */ if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i))) return iov_iter_alignment_iovec(i); if (iov_iter_is_bvec(i)) return iov_iter_alignment_bvec(i); /* With both xarray and folioq types, we're dealing with whole folios. */ if (iov_iter_is_folioq(i)) return i->iov_offset | i->count; if (iov_iter_is_xarray(i)) return (i->xarray_start + i->iov_offset) | i->count; return 0; } EXPORT_SYMBOL(iov_iter_alignment); unsigned long iov_iter_gap_alignment(const struct iov_iter *i) { unsigned long res = 0; unsigned long v = 0; size_t size = i->count; unsigned k; if (iter_is_ubuf(i)) return 0; if (WARN_ON(!iter_is_iovec(i))) return ~0U; for (k = 0; k < i->nr_segs; k++) { const struct iovec *iov = iter_iov(i) + k; if (iov->iov_len) { unsigned long base = (unsigned long)iov->iov_base; if (v) // if not the first one res |= base | v; // this start | previous end v = base + iov->iov_len; if (size <= iov->iov_len) break; size -= iov->iov_len; } } return res; } EXPORT_SYMBOL(iov_iter_gap_alignment); static int want_pages_array(struct page ***res, size_t size, size_t start, unsigned int maxpages) { unsigned int count = DIV_ROUND_UP(size + start, PAGE_SIZE); if (count > maxpages) count = maxpages; WARN_ON(!count); // caller should've prevented that if (!*res) { *res = kvmalloc_array(count, sizeof(struct page *), GFP_KERNEL); if (!*res) return 0; } return count; } static ssize_t iter_folioq_get_pages(struct iov_iter *iter, struct page ***ppages, size_t maxsize, unsigned maxpages, size_t *_start_offset) { const struct folio_queue *folioq = iter->folioq; struct page **pages; unsigned int slot = iter->folioq_slot; size_t extracted = 0, count = iter->count, iov_offset = iter->iov_offset; if (slot >= folioq_nr_slots(folioq)) { folioq = folioq->next; slot = 0; if (WARN_ON(iov_offset != 0)) return -EIO; } maxpages = want_pages_array(ppages, maxsize, iov_offset & ~PAGE_MASK, maxpages); if (!maxpages) return -ENOMEM; *_start_offset = iov_offset & ~PAGE_MASK; pages = *ppages; for (;;) { struct folio *folio = folioq_folio(folioq, slot); size_t offset = iov_offset, fsize = folioq_folio_size(folioq, slot); size_t part = PAGE_SIZE - offset % PAGE_SIZE; if (offset < fsize) { part = umin(part, umin(maxsize - extracted, fsize - offset)); count -= part; iov_offset += part; extracted += part; *pages = folio_page(folio, offset / PAGE_SIZE); get_page(*pages); pages++; maxpages--; } if (maxpages == 0 || extracted >= maxsize) break; if (iov_offset >= fsize) { iov_offset = 0; slot++; if (slot == folioq_nr_slots(folioq) && folioq->next) { folioq = folioq->next; slot = 0; } } } iter->count = count; iter->iov_offset = iov_offset; iter->folioq = folioq; iter->folioq_slot = slot; return extracted; } static ssize_t iter_xarray_populate_pages(struct page **pages, struct xarray *xa, pgoff_t index, unsigned int nr_pages) { XA_STATE(xas, xa, index); struct page *page; unsigned int ret = 0; rcu_read_lock(); for (page = xas_load(&xas); page; page = xas_next(&xas)) { if (xas_retry(&xas, page)) continue; /* Has the page moved or been split? */ if (unlikely(page != xas_reload(&xas))) { xas_reset(&xas); continue; } pages[ret] = find_subpage(page, xas.xa_index); get_page(pages[ret]); if (++ret == nr_pages) break; } rcu_read_unlock(); return ret; } static ssize_t iter_xarray_get_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned maxpages, size_t *_start_offset) { unsigned nr, offset, count; pgoff_t index; loff_t pos; pos = i->xarray_start + i->iov_offset; index = pos >> PAGE_SHIFT; offset = pos & ~PAGE_MASK; *_start_offset = offset; count = want_pages_array(pages, maxsize, offset, maxpages); if (!count) return -ENOMEM; nr = iter_xarray_populate_pages(*pages, i->xarray, index, count); if (nr == 0) return 0; maxsize = min_t(size_t, nr * PAGE_SIZE - offset, maxsize); i->iov_offset += maxsize; i->count -= maxsize; return maxsize; } /* must be done on non-empty ITER_UBUF or ITER_IOVEC one */ static unsigned long first_iovec_segment(const struct iov_iter *i, size_t *size) { size_t skip; long k; if (iter_is_ubuf(i)) return (unsigned long)i->ubuf + i->iov_offset; for (k = 0, skip = i->iov_offset; k < i->nr_segs; k++, skip = 0) { const struct iovec *iov = iter_iov(i) + k; size_t len = iov->iov_len - skip; if (unlikely(!len)) continue; if (*size > len) *size = len; return (unsigned long)iov->iov_base + skip; } BUG(); // if it had been empty, we wouldn't get called } /* must be done on non-empty ITER_BVEC one */ static struct page *first_bvec_segment(const struct iov_iter *i, size_t *size, size_t *start) { struct page *page; size_t skip = i->iov_offset, len; len = i->bvec->bv_len - skip; if (*size > len) *size = len; skip += i->bvec->bv_offset; page = i->bvec->bv_page + skip / PAGE_SIZE; *start = skip % PAGE_SIZE; return page; } static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, size_t *start) { unsigned int n, gup_flags = 0; if (maxsize > i->count) maxsize = i->count; if (!maxsize) return 0; if (maxsize > MAX_RW_COUNT) maxsize = MAX_RW_COUNT; if (likely(user_backed_iter(i))) { unsigned long addr; int res; if (iov_iter_rw(i) != WRITE) gup_flags |= FOLL_WRITE; if (i->nofault) gup_flags |= FOLL_NOFAULT; addr = first_iovec_segment(i, &maxsize); *start = addr % PAGE_SIZE; addr &= PAGE_MASK; n = want_pages_array(pages, maxsize, *start, maxpages); if (!n) return -ENOMEM; res = get_user_pages_fast(addr, n, gup_flags, *pages); if (unlikely(res <= 0)) return res; maxsize = min_t(size_t, maxsize, res * PAGE_SIZE - *start); iov_iter_advance(i, maxsize); return maxsize; } if (iov_iter_is_bvec(i)) { struct page **p; struct page *page; page = first_bvec_segment(i, &maxsize, start); n = want_pages_array(pages, maxsize, *start, maxpages); if (!n) return -ENOMEM; p = *pages; for (int k = 0; k < n; k++) get_page(p[k] = page + k); maxsize = min_t(size_t, maxsize, n * PAGE_SIZE - *start); i->count -= maxsize; i->iov_offset += maxsize; if (i->iov_offset == i->bvec->bv_len) { i->iov_offset = 0; i->bvec++; i->nr_segs--; } return maxsize; } if (iov_iter_is_folioq(i)) return iter_folioq_get_pages(i, pages, maxsize, maxpages, start); if (iov_iter_is_xarray(i)) return iter_xarray_get_pages(i, pages, maxsize, maxpages, start); return -EFAULT; } ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start) { if (!maxpages) return 0; BUG_ON(!pages); return __iov_iter_get_pages_alloc(i, &pages, maxsize, maxpages, start); } EXPORT_SYMBOL(iov_iter_get_pages2); ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start) { ssize_t len; *pages = NULL; len = __iov_iter_get_pages_alloc(i, pages, maxsize, ~0U, start); if (len <= 0) { kvfree(*pages); *pages = NULL; } return len; } EXPORT_SYMBOL(iov_iter_get_pages_alloc2); static int iov_npages(const struct iov_iter *i, int maxpages) { size_t skip = i->iov_offset, size = i->count; const struct iovec *p; int npages = 0; for (p = iter_iov(i); size; skip = 0, p++) { unsigned offs = offset_in_page(p->iov_base + skip); size_t len = min(p->iov_len - skip, size); if (len) { size -= len; npages += DIV_ROUND_UP(offs + len, PAGE_SIZE); if (unlikely(npages > maxpages)) return maxpages; } } return npages; } static int bvec_npages(const struct iov_iter *i, int maxpages) { size_t skip = i->iov_offset, size = i->count; const struct bio_vec *p; int npages = 0; for (p = i->bvec; size; skip = 0, p++) { unsigned offs = (p->bv_offset + skip) % PAGE_SIZE; size_t len = min(p->bv_len - skip, size); size -= len; npages += DIV_ROUND_UP(offs + len, PAGE_SIZE); if (unlikely(npages > maxpages)) return maxpages; } return npages; } int iov_iter_npages(const struct iov_iter *i, int maxpages) { if (unlikely(!i->count)) return 0; if (likely(iter_is_ubuf(i))) { unsigned offs = offset_in_page(i->ubuf + i->iov_offset); int npages = DIV_ROUND_UP(offs + i->count, PAGE_SIZE); return min(npages, maxpages); } /* iovec and kvec have identical layouts */ if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i))) return iov_npages(i, maxpages); if (iov_iter_is_bvec(i)) return bvec_npages(i, maxpages); if (iov_iter_is_folioq(i)) { unsigned offset = i->iov_offset % PAGE_SIZE; int npages = DIV_ROUND_UP(offset + i->count, PAGE_SIZE); return min(npages, maxpages); } if (iov_iter_is_xarray(i)) { unsigned offset = (i->xarray_start + i->iov_offset) % PAGE_SIZE; int npages = DIV_ROUND_UP(offset + i->count, PAGE_SIZE); return min(npages, maxpages); } return 0; } EXPORT_SYMBOL(iov_iter_npages); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags) { *new = *old; if (iov_iter_is_bvec(new)) return new->bvec = kmemdup(new->bvec, new->nr_segs * sizeof(struct bio_vec), flags); else if (iov_iter_is_kvec(new) || iter_is_iovec(new)) /* iovec and kvec have identical layout */ return new->__iov = kmemdup(new->__iov, new->nr_segs * sizeof(struct iovec), flags); return NULL; } EXPORT_SYMBOL(dup_iter); static __noclone int copy_compat_iovec_from_user(struct iovec *iov, const struct iovec __user *uvec, u32 nr_segs) { const struct compat_iovec __user *uiov = (const struct compat_iovec __user *)uvec; int ret = -EFAULT; u32 i; if (!user_access_begin(uiov, nr_segs * sizeof(*uiov))) return -EFAULT; for (i = 0; i < nr_segs; i++) { compat_uptr_t buf; compat_ssize_t len; unsafe_get_user(len, &uiov[i].iov_len, uaccess_end); unsafe_get_user(buf, &uiov[i].iov_base, uaccess_end); /* check for compat_size_t not fitting in compat_ssize_t .. */ if (len < 0) { ret = -EINVAL; goto uaccess_end; } iov[i].iov_base = compat_ptr(buf); iov[i].iov_len = len; } ret = 0; uaccess_end: user_access_end(); return ret; } static __noclone int copy_iovec_from_user(struct iovec *iov, const struct iovec __user *uiov, unsigned long nr_segs) { int ret = -EFAULT; if (!user_access_begin(uiov, nr_segs * sizeof(*uiov))) return -EFAULT; do { void __user *buf; ssize_t len; unsafe_get_user(len, &uiov->iov_len, uaccess_end); unsafe_get_user(buf, &uiov->iov_base, uaccess_end); /* check for size_t not fitting in ssize_t .. */ if (unlikely(len < 0)) { ret = -EINVAL; goto uaccess_end; } iov->iov_base = buf; iov->iov_len = len; uiov++; iov++; } while (--nr_segs); ret = 0; uaccess_end: user_access_end(); return ret; } struct iovec *iovec_from_user(const struct iovec __user *uvec, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_iov, bool compat) { struct iovec *iov = fast_iov; int ret; /* * SuS says "The readv() function *may* fail if the iovcnt argument was * less than or equal to 0, or greater than {IOV_MAX}. Linux has * traditionally returned zero for zero segments, so... */ if (nr_segs == 0) return iov; if (nr_segs > UIO_MAXIOV) return ERR_PTR(-EINVAL); if (nr_segs > fast_segs) { iov = kmalloc_array(nr_segs, sizeof(struct iovec), GFP_KERNEL); if (!iov) return ERR_PTR(-ENOMEM); } if (unlikely(compat)) ret = copy_compat_iovec_from_user(iov, uvec, nr_segs); else ret = copy_iovec_from_user(iov, uvec, nr_segs); if (ret) { if (iov != fast_iov) kfree(iov); return ERR_PTR(ret); } return iov; } /* * Single segment iovec supplied by the user, import it as ITER_UBUF. */ static ssize_t __import_iovec_ubuf(int type, const struct iovec __user *uvec, struct iovec **iovp, struct iov_iter *i, bool compat) { struct iovec *iov = *iovp; ssize_t ret; if (compat) ret = copy_compat_iovec_from_user(iov, uvec, 1); else ret = copy_iovec_from_user(iov, uvec, 1); if (unlikely(ret)) return ret; ret = import_ubuf(type, iov->iov_base, iov->iov_len, i); if (unlikely(ret)) return ret; *iovp = NULL; return i->count; } ssize_t __import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i, bool compat) { ssize_t total_len = 0; unsigned long seg; struct iovec *iov; if (nr_segs == 1) return __import_iovec_ubuf(type, uvec, iovp, i, compat); iov = iovec_from_user(uvec, nr_segs, fast_segs, *iovp, compat); if (IS_ERR(iov)) { *iovp = NULL; return PTR_ERR(iov); } /* * According to the Single Unix Specification we should return EINVAL if * an element length is < 0 when cast to ssize_t or if the total length * would overflow the ssize_t return value of the system call. * * Linux caps all read/write calls to MAX_RW_COUNT, and avoids the * overflow case. */ for (seg = 0; seg < nr_segs; seg++) { ssize_t len = (ssize_t)iov[seg].iov_len; if (!access_ok(iov[seg].iov_base, len)) { if (iov != *iovp) kfree(iov); *iovp = NULL; return -EFAULT; } if (len > MAX_RW_COUNT - total_len) { len = MAX_RW_COUNT - total_len; iov[seg].iov_len = len; } total_len += len; } iov_iter_init(i, type, iov, nr_segs, total_len); if (iov == *iovp) *iovp = NULL; else *iovp = iov; return total_len; } /** * import_iovec() - Copy an array of &struct iovec from userspace * into the kernel, check that it is valid, and initialize a new * &struct iov_iter iterator to access it. * * @type: One of %READ or %WRITE. * @uvec: Pointer to the userspace array. * @nr_segs: Number of elements in userspace array. * @fast_segs: Number of elements in @iov. * @iovp: (input and output parameter) Pointer to pointer to (usually small * on-stack) kernel array. * @i: Pointer to iterator that will be initialized on success. * * If the array pointed to by *@iov is large enough to hold all @nr_segs, * then this function places %NULL in *@iov on return. Otherwise, a new * array will be allocated and the result placed in *@iov. This means that * the caller may call kfree() on *@iov regardless of whether the small * on-stack array was used or not (and regardless of whether this function * returns an error or not). * * Return: Negative error code on error, bytes imported on success */ ssize_t import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i) { return __import_iovec(type, uvec, nr_segs, fast_segs, iovp, i, in_compat_syscall()); } EXPORT_SYMBOL(import_iovec); int import_ubuf(int rw, void __user *buf, size_t len, struct iov_iter *i) { if (len > MAX_RW_COUNT) len = MAX_RW_COUNT; if (unlikely(!access_ok(buf, len))) return -EFAULT; iov_iter_ubuf(i, rw, buf, len); return 0; } EXPORT_SYMBOL_GPL(import_ubuf); /** * iov_iter_restore() - Restore a &struct iov_iter to the same state as when * iov_iter_save_state() was called. * * @i: &struct iov_iter to restore * @state: state to restore from * * Used after iov_iter_save_state() to bring restore @i, if operations may * have advanced it. * * Note: only works on ITER_IOVEC, ITER_BVEC, and ITER_KVEC */ void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state) { if (WARN_ON_ONCE(!iov_iter_is_bvec(i) && !iter_is_iovec(i) && !iter_is_ubuf(i)) && !iov_iter_is_kvec(i)) return; i->iov_offset = state->iov_offset; i->count = state->count; if (iter_is_ubuf(i)) return; /* * For the *vec iters, nr_segs + iov is constant - if we increment * the vec, then we also decrement the nr_segs count. Hence we don't * need to track both of these, just one is enough and we can deduct * the other from that. ITER_KVEC and ITER_IOVEC are the same struct * size, so we can just increment the iov pointer as they are unionzed. * ITER_BVEC _may_ be the same size on some archs, but on others it is * not. Be safe and handle it separately. */ BUILD_BUG_ON(sizeof(struct iovec) != sizeof(struct kvec)); if (iov_iter_is_bvec(i)) i->bvec -= state->nr_segs - i->nr_segs; else i->__iov -= state->nr_segs - i->nr_segs; i->nr_segs = state->nr_segs; } /* * Extract a list of contiguous pages from an ITER_FOLIOQ iterator. This does * not get references on the pages, nor does it get a pin on them. */ static ssize_t iov_iter_extract_folioq_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, iov_iter_extraction_t extraction_flags, size_t *offset0) { const struct folio_queue *folioq = i->folioq; struct page **p; unsigned int nr = 0; size_t extracted = 0, offset, slot = i->folioq_slot; if (slot >= folioq_nr_slots(folioq)) { folioq = folioq->next; slot = 0; if (WARN_ON(i->iov_offset != 0)) return -EIO; } offset = i->iov_offset & ~PAGE_MASK; *offset0 = offset; maxpages = want_pages_array(pages, maxsize, offset, maxpages); if (!maxpages) return -ENOMEM; p = *pages; for (;;) { struct folio *folio = folioq_folio(folioq, slot); size_t offset = i->iov_offset, fsize = folioq_folio_size(folioq, slot); size_t part = PAGE_SIZE - offset % PAGE_SIZE; if (offset < fsize) { part = umin(part, umin(maxsize - extracted, fsize - offset)); i->count -= part; i->iov_offset += part; extracted += part; p[nr++] = folio_page(folio, offset / PAGE_SIZE); } if (nr >= maxpages || extracted >= maxsize) break; if (i->iov_offset >= fsize) { i->iov_offset = 0; slot++; if (slot == folioq_nr_slots(folioq) && folioq->next) { folioq = folioq->next; slot = 0; } } } i->folioq = folioq; i->folioq_slot = slot; return extracted; } /* * Extract a list of contiguous pages from an ITER_XARRAY iterator. This does not * get references on the pages, nor does it get a pin on them. */ static ssize_t iov_iter_extract_xarray_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, iov_iter_extraction_t extraction_flags, size_t *offset0) { struct page *page, **p; unsigned int nr = 0, offset; loff_t pos = i->xarray_start + i->iov_offset; pgoff_t index = pos >> PAGE_SHIFT; XA_STATE(xas, i->xarray, index); offset = pos & ~PAGE_MASK; *offset0 = offset; maxpages = want_pages_array(pages, maxsize, offset, maxpages); if (!maxpages) return -ENOMEM; p = *pages; rcu_read_lock(); for (page = xas_load(&xas); page; page = xas_next(&xas)) { if (xas_retry(&xas, page)) continue; /* Has the page moved or been split? */ if (unlikely(page != xas_reload(&xas))) { xas_reset(&xas); continue; } p[nr++] = find_subpage(page, xas.xa_index); if (nr == maxpages) break; } rcu_read_unlock(); maxsize = min_t(size_t, nr * PAGE_SIZE - offset, maxsize); iov_iter_advance(i, maxsize); return maxsize; } /* * Extract a list of virtually contiguous pages from an ITER_BVEC iterator. * This does not get references on the pages, nor does it get a pin on them. */ static ssize_t iov_iter_extract_bvec_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, iov_iter_extraction_t extraction_flags, size_t *offset0) { size_t skip = i->iov_offset, size = 0; struct bvec_iter bi; int k = 0; if (i->nr_segs == 0) return 0; if (i->iov_offset == i->bvec->bv_len) { i->iov_offset = 0; i->nr_segs--; i->bvec++; skip = 0; } bi.bi_idx = 0; bi.bi_size = maxsize; bi.bi_bvec_done = skip; maxpages = want_pages_array(pages, maxsize, skip, maxpages); while (bi.bi_size && bi.bi_idx < i->nr_segs) { struct bio_vec bv = bvec_iter_bvec(i->bvec, bi); /* * The iov_iter_extract_pages interface only allows an offset * into the first page. Break out of the loop if we see an * offset into subsequent pages, the caller will have to call * iov_iter_extract_pages again for the reminder. */ if (k) { if (bv.bv_offset) break; } else { *offset0 = bv.bv_offset; } (*pages)[k++] = bv.bv_page; size += bv.bv_len; if (k >= maxpages) break; /* * We are done when the end of the bvec doesn't align to a page * boundary as that would create a hole in the returned space. * The caller will handle this with another call to * iov_iter_extract_pages. */ if (bv.bv_offset + bv.bv_len != PAGE_SIZE) break; bvec_iter_advance_single(i->bvec, &bi, bv.bv_len); } iov_iter_advance(i, size); return size; } /* * Extract a list of virtually contiguous pages from an ITER_KVEC iterator. * This does not get references on the pages, nor does it get a pin on them. */ static ssize_t iov_iter_extract_kvec_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, iov_iter_extraction_t extraction_flags, size_t *offset0) { struct page **p, *page; const void *kaddr; size_t skip = i->iov_offset, offset, len, size; int k; for (;;) { if (i->nr_segs == 0) return 0; size = min(maxsize, i->kvec->iov_len - skip); if (size) break; i->iov_offset = 0; i->nr_segs--; i->kvec++; skip = 0; } kaddr = i->kvec->iov_base + skip; offset = (unsigned long)kaddr & ~PAGE_MASK; *offset0 = offset; maxpages = want_pages_array(pages, size, offset, maxpages); if (!maxpages) return -ENOMEM; p = *pages; kaddr -= offset; len = offset + size; for (k = 0; k < maxpages; k++) { size_t seg = min_t(size_t, len, PAGE_SIZE); if (is_vmalloc_or_module_addr(kaddr)) page = vmalloc_to_page(kaddr); else page = virt_to_page(kaddr); p[k] = page; len -= seg; kaddr += PAGE_SIZE; } size = min_t(size_t, size, maxpages * PAGE_SIZE - offset); iov_iter_advance(i, size); return size; } /* * Extract a list of contiguous pages from a user iterator and get a pin on * each of them. This should only be used if the iterator is user-backed * (IOBUF/UBUF). * * It does not get refs on the pages, but the pages must be unpinned by the * caller once the transfer is complete. * * This is safe to be used where background IO/DMA *is* going to be modifying * the buffer; using a pin rather than a ref makes forces fork() to give the * child a copy of the page. */ static ssize_t iov_iter_extract_user_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, iov_iter_extraction_t extraction_flags, size_t *offset0) { unsigned long addr; unsigned int gup_flags = 0; size_t offset; int res; if (i->data_source == ITER_DEST) gup_flags |= FOLL_WRITE; if (extraction_flags & ITER_ALLOW_P2PDMA) gup_flags |= FOLL_PCI_P2PDMA; if (i->nofault) gup_flags |= FOLL_NOFAULT; addr = first_iovec_segment(i, &maxsize); *offset0 = offset = addr % PAGE_SIZE; addr &= PAGE_MASK; maxpages = want_pages_array(pages, maxsize, offset, maxpages); if (!maxpages) return -ENOMEM; res = pin_user_pages_fast(addr, maxpages, gup_flags, *pages); if (unlikely(res <= 0)) return res; maxsize = min_t(size_t, maxsize, res * PAGE_SIZE - offset); iov_iter_advance(i, maxsize); return maxsize; } /** * iov_iter_extract_pages - Extract a list of contiguous pages from an iterator * @i: The iterator to extract from * @pages: Where to return the list of pages * @maxsize: The maximum amount of iterator to extract * @maxpages: The maximum size of the list of pages * @extraction_flags: Flags to qualify request * @offset0: Where to return the starting offset into (*@pages)[0] * * Extract a list of contiguous pages from the current point of the iterator, * advancing the iterator. The maximum number of pages and the maximum amount * of page contents can be set. * * If *@pages is NULL, a page list will be allocated to the required size and * *@pages will be set to its base. If *@pages is not NULL, it will be assumed * that the caller allocated a page list at least @maxpages in size and this * will be filled in. * * @extraction_flags can have ITER_ALLOW_P2PDMA set to request peer-to-peer DMA * be allowed on the pages extracted. * * The iov_iter_extract_will_pin() function can be used to query how cleanup * should be performed. * * Extra refs or pins on the pages may be obtained as follows: * * (*) If the iterator is user-backed (ITER_IOVEC/ITER_UBUF), pins will be * added to the pages, but refs will not be taken. * iov_iter_extract_will_pin() will return true. * * (*) If the iterator is ITER_KVEC, ITER_BVEC, ITER_FOLIOQ or ITER_XARRAY, the * pages are merely listed; no extra refs or pins are obtained. * iov_iter_extract_will_pin() will return 0. * * Note also: * * (*) Use with ITER_DISCARD is not supported as that has no content. * * On success, the function sets *@pages to the new pagelist, if allocated, and * sets *offset0 to the offset into the first page. * * It may also return -ENOMEM and -EFAULT. */ ssize_t iov_iter_extract_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, iov_iter_extraction_t extraction_flags, size_t *offset0) { maxsize = min_t(size_t, min_t(size_t, maxsize, i->count), MAX_RW_COUNT); if (!maxsize) return 0; if (likely(user_backed_iter(i))) return iov_iter_extract_user_pages(i, pages, maxsize, maxpages, extraction_flags, offset0); if (iov_iter_is_kvec(i)) return iov_iter_extract_kvec_pages(i, pages, maxsize, maxpages, extraction_flags, offset0); if (iov_iter_is_bvec(i)) return iov_iter_extract_bvec_pages(i, pages, maxsize, maxpages, extraction_flags, offset0); if (iov_iter_is_folioq(i)) return iov_iter_extract_folioq_pages(i, pages, maxsize, maxpages, extraction_flags, offset0); if (iov_iter_is_xarray(i)) return iov_iter_extract_xarray_pages(i, pages, maxsize, maxpages, extraction_flags, offset0); return -EFAULT; } EXPORT_SYMBOL_GPL(iov_iter_extract_pages); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 | #ifndef LLC_PDU_H #define LLC_PDU_H /* * Copyright (c) 1997 by Procom Technology,Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <linux/if_ether.h> /* Lengths of frame formats */ #define LLC_PDU_LEN_I 4 /* header and 2 control bytes */ #define LLC_PDU_LEN_S 4 #define LLC_PDU_LEN_U 3 /* header and 1 control byte */ /* header and 1 control byte and XID info */ #define LLC_PDU_LEN_U_XID (LLC_PDU_LEN_U + sizeof(struct llc_xid_info)) /* Known SAP addresses */ #define LLC_GLOBAL_SAP 0xFF #define LLC_NULL_SAP 0x00 /* not network-layer visible */ #define LLC_MGMT_INDIV 0x02 /* station LLC mgmt indiv addr */ #define LLC_MGMT_GRP 0x03 /* station LLC mgmt group addr */ #define LLC_RDE_SAP 0xA6 /* route ... */ /* SAP field bit masks */ #define LLC_ISO_RESERVED_SAP 0x02 #define LLC_SAP_GROUP_DSAP 0x01 #define LLC_SAP_RESP_SSAP 0x01 /* Group/individual DSAP indicator is DSAP field */ #define LLC_PDU_GROUP_DSAP_MASK 0x01 #define LLC_PDU_IS_GROUP_DSAP(pdu) \ ((pdu->dsap & LLC_PDU_GROUP_DSAP_MASK) ? 0 : 1) #define LLC_PDU_IS_INDIV_DSAP(pdu) \ (!(pdu->dsap & LLC_PDU_GROUP_DSAP_MASK) ? 0 : 1) /* Command/response PDU indicator in SSAP field */ #define LLC_PDU_CMD_RSP_MASK 0x01 #define LLC_PDU_CMD 0 #define LLC_PDU_RSP 1 #define LLC_PDU_IS_CMD(pdu) ((pdu->ssap & LLC_PDU_RSP) ? 0 : 1) #define LLC_PDU_IS_RSP(pdu) ((pdu->ssap & LLC_PDU_RSP) ? 1 : 0) /* Get PDU type from 2 lowest-order bits of control field first byte */ #define LLC_PDU_TYPE_I_MASK 0x01 /* 16-bit control field */ #define LLC_PDU_TYPE_S_MASK 0x03 #define LLC_PDU_TYPE_U_MASK 0x03 /* 8-bit control field */ #define LLC_PDU_TYPE_MASK 0x03 #define LLC_PDU_TYPE_I 0 /* first bit */ #define LLC_PDU_TYPE_S 1 /* first two bits */ #define LLC_PDU_TYPE_U 3 /* first two bits */ #define LLC_PDU_TYPE_U_XID 4 /* private type for detecting XID commands */ #define LLC_PDU_TYPE_IS_I(pdu) \ ((!(pdu->ctrl_1 & LLC_PDU_TYPE_I_MASK)) ? 1 : 0) #define LLC_PDU_TYPE_IS_U(pdu) \ (((pdu->ctrl_1 & LLC_PDU_TYPE_U_MASK) == LLC_PDU_TYPE_U) ? 1 : 0) #define LLC_PDU_TYPE_IS_S(pdu) \ (((pdu->ctrl_1 & LLC_PDU_TYPE_S_MASK) == LLC_PDU_TYPE_S) ? 1 : 0) /* U-format PDU control field masks */ #define LLC_U_PF_BIT_MASK 0x10 /* P/F bit mask */ #define LLC_U_PF_IS_1(pdu) ((pdu->ctrl_1 & LLC_U_PF_BIT_MASK) ? 1 : 0) #define LLC_U_PF_IS_0(pdu) ((!(pdu->ctrl_1 & LLC_U_PF_BIT_MASK)) ? 1 : 0) #define LLC_U_PDU_CMD_MASK 0xEC /* cmd/rsp mask */ #define LLC_U_PDU_CMD(pdu) (pdu->ctrl_1 & LLC_U_PDU_CMD_MASK) #define LLC_U_PDU_RSP(pdu) (pdu->ctrl_1 & LLC_U_PDU_CMD_MASK) #define LLC_1_PDU_CMD_UI 0x00 /* Type 1 cmds/rsps */ #define LLC_1_PDU_CMD_XID 0xAC #define LLC_1_PDU_CMD_TEST 0xE0 #define LLC_2_PDU_CMD_SABME 0x6C /* Type 2 cmds/rsps */ #define LLC_2_PDU_CMD_DISC 0x40 #define LLC_2_PDU_RSP_UA 0x60 #define LLC_2_PDU_RSP_DM 0x0C #define LLC_2_PDU_RSP_FRMR 0x84 /* Type 1 operations */ /* XID information field bit masks */ /* LLC format identifier (byte 1) */ #define LLC_XID_FMT_ID 0x81 /* first byte must be this */ /* LLC types/classes identifier (byte 2) */ #define LLC_XID_CLASS_ZEROS_MASK 0xE0 /* these must be zeros */ #define LLC_XID_CLASS_MASK 0x1F /* AND with byte to get below */ #define LLC_XID_NULL_CLASS_1 0x01 /* if NULL LSAP...use these */ #define LLC_XID_NULL_CLASS_2 0x03 #define LLC_XID_NULL_CLASS_3 0x05 #define LLC_XID_NULL_CLASS_4 0x07 #define LLC_XID_NNULL_TYPE_1 0x01 /* if non-NULL LSAP...use these */ #define LLC_XID_NNULL_TYPE_2 0x02 #define LLC_XID_NNULL_TYPE_3 0x04 #define LLC_XID_NNULL_TYPE_1_2 0x03 #define LLC_XID_NNULL_TYPE_1_3 0x05 #define LLC_XID_NNULL_TYPE_2_3 0x06 #define LLC_XID_NNULL_ALL 0x07 /* Sender Receive Window (byte 3) */ #define LLC_XID_RW_MASK 0xFE /* AND with value to get below */ #define LLC_XID_MIN_RW 0x02 /* lowest-order bit always zero */ /* Type 2 operations */ #define LLC_2_SEQ_NBR_MODULO ((u8) 128) /* I-PDU masks ('ctrl' is I-PDU control word) */ #define LLC_I_GET_NS(pdu) (u8)((pdu->ctrl_1 & 0xFE) >> 1) #define LLC_I_GET_NR(pdu) (u8)((pdu->ctrl_2 & 0xFE) >> 1) #define LLC_I_PF_BIT_MASK 0x01 #define LLC_I_PF_IS_0(pdu) ((!(pdu->ctrl_2 & LLC_I_PF_BIT_MASK)) ? 1 : 0) #define LLC_I_PF_IS_1(pdu) ((pdu->ctrl_2 & LLC_I_PF_BIT_MASK) ? 1 : 0) /* S-PDU supervisory commands and responses */ #define LLC_S_PDU_CMD_MASK 0x0C #define LLC_S_PDU_CMD(pdu) (pdu->ctrl_1 & LLC_S_PDU_CMD_MASK) #define LLC_S_PDU_RSP(pdu) (pdu->ctrl_1 & LLC_S_PDU_CMD_MASK) #define LLC_2_PDU_CMD_RR 0x00 /* rx ready cmd */ #define LLC_2_PDU_RSP_RR 0x00 /* rx ready rsp */ #define LLC_2_PDU_CMD_REJ 0x08 /* reject PDU cmd */ #define LLC_2_PDU_RSP_REJ 0x08 /* reject PDU rsp */ #define LLC_2_PDU_CMD_RNR 0x04 /* rx not ready cmd */ #define LLC_2_PDU_RSP_RNR 0x04 /* rx not ready rsp */ #define LLC_S_PF_BIT_MASK 0x01 #define LLC_S_PF_IS_0(pdu) ((!(pdu->ctrl_2 & LLC_S_PF_BIT_MASK)) ? 1 : 0) #define LLC_S_PF_IS_1(pdu) ((pdu->ctrl_2 & LLC_S_PF_BIT_MASK) ? 1 : 0) #define PDU_SUPV_GET_Nr(pdu) ((pdu->ctrl_2 & 0xFE) >> 1) #define PDU_GET_NEXT_Vr(sn) (((sn) + 1) & ~LLC_2_SEQ_NBR_MODULO) /* FRMR information field macros */ #define FRMR_INFO_LENGTH 5 /* 5 bytes of information */ /* * info is pointer to FRMR info field structure; 'rej_ctrl' is byte pointer * (if U-PDU) or word pointer to rejected PDU control field */ #define FRMR_INFO_SET_REJ_CNTRL(info,rej_ctrl) \ info->rej_pdu_ctrl = ((*((u8 *) rej_ctrl) & \ LLC_PDU_TYPE_U) != LLC_PDU_TYPE_U ? \ (u16)*((u16 *) rej_ctrl) : \ (((u16) *((u8 *) rej_ctrl)) & 0x00FF)) /* * Info is pointer to FRMR info field structure; 'vs' is a byte containing * send state variable value in low-order 7 bits (insure the lowest-order * bit remains zero (0)) */ #define FRMR_INFO_SET_Vs(info,vs) (info->curr_ssv = (((u8) vs) << 1)) #define FRMR_INFO_SET_Vr(info,vr) (info->curr_rsv = (((u8) vr) << 1)) /* * Info is pointer to FRMR info field structure; 'cr' is a byte containing * the C/R bit value in the low-order bit */ #define FRMR_INFO_SET_C_R_BIT(info, cr) (info->curr_rsv |= (((u8) cr) & 0x01)) /* * In the remaining five macros, 'info' is pointer to FRMR info field * structure; 'ind' is a byte containing the bit value to set in the * lowest-order bit) */ #define FRMR_INFO_SET_INVALID_PDU_CTRL_IND(info, ind) \ (info->ind_bits = ((info->ind_bits & 0xFE) | (((u8) ind) & 0x01))) #define FRMR_INFO_SET_INVALID_PDU_INFO_IND(info, ind) \ (info->ind_bits = ( (info->ind_bits & 0xFD) | (((u8) ind) & 0x02))) #define FRMR_INFO_SET_PDU_INFO_2LONG_IND(info, ind) \ (info->ind_bits = ( (info->ind_bits & 0xFB) | (((u8) ind) & 0x04))) #define FRMR_INFO_SET_PDU_INVALID_Nr_IND(info, ind) \ (info->ind_bits = ( (info->ind_bits & 0xF7) | (((u8) ind) & 0x08))) #define FRMR_INFO_SET_PDU_INVALID_Ns_IND(info, ind) \ (info->ind_bits = ( (info->ind_bits & 0xEF) | (((u8) ind) & 0x10))) /* Sequence-numbered PDU format (4 bytes in length) */ struct llc_pdu_sn { u8 dsap; u8 ssap; u8 ctrl_1; u8 ctrl_2; } __packed; static inline struct llc_pdu_sn *llc_pdu_sn_hdr(struct sk_buff *skb) { return (struct llc_pdu_sn *)skb_network_header(skb); } /* Un-numbered PDU format (3 bytes in length) */ struct llc_pdu_un { u8 dsap; u8 ssap; u8 ctrl_1; } __packed; static inline struct llc_pdu_un *llc_pdu_un_hdr(struct sk_buff *skb) { return (struct llc_pdu_un *)skb_network_header(skb); } /** * llc_pdu_header_init - initializes pdu header * @skb: input skb that header must be set into it. * @type: type of PDU (U, I or S). * @ssap: source sap. * @dsap: destination sap. * @cr: command/response bit (0 or 1). * * This function sets DSAP, SSAP and command/Response bit in LLC header. */ static inline void llc_pdu_header_init(struct sk_buff *skb, u8 type, u8 ssap, u8 dsap, u8 cr) { int hlen = 4; /* default value for I and S types */ struct llc_pdu_un *pdu; switch (type) { case LLC_PDU_TYPE_U: hlen = 3; break; case LLC_PDU_TYPE_U_XID: hlen = 6; break; } skb_push(skb, hlen); skb_reset_network_header(skb); pdu = llc_pdu_un_hdr(skb); pdu->dsap = dsap; pdu->ssap = ssap; pdu->ssap |= cr; } /** * llc_pdu_decode_sa - extracts, source address (MAC) of input frame * @skb: input skb that source address must be extracted from it. * @sa: pointer to source address (6 byte array). * * This function extracts source address(MAC) of input frame. */ static inline void llc_pdu_decode_sa(struct sk_buff *skb, u8 *sa) { memcpy(sa, eth_hdr(skb)->h_source, ETH_ALEN); } /** * llc_pdu_decode_da - extracts dest address of input frame * @skb: input skb that destination address must be extracted from it * @da: pointer to destination address (6 byte array). * * This function extracts destination address(MAC) of input frame. */ static inline void llc_pdu_decode_da(struct sk_buff *skb, u8 *da) { memcpy(da, eth_hdr(skb)->h_dest, ETH_ALEN); } /** * llc_pdu_decode_ssap - extracts source SAP of input frame * @skb: input skb that source SAP must be extracted from it. * @ssap: source SAP (output argument). * * This function extracts source SAP of input frame. Right bit of SSAP is * command/response bit. */ static inline void llc_pdu_decode_ssap(struct sk_buff *skb, u8 *ssap) { *ssap = llc_pdu_un_hdr(skb)->ssap & 0xFE; } /** * llc_pdu_decode_dsap - extracts dest SAP of input frame * @skb: input skb that destination SAP must be extracted from it. * @dsap: destination SAP (output argument). * * This function extracts destination SAP of input frame. right bit of * DSAP designates individual/group SAP. */ static inline void llc_pdu_decode_dsap(struct sk_buff *skb, u8 *dsap) { *dsap = llc_pdu_un_hdr(skb)->dsap & 0xFE; } /** * llc_pdu_init_as_ui_cmd - sets LLC header as UI PDU * @skb: input skb that header must be set into it. * * This function sets third byte of LLC header as a UI PDU. */ static inline void llc_pdu_init_as_ui_cmd(struct sk_buff *skb) { struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); pdu->ctrl_1 = LLC_PDU_TYPE_U; pdu->ctrl_1 |= LLC_1_PDU_CMD_UI; } /** * llc_pdu_init_as_test_cmd - sets PDU as TEST * @skb: Address of the skb to build * * Sets a PDU as TEST */ static inline void llc_pdu_init_as_test_cmd(struct sk_buff *skb) { struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); pdu->ctrl_1 = LLC_PDU_TYPE_U; pdu->ctrl_1 |= LLC_1_PDU_CMD_TEST; pdu->ctrl_1 |= LLC_U_PF_BIT_MASK; } /** * llc_pdu_init_as_test_rsp - build TEST response PDU * @skb: Address of the skb to build * @ev_skb: The received TEST command PDU frame * * Builds a pdu frame as a TEST response. */ static inline void llc_pdu_init_as_test_rsp(struct sk_buff *skb, struct sk_buff *ev_skb) { struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); pdu->ctrl_1 = LLC_PDU_TYPE_U; pdu->ctrl_1 |= LLC_1_PDU_CMD_TEST; pdu->ctrl_1 |= LLC_U_PF_BIT_MASK; if (ev_skb->protocol == htons(ETH_P_802_2)) { struct llc_pdu_un *ev_pdu = llc_pdu_un_hdr(ev_skb); int dsize; dsize = ntohs(eth_hdr(ev_skb)->h_proto) - 3; memcpy(((u8 *)pdu) + 3, ((u8 *)ev_pdu) + 3, dsize); skb_put(skb, dsize); } } /* LLC Type 1 XID command/response information fields format */ struct llc_xid_info { u8 fmt_id; /* always 0x81 for LLC */ u8 type; /* different if NULL/non-NULL LSAP */ u8 rw; /* sender receive window */ } __packed; /** * llc_pdu_init_as_xid_cmd - sets bytes 3, 4 & 5 of LLC header as XID * @skb: input skb that header must be set into it. * @svcs_supported: The class of the LLC (I or II) * @rx_window: The size of the receive window of the LLC * * This function sets third,fourth,fifth and sixth bytes of LLC header as * a XID PDU. */ static inline void llc_pdu_init_as_xid_cmd(struct sk_buff *skb, u8 svcs_supported, u8 rx_window) { struct llc_xid_info *xid_info; struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); pdu->ctrl_1 = LLC_PDU_TYPE_U; pdu->ctrl_1 |= LLC_1_PDU_CMD_XID; pdu->ctrl_1 |= LLC_U_PF_BIT_MASK; xid_info = (struct llc_xid_info *)(((u8 *)&pdu->ctrl_1) + 1); xid_info->fmt_id = LLC_XID_FMT_ID; /* 0x81 */ xid_info->type = svcs_supported; xid_info->rw = rx_window << 1; /* size of receive window */ /* no need to push/put since llc_pdu_header_init() has already * pushed 3 + 3 bytes */ } /** * llc_pdu_init_as_xid_rsp - builds XID response PDU * @skb: Address of the skb to build * @svcs_supported: The class of the LLC (I or II) * @rx_window: The size of the receive window of the LLC * * Builds a pdu frame as an XID response. */ static inline void llc_pdu_init_as_xid_rsp(struct sk_buff *skb, u8 svcs_supported, u8 rx_window) { struct llc_xid_info *xid_info; struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); pdu->ctrl_1 = LLC_PDU_TYPE_U; pdu->ctrl_1 |= LLC_1_PDU_CMD_XID; pdu->ctrl_1 |= LLC_U_PF_BIT_MASK; xid_info = (struct llc_xid_info *)(((u8 *)&pdu->ctrl_1) + 1); xid_info->fmt_id = LLC_XID_FMT_ID; xid_info->type = svcs_supported; xid_info->rw = rx_window << 1; skb_put(skb, sizeof(struct llc_xid_info)); } /* LLC Type 2 FRMR response information field format */ struct llc_frmr_info { u16 rej_pdu_ctrl; /* bits 1-8 if U-PDU */ u8 curr_ssv; /* current send state variable val */ u8 curr_rsv; /* current receive state variable */ u8 ind_bits; /* indicator bits set with macro */ } __packed; void llc_pdu_set_cmd_rsp(struct sk_buff *skb, u8 type); void llc_pdu_set_pf_bit(struct sk_buff *skb, u8 bit_value); void llc_pdu_decode_pf_bit(struct sk_buff *skb, u8 *pf_bit); void llc_pdu_init_as_disc_cmd(struct sk_buff *skb, u8 p_bit); void llc_pdu_init_as_i_cmd(struct sk_buff *skb, u8 p_bit, u8 ns, u8 nr); void llc_pdu_init_as_rej_cmd(struct sk_buff *skb, u8 p_bit, u8 nr); void llc_pdu_init_as_rnr_cmd(struct sk_buff *skb, u8 p_bit, u8 nr); void llc_pdu_init_as_rr_cmd(struct sk_buff *skb, u8 p_bit, u8 nr); void llc_pdu_init_as_sabme_cmd(struct sk_buff *skb, u8 p_bit); void llc_pdu_init_as_dm_rsp(struct sk_buff *skb, u8 f_bit); void llc_pdu_init_as_frmr_rsp(struct sk_buff *skb, struct llc_pdu_sn *prev_pdu, u8 f_bit, u8 vs, u8 vr, u8 vzyxw); void llc_pdu_init_as_rr_rsp(struct sk_buff *skb, u8 f_bit, u8 nr); void llc_pdu_init_as_rej_rsp(struct sk_buff *skb, u8 f_bit, u8 nr); void llc_pdu_init_as_rnr_rsp(struct sk_buff *skb, u8 f_bit, u8 nr); void llc_pdu_init_as_ua_rsp(struct sk_buff *skb, u8 f_bit); #endif /* LLC_PDU_H */ |
| 359 47 47 95 359 39 357 358 358 358 359 356 95 356 357 95 95 355 357 39 352 252 172 171 357 357 95 95 95 95 95 95 357 357 39 39 39 95 95 19 19 312 21 348 348 395 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef LINUX_MM_INLINE_H #define LINUX_MM_INLINE_H #include <linux/atomic.h> #include <linux/huge_mm.h> #include <linux/mm_types.h> #include <linux/swap.h> #include <linux/string.h> #include <linux/userfaultfd_k.h> #include <linux/swapops.h> /** * folio_is_file_lru - Should the folio be on a file LRU or anon LRU? * @folio: The folio to test. * * We would like to get this info without a page flag, but the state * needs to survive until the folio is last deleted from the LRU, which * could be as far down as __page_cache_release. * * Return: An integer (not a boolean!) used to sort a folio onto the * right LRU list and to account folios correctly. * 1 if @folio is a regular filesystem backed page cache folio * or a lazily freed anonymous folio (e.g. via MADV_FREE). * 0 if @folio is a normal anonymous folio, a tmpfs folio or otherwise * ram or swap backed folio. */ static inline int folio_is_file_lru(struct folio *folio) { return !folio_test_swapbacked(folio); } static inline int page_is_file_lru(struct page *page) { return folio_is_file_lru(page_folio(page)); } static __always_inline void __update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, long nr_pages) { struct pglist_data *pgdat = lruvec_pgdat(lruvec); lockdep_assert_held(&lruvec->lru_lock); WARN_ON_ONCE(nr_pages != (int)nr_pages); __mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages); __mod_zone_page_state(&pgdat->node_zones[zid], NR_ZONE_LRU_BASE + lru, nr_pages); } static __always_inline void update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, long nr_pages) { __update_lru_size(lruvec, lru, zid, nr_pages); #ifdef CONFIG_MEMCG mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages); #endif } /** * __folio_clear_lru_flags - Clear page lru flags before releasing a page. * @folio: The folio that was on lru and now has a zero reference. */ static __always_inline void __folio_clear_lru_flags(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_lru(folio), folio); __folio_clear_lru(folio); /* this shouldn't happen, so leave the flags to bad_page() */ if (folio_test_active(folio) && folio_test_unevictable(folio)) return; __folio_clear_active(folio); __folio_clear_unevictable(folio); } /** * folio_lru_list - Which LRU list should a folio be on? * @folio: The folio to test. * * Return: The LRU list a folio should be on, as an index * into the array of LRU lists. */ static __always_inline enum lru_list folio_lru_list(struct folio *folio) { enum lru_list lru; VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio); if (folio_test_unevictable(folio)) return LRU_UNEVICTABLE; lru = folio_is_file_lru(folio) ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON; if (folio_test_active(folio)) lru += LRU_ACTIVE; return lru; } #ifdef CONFIG_LRU_GEN #ifdef CONFIG_LRU_GEN_ENABLED static inline bool lru_gen_enabled(void) { DECLARE_STATIC_KEY_TRUE(lru_gen_caps[NR_LRU_GEN_CAPS]); return static_branch_likely(&lru_gen_caps[LRU_GEN_CORE]); } #else static inline bool lru_gen_enabled(void) { DECLARE_STATIC_KEY_FALSE(lru_gen_caps[NR_LRU_GEN_CAPS]); return static_branch_unlikely(&lru_gen_caps[LRU_GEN_CORE]); } #endif static inline bool lru_gen_in_fault(void) { return current->in_lru_fault; } static inline int lru_gen_from_seq(unsigned long seq) { return seq % MAX_NR_GENS; } static inline int lru_hist_from_seq(unsigned long seq) { return seq % NR_HIST_GENS; } static inline int lru_tier_from_refs(int refs) { VM_WARN_ON_ONCE(refs > BIT(LRU_REFS_WIDTH)); /* see the comment in folio_lru_refs() */ return order_base_2(refs + 1); } static inline int folio_lru_refs(struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags); bool workingset = flags & BIT(PG_workingset); /* * Return the number of accesses beyond PG_referenced, i.e., N-1 if the * total number of accesses is N>1, since N=0,1 both map to the first * tier. lru_tier_from_refs() will account for this off-by-one. Also see * the comment on MAX_NR_TIERS. */ return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + workingset; } static inline void folio_clear_lru_refs(struct folio *folio) { set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, 0); } static inline int folio_lru_gen(struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags); return ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; } static inline bool lru_gen_is_active(struct lruvec *lruvec, int gen) { unsigned long max_seq = lruvec->lrugen.max_seq; VM_WARN_ON_ONCE(gen >= MAX_NR_GENS); /* see the comment on MIN_NR_GENS */ return gen == lru_gen_from_seq(max_seq) || gen == lru_gen_from_seq(max_seq - 1); } static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *folio, int old_gen, int new_gen) { int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); enum lru_list lru = type * LRU_INACTIVE_FILE; struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE(old_gen != -1 && old_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(new_gen != -1 && new_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(old_gen == -1 && new_gen == -1); if (old_gen >= 0) WRITE_ONCE(lrugen->nr_pages[old_gen][type][zone], lrugen->nr_pages[old_gen][type][zone] - delta); if (new_gen >= 0) WRITE_ONCE(lrugen->nr_pages[new_gen][type][zone], lrugen->nr_pages[new_gen][type][zone] + delta); /* addition */ if (old_gen < 0) { if (lru_gen_is_active(lruvec, new_gen)) lru += LRU_ACTIVE; __update_lru_size(lruvec, lru, zone, delta); return; } /* deletion */ if (new_gen < 0) { if (lru_gen_is_active(lruvec, old_gen)) lru += LRU_ACTIVE; __update_lru_size(lruvec, lru, zone, -delta); return; } /* promotion */ if (!lru_gen_is_active(lruvec, old_gen) && lru_gen_is_active(lruvec, new_gen)) { __update_lru_size(lruvec, lru, zone, -delta); __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, delta); } /* demotion requires isolation, e.g., lru_deactivate_fn() */ VM_WARN_ON_ONCE(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen)); } static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { unsigned long seq; unsigned long flags; unsigned long mask; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE_FOLIO(gen != -1, folio); if (folio_test_unevictable(folio) || !lrugen->enabled) return false; /* * There are four common cases for this page: * 1. If it's hot, i.e., freshly faulted in, add it to the youngest * generation, and it's protected over the rest below. * 2. If it can't be evicted immediately, i.e., a dirty page pending * writeback, add it to the second youngest generation. * 3. If it should be evicted first, e.g., cold and clean from * folio_rotate_reclaimable(), add it to the oldest generation. * 4. Everything else falls between 2 & 3 above and is added to the * second oldest generation if it's considered inactive, or the * oldest generation otherwise. See lru_gen_is_active(). */ if (folio_test_active(folio)) seq = lrugen->max_seq; else if ((type == LRU_GEN_ANON && !folio_test_swapcache(folio)) || (folio_test_reclaim(folio) && (folio_test_dirty(folio) || folio_test_writeback(folio)))) seq = lrugen->max_seq - 1; else if (reclaiming || lrugen->min_seq[type] + MIN_NR_GENS >= lrugen->max_seq) seq = lrugen->min_seq[type]; else seq = lrugen->min_seq[type] + 1; gen = lru_gen_from_seq(seq); flags = (gen + 1UL) << LRU_GEN_PGOFF; /* see the comment on MIN_NR_GENS about PG_active */ mask = LRU_GEN_MASK; /* * Don't clear PG_workingset here because it can affect PSI accounting * if the activation is due to workingset refault. */ if (folio_test_active(folio)) mask |= LRU_REFS_MASK | BIT(PG_referenced) | BIT(PG_active); set_mask_bits(&folio->flags, mask, flags); lru_gen_update_size(lruvec, folio, -1, gen); /* for folio_rotate_reclaimable() */ if (reclaiming) list_add_tail(&folio->lru, &lrugen->folios[gen][type][zone]); else list_add(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { unsigned long flags; int gen = folio_lru_gen(folio); if (gen < 0) return false; VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); /* for folio_migrate_flags() */ flags = !reclaiming && lru_gen_is_active(lruvec, gen) ? BIT(PG_active) : 0; flags = set_mask_bits(&folio->flags, LRU_GEN_MASK, flags); gen = ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; lru_gen_update_size(lruvec, folio, gen, -1); list_del(&folio->lru); return true; } static inline void folio_migrate_refs(struct folio *new, struct folio *old) { unsigned long refs = READ_ONCE(old->flags) & LRU_REFS_MASK; set_mask_bits(&new->flags, LRU_REFS_MASK, refs); } #else /* !CONFIG_LRU_GEN */ static inline bool lru_gen_enabled(void) { return false; } static inline bool lru_gen_in_fault(void) { return false; } static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { return false; } static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { return false; } static inline void folio_migrate_refs(struct folio *new, struct folio *old) { } #endif /* CONFIG_LRU_GEN */ static __always_inline void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); if (lru_gen_add_folio(lruvec, folio, false)) return; update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); if (lru != LRU_UNEVICTABLE) list_add(&folio->lru, &lruvec->lists[lru]); } static __always_inline void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); if (lru_gen_add_folio(lruvec, folio, true)) return; update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); /* This is not expected to be used on LRU_UNEVICTABLE */ list_add_tail(&folio->lru, &lruvec->lists[lru]); } static __always_inline void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); if (lru_gen_del_folio(lruvec, folio, false)) return; if (lru != LRU_UNEVICTABLE) list_del(&folio->lru); update_lru_size(lruvec, lru, folio_zonenum(folio), -folio_nr_pages(folio)); } #ifdef CONFIG_ANON_VMA_NAME /* mmap_lock should be read-locked */ static inline void anon_vma_name_get(struct anon_vma_name *anon_name) { if (anon_name) kref_get(&anon_name->kref); } static inline void anon_vma_name_put(struct anon_vma_name *anon_name) { if (anon_name) kref_put(&anon_name->kref, anon_vma_name_free); } static inline struct anon_vma_name *anon_vma_name_reuse(struct anon_vma_name *anon_name) { /* Prevent anon_name refcount saturation early on */ if (kref_read(&anon_name->kref) < REFCOUNT_MAX) { anon_vma_name_get(anon_name); return anon_name; } return anon_vma_name_alloc(anon_name->name); } static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, struct vm_area_struct *new_vma) { struct anon_vma_name *anon_name = anon_vma_name(orig_vma); if (anon_name) new_vma->anon_name = anon_vma_name_reuse(anon_name); } static inline void free_anon_vma_name(struct vm_area_struct *vma) { /* * Not using anon_vma_name because it generates a warning if mmap_lock * is not held, which might be the case here. */ anon_vma_name_put(vma->anon_name); } static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, struct anon_vma_name *anon_name2) { if (anon_name1 == anon_name2) return true; return anon_name1 && anon_name2 && !strcmp(anon_name1->name, anon_name2->name); } #else /* CONFIG_ANON_VMA_NAME */ static inline void anon_vma_name_get(struct anon_vma_name *anon_name) {} static inline void anon_vma_name_put(struct anon_vma_name *anon_name) {} static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, struct vm_area_struct *new_vma) {} static inline void free_anon_vma_name(struct vm_area_struct *vma) {} static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, struct anon_vma_name *anon_name2) { return true; } #endif /* CONFIG_ANON_VMA_NAME */ static inline void init_tlb_flush_pending(struct mm_struct *mm) { atomic_set(&mm->tlb_flush_pending, 0); } static inline void inc_tlb_flush_pending(struct mm_struct *mm) { atomic_inc(&mm->tlb_flush_pending); /* * The only time this value is relevant is when there are indeed pages * to flush. And we'll only flush pages after changing them, which * requires the PTL. * * So the ordering here is: * * atomic_inc(&mm->tlb_flush_pending); * spin_lock(&ptl); * ... * set_pte_at(); * spin_unlock(&ptl); * * spin_lock(&ptl) * mm_tlb_flush_pending(); * .... * spin_unlock(&ptl); * * flush_tlb_range(); * atomic_dec(&mm->tlb_flush_pending); * * Where the increment if constrained by the PTL unlock, it thus * ensures that the increment is visible if the PTE modification is * visible. After all, if there is no PTE modification, nobody cares * about TLB flushes either. * * This very much relies on users (mm_tlb_flush_pending() and * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc * locks (PPC) the unlock of one doesn't order against the lock of * another PTL. * * The decrement is ordered by the flush_tlb_range(), such that * mm_tlb_flush_pending() will not return false unless all flushes have * completed. */ } static inline void dec_tlb_flush_pending(struct mm_struct *mm) { /* * See inc_tlb_flush_pending(). * * This cannot be smp_mb__before_atomic() because smp_mb() simply does * not order against TLB invalidate completion, which is what we need. * * Therefore we must rely on tlb_flush_*() to guarantee order. */ atomic_dec(&mm->tlb_flush_pending); } static inline bool mm_tlb_flush_pending(struct mm_struct *mm) { /* * Must be called after having acquired the PTL; orders against that * PTLs release and therefore ensures that if we observe the modified * PTE we must also observe the increment from inc_tlb_flush_pending(). * * That is, it only guarantees to return true if there is a flush * pending for _this_ PTL. */ return atomic_read(&mm->tlb_flush_pending); } static inline bool mm_tlb_flush_nested(struct mm_struct *mm) { /* * Similar to mm_tlb_flush_pending(), we must have acquired the PTL * for which there is a TLB flush pending in order to guarantee * we've seen both that PTE modification and the increment. * * (no requirement on actually still holding the PTL, that is irrelevant) */ return atomic_read(&mm->tlb_flush_pending) > 1; } #ifdef CONFIG_MMU /* * Computes the pte marker to copy from the given source entry into dst_vma. * If no marker should be copied, returns 0. * The caller should insert a new pte created with make_pte_marker(). */ static inline pte_marker copy_pte_marker( swp_entry_t entry, struct vm_area_struct *dst_vma) { pte_marker srcm = pte_marker_get(entry); /* Always copy error entries. */ pte_marker dstm = srcm & (PTE_MARKER_POISONED | PTE_MARKER_GUARD); /* Only copy PTE markers if UFFD register matches. */ if ((srcm & PTE_MARKER_UFFD_WP) && userfaultfd_wp(dst_vma)) dstm |= PTE_MARKER_UFFD_WP; return dstm; } #endif /* * If this pte is wr-protected by uffd-wp in any form, arm the special pte to * replace a none pte. NOTE! This should only be called when *pte is already * cleared so we will never accidentally replace something valuable. Meanwhile * none pte also means we are not demoting the pte so tlb flushed is not needed. * E.g., when pte cleared the caller should have taken care of the tlb flush. * * Must be called with pgtable lock held so that no thread will see the none * pte, and if they see it, they'll fault and serialize at the pgtable lock. * * This function is a no-op if PTE_MARKER_UFFD_WP is not enabled. */ static inline void pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, pte_t *pte, pte_t pteval) { #ifdef CONFIG_PTE_MARKER_UFFD_WP bool arm_uffd_pte = false; /* The current status of the pte should be "cleared" before calling */ WARN_ON_ONCE(!pte_none(ptep_get(pte))); /* * NOTE: userfaultfd_wp_unpopulated() doesn't need this whole * thing, because when zapping either it means it's dropping the * page, or in TTU where the present pte will be quickly replaced * with a swap pte. There's no way of leaking the bit. */ if (vma_is_anonymous(vma) || !userfaultfd_wp(vma)) return; /* A uffd-wp wr-protected normal pte */ if (unlikely(pte_present(pteval) && pte_uffd_wp(pteval))) arm_uffd_pte = true; /* * A uffd-wp wr-protected swap pte. Note: this should even cover an * existing pte marker with uffd-wp bit set. */ if (unlikely(pte_swp_uffd_wp_any(pteval))) arm_uffd_pte = true; if (unlikely(arm_uffd_pte)) set_pte_at(vma->vm_mm, addr, pte, make_pte_marker(PTE_MARKER_UFFD_WP)); #endif } static inline bool vma_has_recency(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ)) return false; if (vma->vm_file && (vma->vm_file->f_mode & FMODE_NOREUSE)) return false; return true; } #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NET_NF_TABLES_H #define _NET_NF_TABLES_H #include <linux/unaligned.h> #include <linux/list.h> #include <linux/netfilter.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/nf_tables.h> #include <linux/u64_stats_sync.h> #include <linux/rhashtable.h> #include <net/netfilter/nf_flow_table.h> #include <net/netlink.h> #include <net/flow_offload.h> #include <net/netns/generic.h> #define NFT_MAX_HOOKS (NF_INET_INGRESS + 1) struct module; #define NFT_JUMP_STACK_SIZE 16 enum { NFT_PKTINFO_L4PROTO = (1 << 0), NFT_PKTINFO_INNER = (1 << 1), NFT_PKTINFO_INNER_FULL = (1 << 2), }; struct nft_pktinfo { struct sk_buff *skb; const struct nf_hook_state *state; u8 flags; u8 tprot; u16 fragoff; u16 thoff; u16 inneroff; }; static inline struct sock *nft_sk(const struct nft_pktinfo *pkt) { return pkt->state->sk; } static inline unsigned int nft_thoff(const struct nft_pktinfo *pkt) { return pkt->thoff; } static inline struct net *nft_net(const struct nft_pktinfo *pkt) { return pkt->state->net; } static inline unsigned int nft_hook(const struct nft_pktinfo *pkt) { return pkt->state->hook; } static inline u8 nft_pf(const struct nft_pktinfo *pkt) { return pkt->state->pf; } static inline const struct net_device *nft_in(const struct nft_pktinfo *pkt) { return pkt->state->in; } static inline const struct net_device *nft_out(const struct nft_pktinfo *pkt) { return pkt->state->out; } static inline void nft_set_pktinfo(struct nft_pktinfo *pkt, struct sk_buff *skb, const struct nf_hook_state *state) { pkt->skb = skb; pkt->state = state; } static inline void nft_set_pktinfo_unspec(struct nft_pktinfo *pkt) { pkt->flags = 0; pkt->tprot = 0; pkt->thoff = 0; pkt->fragoff = 0; } /** * struct nft_verdict - nf_tables verdict * * @code: nf_tables/netfilter verdict code * @chain: destination chain for NFT_JUMP/NFT_GOTO */ struct nft_verdict { u32 code; struct nft_chain *chain; }; struct nft_data { union { u32 data[4]; struct nft_verdict verdict; }; } __attribute__((aligned(__alignof__(u64)))); #define NFT_REG32_NUM 20 /** * struct nft_regs - nf_tables register set * * @data: data registers * @verdict: verdict register * * The first four data registers alias to the verdict register. */ struct nft_regs { union { u32 data[NFT_REG32_NUM]; struct nft_verdict verdict; }; }; struct nft_regs_track { struct { const struct nft_expr *selector; const struct nft_expr *bitwise; u8 num_reg; } regs[NFT_REG32_NUM]; const struct nft_expr *cur; const struct nft_expr *last; }; /* Store/load an u8, u16 or u64 integer to/from the u32 data register. * * Note, when using concatenations, register allocation happens at 32-bit * level. So for store instruction, pad the rest part with zero to avoid * garbage values. */ static inline void nft_reg_store8(u32 *dreg, u8 val) { *dreg = 0; *(u8 *)dreg = val; } static inline u8 nft_reg_load8(const u32 *sreg) { return *(u8 *)sreg; } static inline void nft_reg_store16(u32 *dreg, u16 val) { *dreg = 0; *(u16 *)dreg = val; } static inline void nft_reg_store_be16(u32 *dreg, __be16 val) { nft_reg_store16(dreg, (__force __u16)val); } static inline u16 nft_reg_load16(const u32 *sreg) { return *(u16 *)sreg; } static inline __be16 nft_reg_load_be16(const u32 *sreg) { return (__force __be16)nft_reg_load16(sreg); } static inline __be32 nft_reg_load_be32(const u32 *sreg) { return *(__force __be32 *)sreg; } static inline void nft_reg_store64(u64 *dreg, u64 val) { put_unaligned(val, dreg); } static inline u64 nft_reg_load64(const u32 *sreg) { return get_unaligned((u64 *)sreg); } static inline void nft_data_copy(u32 *dst, const struct nft_data *src, unsigned int len) { if (len % NFT_REG32_SIZE) dst[len / NFT_REG32_SIZE] = 0; memcpy(dst, src, len); } /** * struct nft_ctx - nf_tables rule/set context * * @net: net namespace * @table: the table the chain is contained in * @chain: the chain the rule is contained in * @nla: netlink attributes * @portid: netlink portID of the original message * @seq: netlink sequence number * @flags: modifiers to new request * @family: protocol family * @level: depth of the chains * @report: notify via unicast netlink message * @reg_inited: bitmap of initialised registers */ struct nft_ctx { struct net *net; struct nft_table *table; struct nft_chain *chain; const struct nlattr * const *nla; u32 portid; u32 seq; u16 flags; u8 family; u8 level; bool report; DECLARE_BITMAP(reg_inited, NFT_REG32_NUM); }; enum nft_data_desc_flags { NFT_DATA_DESC_SETELEM = (1 << 0), }; struct nft_data_desc { enum nft_data_types type; unsigned int size; unsigned int len; unsigned int flags; }; int nft_data_init(const struct nft_ctx *ctx, struct nft_data *data, struct nft_data_desc *desc, const struct nlattr *nla); void nft_data_hold(const struct nft_data *data, enum nft_data_types type); void nft_data_release(const struct nft_data *data, enum nft_data_types type); int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data, enum nft_data_types type, unsigned int len); static inline enum nft_data_types nft_dreg_to_type(enum nft_registers reg) { return reg == NFT_REG_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE; } static inline enum nft_registers nft_type_to_reg(enum nft_data_types type) { return type == NFT_DATA_VERDICT ? NFT_REG_VERDICT : NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE; } int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest); int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg); int nft_parse_register_load(const struct nft_ctx *ctx, const struct nlattr *attr, u8 *sreg, u32 len); int nft_parse_register_store(const struct nft_ctx *ctx, const struct nlattr *attr, u8 *dreg, const struct nft_data *data, enum nft_data_types type, unsigned int len); /** * struct nft_userdata - user defined data associated with an object * * @len: length of the data * @data: content * * The presence of user data is indicated in an object specific fashion, * so a length of zero can't occur and the value "len" indicates data * of length len + 1. */ struct nft_userdata { u8 len; unsigned char data[]; }; /* placeholder structure for opaque set element backend representation. */ struct nft_elem_priv { }; /** * struct nft_set_elem - generic representation of set elements * * @key: element key * @key_end: closing element key * @data: element data * @priv: element private data and extensions */ struct nft_set_elem { union { u32 buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)]; struct nft_data val; } key; union { u32 buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)]; struct nft_data val; } key_end; union { u32 buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)]; struct nft_data val; } data; struct nft_elem_priv *priv; }; static inline void *nft_elem_priv_cast(const struct nft_elem_priv *priv) { return (void *)priv; } /** * enum nft_iter_type - nftables set iterator type * * @NFT_ITER_UNSPEC: unspecified, to catch errors * @NFT_ITER_READ: read-only iteration over set elements * @NFT_ITER_UPDATE: iteration under mutex to update set element state */ enum nft_iter_type { NFT_ITER_UNSPEC, NFT_ITER_READ, NFT_ITER_UPDATE, }; struct nft_set; struct nft_set_iter { u8 genmask; enum nft_iter_type type:8; unsigned int count; unsigned int skip; int err; int (*fn)(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv); }; /** * struct nft_set_desc - description of set elements * * @ktype: key type * @klen: key length * @dtype: data type * @dlen: data length * @objtype: object type * @size: number of set elements * @policy: set policy * @gc_int: garbage collector interval * @timeout: element timeout * @field_len: length of each field in concatenation, bytes * @field_count: number of concatenated fields in element * @expr: set must support for expressions */ struct nft_set_desc { u32 ktype; unsigned int klen; u32 dtype; unsigned int dlen; u32 objtype; unsigned int size; u32 policy; u32 gc_int; u64 timeout; u8 field_len[NFT_REG32_COUNT]; u8 field_count; bool expr; }; /** * enum nft_set_class - performance class * * @NFT_SET_CLASS_O_1: constant, O(1) * @NFT_SET_CLASS_O_LOG_N: logarithmic, O(log N) * @NFT_SET_CLASS_O_N: linear, O(N) */ enum nft_set_class { NFT_SET_CLASS_O_1, NFT_SET_CLASS_O_LOG_N, NFT_SET_CLASS_O_N, }; /** * struct nft_set_estimate - estimation of memory and performance * characteristics * * @size: required memory * @lookup: lookup performance class * @space: memory class */ struct nft_set_estimate { u64 size; enum nft_set_class lookup; enum nft_set_class space; }; #define NFT_EXPR_MAXATTR 16 #define NFT_EXPR_SIZE(size) (sizeof(struct nft_expr) + \ ALIGN(size, __alignof__(struct nft_expr))) /** * struct nft_expr - nf_tables expression * * @ops: expression ops * @data: expression private data */ struct nft_expr { const struct nft_expr_ops *ops; unsigned char data[] __attribute__((aligned(__alignof__(u64)))); }; static inline void *nft_expr_priv(const struct nft_expr *expr) { return (void *)expr->data; } struct nft_expr_info; int nft_expr_inner_parse(const struct nft_ctx *ctx, const struct nlattr *nla, struct nft_expr_info *info); int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src, gfp_t gfp); void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr); int nft_expr_dump(struct sk_buff *skb, unsigned int attr, const struct nft_expr *expr, bool reset); bool nft_expr_reduce_bitwise(struct nft_regs_track *track, const struct nft_expr *expr); struct nft_set_ext; /** * struct nft_set_ops - nf_tables set operations * * @lookup: look up an element within the set * @update: update an element if exists, add it if doesn't exist * @delete: delete an element * @insert: insert new element into set * @activate: activate new element in the next generation * @deactivate: lookup for element and deactivate it in the next generation * @flush: deactivate element in the next generation * @remove: remove element from set * @walk: iterate over all set elements * @get: get set elements * @commit: commit set elements * @abort: abort set elements * @privsize: function to return size of set private data * @estimate: estimate the required memory size and the lookup complexity class * @init: initialize private data of new set instance * @destroy: destroy private data of set instance * @gc_init: initialize garbage collection * @elemsize: element private size * * Operations lookup, update and delete have simpler interfaces, are faster * and currently only used in the packet path. All the rest are slower, * control plane functions. */ struct nft_set_ops { bool (*lookup)(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext); bool (*update)(struct nft_set *set, const u32 *key, struct nft_elem_priv * (*new)(struct nft_set *, const struct nft_expr *, struct nft_regs *), const struct nft_expr *expr, struct nft_regs *regs, const struct nft_set_ext **ext); bool (*delete)(const struct nft_set *set, const u32 *key); int (*insert)(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, struct nft_elem_priv **priv); void (*activate)(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv); struct nft_elem_priv * (*deactivate)(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem); void (*flush)(const struct net *net, const struct nft_set *set, struct nft_elem_priv *priv); void (*remove)(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv); void (*walk)(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_iter *iter); struct nft_elem_priv * (*get)(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags); void (*commit)(struct nft_set *set); void (*abort)(const struct nft_set *set); u64 (*privsize)(const struct nlattr * const nla[], const struct nft_set_desc *desc); bool (*estimate)(const struct nft_set_desc *desc, u32 features, struct nft_set_estimate *est); int (*init)(const struct nft_set *set, const struct nft_set_desc *desc, const struct nlattr * const nla[]); void (*destroy)(const struct nft_ctx *ctx, const struct nft_set *set); void (*gc_init)(const struct nft_set *set); unsigned int elemsize; }; /** * struct nft_set_type - nf_tables set type * * @ops: set ops for this type * @features: features supported by the implementation */ struct nft_set_type { const struct nft_set_ops ops; u32 features; }; #define to_set_type(o) container_of(o, struct nft_set_type, ops) struct nft_set_elem_expr { u8 size; unsigned char data[] __attribute__((aligned(__alignof__(struct nft_expr)))); }; #define nft_setelem_expr_at(__elem_expr, __offset) \ ((struct nft_expr *)&__elem_expr->data[__offset]) #define nft_setelem_expr_foreach(__expr, __elem_expr, __size) \ for (__expr = nft_setelem_expr_at(__elem_expr, 0), __size = 0; \ __size < (__elem_expr)->size; \ __size += (__expr)->ops->size, __expr = ((void *)(__expr)) + (__expr)->ops->size) #define NFT_SET_EXPR_MAX 2 /** * struct nft_set - nf_tables set instance * * @list: table set list node * @bindings: list of set bindings * @refs: internal refcounting for async set destruction * @table: table this set belongs to * @net: netnamespace this set belongs to * @name: name of the set * @handle: unique handle of the set * @ktype: key type (numeric type defined by userspace, not used in the kernel) * @dtype: data type (verdict or numeric type defined by userspace) * @objtype: object type (see NFT_OBJECT_* definitions) * @size: maximum set size * @field_len: length of each field in concatenation, bytes * @field_count: number of concatenated fields in element * @use: number of rules references to this set * @nelems: number of elements * @ndeact: number of deactivated elements queued for removal * @timeout: default timeout value in jiffies * @gc_int: garbage collection interval in msecs * @policy: set parameterization (see enum nft_set_policies) * @udlen: user data length * @udata: user data * @pending_update: list of pending update set element * @ops: set ops * @flags: set flags * @dead: set will be freed, never cleared * @genmask: generation mask * @klen: key length * @dlen: data length * @num_exprs: numbers of exprs * @exprs: stateful expression * @catchall_list: list of catch-all set element * @data: private set data */ struct nft_set { struct list_head list; struct list_head bindings; refcount_t refs; struct nft_table *table; possible_net_t net; char *name; u64 handle; u32 ktype; u32 dtype; u32 objtype; u32 size; u8 field_len[NFT_REG32_COUNT]; u8 field_count; u32 use; atomic_t nelems; u32 ndeact; u64 timeout; u32 gc_int; u16 policy; u16 udlen; unsigned char *udata; struct list_head pending_update; /* runtime data below here */ const struct nft_set_ops *ops ____cacheline_aligned; u16 flags:13, dead:1, genmask:2; u8 klen; u8 dlen; u8 num_exprs; struct nft_expr *exprs[NFT_SET_EXPR_MAX]; struct list_head catchall_list; unsigned char data[] __attribute__((aligned(__alignof__(u64)))); }; static inline bool nft_set_is_anonymous(const struct nft_set *set) { return set->flags & NFT_SET_ANONYMOUS; } static inline void *nft_set_priv(const struct nft_set *set) { return (void *)set->data; } static inline enum nft_data_types nft_set_datatype(const struct nft_set *set) { return set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE; } static inline bool nft_set_gc_is_pending(const struct nft_set *s) { return refcount_read(&s->refs) != 1; } static inline struct nft_set *nft_set_container_of(const void *priv) { return (void *)priv - offsetof(struct nft_set, data); } struct nft_set *nft_set_lookup_global(const struct net *net, const struct nft_table *table, const struct nlattr *nla_set_name, const struct nlattr *nla_set_id, u8 genmask); struct nft_set_ext *nft_set_catchall_lookup(const struct net *net, const struct nft_set *set); static inline unsigned long nft_set_gc_interval(const struct nft_set *set) { u32 gc_int = READ_ONCE(set->gc_int); return gc_int ? msecs_to_jiffies(gc_int) : HZ; } /** * struct nft_set_binding - nf_tables set binding * * @list: set bindings list node * @chain: chain containing the rule bound to the set * @flags: set action flags * * A set binding contains all information necessary for validation * of new elements added to a bound set. */ struct nft_set_binding { struct list_head list; const struct nft_chain *chain; u32 flags; }; enum nft_trans_phase; void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set); void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding, enum nft_trans_phase phase); int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding); void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set); /** * enum nft_set_extensions - set extension type IDs * * @NFT_SET_EXT_KEY: element key * @NFT_SET_EXT_KEY_END: upper bound element key, for ranges * @NFT_SET_EXT_DATA: mapping data * @NFT_SET_EXT_FLAGS: element flags * @NFT_SET_EXT_TIMEOUT: element timeout * @NFT_SET_EXT_USERDATA: user data associated with the element * @NFT_SET_EXT_EXPRESSIONS: expressions associated with the element * @NFT_SET_EXT_OBJREF: stateful object reference associated with element * @NFT_SET_EXT_NUM: number of extension types */ enum nft_set_extensions { NFT_SET_EXT_KEY, NFT_SET_EXT_KEY_END, NFT_SET_EXT_DATA, NFT_SET_EXT_FLAGS, NFT_SET_EXT_TIMEOUT, NFT_SET_EXT_USERDATA, NFT_SET_EXT_EXPRESSIONS, NFT_SET_EXT_OBJREF, NFT_SET_EXT_NUM }; /** * struct nft_set_ext_type - set extension type * * @len: fixed part length of the extension * @align: alignment requirements of the extension */ struct nft_set_ext_type { u8 len; u8 align; }; extern const struct nft_set_ext_type nft_set_ext_types[]; /** * struct nft_set_ext_tmpl - set extension template * * @len: length of extension area * @offset: offsets of individual extension types * @ext_len: length of the expected extension(used to sanity check) */ struct nft_set_ext_tmpl { u16 len; u8 offset[NFT_SET_EXT_NUM]; u8 ext_len[NFT_SET_EXT_NUM]; }; /** * struct nft_set_ext - set extensions * * @genmask: generation mask * @offset: offsets of individual extension types * @data: beginning of extension data */ struct nft_set_ext { u8 genmask; u8 offset[NFT_SET_EXT_NUM]; char data[]; }; static inline void nft_set_ext_prepare(struct nft_set_ext_tmpl *tmpl) { memset(tmpl, 0, sizeof(*tmpl)); tmpl->len = sizeof(struct nft_set_ext); } static inline int nft_set_ext_add_length(struct nft_set_ext_tmpl *tmpl, u8 id, unsigned int len) { tmpl->len = ALIGN(tmpl->len, nft_set_ext_types[id].align); if (tmpl->len > U8_MAX) return -EINVAL; tmpl->offset[id] = tmpl->len; tmpl->ext_len[id] = nft_set_ext_types[id].len + len; tmpl->len += tmpl->ext_len[id]; return 0; } static inline int nft_set_ext_add(struct nft_set_ext_tmpl *tmpl, u8 id) { return nft_set_ext_add_length(tmpl, id, 0); } static inline void nft_set_ext_init(struct nft_set_ext *ext, const struct nft_set_ext_tmpl *tmpl) { memcpy(ext->offset, tmpl->offset, sizeof(ext->offset)); } static inline bool __nft_set_ext_exists(const struct nft_set_ext *ext, u8 id) { return !!ext->offset[id]; } static inline bool nft_set_ext_exists(const struct nft_set_ext *ext, u8 id) { return ext && __nft_set_ext_exists(ext, id); } static inline void *nft_set_ext(const struct nft_set_ext *ext, u8 id) { return (void *)ext + ext->offset[id]; } static inline struct nft_data *nft_set_ext_key(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_KEY); } static inline struct nft_data *nft_set_ext_key_end(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_KEY_END); } static inline struct nft_data *nft_set_ext_data(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_DATA); } static inline u8 *nft_set_ext_flags(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_FLAGS); } struct nft_timeout { u64 timeout; u64 expiration; }; static inline struct nft_timeout *nft_set_ext_timeout(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_TIMEOUT); } static inline struct nft_userdata *nft_set_ext_userdata(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_USERDATA); } static inline struct nft_set_elem_expr *nft_set_ext_expr(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_EXPRESSIONS); } static inline bool __nft_set_elem_expired(const struct nft_set_ext *ext, u64 tstamp) { if (!nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) || READ_ONCE(nft_set_ext_timeout(ext)->timeout) == 0) return false; return time_after_eq64(tstamp, READ_ONCE(nft_set_ext_timeout(ext)->expiration)); } static inline bool nft_set_elem_expired(const struct nft_set_ext *ext) { return __nft_set_elem_expired(ext, get_jiffies_64()); } static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set, const struct nft_elem_priv *elem_priv) { return (void *)elem_priv + set->ops->elemsize; } static inline struct nft_object **nft_set_ext_obj(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_OBJREF); } struct nft_expr *nft_set_elem_expr_alloc(const struct nft_ctx *ctx, const struct nft_set *set, const struct nlattr *attr); struct nft_elem_priv *nft_set_elem_init(const struct nft_set *set, const struct nft_set_ext_tmpl *tmpl, const u32 *key, const u32 *key_end, const u32 *data, u64 timeout, u64 expiration, gfp_t gfp); int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set, struct nft_expr *expr_array[]); void nft_set_elem_destroy(const struct nft_set *set, const struct nft_elem_priv *elem_priv, bool destroy_expr); void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, const struct nft_set *set, const struct nft_elem_priv *elem_priv); struct nft_expr_ops; /** * struct nft_expr_type - nf_tables expression type * * @select_ops: function to select nft_expr_ops * @release_ops: release nft_expr_ops * @ops: default ops, used when no select_ops functions is present * @inner_ops: inner ops, used for inner packet operation * @list: used internally * @name: Identifier * @owner: module reference * @policy: netlink attribute policy * @maxattr: highest netlink attribute number * @family: address family for AF-specific types * @flags: expression type flags */ struct nft_expr_type { const struct nft_expr_ops *(*select_ops)(const struct nft_ctx *, const struct nlattr * const tb[]); void (*release_ops)(const struct nft_expr_ops *ops); const struct nft_expr_ops *ops; const struct nft_expr_ops *inner_ops; struct list_head list; const char *name; struct module *owner; const struct nla_policy *policy; unsigned int maxattr; u8 family; u8 flags; }; #define NFT_EXPR_STATEFUL 0x1 #define NFT_EXPR_GC 0x2 enum nft_trans_phase { NFT_TRANS_PREPARE, NFT_TRANS_PREPARE_ERROR, NFT_TRANS_ABORT, NFT_TRANS_COMMIT, NFT_TRANS_RELEASE }; struct nft_flow_rule; struct nft_offload_ctx; /** * struct nft_expr_ops - nf_tables expression operations * * @eval: Expression evaluation function * @clone: Expression clone function * @size: full expression size, including private data size * @init: initialization function * @activate: activate expression in the next generation * @deactivate: deactivate expression in next generation * @destroy: destruction function, called after synchronize_rcu * @destroy_clone: destruction clone function * @dump: function to dump parameters * @validate: validate expression, called during loop detection * @reduce: reduce expression * @gc: garbage collection expression * @offload: hardware offload expression * @offload_action: function to report true/false to allocate one slot or not in the flow * offload array * @offload_stats: function to synchronize hardware stats via updating the counter expression * @type: expression type * @data: extra data to attach to this expression operation */ struct nft_expr_ops { void (*eval)(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); int (*clone)(struct nft_expr *dst, const struct nft_expr *src, gfp_t gfp); unsigned int size; int (*init)(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]); void (*activate)(const struct nft_ctx *ctx, const struct nft_expr *expr); void (*deactivate)(const struct nft_ctx *ctx, const struct nft_expr *expr, enum nft_trans_phase phase); void (*destroy)(const struct nft_ctx *ctx, const struct nft_expr *expr); void (*destroy_clone)(const struct nft_ctx *ctx, const struct nft_expr *expr); int (*dump)(struct sk_buff *skb, const struct nft_expr *expr, bool reset); int (*validate)(const struct nft_ctx *ctx, const struct nft_expr *expr); bool (*reduce)(struct nft_regs_track *track, const struct nft_expr *expr); bool (*gc)(struct net *net, const struct nft_expr *expr); int (*offload)(struct nft_offload_ctx *ctx, struct nft_flow_rule *flow, const struct nft_expr *expr); bool (*offload_action)(const struct nft_expr *expr); void (*offload_stats)(struct nft_expr *expr, const struct flow_stats *stats); const struct nft_expr_type *type; void *data; }; /** * struct nft_rule - nf_tables rule * * @list: used internally * @handle: rule handle * @genmask: generation mask * @dlen: length of expression data * @udata: user data is appended to the rule * @data: expression data */ struct nft_rule { struct list_head list; u64 handle:42, genmask:2, dlen:12, udata:1; unsigned char data[] __attribute__((aligned(__alignof__(struct nft_expr)))); }; static inline struct nft_expr *nft_expr_first(const struct nft_rule *rule) { return (struct nft_expr *)&rule->data[0]; } static inline struct nft_expr *nft_expr_next(const struct nft_expr *expr) { return ((void *)expr) + expr->ops->size; } static inline struct nft_expr *nft_expr_last(const struct nft_rule *rule) { return (struct nft_expr *)&rule->data[rule->dlen]; } static inline bool nft_expr_more(const struct nft_rule *rule, const struct nft_expr *expr) { return expr != nft_expr_last(rule) && expr->ops; } static inline struct nft_userdata *nft_userdata(const struct nft_rule *rule) { return (void *)&rule->data[rule->dlen]; } void nft_rule_expr_activate(const struct nft_ctx *ctx, struct nft_rule *rule); void nft_rule_expr_deactivate(const struct nft_ctx *ctx, struct nft_rule *rule, enum nft_trans_phase phase); void nf_tables_rule_destroy(const struct nft_ctx *ctx, struct nft_rule *rule); static inline void nft_set_elem_update_expr(const struct nft_set_ext *ext, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_set_elem_expr *elem_expr; struct nft_expr *expr; u32 size; if (__nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS)) { elem_expr = nft_set_ext_expr(ext); nft_setelem_expr_foreach(expr, elem_expr, size) { expr->ops->eval(expr, regs, pkt); if (regs->verdict.code == NFT_BREAK) return; } } } /* * The last pointer isn't really necessary, but the compiler isn't able to * determine that the result of nft_expr_last() is always the same since it * can't assume that the dlen value wasn't changed within calls in the loop. */ #define nft_rule_for_each_expr(expr, last, rule) \ for ((expr) = nft_expr_first(rule), (last) = nft_expr_last(rule); \ (expr) != (last); \ (expr) = nft_expr_next(expr)) #define NFT_CHAIN_POLICY_UNSET U8_MAX struct nft_rule_dp { u64 is_last:1, dlen:12, handle:42; /* for tracing */ unsigned char data[] __attribute__((aligned(__alignof__(struct nft_expr)))); }; struct nft_rule_dp_last { struct nft_rule_dp end; /* end of nft_rule_blob marker */ struct rcu_head h; /* call_rcu head */ struct nft_rule_blob *blob; /* ptr to free via call_rcu */ const struct nft_chain *chain; /* for nftables tracing */ }; static inline const struct nft_rule_dp *nft_rule_next(const struct nft_rule_dp *rule) { return (void *)rule + sizeof(*rule) + rule->dlen; } struct nft_rule_blob { unsigned long size; unsigned char data[] __attribute__((aligned(__alignof__(struct nft_rule_dp)))); }; /** * struct nft_chain - nf_tables chain * * @blob_gen_0: rule blob pointer to the current generation * @blob_gen_1: rule blob pointer to the future generation * @rules: list of rules in the chain * @list: used internally * @rhlhead: used internally * @table: table that this chain belongs to * @handle: chain handle * @use: number of jump references to this chain * @flags: bitmask of enum NFTA_CHAIN_FLAGS * @bound: bind or not * @genmask: generation mask * @name: name of the chain * @udlen: user data length * @udata: user data in the chain * @blob_next: rule blob pointer to the next in the chain */ struct nft_chain { struct nft_rule_blob __rcu *blob_gen_0; struct nft_rule_blob __rcu *blob_gen_1; struct list_head rules; struct list_head list; struct rhlist_head rhlhead; struct nft_table *table; u64 handle; u32 use; u8 flags:5, bound:1, genmask:2; char *name; u16 udlen; u8 *udata; /* Only used during control plane commit phase: */ struct nft_rule_blob *blob_next; }; int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain); int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv); int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set); int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); void nf_tables_unbind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); enum nft_chain_types { NFT_CHAIN_T_DEFAULT = 0, NFT_CHAIN_T_ROUTE, NFT_CHAIN_T_NAT, NFT_CHAIN_T_MAX }; /** * struct nft_chain_type - nf_tables chain type info * * @name: name of the type * @type: numeric identifier * @family: address family * @owner: module owner * @hook_mask: mask of valid hooks * @hooks: array of hook functions * @ops_register: base chain register function * @ops_unregister: base chain unregister function */ struct nft_chain_type { const char *name; enum nft_chain_types type; int family; struct module *owner; unsigned int hook_mask; nf_hookfn *hooks[NFT_MAX_HOOKS]; int (*ops_register)(struct net *net, const struct nf_hook_ops *ops); void (*ops_unregister)(struct net *net, const struct nf_hook_ops *ops); }; int nft_chain_validate_dependency(const struct nft_chain *chain, enum nft_chain_types type); int nft_chain_validate_hooks(const struct nft_chain *chain, unsigned int hook_flags); static inline bool nft_chain_binding(const struct nft_chain *chain) { return chain->flags & NFT_CHAIN_BINDING; } static inline bool nft_chain_is_bound(struct nft_chain *chain) { return (chain->flags & NFT_CHAIN_BINDING) && chain->bound; } int nft_chain_add(struct nft_table *table, struct nft_chain *chain); void nft_chain_del(struct nft_chain *chain); void nf_tables_chain_destroy(struct nft_chain *chain); struct nft_stats { u64 bytes; u64 pkts; struct u64_stats_sync syncp; }; struct nft_hook { struct list_head list; struct nf_hook_ops ops; struct rcu_head rcu; }; /** * struct nft_base_chain - nf_tables base chain * * @ops: netfilter hook ops * @hook_list: list of netfilter hooks (for NFPROTO_NETDEV family) * @type: chain type * @policy: default policy * @flags: indicate the base chain disabled or not * @stats: per-cpu chain stats * @chain: the chain * @flow_block: flow block (for hardware offload) */ struct nft_base_chain { struct nf_hook_ops ops; struct list_head hook_list; const struct nft_chain_type *type; u8 policy; u8 flags; struct nft_stats __percpu *stats; struct nft_chain chain; struct flow_block flow_block; }; static inline struct nft_base_chain *nft_base_chain(const struct nft_chain *chain) { return container_of(chain, struct nft_base_chain, chain); } static inline bool nft_is_base_chain(const struct nft_chain *chain) { return chain->flags & NFT_CHAIN_BASE; } int __nft_release_basechain(struct nft_ctx *ctx); unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv); static inline bool nft_use_inc(u32 *use) { if (*use == UINT_MAX) return false; (*use)++; return true; } static inline void nft_use_dec(u32 *use) { WARN_ON_ONCE((*use)-- == 0); } /* For error and abort path: restore use counter to previous state. */ static inline void nft_use_inc_restore(u32 *use) { WARN_ON_ONCE(!nft_use_inc(use)); } #define nft_use_dec_restore nft_use_dec /** * struct nft_table - nf_tables table * * @list: used internally * @chains_ht: chains in the table * @chains: same, for stable walks * @sets: sets in the table * @objects: stateful objects in the table * @flowtables: flow tables in the table * @hgenerator: handle generator state * @handle: table handle * @use: number of chain references to this table * @family:address family * @flags: table flag (see enum nft_table_flags) * @genmask: generation mask * @nlpid: netlink port ID * @name: name of the table * @udlen: length of the user data * @udata: user data * @validate_state: internal, set when transaction adds jumps */ struct nft_table { struct list_head list; struct rhltable chains_ht; struct list_head chains; struct list_head sets; struct list_head objects; struct list_head flowtables; u64 hgenerator; u64 handle; u32 use; u16 family:6, flags:8, genmask:2; u32 nlpid; char *name; u16 udlen; u8 *udata; u8 validate_state; }; static inline bool nft_table_has_owner(const struct nft_table *table) { return table->flags & NFT_TABLE_F_OWNER; } static inline bool nft_table_is_orphan(const struct nft_table *table) { return (table->flags & (NFT_TABLE_F_OWNER | NFT_TABLE_F_PERSIST)) == NFT_TABLE_F_PERSIST; } static inline bool nft_base_chain_netdev(int family, u32 hooknum) { return family == NFPROTO_NETDEV || (family == NFPROTO_INET && hooknum == NF_INET_INGRESS); } void nft_register_chain_type(const struct nft_chain_type *); void nft_unregister_chain_type(const struct nft_chain_type *); int nft_register_expr(struct nft_expr_type *); void nft_unregister_expr(struct nft_expr_type *); int nft_verdict_dump(struct sk_buff *skb, int type, const struct nft_verdict *v); /** * struct nft_object_hash_key - key to lookup nft_object * * @name: name of the stateful object to look up * @table: table the object belongs to */ struct nft_object_hash_key { const char *name; const struct nft_table *table; }; /** * struct nft_object - nf_tables stateful object * * @list: table stateful object list node * @rhlhead: nft_objname_ht node * @key: keys that identify this object * @genmask: generation mask * @use: number of references to this stateful object * @handle: unique object handle * @udlen: length of user data * @udata: user data * @ops: object operations * @data: object data, layout depends on type */ struct nft_object { struct list_head list; struct rhlist_head rhlhead; struct nft_object_hash_key key; u32 genmask:2; u32 use; u64 handle; u16 udlen; u8 *udata; /* runtime data below here */ const struct nft_object_ops *ops ____cacheline_aligned; unsigned char data[] __attribute__((aligned(__alignof__(u64)))); }; static inline void *nft_obj_data(const struct nft_object *obj) { return (void *)obj->data; } #define nft_expr_obj(expr) *((struct nft_object **)nft_expr_priv(expr)) struct nft_object *nft_obj_lookup(const struct net *net, const struct nft_table *table, const struct nlattr *nla, u32 objtype, u8 genmask); void nft_obj_notify(struct net *net, const struct nft_table *table, struct nft_object *obj, u32 portid, u32 seq, int event, u16 flags, int family, int report, gfp_t gfp); /** * struct nft_object_type - stateful object type * * @select_ops: function to select nft_object_ops * @ops: default ops, used when no select_ops functions is present * @list: list node in list of object types * @type: stateful object numeric type * @owner: module owner * @maxattr: maximum netlink attribute * @family: address family for AF-specific object types * @policy: netlink attribute policy */ struct nft_object_type { const struct nft_object_ops *(*select_ops)(const struct nft_ctx *, const struct nlattr * const tb[]); const struct nft_object_ops *ops; struct list_head list; u32 type; unsigned int maxattr; u8 family; struct module *owner; const struct nla_policy *policy; }; /** * struct nft_object_ops - stateful object operations * * @eval: stateful object evaluation function * @size: stateful object size * @init: initialize object from netlink attributes * @destroy: release existing stateful object * @dump: netlink dump stateful object * @update: update stateful object * @type: pointer to object type */ struct nft_object_ops { void (*eval)(struct nft_object *obj, struct nft_regs *regs, const struct nft_pktinfo *pkt); unsigned int size; int (*init)(const struct nft_ctx *ctx, const struct nlattr *const tb[], struct nft_object *obj); void (*destroy)(const struct nft_ctx *ctx, struct nft_object *obj); int (*dump)(struct sk_buff *skb, struct nft_object *obj, bool reset); void (*update)(struct nft_object *obj, struct nft_object *newobj); const struct nft_object_type *type; }; int nft_register_obj(struct nft_object_type *obj_type); void nft_unregister_obj(struct nft_object_type *obj_type); #define NFT_NETDEVICE_MAX 256 /** * struct nft_flowtable - nf_tables flow table * * @list: flow table list node in table list * @table: the table the flow table is contained in * @name: name of this flow table * @hooknum: hook number * @ops_len: number of hooks in array * @genmask: generation mask * @use: number of references to this flow table * @handle: unique object handle * @hook_list: hook list for hooks per net_device in flowtables * @data: rhashtable and garbage collector */ struct nft_flowtable { struct list_head list; struct nft_table *table; char *name; int hooknum; int ops_len; u32 genmask:2; u32 use; u64 handle; /* runtime data below here */ struct list_head hook_list ____cacheline_aligned; struct nf_flowtable data; }; struct nft_flowtable *nft_flowtable_lookup(const struct net *net, const struct nft_table *table, const struct nlattr *nla, u8 genmask); void nf_tables_deactivate_flowtable(const struct nft_ctx *ctx, struct nft_flowtable *flowtable, enum nft_trans_phase phase); void nft_register_flowtable_type(struct nf_flowtable_type *type); void nft_unregister_flowtable_type(struct nf_flowtable_type *type); /** * struct nft_traceinfo - nft tracing information and state * * @trace: other struct members are initialised * @nf_trace: copy of skb->nf_trace before rule evaluation * @type: event type (enum nft_trace_types) * @skbid: hash of skb to be used as trace id * @packet_dumped: packet headers sent in a previous traceinfo message * @basechain: base chain currently processed */ struct nft_traceinfo { bool trace; bool nf_trace; bool packet_dumped; enum nft_trace_types type:8; u32 skbid; const struct nft_base_chain *basechain; }; void nft_trace_init(struct nft_traceinfo *info, const struct nft_pktinfo *pkt, const struct nft_chain *basechain); void nft_trace_notify(const struct nft_pktinfo *pkt, const struct nft_verdict *verdict, const struct nft_rule_dp *rule, struct nft_traceinfo *info); #define MODULE_ALIAS_NFT_CHAIN(family, name) \ MODULE_ALIAS("nft-chain-" __stringify(family) "-" name) #define MODULE_ALIAS_NFT_AF_EXPR(family, name) \ MODULE_ALIAS("nft-expr-" __stringify(family) "-" name) #define MODULE_ALIAS_NFT_EXPR(name) \ MODULE_ALIAS("nft-expr-" name) #define MODULE_ALIAS_NFT_OBJ(type) \ MODULE_ALIAS("nft-obj-" __stringify(type)) #if IS_ENABLED(CONFIG_NF_TABLES) /* * The gencursor defines two generations, the currently active and the * next one. Objects contain a bitmask of 2 bits specifying the generations * they're active in. A set bit means they're inactive in the generation * represented by that bit. * * New objects start out as inactive in the current and active in the * next generation. When committing the ruleset the bitmask is cleared, * meaning they're active in all generations. When removing an object, * it is set inactive in the next generation. After committing the ruleset, * the objects are removed. */ static inline unsigned int nft_gencursor_next(const struct net *net) { return net->nft.gencursor + 1 == 1 ? 1 : 0; } static inline u8 nft_genmask_next(const struct net *net) { return 1 << nft_gencursor_next(net); } static inline u8 nft_genmask_cur(const struct net *net) { /* Use READ_ONCE() to prevent refetching the value for atomicity */ return 1 << READ_ONCE(net->nft.gencursor); } #define NFT_GENMASK_ANY ((1 << 0) | (1 << 1)) /* * Generic transaction helpers */ /* Check if this object is currently active. */ #define nft_is_active(__net, __obj) \ (((__obj)->genmask & nft_genmask_cur(__net)) == 0) /* Check if this object is active in the next generation. */ #define nft_is_active_next(__net, __obj) \ (((__obj)->genmask & nft_genmask_next(__net)) == 0) /* This object becomes active in the next generation. */ #define nft_activate_next(__net, __obj) \ (__obj)->genmask = nft_genmask_cur(__net) /* This object becomes inactive in the next generation. */ #define nft_deactivate_next(__net, __obj) \ (__obj)->genmask = nft_genmask_next(__net) /* After committing the ruleset, clear the stale generation bit. */ #define nft_clear(__net, __obj) \ (__obj)->genmask &= ~nft_genmask_next(__net) #define nft_active_genmask(__obj, __genmask) \ !((__obj)->genmask & __genmask) /* * Set element transaction helpers */ static inline bool nft_set_elem_active(const struct nft_set_ext *ext, u8 genmask) { return !(ext->genmask & genmask); } static inline void nft_set_elem_change_active(const struct net *net, const struct nft_set *set, struct nft_set_ext *ext) { ext->genmask ^= nft_genmask_next(net); } #endif /* IS_ENABLED(CONFIG_NF_TABLES) */ #define NFT_SET_ELEM_DEAD_MASK (1 << 2) #if defined(__LITTLE_ENDIAN_BITFIELD) #define NFT_SET_ELEM_DEAD_BIT 2 #elif defined(__BIG_ENDIAN_BITFIELD) #define NFT_SET_ELEM_DEAD_BIT (BITS_PER_LONG - BITS_PER_BYTE + 2) #else #error #endif static inline void nft_set_elem_dead(struct nft_set_ext *ext) { unsigned long *word = (unsigned long *)ext; BUILD_BUG_ON(offsetof(struct nft_set_ext, genmask) != 0); set_bit(NFT_SET_ELEM_DEAD_BIT, word); } static inline int nft_set_elem_is_dead(const struct nft_set_ext *ext) { unsigned long *word = (unsigned long *)ext; BUILD_BUG_ON(offsetof(struct nft_set_ext, genmask) != 0); return test_bit(NFT_SET_ELEM_DEAD_BIT, word); } /** * struct nft_trans - nf_tables object update in transaction * * @list: used internally * @net: struct net * @table: struct nft_table the object resides in * @msg_type: message type * @seq: netlink sequence number * @flags: modifiers to new request * @report: notify via unicast netlink message * @put_net: net needs to be put * * This is the information common to all objects in the transaction, * this must always be the first member of derived sub-types. */ struct nft_trans { struct list_head list; struct net *net; struct nft_table *table; int msg_type; u32 seq; u16 flags; u8 report:1; u8 put_net:1; }; /** * struct nft_trans_binding - nf_tables object with binding support in transaction * @nft_trans: base structure, MUST be first member * @binding_list: list of objects with possible bindings * * This is the base type used by objects that can be bound to a chain. */ struct nft_trans_binding { struct nft_trans nft_trans; struct list_head binding_list; }; struct nft_trans_rule { struct nft_trans nft_trans; struct nft_rule *rule; struct nft_chain *chain; struct nft_flow_rule *flow; u32 rule_id; bool bound; }; #define nft_trans_container_rule(trans) \ container_of(trans, struct nft_trans_rule, nft_trans) #define nft_trans_rule(trans) \ nft_trans_container_rule(trans)->rule #define nft_trans_flow_rule(trans) \ nft_trans_container_rule(trans)->flow #define nft_trans_rule_id(trans) \ nft_trans_container_rule(trans)->rule_id #define nft_trans_rule_bound(trans) \ nft_trans_container_rule(trans)->bound #define nft_trans_rule_chain(trans) \ nft_trans_container_rule(trans)->chain struct nft_trans_set { struct nft_trans_binding nft_trans_binding; struct list_head list_trans_newset; struct nft_set *set; u32 set_id; u32 gc_int; u64 timeout; bool update; bool bound; u32 size; }; #define nft_trans_container_set(t) \ container_of(t, struct nft_trans_set, nft_trans_binding.nft_trans) #define nft_trans_set(trans) \ nft_trans_container_set(trans)->set #define nft_trans_set_id(trans) \ nft_trans_container_set(trans)->set_id #define nft_trans_set_bound(trans) \ nft_trans_container_set(trans)->bound #define nft_trans_set_update(trans) \ nft_trans_container_set(trans)->update #define nft_trans_set_timeout(trans) \ nft_trans_container_set(trans)->timeout #define nft_trans_set_gc_int(trans) \ nft_trans_container_set(trans)->gc_int #define nft_trans_set_size(trans) \ nft_trans_container_set(trans)->size struct nft_trans_chain { struct nft_trans_binding nft_trans_binding; struct nft_chain *chain; char *name; struct nft_stats __percpu *stats; u8 policy; bool update; bool bound; u32 chain_id; struct nft_base_chain *basechain; struct list_head hook_list; }; #define nft_trans_container_chain(t) \ container_of(t, struct nft_trans_chain, nft_trans_binding.nft_trans) #define nft_trans_chain(trans) \ nft_trans_container_chain(trans)->chain #define nft_trans_chain_update(trans) \ nft_trans_container_chain(trans)->update #define nft_trans_chain_name(trans) \ nft_trans_container_chain(trans)->name #define nft_trans_chain_stats(trans) \ nft_trans_container_chain(trans)->stats #define nft_trans_chain_policy(trans) \ nft_trans_container_chain(trans)->policy #define nft_trans_chain_bound(trans) \ nft_trans_container_chain(trans)->bound #define nft_trans_chain_id(trans) \ nft_trans_container_chain(trans)->chain_id #define nft_trans_basechain(trans) \ nft_trans_container_chain(trans)->basechain #define nft_trans_chain_hooks(trans) \ nft_trans_container_chain(trans)->hook_list struct nft_trans_table { struct nft_trans nft_trans; bool update; }; #define nft_trans_container_table(trans) \ container_of(trans, struct nft_trans_table, nft_trans) #define nft_trans_table_update(trans) \ nft_trans_container_table(trans)->update enum nft_trans_elem_flags { NFT_TRANS_UPD_TIMEOUT = (1 << 0), NFT_TRANS_UPD_EXPIRATION = (1 << 1), }; struct nft_elem_update { u64 timeout; u64 expiration; u8 flags; }; struct nft_trans_one_elem { struct nft_elem_priv *priv; struct nft_elem_update *update; }; struct nft_trans_elem { struct nft_trans nft_trans; struct nft_set *set; bool bound; unsigned int nelems; struct nft_trans_one_elem elems[] __counted_by(nelems); }; #define nft_trans_container_elem(t) \ container_of(t, struct nft_trans_elem, nft_trans) #define nft_trans_elem_set(trans) \ nft_trans_container_elem(trans)->set #define nft_trans_elem_set_bound(trans) \ nft_trans_container_elem(trans)->bound struct nft_trans_obj { struct nft_trans nft_trans; struct nft_object *obj; struct nft_object *newobj; bool update; }; #define nft_trans_container_obj(t) \ container_of(t, struct nft_trans_obj, nft_trans) #define nft_trans_obj(trans) \ nft_trans_container_obj(trans)->obj #define nft_trans_obj_newobj(trans) \ nft_trans_container_obj(trans)->newobj #define nft_trans_obj_update(trans) \ nft_trans_container_obj(trans)->update struct nft_trans_flowtable { struct nft_trans nft_trans; struct nft_flowtable *flowtable; struct list_head hook_list; u32 flags; bool update; }; #define nft_trans_container_flowtable(t) \ container_of(t, struct nft_trans_flowtable, nft_trans) #define nft_trans_flowtable(trans) \ nft_trans_container_flowtable(trans)->flowtable #define nft_trans_flowtable_update(trans) \ nft_trans_container_flowtable(trans)->update #define nft_trans_flowtable_hooks(trans) \ nft_trans_container_flowtable(trans)->hook_list #define nft_trans_flowtable_flags(trans) \ nft_trans_container_flowtable(trans)->flags #define NFT_TRANS_GC_BATCHCOUNT 256 struct nft_trans_gc { struct list_head list; struct net *net; struct nft_set *set; u32 seq; u16 count; struct nft_elem_priv *priv[NFT_TRANS_GC_BATCHCOUNT]; struct rcu_head rcu; }; static inline void nft_ctx_update(struct nft_ctx *ctx, const struct nft_trans *trans) { switch (trans->msg_type) { case NFT_MSG_NEWRULE: case NFT_MSG_DELRULE: case NFT_MSG_DESTROYRULE: ctx->chain = nft_trans_rule_chain(trans); break; case NFT_MSG_NEWCHAIN: case NFT_MSG_DELCHAIN: case NFT_MSG_DESTROYCHAIN: ctx->chain = nft_trans_chain(trans); break; default: ctx->chain = NULL; break; } ctx->net = trans->net; ctx->table = trans->table; ctx->family = trans->table->family; ctx->report = trans->report; ctx->flags = trans->flags; ctx->seq = trans->seq; } struct nft_trans_gc *nft_trans_gc_alloc(struct nft_set *set, unsigned int gc_seq, gfp_t gfp); void nft_trans_gc_destroy(struct nft_trans_gc *trans); struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc, unsigned int gc_seq, gfp_t gfp); void nft_trans_gc_queue_async_done(struct nft_trans_gc *gc); struct nft_trans_gc *nft_trans_gc_queue_sync(struct nft_trans_gc *gc, gfp_t gfp); void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans); void nft_trans_gc_elem_add(struct nft_trans_gc *gc, void *priv); struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc, unsigned int gc_seq); struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc); void nft_setelem_data_deactivate(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv); int __init nft_chain_filter_init(void); void nft_chain_filter_fini(void); void __init nft_chain_route_init(void); void nft_chain_route_fini(void); void nf_tables_trans_destroy_flush_work(void); int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result); __be64 nf_jiffies64_to_msecs(u64 input); #ifdef CONFIG_MODULES __printf(2, 3) int nft_request_module(struct net *net, const char *fmt, ...); #else static inline int nft_request_module(struct net *net, const char *fmt, ...) { return -ENOENT; } #endif struct nftables_pernet { struct list_head tables; struct list_head commit_list; struct list_head commit_set_list; struct list_head binding_list; struct list_head module_list; struct list_head notify_list; struct mutex commit_mutex; u64 table_handle; u64 tstamp; unsigned int base_seq; unsigned int gc_seq; u8 validate_state; }; extern unsigned int nf_tables_net_id; static inline struct nftables_pernet *nft_pernet(const struct net *net) { return net_generic(net, nf_tables_net_id); } static inline u64 nft_net_tstamp(const struct net *net) { return nft_pernet(net)->tstamp; } #define __NFT_REDUCE_READONLY 1UL #define NFT_REDUCE_READONLY (void *)__NFT_REDUCE_READONLY static inline bool nft_reduce_is_readonly(const struct nft_expr *expr) { return expr->ops->reduce == NFT_REDUCE_READONLY; } void nft_reg_track_update(struct nft_regs_track *track, const struct nft_expr *expr, u8 dreg, u8 len); void nft_reg_track_cancel(struct nft_regs_track *track, u8 dreg, u8 len); void __nft_reg_track_cancel(struct nft_regs_track *track, u8 dreg); static inline bool nft_reg_track_cmp(struct nft_regs_track *track, const struct nft_expr *expr, u8 dreg) { return track->regs[dreg].selector && track->regs[dreg].selector->ops == expr->ops && track->regs[dreg].num_reg == 0; } #endif /* _NET_NF_TABLES_H */ |
| 180 180 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/backing-dev.h * * low-level device information and state which is propagated up through * to high-level code. */ #ifndef _LINUX_BACKING_DEV_H #define _LINUX_BACKING_DEV_H #include <linux/kernel.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/device.h> #include <linux/writeback.h> #include <linux/backing-dev-defs.h> #include <linux/slab.h> static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi) { kref_get(&bdi->refcnt); return bdi; } struct backing_dev_info *bdi_get_by_id(u64 id); void bdi_put(struct backing_dev_info *bdi); __printf(2, 3) int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...); __printf(2, 0) int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args); void bdi_set_owner(struct backing_dev_info *bdi, struct device *owner); void bdi_unregister(struct backing_dev_info *bdi); struct backing_dev_info *bdi_alloc(int node_id); void wb_start_background_writeback(struct bdi_writeback *wb); void wb_workfn(struct work_struct *work); void wb_wait_for_completion(struct wb_completion *done); extern spinlock_t bdi_lock; extern struct list_head bdi_list; extern struct workqueue_struct *bdi_wq; static inline bool wb_has_dirty_io(struct bdi_writeback *wb) { return test_bit(WB_has_dirty_io, &wb->state); } static inline bool bdi_has_dirty_io(struct backing_dev_info *bdi) { /* * @bdi->tot_write_bandwidth is guaranteed to be > 0 if there are * any dirty wbs. See wb_update_write_bandwidth(). */ return atomic_long_read(&bdi->tot_write_bandwidth); } static inline void wb_stat_mod(struct bdi_writeback *wb, enum wb_stat_item item, s64 amount) { percpu_counter_add_batch(&wb->stat[item], amount, WB_STAT_BATCH); } static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { wb_stat_mod(wb, item, 1); } static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { wb_stat_mod(wb, item, -1); } static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { return percpu_counter_read_positive(&wb->stat[item]); } static inline s64 wb_stat_sum(struct bdi_writeback *wb, enum wb_stat_item item) { return percpu_counter_sum_positive(&wb->stat[item]); } extern void wb_writeout_inc(struct bdi_writeback *wb); /* * maximal error of a stat counter. */ static inline unsigned long wb_stat_error(void) { #ifdef CONFIG_SMP return nr_cpu_ids * WB_STAT_BATCH; #else return 1; #endif } /* BDI ratio is expressed as part per 1000000 for finer granularity. */ #define BDI_RATIO_SCALE 10000 u64 bdi_get_min_bytes(struct backing_dev_info *bdi); u64 bdi_get_max_bytes(struct backing_dev_info *bdi); int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio); int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); int bdi_set_min_ratio_no_scale(struct backing_dev_info *bdi, unsigned int min_ratio); int bdi_set_max_ratio_no_scale(struct backing_dev_info *bdi, unsigned int max_ratio); int bdi_set_min_bytes(struct backing_dev_info *bdi, u64 min_bytes); int bdi_set_max_bytes(struct backing_dev_info *bdi, u64 max_bytes); int bdi_set_strict_limit(struct backing_dev_info *bdi, unsigned int strict_limit); /* * Flags in backing_dev_info::capability * * BDI_CAP_WRITEBACK: Supports dirty page writeback, and dirty pages * should contribute to accounting * BDI_CAP_WRITEBACK_ACCT: Automatically account writeback pages * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold */ #define BDI_CAP_WRITEBACK (1 << 0) #define BDI_CAP_WRITEBACK_ACCT (1 << 1) #define BDI_CAP_STRICTLIMIT (1 << 2) extern struct backing_dev_info noop_backing_dev_info; int bdi_init(struct backing_dev_info *bdi); /** * writeback_in_progress - determine whether there is writeback in progress * @wb: bdi_writeback of interest * * Determine whether there is writeback waiting to be handled against a * bdi_writeback. */ static inline bool writeback_in_progress(struct bdi_writeback *wb) { return test_bit(WB_writeback_running, &wb->state); } struct backing_dev_info *inode_to_bdi(struct inode *inode); static inline bool mapping_can_writeback(struct address_space *mapping) { return inode_to_bdi(mapping->host)->capabilities & BDI_CAP_WRITEBACK; } #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css); struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp); void wb_memcg_offline(struct mem_cgroup *memcg); void wb_blkcg_offline(struct cgroup_subsys_state *css); /** * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode * @inode: inode of interest * * Cgroup writeback requires support from the filesystem. Also, both memcg and * iocg have to be on the default hierarchy. Test whether all conditions are * met. * * Note that the test result may change dynamically on the same inode * depending on how memcg and iocg are configured. */ static inline bool inode_cgwb_enabled(struct inode *inode) { struct backing_dev_info *bdi = inode_to_bdi(inode); return cgroup_subsys_on_dfl(memory_cgrp_subsys) && cgroup_subsys_on_dfl(io_cgrp_subsys) && (bdi->capabilities & BDI_CAP_WRITEBACK) && (inode->i_sb->s_iflags & SB_I_CGROUPWB); } /** * wb_find_current - find wb for %current on a bdi * @bdi: bdi of interest * * Find the wb of @bdi which matches both the memcg and blkcg of %current. * Must be called under rcu_read_lock() which protects the returend wb. * NULL if not found. */ static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi) { struct cgroup_subsys_state *memcg_css; struct bdi_writeback *wb; memcg_css = task_css(current, memory_cgrp_id); if (!memcg_css->parent) return &bdi->wb; wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); /* * %current's blkcg equals the effective blkcg of its memcg. No * need to use the relatively expensive cgroup_get_e_css(). */ if (likely(wb && wb->blkcg_css == task_css(current, io_cgrp_id))) return wb; return NULL; } /** * wb_get_create_current - get or create wb for %current on a bdi * @bdi: bdi of interest * @gfp: allocation mask * * Equivalent to wb_get_create() on %current's memcg. This function is * called from a relatively hot path and optimizes the common cases using * wb_find_current(). */ static inline struct bdi_writeback * wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp) { struct bdi_writeback *wb; rcu_read_lock(); wb = wb_find_current(bdi); if (wb && unlikely(!wb_tryget(wb))) wb = NULL; rcu_read_unlock(); if (unlikely(!wb)) { struct cgroup_subsys_state *memcg_css; memcg_css = task_get_css(current, memory_cgrp_id); wb = wb_get_create(bdi, memcg_css, gfp); css_put(memcg_css); } return wb; } /** * inode_to_wb - determine the wb of an inode * @inode: inode of interest * * Returns the wb @inode is currently associated with. The caller must be * holding either @inode->i_lock, the i_pages lock, or the * associated wb's list_lock. */ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode) { #ifdef CONFIG_LOCKDEP WARN_ON_ONCE(debug_locks && (!lockdep_is_held(&inode->i_lock) && !lockdep_is_held(&inode->i_mapping->i_pages.xa_lock) && !lockdep_is_held(&inode->i_wb->list_lock))); #endif return inode->i_wb; } static inline struct bdi_writeback *inode_to_wb_wbc( struct inode *inode, struct writeback_control *wbc) { /* * If wbc does not have inode attached, it means cgroup writeback was * disabled when wbc started. Just use the default wb in that case. */ return wbc->wb ? wbc->wb : &inode_to_bdi(inode)->wb; } /** * unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction * @inode: target inode * @cookie: output param, to be passed to the end function * * The caller wants to access the wb associated with @inode but isn't * holding inode->i_lock, the i_pages lock or wb->list_lock. This * function determines the wb associated with @inode and ensures that the * association doesn't change until the transaction is finished with * unlocked_inode_to_wb_end(). * * The caller must call unlocked_inode_to_wb_end() with *@cookie afterwards and * can't sleep during the transaction. IRQs may or may not be disabled on * return. */ static inline struct bdi_writeback * unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) { rcu_read_lock(); /* * Paired with store_release in inode_switch_wbs_work_fn() and * ensures that we see the new wb if we see cleared I_WB_SWITCH. */ cookie->locked = smp_load_acquire(&inode->i_state) & I_WB_SWITCH; if (unlikely(cookie->locked)) xa_lock_irqsave(&inode->i_mapping->i_pages, cookie->flags); /* * Protected by either !I_WB_SWITCH + rcu_read_lock() or the i_pages * lock. inode_to_wb() will bark. Deref directly. */ return inode->i_wb; } /** * unlocked_inode_to_wb_end - end inode wb access transaction * @inode: target inode * @cookie: @cookie from unlocked_inode_to_wb_begin() */ static inline void unlocked_inode_to_wb_end(struct inode *inode, struct wb_lock_cookie *cookie) { if (unlikely(cookie->locked)) xa_unlock_irqrestore(&inode->i_mapping->i_pages, cookie->flags); rcu_read_unlock(); } #else /* CONFIG_CGROUP_WRITEBACK */ static inline bool inode_cgwb_enabled(struct inode *inode) { return false; } static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi) { return &bdi->wb; } static inline struct bdi_writeback * wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp) { return &bdi->wb; } static inline struct bdi_writeback *inode_to_wb(struct inode *inode) { return &inode_to_bdi(inode)->wb; } static inline struct bdi_writeback *inode_to_wb_wbc( struct inode *inode, struct writeback_control *wbc) { return inode_to_wb(inode); } static inline struct bdi_writeback * unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) { return inode_to_wb(inode); } static inline void unlocked_inode_to_wb_end(struct inode *inode, struct wb_lock_cookie *cookie) { } static inline void wb_memcg_offline(struct mem_cgroup *memcg) { } static inline void wb_blkcg_offline(struct cgroup_subsys_state *css) { } #endif /* CONFIG_CGROUP_WRITEBACK */ const char *bdi_dev_name(struct backing_dev_info *bdi); #endif /* _LINUX_BACKING_DEV_H */ |
| 978 979 979 974 979 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/common.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include <linux/uaccess.h> #include <linux/slab.h> #include <linux/security.h> #include <linux/string_helpers.h> #include "common.h" /* String table for operation mode. */ const char * const tomoyo_mode[TOMOYO_CONFIG_MAX_MODE] = { [TOMOYO_CONFIG_DISABLED] = "disabled", [TOMOYO_CONFIG_LEARNING] = "learning", [TOMOYO_CONFIG_PERMISSIVE] = "permissive", [TOMOYO_CONFIG_ENFORCING] = "enforcing" }; /* String table for /sys/kernel/security/tomoyo/profile */ const char * const tomoyo_mac_keywords[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX] = { /* CONFIG::file group */ [TOMOYO_MAC_FILE_EXECUTE] = "execute", [TOMOYO_MAC_FILE_OPEN] = "open", [TOMOYO_MAC_FILE_CREATE] = "create", [TOMOYO_MAC_FILE_UNLINK] = "unlink", [TOMOYO_MAC_FILE_GETATTR] = "getattr", [TOMOYO_MAC_FILE_MKDIR] = "mkdir", [TOMOYO_MAC_FILE_RMDIR] = "rmdir", [TOMOYO_MAC_FILE_MKFIFO] = "mkfifo", [TOMOYO_MAC_FILE_MKSOCK] = "mksock", [TOMOYO_MAC_FILE_TRUNCATE] = "truncate", [TOMOYO_MAC_FILE_SYMLINK] = "symlink", [TOMOYO_MAC_FILE_MKBLOCK] = "mkblock", [TOMOYO_MAC_FILE_MKCHAR] = "mkchar", [TOMOYO_MAC_FILE_LINK] = "link", [TOMOYO_MAC_FILE_RENAME] = "rename", [TOMOYO_MAC_FILE_CHMOD] = "chmod", [TOMOYO_MAC_FILE_CHOWN] = "chown", [TOMOYO_MAC_FILE_CHGRP] = "chgrp", [TOMOYO_MAC_FILE_IOCTL] = "ioctl", [TOMOYO_MAC_FILE_CHROOT] = "chroot", [TOMOYO_MAC_FILE_MOUNT] = "mount", [TOMOYO_MAC_FILE_UMOUNT] = "unmount", [TOMOYO_MAC_FILE_PIVOT_ROOT] = "pivot_root", /* CONFIG::network group */ [TOMOYO_MAC_NETWORK_INET_STREAM_BIND] = "inet_stream_bind", [TOMOYO_MAC_NETWORK_INET_STREAM_LISTEN] = "inet_stream_listen", [TOMOYO_MAC_NETWORK_INET_STREAM_CONNECT] = "inet_stream_connect", [TOMOYO_MAC_NETWORK_INET_DGRAM_BIND] = "inet_dgram_bind", [TOMOYO_MAC_NETWORK_INET_DGRAM_SEND] = "inet_dgram_send", [TOMOYO_MAC_NETWORK_INET_RAW_BIND] = "inet_raw_bind", [TOMOYO_MAC_NETWORK_INET_RAW_SEND] = "inet_raw_send", [TOMOYO_MAC_NETWORK_UNIX_STREAM_BIND] = "unix_stream_bind", [TOMOYO_MAC_NETWORK_UNIX_STREAM_LISTEN] = "unix_stream_listen", [TOMOYO_MAC_NETWORK_UNIX_STREAM_CONNECT] = "unix_stream_connect", [TOMOYO_MAC_NETWORK_UNIX_DGRAM_BIND] = "unix_dgram_bind", [TOMOYO_MAC_NETWORK_UNIX_DGRAM_SEND] = "unix_dgram_send", [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_BIND] = "unix_seqpacket_bind", [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_LISTEN] = "unix_seqpacket_listen", [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_CONNECT] = "unix_seqpacket_connect", /* CONFIG::misc group */ [TOMOYO_MAC_ENVIRON] = "env", /* CONFIG group */ [TOMOYO_MAX_MAC_INDEX + TOMOYO_MAC_CATEGORY_FILE] = "file", [TOMOYO_MAX_MAC_INDEX + TOMOYO_MAC_CATEGORY_NETWORK] = "network", [TOMOYO_MAX_MAC_INDEX + TOMOYO_MAC_CATEGORY_MISC] = "misc", }; /* String table for conditions. */ const char * const tomoyo_condition_keyword[TOMOYO_MAX_CONDITION_KEYWORD] = { [TOMOYO_TASK_UID] = "task.uid", [TOMOYO_TASK_EUID] = "task.euid", [TOMOYO_TASK_SUID] = "task.suid", [TOMOYO_TASK_FSUID] = "task.fsuid", [TOMOYO_TASK_GID] = "task.gid", [TOMOYO_TASK_EGID] = "task.egid", [TOMOYO_TASK_SGID] = "task.sgid", [TOMOYO_TASK_FSGID] = "task.fsgid", [TOMOYO_TASK_PID] = "task.pid", [TOMOYO_TASK_PPID] = "task.ppid", [TOMOYO_EXEC_ARGC] = "exec.argc", [TOMOYO_EXEC_ENVC] = "exec.envc", [TOMOYO_TYPE_IS_SOCKET] = "socket", [TOMOYO_TYPE_IS_SYMLINK] = "symlink", [TOMOYO_TYPE_IS_FILE] = "file", [TOMOYO_TYPE_IS_BLOCK_DEV] = "block", [TOMOYO_TYPE_IS_DIRECTORY] = "directory", [TOMOYO_TYPE_IS_CHAR_DEV] = "char", [TOMOYO_TYPE_IS_FIFO] = "fifo", [TOMOYO_MODE_SETUID] = "setuid", [TOMOYO_MODE_SETGID] = "setgid", [TOMOYO_MODE_STICKY] = "sticky", [TOMOYO_MODE_OWNER_READ] = "owner_read", [TOMOYO_MODE_OWNER_WRITE] = "owner_write", [TOMOYO_MODE_OWNER_EXECUTE] = "owner_execute", [TOMOYO_MODE_GROUP_READ] = "group_read", [TOMOYO_MODE_GROUP_WRITE] = "group_write", [TOMOYO_MODE_GROUP_EXECUTE] = "group_execute", [TOMOYO_MODE_OTHERS_READ] = "others_read", [TOMOYO_MODE_OTHERS_WRITE] = "others_write", [TOMOYO_MODE_OTHERS_EXECUTE] = "others_execute", [TOMOYO_EXEC_REALPATH] = "exec.realpath", [TOMOYO_SYMLINK_TARGET] = "symlink.target", [TOMOYO_PATH1_UID] = "path1.uid", [TOMOYO_PATH1_GID] = "path1.gid", [TOMOYO_PATH1_INO] = "path1.ino", [TOMOYO_PATH1_MAJOR] = "path1.major", [TOMOYO_PATH1_MINOR] = "path1.minor", [TOMOYO_PATH1_PERM] = "path1.perm", [TOMOYO_PATH1_TYPE] = "path1.type", [TOMOYO_PATH1_DEV_MAJOR] = "path1.dev_major", [TOMOYO_PATH1_DEV_MINOR] = "path1.dev_minor", [TOMOYO_PATH2_UID] = "path2.uid", [TOMOYO_PATH2_GID] = "path2.gid", [TOMOYO_PATH2_INO] = "path2.ino", [TOMOYO_PATH2_MAJOR] = "path2.major", [TOMOYO_PATH2_MINOR] = "path2.minor", [TOMOYO_PATH2_PERM] = "path2.perm", [TOMOYO_PATH2_TYPE] = "path2.type", [TOMOYO_PATH2_DEV_MAJOR] = "path2.dev_major", [TOMOYO_PATH2_DEV_MINOR] = "path2.dev_minor", [TOMOYO_PATH1_PARENT_UID] = "path1.parent.uid", [TOMOYO_PATH1_PARENT_GID] = "path1.parent.gid", [TOMOYO_PATH1_PARENT_INO] = "path1.parent.ino", [TOMOYO_PATH1_PARENT_PERM] = "path1.parent.perm", [TOMOYO_PATH2_PARENT_UID] = "path2.parent.uid", [TOMOYO_PATH2_PARENT_GID] = "path2.parent.gid", [TOMOYO_PATH2_PARENT_INO] = "path2.parent.ino", [TOMOYO_PATH2_PARENT_PERM] = "path2.parent.perm", }; /* String table for PREFERENCE keyword. */ static const char * const tomoyo_pref_keywords[TOMOYO_MAX_PREF] = { [TOMOYO_PREF_MAX_AUDIT_LOG] = "max_audit_log", [TOMOYO_PREF_MAX_LEARNING_ENTRY] = "max_learning_entry", }; /* String table for path operation. */ const char * const tomoyo_path_keyword[TOMOYO_MAX_PATH_OPERATION] = { [TOMOYO_TYPE_EXECUTE] = "execute", [TOMOYO_TYPE_READ] = "read", [TOMOYO_TYPE_WRITE] = "write", [TOMOYO_TYPE_APPEND] = "append", [TOMOYO_TYPE_UNLINK] = "unlink", [TOMOYO_TYPE_GETATTR] = "getattr", [TOMOYO_TYPE_RMDIR] = "rmdir", [TOMOYO_TYPE_TRUNCATE] = "truncate", [TOMOYO_TYPE_SYMLINK] = "symlink", [TOMOYO_TYPE_CHROOT] = "chroot", [TOMOYO_TYPE_UMOUNT] = "unmount", }; /* String table for socket's operation. */ const char * const tomoyo_socket_keyword[TOMOYO_MAX_NETWORK_OPERATION] = { [TOMOYO_NETWORK_BIND] = "bind", [TOMOYO_NETWORK_LISTEN] = "listen", [TOMOYO_NETWORK_CONNECT] = "connect", [TOMOYO_NETWORK_SEND] = "send", }; /* String table for categories. */ static const char * const tomoyo_category_keywords [TOMOYO_MAX_MAC_CATEGORY_INDEX] = { [TOMOYO_MAC_CATEGORY_FILE] = "file", [TOMOYO_MAC_CATEGORY_NETWORK] = "network", [TOMOYO_MAC_CATEGORY_MISC] = "misc", }; /* Permit policy management by non-root user? */ static bool tomoyo_manage_by_non_root; /* Utility functions. */ /** * tomoyo_addprintf - strncat()-like-snprintf(). * * @buffer: Buffer to write to. Must be '\0'-terminated. * @len: Size of @buffer. * @fmt: The printf()'s format string, followed by parameters. * * Returns nothing. */ __printf(3, 4) static void tomoyo_addprintf(char *buffer, int len, const char *fmt, ...) { va_list args; const int pos = strlen(buffer); va_start(args, fmt); vsnprintf(buffer + pos, len - pos - 1, fmt, args); va_end(args); } /** * tomoyo_flush - Flush queued string to userspace's buffer. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns true if all data was flushed, false otherwise. */ static bool tomoyo_flush(struct tomoyo_io_buffer *head) { while (head->r.w_pos) { const char *w = head->r.w[0]; size_t len = strlen(w); if (len) { if (len > head->read_user_buf_avail) len = head->read_user_buf_avail; if (!len) return false; if (copy_to_user(head->read_user_buf, w, len)) return false; head->read_user_buf_avail -= len; head->read_user_buf += len; w += len; } head->r.w[0] = w; if (*w) return false; /* Add '\0' for audit logs and query. */ if (head->poll) { if (!head->read_user_buf_avail || copy_to_user(head->read_user_buf, "", 1)) return false; head->read_user_buf_avail--; head->read_user_buf++; } head->r.w_pos--; for (len = 0; len < head->r.w_pos; len++) head->r.w[len] = head->r.w[len + 1]; } head->r.avail = 0; return true; } /** * tomoyo_set_string - Queue string to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * @string: String to print. * * Note that @string has to be kept valid until @head is kfree()d. * This means that char[] allocated on stack memory cannot be passed to * this function. Use tomoyo_io_printf() for char[] allocated on stack memory. */ static void tomoyo_set_string(struct tomoyo_io_buffer *head, const char *string) { if (head->r.w_pos < TOMOYO_MAX_IO_READ_QUEUE) { head->r.w[head->r.w_pos++] = string; tomoyo_flush(head); } else WARN_ON(1); } static void tomoyo_io_printf(struct tomoyo_io_buffer *head, const char *fmt, ...) __printf(2, 3); /** * tomoyo_io_printf - printf() to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * @fmt: The printf()'s format string, followed by parameters. */ static void tomoyo_io_printf(struct tomoyo_io_buffer *head, const char *fmt, ...) { va_list args; size_t len; size_t pos = head->r.avail; int size = head->readbuf_size - pos; if (size <= 0) return; va_start(args, fmt); len = vsnprintf(head->read_buf + pos, size, fmt, args) + 1; va_end(args); if (pos + len >= head->readbuf_size) { WARN_ON(1); return; } head->r.avail += len; tomoyo_set_string(head, head->read_buf + pos); } /** * tomoyo_set_space - Put a space to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static void tomoyo_set_space(struct tomoyo_io_buffer *head) { tomoyo_set_string(head, " "); } /** * tomoyo_set_lf - Put a line feed to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static bool tomoyo_set_lf(struct tomoyo_io_buffer *head) { tomoyo_set_string(head, "\n"); return !head->r.w_pos; } /** * tomoyo_set_slash - Put a shash to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static void tomoyo_set_slash(struct tomoyo_io_buffer *head) { tomoyo_set_string(head, "/"); } /* List of namespaces. */ LIST_HEAD(tomoyo_namespace_list); /* True if namespace other than tomoyo_kernel_namespace is defined. */ static bool tomoyo_namespace_enabled; /** * tomoyo_init_policy_namespace - Initialize namespace. * * @ns: Pointer to "struct tomoyo_policy_namespace". * * Returns nothing. */ void tomoyo_init_policy_namespace(struct tomoyo_policy_namespace *ns) { unsigned int idx; for (idx = 0; idx < TOMOYO_MAX_ACL_GROUPS; idx++) INIT_LIST_HEAD(&ns->acl_group[idx]); for (idx = 0; idx < TOMOYO_MAX_GROUP; idx++) INIT_LIST_HEAD(&ns->group_list[idx]); for (idx = 0; idx < TOMOYO_MAX_POLICY; idx++) INIT_LIST_HEAD(&ns->policy_list[idx]); ns->profile_version = 20150505; tomoyo_namespace_enabled = !list_empty(&tomoyo_namespace_list); list_add_tail_rcu(&ns->namespace_list, &tomoyo_namespace_list); } /** * tomoyo_print_namespace - Print namespace header. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static void tomoyo_print_namespace(struct tomoyo_io_buffer *head) { if (!tomoyo_namespace_enabled) return; tomoyo_set_string(head, container_of(head->r.ns, struct tomoyo_policy_namespace, namespace_list)->name); tomoyo_set_space(head); } /** * tomoyo_print_name_union - Print a tomoyo_name_union. * * @head: Pointer to "struct tomoyo_io_buffer". * @ptr: Pointer to "struct tomoyo_name_union". */ static void tomoyo_print_name_union(struct tomoyo_io_buffer *head, const struct tomoyo_name_union *ptr) { tomoyo_set_space(head); if (ptr->group) { tomoyo_set_string(head, "@"); tomoyo_set_string(head, ptr->group->group_name->name); } else { tomoyo_set_string(head, ptr->filename->name); } } /** * tomoyo_print_name_union_quoted - Print a tomoyo_name_union with a quote. * * @head: Pointer to "struct tomoyo_io_buffer". * @ptr: Pointer to "struct tomoyo_name_union". * * Returns nothing. */ static void tomoyo_print_name_union_quoted(struct tomoyo_io_buffer *head, const struct tomoyo_name_union *ptr) { if (ptr->group) { tomoyo_set_string(head, "@"); tomoyo_set_string(head, ptr->group->group_name->name); } else { tomoyo_set_string(head, "\""); tomoyo_set_string(head, ptr->filename->name); tomoyo_set_string(head, "\""); } } /** * tomoyo_print_number_union_nospace - Print a tomoyo_number_union without a space. * * @head: Pointer to "struct tomoyo_io_buffer". * @ptr: Pointer to "struct tomoyo_number_union". * * Returns nothing. */ static void tomoyo_print_number_union_nospace (struct tomoyo_io_buffer *head, const struct tomoyo_number_union *ptr) { if (ptr->group) { tomoyo_set_string(head, "@"); tomoyo_set_string(head, ptr->group->group_name->name); } else { int i; unsigned long min = ptr->values[0]; const unsigned long max = ptr->values[1]; u8 min_type = ptr->value_type[0]; const u8 max_type = ptr->value_type[1]; char buffer[128]; buffer[0] = '\0'; for (i = 0; i < 2; i++) { switch (min_type) { case TOMOYO_VALUE_TYPE_HEXADECIMAL: tomoyo_addprintf(buffer, sizeof(buffer), "0x%lX", min); break; case TOMOYO_VALUE_TYPE_OCTAL: tomoyo_addprintf(buffer, sizeof(buffer), "0%lo", min); break; default: tomoyo_addprintf(buffer, sizeof(buffer), "%lu", min); break; } if (min == max && min_type == max_type) break; tomoyo_addprintf(buffer, sizeof(buffer), "-"); min_type = max_type; min = max; } tomoyo_io_printf(head, "%s", buffer); } } /** * tomoyo_print_number_union - Print a tomoyo_number_union. * * @head: Pointer to "struct tomoyo_io_buffer". * @ptr: Pointer to "struct tomoyo_number_union". * * Returns nothing. */ static void tomoyo_print_number_union(struct tomoyo_io_buffer *head, const struct tomoyo_number_union *ptr) { tomoyo_set_space(head); tomoyo_print_number_union_nospace(head, ptr); } /** * tomoyo_assign_profile - Create a new profile. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @profile: Profile number to create. * * Returns pointer to "struct tomoyo_profile" on success, NULL otherwise. */ static struct tomoyo_profile *tomoyo_assign_profile (struct tomoyo_policy_namespace *ns, const unsigned int profile) { struct tomoyo_profile *ptr; struct tomoyo_profile *entry; if (profile >= TOMOYO_MAX_PROFILES) return NULL; ptr = ns->profile_ptr[profile]; if (ptr) return ptr; entry = kzalloc(sizeof(*entry), GFP_NOFS | __GFP_NOWARN); if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; ptr = ns->profile_ptr[profile]; if (!ptr && tomoyo_memory_ok(entry)) { ptr = entry; ptr->default_config = TOMOYO_CONFIG_DISABLED | TOMOYO_CONFIG_WANT_GRANT_LOG | TOMOYO_CONFIG_WANT_REJECT_LOG; memset(ptr->config, TOMOYO_CONFIG_USE_DEFAULT, sizeof(ptr->config)); ptr->pref[TOMOYO_PREF_MAX_AUDIT_LOG] = CONFIG_SECURITY_TOMOYO_MAX_AUDIT_LOG; ptr->pref[TOMOYO_PREF_MAX_LEARNING_ENTRY] = CONFIG_SECURITY_TOMOYO_MAX_ACCEPT_ENTRY; mb(); /* Avoid out-of-order execution. */ ns->profile_ptr[profile] = ptr; entry = NULL; } mutex_unlock(&tomoyo_policy_lock); out: kfree(entry); return ptr; } /** * tomoyo_profile - Find a profile. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @profile: Profile number to find. * * Returns pointer to "struct tomoyo_profile". */ struct tomoyo_profile *tomoyo_profile(const struct tomoyo_policy_namespace *ns, const u8 profile) { static struct tomoyo_profile tomoyo_null_profile; struct tomoyo_profile *ptr = ns->profile_ptr[profile]; if (!ptr) ptr = &tomoyo_null_profile; return ptr; } /** * tomoyo_find_yesno - Find values for specified keyword. * * @string: String to check. * @find: Name of keyword. * * Returns 1 if "@find=yes" was found, 0 if "@find=no" was found, -1 otherwise. */ static s8 tomoyo_find_yesno(const char *string, const char *find) { const char *cp = strstr(string, find); if (cp) { cp += strlen(find); if (!strncmp(cp, "=yes", 4)) return 1; else if (!strncmp(cp, "=no", 3)) return 0; } return -1; } /** * tomoyo_set_uint - Set value for specified preference. * * @i: Pointer to "unsigned int". * @string: String to check. * @find: Name of keyword. * * Returns nothing. */ static void tomoyo_set_uint(unsigned int *i, const char *string, const char *find) { const char *cp = strstr(string, find); if (cp) sscanf(cp + strlen(find), "=%u", i); } /** * tomoyo_set_mode - Set mode for specified profile. * * @name: Name of functionality. * @value: Mode for @name. * @profile: Pointer to "struct tomoyo_profile". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_set_mode(char *name, const char *value, struct tomoyo_profile *profile) { u8 i; u8 config; if (!strcmp(name, "CONFIG")) { i = TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX; config = profile->default_config; } else if (tomoyo_str_starts(&name, "CONFIG::")) { config = 0; for (i = 0; i < TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX; i++) { int len = 0; if (i < TOMOYO_MAX_MAC_INDEX) { const u8 c = tomoyo_index2category[i]; const char *category = tomoyo_category_keywords[c]; len = strlen(category); if (strncmp(name, category, len) || name[len++] != ':' || name[len++] != ':') continue; } if (strcmp(name + len, tomoyo_mac_keywords[i])) continue; config = profile->config[i]; break; } if (i == TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX) return -EINVAL; } else { return -EINVAL; } if (strstr(value, "use_default")) { config = TOMOYO_CONFIG_USE_DEFAULT; } else { u8 mode; for (mode = 0; mode < 4; mode++) if (strstr(value, tomoyo_mode[mode])) /* * Update lower 3 bits in order to distinguish * 'config' from 'TOMOYO_CONFIG_USE_DEFAULT'. */ config = (config & ~7) | mode; if (config != TOMOYO_CONFIG_USE_DEFAULT) { switch (tomoyo_find_yesno(value, "grant_log")) { case 1: config |= TOMOYO_CONFIG_WANT_GRANT_LOG; break; case 0: config &= ~TOMOYO_CONFIG_WANT_GRANT_LOG; break; } switch (tomoyo_find_yesno(value, "reject_log")) { case 1: config |= TOMOYO_CONFIG_WANT_REJECT_LOG; break; case 0: config &= ~TOMOYO_CONFIG_WANT_REJECT_LOG; break; } } } if (i < TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX) profile->config[i] = config; else if (config != TOMOYO_CONFIG_USE_DEFAULT) profile->default_config = config; return 0; } /** * tomoyo_write_profile - Write profile table. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_write_profile(struct tomoyo_io_buffer *head) { char *data = head->write_buf; unsigned int i; char *cp; struct tomoyo_profile *profile; if (sscanf(data, "PROFILE_VERSION=%u", &head->w.ns->profile_version) == 1) return 0; i = simple_strtoul(data, &cp, 10); if (*cp != '-') return -EINVAL; data = cp + 1; profile = tomoyo_assign_profile(head->w.ns, i); if (!profile) return -EINVAL; cp = strchr(data, '='); if (!cp) return -EINVAL; *cp++ = '\0'; if (!strcmp(data, "COMMENT")) { static DEFINE_SPINLOCK(lock); const struct tomoyo_path_info *new_comment = tomoyo_get_name(cp); const struct tomoyo_path_info *old_comment; if (!new_comment) return -ENOMEM; spin_lock(&lock); old_comment = profile->comment; profile->comment = new_comment; spin_unlock(&lock); tomoyo_put_name(old_comment); return 0; } if (!strcmp(data, "PREFERENCE")) { for (i = 0; i < TOMOYO_MAX_PREF; i++) tomoyo_set_uint(&profile->pref[i], cp, tomoyo_pref_keywords[i]); return 0; } return tomoyo_set_mode(data, cp, profile); } /** * tomoyo_print_config - Print mode for specified functionality. * * @head: Pointer to "struct tomoyo_io_buffer". * @config: Mode for that functionality. * * Returns nothing. * * Caller prints functionality's name. */ static void tomoyo_print_config(struct tomoyo_io_buffer *head, const u8 config) { tomoyo_io_printf(head, "={ mode=%s grant_log=%s reject_log=%s }\n", tomoyo_mode[config & 3], str_yes_no(config & TOMOYO_CONFIG_WANT_GRANT_LOG), str_yes_no(config & TOMOYO_CONFIG_WANT_REJECT_LOG)); } /** * tomoyo_read_profile - Read profile table. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static void tomoyo_read_profile(struct tomoyo_io_buffer *head) { u8 index; struct tomoyo_policy_namespace *ns = container_of(head->r.ns, typeof(*ns), namespace_list); const struct tomoyo_profile *profile; if (head->r.eof) return; next: index = head->r.index; profile = ns->profile_ptr[index]; switch (head->r.step) { case 0: tomoyo_print_namespace(head); tomoyo_io_printf(head, "PROFILE_VERSION=%u\n", ns->profile_version); head->r.step++; break; case 1: for ( ; head->r.index < TOMOYO_MAX_PROFILES; head->r.index++) if (ns->profile_ptr[head->r.index]) break; if (head->r.index == TOMOYO_MAX_PROFILES) { head->r.eof = true; return; } head->r.step++; break; case 2: { u8 i; const struct tomoyo_path_info *comment = profile->comment; tomoyo_print_namespace(head); tomoyo_io_printf(head, "%u-COMMENT=", index); tomoyo_set_string(head, comment ? comment->name : ""); tomoyo_set_lf(head); tomoyo_print_namespace(head); tomoyo_io_printf(head, "%u-PREFERENCE={ ", index); for (i = 0; i < TOMOYO_MAX_PREF; i++) tomoyo_io_printf(head, "%s=%u ", tomoyo_pref_keywords[i], profile->pref[i]); tomoyo_set_string(head, "}\n"); head->r.step++; } break; case 3: { tomoyo_print_namespace(head); tomoyo_io_printf(head, "%u-%s", index, "CONFIG"); tomoyo_print_config(head, profile->default_config); head->r.bit = 0; head->r.step++; } break; case 4: for ( ; head->r.bit < TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX; head->r.bit++) { const u8 i = head->r.bit; const u8 config = profile->config[i]; if (config == TOMOYO_CONFIG_USE_DEFAULT) continue; tomoyo_print_namespace(head); if (i < TOMOYO_MAX_MAC_INDEX) tomoyo_io_printf(head, "%u-CONFIG::%s::%s", index, tomoyo_category_keywords [tomoyo_index2category[i]], tomoyo_mac_keywords[i]); else tomoyo_io_printf(head, "%u-CONFIG::%s", index, tomoyo_mac_keywords[i]); tomoyo_print_config(head, config); head->r.bit++; break; } if (head->r.bit == TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX) { head->r.index++; head->r.step = 1; } break; } if (tomoyo_flush(head)) goto next; } /** * tomoyo_same_manager - Check for duplicated "struct tomoyo_manager" entry. * * @a: Pointer to "struct tomoyo_acl_head". * @b: Pointer to "struct tomoyo_acl_head". * * Returns true if @a == @b, false otherwise. */ static bool tomoyo_same_manager(const struct tomoyo_acl_head *a, const struct tomoyo_acl_head *b) { return container_of(a, struct tomoyo_manager, head)->manager == container_of(b, struct tomoyo_manager, head)->manager; } /** * tomoyo_update_manager_entry - Add a manager entry. * * @manager: The path to manager or the domainnamme. * @is_delete: True if it is a delete request. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_update_manager_entry(const char *manager, const bool is_delete) { struct tomoyo_manager e = { }; struct tomoyo_acl_param param = { /* .ns = &tomoyo_kernel_namespace, */ .is_delete = is_delete, .list = &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER], }; int error = is_delete ? -ENOENT : -ENOMEM; if (!tomoyo_correct_domain(manager) && !tomoyo_correct_word(manager)) return -EINVAL; e.manager = tomoyo_get_name(manager); if (e.manager) { error = tomoyo_update_policy(&e.head, sizeof(e), ¶m, tomoyo_same_manager); tomoyo_put_name(e.manager); } return error; } /** * tomoyo_write_manager - Write manager policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_write_manager(struct tomoyo_io_buffer *head) { char *data = head->write_buf; if (!strcmp(data, "manage_by_non_root")) { tomoyo_manage_by_non_root = !head->w.is_delete; return 0; } return tomoyo_update_manager_entry(data, head->w.is_delete); } /** * tomoyo_read_manager - Read manager policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Caller holds tomoyo_read_lock(). */ static void tomoyo_read_manager(struct tomoyo_io_buffer *head) { if (head->r.eof) return; list_for_each_cookie(head->r.acl, &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER]) { struct tomoyo_manager *ptr = list_entry(head->r.acl, typeof(*ptr), head.list); if (ptr->head.is_deleted) continue; if (!tomoyo_flush(head)) return; tomoyo_set_string(head, ptr->manager->name); tomoyo_set_lf(head); } head->r.eof = true; } /** * tomoyo_manager - Check whether the current process is a policy manager. * * Returns true if the current process is permitted to modify policy * via /sys/kernel/security/tomoyo/ interface. * * Caller holds tomoyo_read_lock(). */ static bool tomoyo_manager(void) { struct tomoyo_manager *ptr; const char *exe; const struct task_struct *task = current; const struct tomoyo_path_info *domainname = tomoyo_domain()->domainname; bool found = IS_ENABLED(CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING); if (!tomoyo_policy_loaded) return true; if (!tomoyo_manage_by_non_root && (!uid_eq(task->cred->uid, GLOBAL_ROOT_UID) || !uid_eq(task->cred->euid, GLOBAL_ROOT_UID))) return false; exe = tomoyo_get_exe(); if (!exe) return false; list_for_each_entry_rcu(ptr, &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER], head.list, srcu_read_lock_held(&tomoyo_ss)) { if (!ptr->head.is_deleted && (!tomoyo_pathcmp(domainname, ptr->manager) || !strcmp(exe, ptr->manager->name))) { found = true; break; } } if (!found) { /* Reduce error messages. */ static pid_t last_pid; const pid_t pid = current->pid; if (last_pid != pid) { pr_warn("%s ( %s ) is not permitted to update policies.\n", domainname->name, exe); last_pid = pid; } } kfree(exe); return found; } static struct tomoyo_domain_info *tomoyo_find_domain_by_qid (unsigned int serial); /** * tomoyo_select_domain - Parse select command. * * @head: Pointer to "struct tomoyo_io_buffer". * @data: String to parse. * * Returns true on success, false otherwise. * * Caller holds tomoyo_read_lock(). */ static bool tomoyo_select_domain(struct tomoyo_io_buffer *head, const char *data) { unsigned int pid; struct tomoyo_domain_info *domain = NULL; bool global_pid = false; if (strncmp(data, "select ", 7)) return false; data += 7; if (sscanf(data, "pid=%u", &pid) == 1 || (global_pid = true, sscanf(data, "global-pid=%u", &pid) == 1)) { struct task_struct *p; rcu_read_lock(); if (global_pid) p = find_task_by_pid_ns(pid, &init_pid_ns); else p = find_task_by_vpid(pid); if (p) domain = tomoyo_task(p)->domain_info; rcu_read_unlock(); } else if (!strncmp(data, "domain=", 7)) { if (tomoyo_domain_def(data + 7)) domain = tomoyo_find_domain(data + 7); } else if (sscanf(data, "Q=%u", &pid) == 1) { domain = tomoyo_find_domain_by_qid(pid); } else return false; head->w.domain = domain; /* Accessing read_buf is safe because head->io_sem is held. */ if (!head->read_buf) return true; /* Do nothing if open(O_WRONLY). */ memset(&head->r, 0, sizeof(head->r)); head->r.print_this_domain_only = true; if (domain) head->r.domain = &domain->list; else head->r.eof = true; tomoyo_io_printf(head, "# select %s\n", data); if (domain && domain->is_deleted) tomoyo_io_printf(head, "# This is a deleted domain.\n"); return true; } /** * tomoyo_same_task_acl - Check for duplicated "struct tomoyo_task_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b, false otherwise. */ static bool tomoyo_same_task_acl(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { const struct tomoyo_task_acl *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_task_acl *p2 = container_of(b, typeof(*p2), head); return p1->domainname == p2->domainname; } /** * tomoyo_write_task - Update task related list. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_write_task(struct tomoyo_acl_param *param) { int error = -EINVAL; if (tomoyo_str_starts(¶m->data, "manual_domain_transition ")) { struct tomoyo_task_acl e = { .head.type = TOMOYO_TYPE_MANUAL_TASK_ACL, .domainname = tomoyo_get_domainname(param), }; if (e.domainname) error = tomoyo_update_domain(&e.head, sizeof(e), param, tomoyo_same_task_acl, NULL); tomoyo_put_name(e.domainname); } return error; } /** * tomoyo_delete_domain - Delete a domain. * * @domainname: The name of domain. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_delete_domain(char *domainname) { struct tomoyo_domain_info *domain; struct tomoyo_path_info name; name.name = domainname; tomoyo_fill_path_info(&name); if (mutex_lock_interruptible(&tomoyo_policy_lock)) return -EINTR; /* Is there an active domain? */ list_for_each_entry_rcu(domain, &tomoyo_domain_list, list, srcu_read_lock_held(&tomoyo_ss)) { /* Never delete tomoyo_kernel_domain */ if (domain == &tomoyo_kernel_domain) continue; if (domain->is_deleted || tomoyo_pathcmp(domain->domainname, &name)) continue; domain->is_deleted = true; break; } mutex_unlock(&tomoyo_policy_lock); return 0; } /** * tomoyo_write_domain2 - Write domain policy. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @list: Pointer to "struct list_head". * @data: Policy to be interpreted. * @is_delete: True if it is a delete request. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_write_domain2(struct tomoyo_policy_namespace *ns, struct list_head *list, char *data, const bool is_delete) { struct tomoyo_acl_param param = { .ns = ns, .list = list, .data = data, .is_delete = is_delete, }; static const struct { const char *keyword; int (*write)(struct tomoyo_acl_param *param); } tomoyo_callback[5] = { { "file ", tomoyo_write_file }, { "network inet ", tomoyo_write_inet_network }, { "network unix ", tomoyo_write_unix_network }, { "misc ", tomoyo_write_misc }, { "task ", tomoyo_write_task }, }; u8 i; for (i = 0; i < ARRAY_SIZE(tomoyo_callback); i++) { if (!tomoyo_str_starts(¶m.data, tomoyo_callback[i].keyword)) continue; return tomoyo_callback[i].write(¶m); } return -EINVAL; } /* String table for domain flags. */ const char * const tomoyo_dif[TOMOYO_MAX_DOMAIN_INFO_FLAGS] = { [TOMOYO_DIF_QUOTA_WARNED] = "quota_exceeded\n", [TOMOYO_DIF_TRANSITION_FAILED] = "transition_failed\n", }; /** * tomoyo_write_domain - Write domain policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_write_domain(struct tomoyo_io_buffer *head) { char *data = head->write_buf; struct tomoyo_policy_namespace *ns; struct tomoyo_domain_info *domain = head->w.domain; const bool is_delete = head->w.is_delete; bool is_select = !is_delete && tomoyo_str_starts(&data, "select "); unsigned int idx; if (*data == '<') { int ret = 0; domain = NULL; if (is_delete) ret = tomoyo_delete_domain(data); else if (is_select) domain = tomoyo_find_domain(data); else domain = tomoyo_assign_domain(data, false); head->w.domain = domain; return ret; } if (!domain) return -EINVAL; ns = domain->ns; if (sscanf(data, "use_profile %u", &idx) == 1 && idx < TOMOYO_MAX_PROFILES) { if (!tomoyo_policy_loaded || ns->profile_ptr[idx]) if (!is_delete) domain->profile = (u8) idx; return 0; } if (sscanf(data, "use_group %u\n", &idx) == 1 && idx < TOMOYO_MAX_ACL_GROUPS) { if (!is_delete) set_bit(idx, domain->group); else clear_bit(idx, domain->group); return 0; } for (idx = 0; idx < TOMOYO_MAX_DOMAIN_INFO_FLAGS; idx++) { const char *cp = tomoyo_dif[idx]; if (strncmp(data, cp, strlen(cp) - 1)) continue; domain->flags[idx] = !is_delete; return 0; } return tomoyo_write_domain2(ns, &domain->acl_info_list, data, is_delete); } /** * tomoyo_print_condition - Print condition part. * * @head: Pointer to "struct tomoyo_io_buffer". * @cond: Pointer to "struct tomoyo_condition". * * Returns true on success, false otherwise. */ static bool tomoyo_print_condition(struct tomoyo_io_buffer *head, const struct tomoyo_condition *cond) { switch (head->r.cond_step) { case 0: head->r.cond_index = 0; head->r.cond_step++; if (cond->transit) { tomoyo_set_space(head); tomoyo_set_string(head, cond->transit->name); } fallthrough; case 1: { const u16 condc = cond->condc; const struct tomoyo_condition_element *condp = (typeof(condp)) (cond + 1); const struct tomoyo_number_union *numbers_p = (typeof(numbers_p)) (condp + condc); const struct tomoyo_name_union *names_p = (typeof(names_p)) (numbers_p + cond->numbers_count); const struct tomoyo_argv *argv = (typeof(argv)) (names_p + cond->names_count); const struct tomoyo_envp *envp = (typeof(envp)) (argv + cond->argc); u16 skip; for (skip = 0; skip < head->r.cond_index; skip++) { const u8 left = condp->left; const u8 right = condp->right; condp++; switch (left) { case TOMOYO_ARGV_ENTRY: argv++; continue; case TOMOYO_ENVP_ENTRY: envp++; continue; case TOMOYO_NUMBER_UNION: numbers_p++; break; } switch (right) { case TOMOYO_NAME_UNION: names_p++; break; case TOMOYO_NUMBER_UNION: numbers_p++; break; } } while (head->r.cond_index < condc) { const u8 match = condp->equals; const u8 left = condp->left; const u8 right = condp->right; if (!tomoyo_flush(head)) return false; condp++; head->r.cond_index++; tomoyo_set_space(head); switch (left) { case TOMOYO_ARGV_ENTRY: tomoyo_io_printf(head, "exec.argv[%lu]%s=\"", argv->index, argv->is_not ? "!" : ""); tomoyo_set_string(head, argv->value->name); tomoyo_set_string(head, "\""); argv++; continue; case TOMOYO_ENVP_ENTRY: tomoyo_set_string(head, "exec.envp[\""); tomoyo_set_string(head, envp->name->name); tomoyo_io_printf(head, "\"]%s=", envp->is_not ? "!" : ""); if (envp->value) { tomoyo_set_string(head, "\""); tomoyo_set_string(head, envp->value->name); tomoyo_set_string(head, "\""); } else { tomoyo_set_string(head, "NULL"); } envp++; continue; case TOMOYO_NUMBER_UNION: tomoyo_print_number_union_nospace (head, numbers_p++); break; default: tomoyo_set_string(head, tomoyo_condition_keyword[left]); break; } tomoyo_set_string(head, match ? "=" : "!="); switch (right) { case TOMOYO_NAME_UNION: tomoyo_print_name_union_quoted (head, names_p++); break; case TOMOYO_NUMBER_UNION: tomoyo_print_number_union_nospace (head, numbers_p++); break; default: tomoyo_set_string(head, tomoyo_condition_keyword[right]); break; } } } head->r.cond_step++; fallthrough; case 2: if (!tomoyo_flush(head)) break; head->r.cond_step++; fallthrough; case 3: if (cond->grant_log != TOMOYO_GRANTLOG_AUTO) tomoyo_io_printf(head, " grant_log=%s", str_yes_no(cond->grant_log == TOMOYO_GRANTLOG_YES)); tomoyo_set_lf(head); return true; } return false; } /** * tomoyo_set_group - Print "acl_group " header keyword and category name. * * @head: Pointer to "struct tomoyo_io_buffer". * @category: Category name. * * Returns nothing. */ static void tomoyo_set_group(struct tomoyo_io_buffer *head, const char *category) { if (head->type == TOMOYO_EXCEPTIONPOLICY) { tomoyo_print_namespace(head); tomoyo_io_printf(head, "acl_group %u ", head->r.acl_group_index); } tomoyo_set_string(head, category); } /** * tomoyo_print_entry - Print an ACL entry. * * @head: Pointer to "struct tomoyo_io_buffer". * @acl: Pointer to an ACL entry. * * Returns true on success, false otherwise. */ static bool tomoyo_print_entry(struct tomoyo_io_buffer *head, struct tomoyo_acl_info *acl) { const u8 acl_type = acl->type; bool first = true; u8 bit; if (head->r.print_cond_part) goto print_cond_part; if (acl->is_deleted) return true; if (!tomoyo_flush(head)) return false; else if (acl_type == TOMOYO_TYPE_PATH_ACL) { struct tomoyo_path_acl *ptr = container_of(acl, typeof(*ptr), head); const u16 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_PATH_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (head->r.print_transition_related_only && bit != TOMOYO_TYPE_EXECUTE) continue; if (first) { tomoyo_set_group(head, "file "); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_path_keyword[bit]); } if (first) return true; tomoyo_print_name_union(head, &ptr->name); } else if (acl_type == TOMOYO_TYPE_MANUAL_TASK_ACL) { struct tomoyo_task_acl *ptr = container_of(acl, typeof(*ptr), head); tomoyo_set_group(head, "task "); tomoyo_set_string(head, "manual_domain_transition "); tomoyo_set_string(head, ptr->domainname->name); } else if (head->r.print_transition_related_only) { return true; } else if (acl_type == TOMOYO_TYPE_PATH2_ACL) { struct tomoyo_path2_acl *ptr = container_of(acl, typeof(*ptr), head); const u8 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_PATH2_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (first) { tomoyo_set_group(head, "file "); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_mac_keywords [tomoyo_pp2mac[bit]]); } if (first) return true; tomoyo_print_name_union(head, &ptr->name1); tomoyo_print_name_union(head, &ptr->name2); } else if (acl_type == TOMOYO_TYPE_PATH_NUMBER_ACL) { struct tomoyo_path_number_acl *ptr = container_of(acl, typeof(*ptr), head); const u8 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_PATH_NUMBER_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (first) { tomoyo_set_group(head, "file "); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_mac_keywords [tomoyo_pn2mac[bit]]); } if (first) return true; tomoyo_print_name_union(head, &ptr->name); tomoyo_print_number_union(head, &ptr->number); } else if (acl_type == TOMOYO_TYPE_MKDEV_ACL) { struct tomoyo_mkdev_acl *ptr = container_of(acl, typeof(*ptr), head); const u8 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_MKDEV_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (first) { tomoyo_set_group(head, "file "); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_mac_keywords [tomoyo_pnnn2mac[bit]]); } if (first) return true; tomoyo_print_name_union(head, &ptr->name); tomoyo_print_number_union(head, &ptr->mode); tomoyo_print_number_union(head, &ptr->major); tomoyo_print_number_union(head, &ptr->minor); } else if (acl_type == TOMOYO_TYPE_INET_ACL) { struct tomoyo_inet_acl *ptr = container_of(acl, typeof(*ptr), head); const u8 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_NETWORK_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (first) { tomoyo_set_group(head, "network inet "); tomoyo_set_string(head, tomoyo_proto_keyword [ptr->protocol]); tomoyo_set_space(head); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_socket_keyword[bit]); } if (first) return true; tomoyo_set_space(head); if (ptr->address.group) { tomoyo_set_string(head, "@"); tomoyo_set_string(head, ptr->address.group->group_name ->name); } else { char buf[128]; tomoyo_print_ip(buf, sizeof(buf), &ptr->address); tomoyo_io_printf(head, "%s", buf); } tomoyo_print_number_union(head, &ptr->port); } else if (acl_type == TOMOYO_TYPE_UNIX_ACL) { struct tomoyo_unix_acl *ptr = container_of(acl, typeof(*ptr), head); const u8 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_NETWORK_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (first) { tomoyo_set_group(head, "network unix "); tomoyo_set_string(head, tomoyo_proto_keyword [ptr->protocol]); tomoyo_set_space(head); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_socket_keyword[bit]); } if (first) return true; tomoyo_print_name_union(head, &ptr->name); } else if (acl_type == TOMOYO_TYPE_MOUNT_ACL) { struct tomoyo_mount_acl *ptr = container_of(acl, typeof(*ptr), head); tomoyo_set_group(head, "file mount"); tomoyo_print_name_union(head, &ptr->dev_name); tomoyo_print_name_union(head, &ptr->dir_name); tomoyo_print_name_union(head, &ptr->fs_type); tomoyo_print_number_union(head, &ptr->flags); } else if (acl_type == TOMOYO_TYPE_ENV_ACL) { struct tomoyo_env_acl *ptr = container_of(acl, typeof(*ptr), head); tomoyo_set_group(head, "misc env "); tomoyo_set_string(head, ptr->env->name); } if (acl->cond) { head->r.print_cond_part = true; head->r.cond_step = 0; if (!tomoyo_flush(head)) return false; print_cond_part: if (!tomoyo_print_condition(head, acl->cond)) return false; head->r.print_cond_part = false; } else { tomoyo_set_lf(head); } return true; } /** * tomoyo_read_domain2 - Read domain policy. * * @head: Pointer to "struct tomoyo_io_buffer". * @list: Pointer to "struct list_head". * * Caller holds tomoyo_read_lock(). * * Returns true on success, false otherwise. */ static bool tomoyo_read_domain2(struct tomoyo_io_buffer *head, struct list_head *list) { list_for_each_cookie(head->r.acl, list) { struct tomoyo_acl_info *ptr = list_entry(head->r.acl, typeof(*ptr), list); if (!tomoyo_print_entry(head, ptr)) return false; } head->r.acl = NULL; return true; } /** * tomoyo_read_domain - Read domain policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Caller holds tomoyo_read_lock(). */ static void tomoyo_read_domain(struct tomoyo_io_buffer *head) { if (head->r.eof) return; list_for_each_cookie(head->r.domain, &tomoyo_domain_list) { struct tomoyo_domain_info *domain = list_entry(head->r.domain, typeof(*domain), list); u8 i; switch (head->r.step) { case 0: if (domain->is_deleted && !head->r.print_this_domain_only) continue; /* Print domainname and flags. */ tomoyo_set_string(head, domain->domainname->name); tomoyo_set_lf(head); tomoyo_io_printf(head, "use_profile %u\n", domain->profile); for (i = 0; i < TOMOYO_MAX_DOMAIN_INFO_FLAGS; i++) if (domain->flags[i]) tomoyo_set_string(head, tomoyo_dif[i]); head->r.index = 0; head->r.step++; fallthrough; case 1: while (head->r.index < TOMOYO_MAX_ACL_GROUPS) { i = head->r.index++; if (!test_bit(i, domain->group)) continue; tomoyo_io_printf(head, "use_group %u\n", i); if (!tomoyo_flush(head)) return; } head->r.index = 0; head->r.step++; tomoyo_set_lf(head); fallthrough; case 2: if (!tomoyo_read_domain2(head, &domain->acl_info_list)) return; head->r.step++; if (!tomoyo_set_lf(head)) return; fallthrough; case 3: head->r.step = 0; if (head->r.print_this_domain_only) goto done; } } done: head->r.eof = true; } /** * tomoyo_write_pid: Specify PID to obtain domainname. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0. */ static int tomoyo_write_pid(struct tomoyo_io_buffer *head) { head->r.eof = false; return 0; } /** * tomoyo_read_pid - Get domainname of the specified PID. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns the domainname which the specified PID is in on success, * empty string otherwise. * The PID is specified by tomoyo_write_pid() so that the user can obtain * using read()/write() interface rather than sysctl() interface. */ static void tomoyo_read_pid(struct tomoyo_io_buffer *head) { char *buf = head->write_buf; bool global_pid = false; unsigned int pid; struct task_struct *p; struct tomoyo_domain_info *domain = NULL; /* Accessing write_buf is safe because head->io_sem is held. */ if (!buf) { head->r.eof = true; return; /* Do nothing if open(O_RDONLY). */ } if (head->r.w_pos || head->r.eof) return; head->r.eof = true; if (tomoyo_str_starts(&buf, "global-pid ")) global_pid = true; if (kstrtouint(buf, 10, &pid)) return; rcu_read_lock(); if (global_pid) p = find_task_by_pid_ns(pid, &init_pid_ns); else p = find_task_by_vpid(pid); if (p) domain = tomoyo_task(p)->domain_info; rcu_read_unlock(); if (!domain) return; tomoyo_io_printf(head, "%u %u ", pid, domain->profile); tomoyo_set_string(head, domain->domainname->name); } /* String table for domain transition control keywords. */ static const char *tomoyo_transition_type[TOMOYO_MAX_TRANSITION_TYPE] = { [TOMOYO_TRANSITION_CONTROL_NO_RESET] = "no_reset_domain ", [TOMOYO_TRANSITION_CONTROL_RESET] = "reset_domain ", [TOMOYO_TRANSITION_CONTROL_NO_INITIALIZE] = "no_initialize_domain ", [TOMOYO_TRANSITION_CONTROL_INITIALIZE] = "initialize_domain ", [TOMOYO_TRANSITION_CONTROL_NO_KEEP] = "no_keep_domain ", [TOMOYO_TRANSITION_CONTROL_KEEP] = "keep_domain ", }; /* String table for grouping keywords. */ static const char *tomoyo_group_name[TOMOYO_MAX_GROUP] = { [TOMOYO_PATH_GROUP] = "path_group ", [TOMOYO_NUMBER_GROUP] = "number_group ", [TOMOYO_ADDRESS_GROUP] = "address_group ", }; /** * tomoyo_write_exception - Write exception policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_write_exception(struct tomoyo_io_buffer *head) { const bool is_delete = head->w.is_delete; struct tomoyo_acl_param param = { .ns = head->w.ns, .is_delete = is_delete, .data = head->write_buf, }; u8 i; if (tomoyo_str_starts(¶m.data, "aggregator ")) return tomoyo_write_aggregator(¶m); for (i = 0; i < TOMOYO_MAX_TRANSITION_TYPE; i++) if (tomoyo_str_starts(¶m.data, tomoyo_transition_type[i])) return tomoyo_write_transition_control(¶m, i); for (i = 0; i < TOMOYO_MAX_GROUP; i++) if (tomoyo_str_starts(¶m.data, tomoyo_group_name[i])) return tomoyo_write_group(¶m, i); if (tomoyo_str_starts(¶m.data, "acl_group ")) { unsigned int group; char *data; group = simple_strtoul(param.data, &data, 10); if (group < TOMOYO_MAX_ACL_GROUPS && *data++ == ' ') return tomoyo_write_domain2 (head->w.ns, &head->w.ns->acl_group[group], data, is_delete); } return -EINVAL; } /** * tomoyo_read_group - Read "struct tomoyo_path_group"/"struct tomoyo_number_group"/"struct tomoyo_address_group" list. * * @head: Pointer to "struct tomoyo_io_buffer". * @idx: Index number. * * Returns true on success, false otherwise. * * Caller holds tomoyo_read_lock(). */ static bool tomoyo_read_group(struct tomoyo_io_buffer *head, const int idx) { struct tomoyo_policy_namespace *ns = container_of(head->r.ns, typeof(*ns), namespace_list); struct list_head *list = &ns->group_list[idx]; list_for_each_cookie(head->r.group, list) { struct tomoyo_group *group = list_entry(head->r.group, typeof(*group), head.list); list_for_each_cookie(head->r.acl, &group->member_list) { struct tomoyo_acl_head *ptr = list_entry(head->r.acl, typeof(*ptr), list); if (ptr->is_deleted) continue; if (!tomoyo_flush(head)) return false; tomoyo_print_namespace(head); tomoyo_set_string(head, tomoyo_group_name[idx]); tomoyo_set_string(head, group->group_name->name); if (idx == TOMOYO_PATH_GROUP) { tomoyo_set_space(head); tomoyo_set_string(head, container_of (ptr, struct tomoyo_path_group, head)->member_name->name); } else if (idx == TOMOYO_NUMBER_GROUP) { tomoyo_print_number_union(head, &container_of (ptr, struct tomoyo_number_group, head)->number); } else if (idx == TOMOYO_ADDRESS_GROUP) { char buffer[128]; struct tomoyo_address_group *member = container_of(ptr, typeof(*member), head); tomoyo_print_ip(buffer, sizeof(buffer), &member->address); tomoyo_io_printf(head, " %s", buffer); } tomoyo_set_lf(head); } head->r.acl = NULL; } head->r.group = NULL; return true; } /** * tomoyo_read_policy - Read "struct tomoyo_..._entry" list. * * @head: Pointer to "struct tomoyo_io_buffer". * @idx: Index number. * * Returns true on success, false otherwise. * * Caller holds tomoyo_read_lock(). */ static bool tomoyo_read_policy(struct tomoyo_io_buffer *head, const int idx) { struct tomoyo_policy_namespace *ns = container_of(head->r.ns, typeof(*ns), namespace_list); struct list_head *list = &ns->policy_list[idx]; list_for_each_cookie(head->r.acl, list) { struct tomoyo_acl_head *acl = container_of(head->r.acl, typeof(*acl), list); if (acl->is_deleted) continue; if (!tomoyo_flush(head)) return false; switch (idx) { case TOMOYO_ID_TRANSITION_CONTROL: { struct tomoyo_transition_control *ptr = container_of(acl, typeof(*ptr), head); tomoyo_print_namespace(head); tomoyo_set_string(head, tomoyo_transition_type [ptr->type]); tomoyo_set_string(head, ptr->program ? ptr->program->name : "any"); tomoyo_set_string(head, " from "); tomoyo_set_string(head, ptr->domainname ? ptr->domainname->name : "any"); } break; case TOMOYO_ID_AGGREGATOR: { struct tomoyo_aggregator *ptr = container_of(acl, typeof(*ptr), head); tomoyo_print_namespace(head); tomoyo_set_string(head, "aggregator "); tomoyo_set_string(head, ptr->original_name->name); tomoyo_set_space(head); tomoyo_set_string(head, ptr->aggregated_name->name); } break; default: continue; } tomoyo_set_lf(head); } head->r.acl = NULL; return true; } /** * tomoyo_read_exception - Read exception policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Caller holds tomoyo_read_lock(). */ static void tomoyo_read_exception(struct tomoyo_io_buffer *head) { struct tomoyo_policy_namespace *ns = container_of(head->r.ns, typeof(*ns), namespace_list); if (head->r.eof) return; while (head->r.step < TOMOYO_MAX_POLICY && tomoyo_read_policy(head, head->r.step)) head->r.step++; if (head->r.step < TOMOYO_MAX_POLICY) return; while (head->r.step < TOMOYO_MAX_POLICY + TOMOYO_MAX_GROUP && tomoyo_read_group(head, head->r.step - TOMOYO_MAX_POLICY)) head->r.step++; if (head->r.step < TOMOYO_MAX_POLICY + TOMOYO_MAX_GROUP) return; while (head->r.step < TOMOYO_MAX_POLICY + TOMOYO_MAX_GROUP + TOMOYO_MAX_ACL_GROUPS) { head->r.acl_group_index = head->r.step - TOMOYO_MAX_POLICY - TOMOYO_MAX_GROUP; if (!tomoyo_read_domain2(head, &ns->acl_group [head->r.acl_group_index])) return; head->r.step++; } head->r.eof = true; } /* Wait queue for kernel -> userspace notification. */ static DECLARE_WAIT_QUEUE_HEAD(tomoyo_query_wait); /* Wait queue for userspace -> kernel notification. */ static DECLARE_WAIT_QUEUE_HEAD(tomoyo_answer_wait); /* Structure for query. */ struct tomoyo_query { struct list_head list; struct tomoyo_domain_info *domain; char *query; size_t query_len; unsigned int serial; u8 timer; u8 answer; u8 retry; }; /* The list for "struct tomoyo_query". */ static LIST_HEAD(tomoyo_query_list); /* Lock for manipulating tomoyo_query_list. */ static DEFINE_SPINLOCK(tomoyo_query_list_lock); /* * Number of "struct file" referring /sys/kernel/security/tomoyo/query * interface. */ static atomic_t tomoyo_query_observers = ATOMIC_INIT(0); /** * tomoyo_truncate - Truncate a line. * * @str: String to truncate. * * Returns length of truncated @str. */ static int tomoyo_truncate(char *str) { char *start = str; while (*(unsigned char *) str > (unsigned char) ' ') str++; *str = '\0'; return strlen(start) + 1; } /** * tomoyo_add_entry - Add an ACL to current thread's domain. Used by learning mode. * * @domain: Pointer to "struct tomoyo_domain_info". * @header: Lines containing ACL. * * Returns nothing. */ static void tomoyo_add_entry(struct tomoyo_domain_info *domain, char *header) { char *buffer; char *realpath = NULL; char *argv0 = NULL; char *symlink = NULL; char *cp = strchr(header, '\n'); int len; if (!cp) return; cp = strchr(cp + 1, '\n'); if (!cp) return; *cp++ = '\0'; len = strlen(cp) + 1; /* strstr() will return NULL if ordering is wrong. */ if (*cp == 'f') { argv0 = strstr(header, " argv[]={ \""); if (argv0) { argv0 += 10; len += tomoyo_truncate(argv0) + 14; } realpath = strstr(header, " exec={ realpath=\""); if (realpath) { realpath += 8; len += tomoyo_truncate(realpath) + 6; } symlink = strstr(header, " symlink.target=\""); if (symlink) len += tomoyo_truncate(symlink + 1) + 1; } buffer = kmalloc(len, GFP_NOFS); if (!buffer) return; snprintf(buffer, len - 1, "%s", cp); if (realpath) tomoyo_addprintf(buffer, len, " exec.%s", realpath); if (argv0) tomoyo_addprintf(buffer, len, " exec.argv[0]=%s", argv0); if (symlink) tomoyo_addprintf(buffer, len, "%s", symlink); tomoyo_normalize_line(buffer); if (!tomoyo_write_domain2(domain->ns, &domain->acl_info_list, buffer, false)) tomoyo_update_stat(TOMOYO_STAT_POLICY_UPDATES); kfree(buffer); } /** * tomoyo_supervisor - Ask for the supervisor's decision. * * @r: Pointer to "struct tomoyo_request_info". * @fmt: The printf()'s format string, followed by parameters. * * Returns 0 if the supervisor decided to permit the access request which * violated the policy in enforcing mode, TOMOYO_RETRY_REQUEST if the * supervisor decided to retry the access request which violated the policy in * enforcing mode, 0 if it is not in enforcing mode, -EPERM otherwise. */ int tomoyo_supervisor(struct tomoyo_request_info *r, const char *fmt, ...) { va_list args; int error; int len; static unsigned int tomoyo_serial; struct tomoyo_query entry = { }; bool quota_exceeded = false; va_start(args, fmt); len = vsnprintf(NULL, 0, fmt, args) + 1; va_end(args); /* Write /sys/kernel/security/tomoyo/audit. */ va_start(args, fmt); tomoyo_write_log2(r, len, fmt, args); va_end(args); /* Nothing more to do if granted. */ if (r->granted) return 0; if (r->mode) tomoyo_update_stat(r->mode); switch (r->mode) { case TOMOYO_CONFIG_ENFORCING: error = -EPERM; if (atomic_read(&tomoyo_query_observers)) break; goto out; case TOMOYO_CONFIG_LEARNING: error = 0; /* Check max_learning_entry parameter. */ if (tomoyo_domain_quota_is_ok(r)) break; fallthrough; default: return 0; } /* Get message. */ va_start(args, fmt); entry.query = tomoyo_init_log(r, len, fmt, args); va_end(args); if (!entry.query) goto out; entry.query_len = strlen(entry.query) + 1; if (!error) { tomoyo_add_entry(r->domain, entry.query); goto out; } len = kmalloc_size_roundup(entry.query_len); entry.domain = r->domain; spin_lock(&tomoyo_query_list_lock); if (tomoyo_memory_quota[TOMOYO_MEMORY_QUERY] && tomoyo_memory_used[TOMOYO_MEMORY_QUERY] + len >= tomoyo_memory_quota[TOMOYO_MEMORY_QUERY]) { quota_exceeded = true; } else { entry.serial = tomoyo_serial++; entry.retry = r->retry; tomoyo_memory_used[TOMOYO_MEMORY_QUERY] += len; list_add_tail(&entry.list, &tomoyo_query_list); } spin_unlock(&tomoyo_query_list_lock); if (quota_exceeded) goto out; /* Give 10 seconds for supervisor's opinion. */ while (entry.timer < 10) { wake_up_all(&tomoyo_query_wait); if (wait_event_interruptible_timeout (tomoyo_answer_wait, entry.answer || !atomic_read(&tomoyo_query_observers), HZ)) break; entry.timer++; } spin_lock(&tomoyo_query_list_lock); list_del(&entry.list); tomoyo_memory_used[TOMOYO_MEMORY_QUERY] -= len; spin_unlock(&tomoyo_query_list_lock); switch (entry.answer) { case 3: /* Asked to retry by administrator. */ error = TOMOYO_RETRY_REQUEST; r->retry++; break; case 1: /* Granted by administrator. */ error = 0; break; default: /* Timed out or rejected by administrator. */ break; } out: kfree(entry.query); return error; } /** * tomoyo_find_domain_by_qid - Get domain by query id. * * @serial: Query ID assigned by tomoyo_supervisor(). * * Returns pointer to "struct tomoyo_domain_info" if found, NULL otherwise. */ static struct tomoyo_domain_info *tomoyo_find_domain_by_qid (unsigned int serial) { struct tomoyo_query *ptr; struct tomoyo_domain_info *domain = NULL; spin_lock(&tomoyo_query_list_lock); list_for_each_entry(ptr, &tomoyo_query_list, list) { if (ptr->serial != serial) continue; domain = ptr->domain; break; } spin_unlock(&tomoyo_query_list_lock); return domain; } /** * tomoyo_poll_query - poll() for /sys/kernel/security/tomoyo/query. * * @file: Pointer to "struct file". * @wait: Pointer to "poll_table". * * Returns EPOLLIN | EPOLLRDNORM when ready to read, 0 otherwise. * * Waits for access requests which violated policy in enforcing mode. */ static __poll_t tomoyo_poll_query(struct file *file, poll_table *wait) { if (!list_empty(&tomoyo_query_list)) return EPOLLIN | EPOLLRDNORM; poll_wait(file, &tomoyo_query_wait, wait); if (!list_empty(&tomoyo_query_list)) return EPOLLIN | EPOLLRDNORM; return 0; } /** * tomoyo_read_query - Read access requests which violated policy in enforcing mode. * * @head: Pointer to "struct tomoyo_io_buffer". */ static void tomoyo_read_query(struct tomoyo_io_buffer *head) { struct list_head *tmp; unsigned int pos = 0; size_t len = 0; char *buf; if (head->r.w_pos) return; kfree(head->read_buf); head->read_buf = NULL; spin_lock(&tomoyo_query_list_lock); list_for_each(tmp, &tomoyo_query_list) { struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list); if (pos++ != head->r.query_index) continue; len = ptr->query_len; break; } spin_unlock(&tomoyo_query_list_lock); if (!len) { head->r.query_index = 0; return; } buf = kzalloc(len + 32, GFP_NOFS); if (!buf) return; pos = 0; spin_lock(&tomoyo_query_list_lock); list_for_each(tmp, &tomoyo_query_list) { struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list); if (pos++ != head->r.query_index) continue; /* * Some query can be skipped because tomoyo_query_list * can change, but I don't care. */ if (len == ptr->query_len) snprintf(buf, len + 31, "Q%u-%hu\n%s", ptr->serial, ptr->retry, ptr->query); break; } spin_unlock(&tomoyo_query_list_lock); if (buf[0]) { head->read_buf = buf; head->r.w[head->r.w_pos++] = buf; head->r.query_index++; } else { kfree(buf); } } /** * tomoyo_write_answer - Write the supervisor's decision. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0 on success, -EINVAL otherwise. */ static int tomoyo_write_answer(struct tomoyo_io_buffer *head) { char *data = head->write_buf; struct list_head *tmp; unsigned int serial; unsigned int answer; spin_lock(&tomoyo_query_list_lock); list_for_each(tmp, &tomoyo_query_list) { struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list); ptr->timer = 0; } spin_unlock(&tomoyo_query_list_lock); if (sscanf(data, "A%u=%u", &serial, &answer) != 2) return -EINVAL; spin_lock(&tomoyo_query_list_lock); list_for_each(tmp, &tomoyo_query_list) { struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list); if (ptr->serial != serial) continue; ptr->answer = answer; /* Remove from tomoyo_query_list. */ if (ptr->answer) list_del_init(&ptr->list); break; } spin_unlock(&tomoyo_query_list_lock); return 0; } /** * tomoyo_read_version: Get version. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns version information. */ static void tomoyo_read_version(struct tomoyo_io_buffer *head) { if (!head->r.eof) { tomoyo_io_printf(head, "2.6.0"); head->r.eof = true; } } /* String table for /sys/kernel/security/tomoyo/stat interface. */ static const char * const tomoyo_policy_headers[TOMOYO_MAX_POLICY_STAT] = { [TOMOYO_STAT_POLICY_UPDATES] = "update:", [TOMOYO_STAT_POLICY_LEARNING] = "violation in learning mode:", [TOMOYO_STAT_POLICY_PERMISSIVE] = "violation in permissive mode:", [TOMOYO_STAT_POLICY_ENFORCING] = "violation in enforcing mode:", }; /* String table for /sys/kernel/security/tomoyo/stat interface. */ static const char * const tomoyo_memory_headers[TOMOYO_MAX_MEMORY_STAT] = { [TOMOYO_MEMORY_POLICY] = "policy:", [TOMOYO_MEMORY_AUDIT] = "audit log:", [TOMOYO_MEMORY_QUERY] = "query message:", }; /* Counter for number of updates. */ static atomic_t tomoyo_stat_updated[TOMOYO_MAX_POLICY_STAT]; /* Timestamp counter for last updated. */ static time64_t tomoyo_stat_modified[TOMOYO_MAX_POLICY_STAT]; /** * tomoyo_update_stat - Update statistic counters. * * @index: Index for policy type. * * Returns nothing. */ void tomoyo_update_stat(const u8 index) { atomic_inc(&tomoyo_stat_updated[index]); tomoyo_stat_modified[index] = ktime_get_real_seconds(); } /** * tomoyo_read_stat - Read statistic data. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static void tomoyo_read_stat(struct tomoyo_io_buffer *head) { u8 i; unsigned int total = 0; if (head->r.eof) return; for (i = 0; i < TOMOYO_MAX_POLICY_STAT; i++) { tomoyo_io_printf(head, "Policy %-30s %10u", tomoyo_policy_headers[i], atomic_read(&tomoyo_stat_updated[i])); if (tomoyo_stat_modified[i]) { struct tomoyo_time stamp; tomoyo_convert_time(tomoyo_stat_modified[i], &stamp); tomoyo_io_printf(head, " (Last: %04u/%02u/%02u %02u:%02u:%02u)", stamp.year, stamp.month, stamp.day, stamp.hour, stamp.min, stamp.sec); } tomoyo_set_lf(head); } for (i = 0; i < TOMOYO_MAX_MEMORY_STAT; i++) { unsigned int used = tomoyo_memory_used[i]; total += used; tomoyo_io_printf(head, "Memory used by %-22s %10u", tomoyo_memory_headers[i], used); used = tomoyo_memory_quota[i]; if (used) tomoyo_io_printf(head, " (Quota: %10u)", used); tomoyo_set_lf(head); } tomoyo_io_printf(head, "Total memory used: %10u\n", total); head->r.eof = true; } /** * tomoyo_write_stat - Set memory quota. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0. */ static int tomoyo_write_stat(struct tomoyo_io_buffer *head) { char *data = head->write_buf; u8 i; if (tomoyo_str_starts(&data, "Memory used by ")) for (i = 0; i < TOMOYO_MAX_MEMORY_STAT; i++) if (tomoyo_str_starts(&data, tomoyo_memory_headers[i])) sscanf(data, "%u", &tomoyo_memory_quota[i]); return 0; } /** * tomoyo_open_control - open() for /sys/kernel/security/tomoyo/ interface. * * @type: Type of interface. * @file: Pointer to "struct file". * * Returns 0 on success, negative value otherwise. */ int tomoyo_open_control(const u8 type, struct file *file) { struct tomoyo_io_buffer *head = kzalloc(sizeof(*head), GFP_NOFS); if (!head) return -ENOMEM; mutex_init(&head->io_sem); head->type = type; switch (type) { case TOMOYO_DOMAINPOLICY: /* /sys/kernel/security/tomoyo/domain_policy */ head->write = tomoyo_write_domain; head->read = tomoyo_read_domain; break; case TOMOYO_EXCEPTIONPOLICY: /* /sys/kernel/security/tomoyo/exception_policy */ head->write = tomoyo_write_exception; head->read = tomoyo_read_exception; break; case TOMOYO_AUDIT: /* /sys/kernel/security/tomoyo/audit */ head->poll = tomoyo_poll_log; head->read = tomoyo_read_log; break; case TOMOYO_PROCESS_STATUS: /* /sys/kernel/security/tomoyo/.process_status */ head->write = tomoyo_write_pid; head->read = tomoyo_read_pid; break; case TOMOYO_VERSION: /* /sys/kernel/security/tomoyo/version */ head->read = tomoyo_read_version; head->readbuf_size = 128; break; case TOMOYO_STAT: /* /sys/kernel/security/tomoyo/stat */ head->write = tomoyo_write_stat; head->read = tomoyo_read_stat; head->readbuf_size = 1024; break; case TOMOYO_PROFILE: /* /sys/kernel/security/tomoyo/profile */ head->write = tomoyo_write_profile; head->read = tomoyo_read_profile; break; case TOMOYO_QUERY: /* /sys/kernel/security/tomoyo/query */ head->poll = tomoyo_poll_query; head->write = tomoyo_write_answer; head->read = tomoyo_read_query; break; case TOMOYO_MANAGER: /* /sys/kernel/security/tomoyo/manager */ head->write = tomoyo_write_manager; head->read = tomoyo_read_manager; break; } if (!(file->f_mode & FMODE_READ)) { /* * No need to allocate read_buf since it is not opened * for reading. */ head->read = NULL; head->poll = NULL; } else if (!head->poll) { /* Don't allocate read_buf for poll() access. */ if (!head->readbuf_size) head->readbuf_size = 4096 * 2; head->read_buf = kzalloc(head->readbuf_size, GFP_NOFS); if (!head->read_buf) { kfree(head); return -ENOMEM; } } if (!(file->f_mode & FMODE_WRITE)) { /* * No need to allocate write_buf since it is not opened * for writing. */ head->write = NULL; } else if (head->write) { head->writebuf_size = 4096 * 2; head->write_buf = kzalloc(head->writebuf_size, GFP_NOFS); if (!head->write_buf) { kfree(head->read_buf); kfree(head); return -ENOMEM; } } /* * If the file is /sys/kernel/security/tomoyo/query , increment the * observer counter. * The obserber counter is used by tomoyo_supervisor() to see if * there is some process monitoring /sys/kernel/security/tomoyo/query. */ if (type == TOMOYO_QUERY) atomic_inc(&tomoyo_query_observers); file->private_data = head; tomoyo_notify_gc(head, true); return 0; } /** * tomoyo_poll_control - poll() for /sys/kernel/security/tomoyo/ interface. * * @file: Pointer to "struct file". * @wait: Pointer to "poll_table". Maybe NULL. * * Returns EPOLLIN | EPOLLRDNORM | EPOLLOUT | EPOLLWRNORM if ready to read/write, * EPOLLOUT | EPOLLWRNORM otherwise. */ __poll_t tomoyo_poll_control(struct file *file, poll_table *wait) { struct tomoyo_io_buffer *head = file->private_data; if (head->poll) return head->poll(file, wait) | EPOLLOUT | EPOLLWRNORM; return EPOLLIN | EPOLLRDNORM | EPOLLOUT | EPOLLWRNORM; } /** * tomoyo_set_namespace_cursor - Set namespace to read. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static inline void tomoyo_set_namespace_cursor(struct tomoyo_io_buffer *head) { struct list_head *ns; if (head->type != TOMOYO_EXCEPTIONPOLICY && head->type != TOMOYO_PROFILE) return; /* * If this is the first read, or reading previous namespace finished * and has more namespaces to read, update the namespace cursor. */ ns = head->r.ns; if (!ns || (head->r.eof && ns->next != &tomoyo_namespace_list)) { /* Clearing is OK because tomoyo_flush() returned true. */ memset(&head->r, 0, sizeof(head->r)); head->r.ns = ns ? ns->next : tomoyo_namespace_list.next; } } /** * tomoyo_has_more_namespace - Check for unread namespaces. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns true if we have more entries to print, false otherwise. */ static inline bool tomoyo_has_more_namespace(struct tomoyo_io_buffer *head) { return (head->type == TOMOYO_EXCEPTIONPOLICY || head->type == TOMOYO_PROFILE) && head->r.eof && head->r.ns->next != &tomoyo_namespace_list; } /** * tomoyo_read_control - read() for /sys/kernel/security/tomoyo/ interface. * * @head: Pointer to "struct tomoyo_io_buffer". * @buffer: Pointer to buffer to write to. * @buffer_len: Size of @buffer. * * Returns bytes read on success, negative value otherwise. */ ssize_t tomoyo_read_control(struct tomoyo_io_buffer *head, char __user *buffer, const int buffer_len) { int len; int idx; if (!head->read) return -EINVAL; if (mutex_lock_interruptible(&head->io_sem)) return -EINTR; head->read_user_buf = buffer; head->read_user_buf_avail = buffer_len; idx = tomoyo_read_lock(); if (tomoyo_flush(head)) /* Call the policy handler. */ do { tomoyo_set_namespace_cursor(head); head->read(head); } while (tomoyo_flush(head) && tomoyo_has_more_namespace(head)); tomoyo_read_unlock(idx); len = head->read_user_buf - buffer; mutex_unlock(&head->io_sem); return len; } /** * tomoyo_parse_policy - Parse a policy line. * * @head: Pointer to "struct tomoyo_io_buffer". * @line: Line to parse. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_parse_policy(struct tomoyo_io_buffer *head, char *line) { /* Delete request? */ head->w.is_delete = !strncmp(line, "delete ", 7); if (head->w.is_delete) memmove(line, line + 7, strlen(line + 7) + 1); /* Selecting namespace to update. */ if (head->type == TOMOYO_EXCEPTIONPOLICY || head->type == TOMOYO_PROFILE) { if (*line == '<') { char *cp = strchr(line, ' '); if (cp) { *cp++ = '\0'; head->w.ns = tomoyo_assign_namespace(line); memmove(line, cp, strlen(cp) + 1); } else head->w.ns = NULL; } else head->w.ns = &tomoyo_kernel_namespace; /* Don't allow updating if namespace is invalid. */ if (!head->w.ns) return -ENOENT; } /* Do the update. */ return head->write(head); } /** * tomoyo_write_control - write() for /sys/kernel/security/tomoyo/ interface. * * @head: Pointer to "struct tomoyo_io_buffer". * @buffer: Pointer to buffer to read from. * @buffer_len: Size of @buffer. * * Returns @buffer_len on success, negative value otherwise. */ ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head, const char __user *buffer, const int buffer_len) { int error = buffer_len; size_t avail_len = buffer_len; char *cp0; int idx; if (!head->write) return -EINVAL; if (mutex_lock_interruptible(&head->io_sem)) return -EINTR; cp0 = head->write_buf; head->read_user_buf_avail = 0; idx = tomoyo_read_lock(); /* Read a line and dispatch it to the policy handler. */ while (avail_len > 0) { char c; if (head->w.avail >= head->writebuf_size - 1) { const int len = head->writebuf_size * 2; char *cp = kzalloc(len, GFP_NOFS); if (!cp) { error = -ENOMEM; break; } memmove(cp, cp0, head->w.avail); kfree(cp0); head->write_buf = cp; cp0 = cp; head->writebuf_size = len; } if (get_user(c, buffer)) { error = -EFAULT; break; } buffer++; avail_len--; cp0[head->w.avail++] = c; if (c != '\n') continue; cp0[head->w.avail - 1] = '\0'; head->w.avail = 0; tomoyo_normalize_line(cp0); if (!strcmp(cp0, "reset")) { head->w.ns = &tomoyo_kernel_namespace; head->w.domain = NULL; memset(&head->r, 0, sizeof(head->r)); continue; } /* Don't allow updating policies by non manager programs. */ switch (head->type) { case TOMOYO_PROCESS_STATUS: /* This does not write anything. */ break; case TOMOYO_DOMAINPOLICY: if (tomoyo_select_domain(head, cp0)) continue; fallthrough; case TOMOYO_EXCEPTIONPOLICY: if (!strcmp(cp0, "select transition_only")) { head->r.print_transition_related_only = true; continue; } fallthrough; default: if (!tomoyo_manager()) { error = -EPERM; goto out; } } switch (tomoyo_parse_policy(head, cp0)) { case -EPERM: error = -EPERM; goto out; case 0: switch (head->type) { case TOMOYO_DOMAINPOLICY: case TOMOYO_EXCEPTIONPOLICY: case TOMOYO_STAT: case TOMOYO_PROFILE: case TOMOYO_MANAGER: tomoyo_update_stat(TOMOYO_STAT_POLICY_UPDATES); break; default: break; } break; } } out: tomoyo_read_unlock(idx); mutex_unlock(&head->io_sem); return error; } /** * tomoyo_close_control - close() for /sys/kernel/security/tomoyo/ interface. * * @head: Pointer to "struct tomoyo_io_buffer". */ void tomoyo_close_control(struct tomoyo_io_buffer *head) { /* * If the file is /sys/kernel/security/tomoyo/query , decrement the * observer counter. */ if (head->type == TOMOYO_QUERY && atomic_dec_and_test(&tomoyo_query_observers)) wake_up_all(&tomoyo_answer_wait); tomoyo_notify_gc(head, false); } /** * tomoyo_check_profile - Check all profiles currently assigned to domains are defined. */ void tomoyo_check_profile(void) { struct tomoyo_domain_info *domain; const int idx = tomoyo_read_lock(); tomoyo_policy_loaded = true; pr_info("TOMOYO: 2.6.0\n"); list_for_each_entry_rcu(domain, &tomoyo_domain_list, list, srcu_read_lock_held(&tomoyo_ss)) { const u8 profile = domain->profile; struct tomoyo_policy_namespace *ns = domain->ns; if (ns->profile_version == 20110903) { pr_info_once("Converting profile version from %u to %u.\n", 20110903, 20150505); ns->profile_version = 20150505; } if (ns->profile_version != 20150505) pr_err("Profile version %u is not supported.\n", ns->profile_version); else if (!ns->profile_ptr[profile]) pr_err("Profile %u (used by '%s') is not defined.\n", profile, domain->domainname->name); else continue; pr_err("Userland tools for TOMOYO 2.6 must be installed and policy must be initialized.\n"); pr_err("Please see https://tomoyo.sourceforge.net/2.6/ for more information.\n"); panic("STOP!"); } tomoyo_read_unlock(idx); pr_info("Mandatory Access Control activated.\n"); } /** * tomoyo_load_builtin_policy - Load built-in policy. * * Returns nothing. */ void __init tomoyo_load_builtin_policy(void) { #ifdef CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING static char tomoyo_builtin_profile[] __initdata = "PROFILE_VERSION=20150505\n" "0-CONFIG={ mode=learning grant_log=no reject_log=yes }\n"; static char tomoyo_builtin_exception_policy[] __initdata = "aggregator proc:/self/exe /proc/self/exe\n"; static char tomoyo_builtin_domain_policy[] __initdata = ""; static char tomoyo_builtin_manager[] __initdata = ""; static char tomoyo_builtin_stat[] __initdata = ""; #else /* * This include file is manually created and contains built-in policy * named "tomoyo_builtin_profile", "tomoyo_builtin_exception_policy", * "tomoyo_builtin_domain_policy", "tomoyo_builtin_manager", * "tomoyo_builtin_stat" in the form of "static char [] __initdata". */ #include "builtin-policy.h" #endif u8 i; const int idx = tomoyo_read_lock(); for (i = 0; i < 5; i++) { struct tomoyo_io_buffer head = { }; char *start = ""; switch (i) { case 0: start = tomoyo_builtin_profile; head.type = TOMOYO_PROFILE; head.write = tomoyo_write_profile; break; case 1: start = tomoyo_builtin_exception_policy; head.type = TOMOYO_EXCEPTIONPOLICY; head.write = tomoyo_write_exception; break; case 2: start = tomoyo_builtin_domain_policy; head.type = TOMOYO_DOMAINPOLICY; head.write = tomoyo_write_domain; break; case 3: start = tomoyo_builtin_manager; head.type = TOMOYO_MANAGER; head.write = tomoyo_write_manager; break; case 4: start = tomoyo_builtin_stat; head.type = TOMOYO_STAT; head.write = tomoyo_write_stat; break; } while (1) { char *end = strchr(start, '\n'); if (!end) break; *end = '\0'; tomoyo_normalize_line(start); head.write_buf = start; tomoyo_parse_policy(&head, start); start = end + 1; } } tomoyo_read_unlock(idx); #ifdef CONFIG_SECURITY_TOMOYO_OMIT_USERSPACE_LOADER tomoyo_check_profile(); #endif } |
| 677 71 156 122 677 157 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_UACCESS_H__ #define __LINUX_UACCESS_H__ #include <linux/fault-inject-usercopy.h> #include <linux/instrumented.h> #include <linux/minmax.h> #include <linux/nospec.h> #include <linux/sched.h> #include <linux/thread_info.h> #include <asm/uaccess.h> /* * Architectures that support memory tagging (assigning tags to memory regions, * embedding these tags into addresses that point to these memory regions, and * checking that the memory and the pointer tags match on memory accesses) * redefine this macro to strip tags from pointers. * * Passing down mm_struct allows to define untagging rules on per-process * basis. * * It's defined as noop for architectures that don't support memory tagging. */ #ifndef untagged_addr #define untagged_addr(addr) (addr) #endif #ifndef untagged_addr_remote #define untagged_addr_remote(mm, addr) ({ \ mmap_assert_locked(mm); \ untagged_addr(addr); \ }) #endif #ifdef masked_user_access_begin #define can_do_masked_user_access() 1 #else #define can_do_masked_user_access() 0 #define masked_user_access_begin(src) NULL #define mask_user_address(src) (src) #endif /* * Architectures should provide two primitives (raw_copy_{to,from}_user()) * and get rid of their private instances of copy_{to,from}_user() and * __copy_{to,from}_user{,_inatomic}(). * * raw_copy_{to,from}_user(to, from, size) should copy up to size bytes and * return the amount left to copy. They should assume that access_ok() has * already been checked (and succeeded); they should *not* zero-pad anything. * No KASAN or object size checks either - those belong here. * * Both of these functions should attempt to copy size bytes starting at from * into the area starting at to. They must not fetch or store anything * outside of those areas. Return value must be between 0 (everything * copied successfully) and size (nothing copied). * * If raw_copy_{to,from}_user(to, from, size) returns N, size - N bytes starting * at to must become equal to the bytes fetched from the corresponding area * starting at from. All data past to + size - N must be left unmodified. * * If copying succeeds, the return value must be 0. If some data cannot be * fetched, it is permitted to copy less than had been fetched; the only * hard requirement is that not storing anything at all (i.e. returning size) * should happen only when nothing could be copied. In other words, you don't * have to squeeze as much as possible - it is allowed, but not necessary. * * For raw_copy_from_user() to always points to kernel memory and no faults * on store should happen. Interpretation of from is affected by set_fs(). * For raw_copy_to_user() it's the other way round. * * Both can be inlined - it's up to architectures whether it wants to bother * with that. They should not be used directly; they are used to implement * the 6 functions (copy_{to,from}_user(), __copy_{to,from}_user_inatomic()) * that are used instead. Out of those, __... ones are inlined. Plain * copy_{to,from}_user() might or might not be inlined. If you want them * inlined, have asm/uaccess.h define INLINE_COPY_{TO,FROM}_USER. * * NOTE: only copy_from_user() zero-pads the destination in case of short copy. * Neither __copy_from_user() nor __copy_from_user_inatomic() zero anything * at all; their callers absolutely must check the return value. * * Biarch ones should also provide raw_copy_in_user() - similar to the above, * but both source and destination are __user pointers (affected by set_fs() * as usual) and both source and destination can trigger faults. */ static __always_inline __must_check unsigned long __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) { unsigned long res; instrument_copy_from_user_before(to, from, n); check_object_size(to, n, false); res = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, res); return res; } static __always_inline __must_check unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res; might_fault(); instrument_copy_from_user_before(to, from, n); if (should_fail_usercopy()) return n; check_object_size(to, n, false); res = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, res); return res; } /** * __copy_to_user_inatomic: - Copy a block of data into user space, with less checking. * @to: Destination address, in user space. * @from: Source address, in kernel space. * @n: Number of bytes to copy. * * Context: User context only. * * Copy data from kernel space to user space. Caller must check * the specified block with access_ok() before calling this function. * The caller should also make sure he pins the user space address * so that we don't result in page fault and sleep. */ static __always_inline __must_check unsigned long __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) { if (should_fail_usercopy()) return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } static __always_inline __must_check unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } /* * Architectures that #define INLINE_COPY_TO_USER use this function * directly in the normal copy_to/from_user(), the other ones go * through an extern _copy_to/from_user(), which expands the same code * here. * * Rust code always uses the extern definition. */ static inline __must_check unsigned long _inline_copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; might_fault(); if (should_fail_usercopy()) goto fail; if (can_do_masked_user_access()) from = mask_user_address(from); else { if (!access_ok(from, n)) goto fail; /* * Ensure that bad access_ok() speculation will not * lead to nasty side effects *after* the copy is * finished: */ barrier_nospec(); } instrument_copy_from_user_before(to, from, n); res = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, res); if (likely(!res)) return 0; fail: memset(to + (n - res), 0, res); return res; } extern __must_check unsigned long _copy_from_user(void *, const void __user *, unsigned long); static inline __must_check unsigned long _inline_copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; if (access_ok(to, n)) { instrument_copy_to_user(to, from, n); n = raw_copy_to_user(to, from, n); } return n; } extern __must_check unsigned long _copy_to_user(void __user *, const void *, unsigned long); static __always_inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { if (!check_copy_size(to, n, false)) return n; #ifdef INLINE_COPY_FROM_USER return _inline_copy_from_user(to, from, n); #else return _copy_from_user(to, from, n); #endif } static __always_inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n) { if (!check_copy_size(from, n, true)) return n; #ifdef INLINE_COPY_TO_USER return _inline_copy_to_user(to, from, n); #else return _copy_to_user(to, from, n); #endif } #ifndef copy_mc_to_kernel /* * Without arch opt-in this generic copy_mc_to_kernel() will not handle * #MC (or arch equivalent) during source read. */ static inline unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, size_t cnt) { memcpy(dst, src, cnt); return 0; } #endif static __always_inline void pagefault_disabled_inc(void) { current->pagefault_disabled++; } static __always_inline void pagefault_disabled_dec(void) { current->pagefault_disabled--; } /* * These routines enable/disable the pagefault handler. If disabled, it will * not take any locks and go straight to the fixup table. * * User access methods will not sleep when called from a pagefault_disabled() * environment. */ static inline void pagefault_disable(void) { pagefault_disabled_inc(); /* * make sure to have issued the store before a pagefault * can hit. */ barrier(); } static inline void pagefault_enable(void) { /* * make sure to issue those last loads/stores before enabling * the pagefault handler again. */ barrier(); pagefault_disabled_dec(); } /* * Is the pagefault handler disabled? If so, user access methods will not sleep. */ static inline bool pagefault_disabled(void) { return current->pagefault_disabled != 0; } /* * The pagefault handler is in general disabled by pagefault_disable() or * when in irq context (via in_atomic()). * * This function should only be used by the fault handlers. Other users should * stick to pagefault_disabled(). * Please NEVER use preempt_disable() to disable the fault handler. With * !CONFIG_PREEMPT_COUNT, this is like a NOP. So the handler won't be disabled. * in_atomic() will report different values based on !CONFIG_PREEMPT_COUNT. */ #define faulthandler_disabled() (pagefault_disabled() || in_atomic()) #ifndef CONFIG_ARCH_HAS_SUBPAGE_FAULTS /** * probe_subpage_writeable: probe the user range for write faults at sub-page * granularity (e.g. arm64 MTE) * @uaddr: start of address range * @size: size of address range * * Returns 0 on success, the number of bytes not probed on fault. * * It is expected that the caller checked for the write permission of each * page in the range either by put_user() or GUP. The architecture port can * implement a more efficient get_user() probing if the same sub-page faults * are triggered by either a read or a write. */ static inline size_t probe_subpage_writeable(char __user *uaddr, size_t size) { return 0; } #endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */ #ifndef ARCH_HAS_NOCACHE_UACCESS static inline __must_check unsigned long __copy_from_user_inatomic_nocache(void *to, const void __user *from, unsigned long n) { return __copy_from_user_inatomic(to, from, n); } #endif /* ARCH_HAS_NOCACHE_UACCESS */ extern __must_check int check_zeroed_user(const void __user *from, size_t size); /** * copy_struct_from_user: copy a struct from userspace * @dst: Destination address, in kernel space. This buffer must be @ksize * bytes long. * @ksize: Size of @dst struct. * @src: Source address, in userspace. * @usize: (Alleged) size of @src struct. * * Copies a struct from userspace to kernel space, in a way that guarantees * backwards-compatibility for struct syscall arguments (as long as future * struct extensions are made such that all new fields are *appended* to the * old struct, and zeroed-out new fields have the same meaning as the old * struct). * * @ksize is just sizeof(*dst), and @usize should've been passed by userspace. * The recommended usage is something like the following: * * SYSCALL_DEFINE2(foobar, const struct foo __user *, uarg, size_t, usize) * { * int err; * struct foo karg = {}; * * if (usize > PAGE_SIZE) * return -E2BIG; * if (usize < FOO_SIZE_VER0) * return -EINVAL; * * err = copy_struct_from_user(&karg, sizeof(karg), uarg, usize); * if (err) * return err; * * // ... * } * * There are three cases to consider: * * If @usize == @ksize, then it's copied verbatim. * * If @usize < @ksize, then the userspace has passed an old struct to a * newer kernel. The rest of the trailing bytes in @dst (@ksize - @usize) * are to be zero-filled. * * If @usize > @ksize, then the userspace has passed a new struct to an * older kernel. The trailing bytes unknown to the kernel (@usize - @ksize) * are checked to ensure they are zeroed, otherwise -E2BIG is returned. * * Returns (in all cases, some data may have been copied): * * -E2BIG: (@usize > @ksize) and there are non-zero trailing bytes in @src. * * -EFAULT: access to userspace failed. */ static __always_inline __must_check int copy_struct_from_user(void *dst, size_t ksize, const void __user *src, size_t usize) { size_t size = min(ksize, usize); size_t rest = max(ksize, usize) - size; /* Double check if ksize is larger than a known object size. */ if (WARN_ON_ONCE(ksize > __builtin_object_size(dst, 1))) return -E2BIG; /* Deal with trailing bytes. */ if (usize < ksize) { memset(dst + size, 0, rest); } else if (usize > ksize) { int ret = check_zeroed_user(src + size, rest); if (ret <= 0) return ret ?: -E2BIG; } /* Copy the interoperable parts of the struct. */ if (copy_from_user(dst, src, size)) return -EFAULT; return 0; } /** * copy_struct_to_user: copy a struct to userspace * @dst: Destination address, in userspace. This buffer must be @ksize * bytes long. * @usize: (Alleged) size of @dst struct. * @src: Source address, in kernel space. * @ksize: Size of @src struct. * @ignored_trailing: Set to %true if there was a non-zero byte in @src that * userspace cannot see because they are using an smaller struct. * * Copies a struct from kernel space to userspace, in a way that guarantees * backwards-compatibility for struct syscall arguments (as long as future * struct extensions are made such that all new fields are *appended* to the * old struct, and zeroed-out new fields have the same meaning as the old * struct). * * Some syscalls may wish to make sure that userspace knows about everything in * the struct, and if there is a non-zero value that userspce doesn't know * about, they want to return an error (such as -EMSGSIZE) or have some other * fallback (such as adding a "you're missing some information" flag). If * @ignored_trailing is non-%NULL, it will be set to %true if there was a * non-zero byte that could not be copied to userspace (ie. was past @usize). * * While unconditionally returning an error in this case is the simplest * solution, for maximum backward compatibility you should try to only return * -EMSGSIZE if the user explicitly requested the data that couldn't be copied. * Note that structure sizes can change due to header changes and simple * recompilations without code changes(!), so if you care about * @ignored_trailing you probably want to make sure that any new field data is * associated with a flag. Otherwise you might assume that a program knows * about data it does not. * * @ksize is just sizeof(*src), and @usize should've been passed by userspace. * The recommended usage is something like the following: * * SYSCALL_DEFINE2(foobar, struct foo __user *, uarg, size_t, usize) * { * int err; * bool ignored_trailing; * struct foo karg = {}; * * if (usize > PAGE_SIZE) * return -E2BIG; * if (usize < FOO_SIZE_VER0) * return -EINVAL; * * // ... modify karg somehow ... * * err = copy_struct_to_user(uarg, usize, &karg, sizeof(karg), * &ignored_trailing); * if (err) * return err; * if (ignored_trailing) * return -EMSGSIZE: * * // ... * } * * There are three cases to consider: * * If @usize == @ksize, then it's copied verbatim. * * If @usize < @ksize, then the kernel is trying to pass userspace a newer * struct than it supports. Thus we only copy the interoperable portions * (@usize) and ignore the rest (but @ignored_trailing is set to %true if * any of the trailing (@ksize - @usize) bytes are non-zero). * * If @usize > @ksize, then the kernel is trying to pass userspace an older * struct than userspace supports. In order to make sure the * unknown-to-the-kernel fields don't contain garbage values, we zero the * trailing (@usize - @ksize) bytes. * * Returns (in all cases, some data may have been copied): * * -EFAULT: access to userspace failed. */ static __always_inline __must_check int copy_struct_to_user(void __user *dst, size_t usize, const void *src, size_t ksize, bool *ignored_trailing) { size_t size = min(ksize, usize); size_t rest = max(ksize, usize) - size; /* Double check if ksize is larger than a known object size. */ if (WARN_ON_ONCE(ksize > __builtin_object_size(src, 1))) return -E2BIG; /* Deal with trailing bytes. */ if (usize > ksize) { if (clear_user(dst + size, rest)) return -EFAULT; } if (ignored_trailing) *ignored_trailing = ksize < usize && memchr_inv(src + size, 0, rest) != NULL; /* Copy the interoperable parts of the struct. */ if (copy_to_user(dst, src, size)) return -EFAULT; return 0; } bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size); long copy_from_kernel_nofault(void *dst, const void *src, size_t size); long notrace copy_to_kernel_nofault(void *dst, const void *src, size_t size); long copy_from_user_nofault(void *dst, const void __user *src, size_t size); long notrace copy_to_user_nofault(void __user *dst, const void *src, size_t size); long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count); long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count); long strnlen_user_nofault(const void __user *unsafe_addr, long count); #ifndef __get_kernel_nofault #define __get_kernel_nofault(dst, src, type, label) \ do { \ type __user *p = (type __force __user *)(src); \ type data; \ if (__get_user(data, p)) \ goto label; \ *(type *)dst = data; \ } while (0) #define __put_kernel_nofault(dst, src, type, label) \ do { \ type __user *p = (type __force __user *)(dst); \ type data = *(type *)src; \ if (__put_user(data, p)) \ goto label; \ } while (0) #endif /** * get_kernel_nofault(): safely attempt to read from a location * @val: read into this variable * @ptr: address to read from * * Returns 0 on success, or -EFAULT. */ #define get_kernel_nofault(val, ptr) ({ \ const typeof(val) *__gk_ptr = (ptr); \ copy_from_kernel_nofault(&(val), __gk_ptr, sizeof(val));\ }) #ifndef user_access_begin #define user_access_begin(ptr,len) access_ok(ptr, len) #define user_access_end() do { } while (0) #define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0) #define unsafe_get_user(x,p,e) unsafe_op_wrap(__get_user(x,p),e) #define unsafe_put_user(x,p,e) unsafe_op_wrap(__put_user(x,p),e) #define unsafe_copy_to_user(d,s,l,e) unsafe_op_wrap(__copy_to_user(d,s,l),e) #define unsafe_copy_from_user(d,s,l,e) unsafe_op_wrap(__copy_from_user(d,s,l),e) static inline unsigned long user_access_save(void) { return 0UL; } static inline void user_access_restore(unsigned long flags) { } #endif #ifndef user_write_access_begin #define user_write_access_begin user_access_begin #define user_write_access_end user_access_end #endif #ifndef user_read_access_begin #define user_read_access_begin user_access_begin #define user_read_access_end user_access_end #endif #ifdef CONFIG_HARDENED_USERCOPY void __noreturn usercopy_abort(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len); #endif #endif /* __LINUX_UACCESS_H__ */ |
| 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 | /* SPDX-License-Identifier: GPL-2.0 */ /* * kernel/workqueue_internal.h * * Workqueue internal header file. Only to be included by workqueue and * core kernel subsystems. */ #ifndef _KERNEL_WORKQUEUE_INTERNAL_H #define _KERNEL_WORKQUEUE_INTERNAL_H #include <linux/workqueue.h> #include <linux/kthread.h> #include <linux/preempt.h> struct worker_pool; /* * The poor guys doing the actual heavy lifting. All on-duty workers are * either serving the manager role, on idle list or on busy hash. For * details on the locking annotation (L, I, X...), refer to workqueue.c. * * Only to be used in workqueue and async. */ struct worker { /* on idle list while idle, on busy hash table while busy */ union { struct list_head entry; /* L: while idle */ struct hlist_node hentry; /* L: while busy */ }; struct work_struct *current_work; /* K: work being processed and its */ work_func_t current_func; /* K: function */ struct pool_workqueue *current_pwq; /* K: pwq */ u64 current_at; /* K: runtime at start or last wakeup */ unsigned int current_color; /* K: color */ int sleeping; /* S: is worker sleeping? */ /* used by the scheduler to determine a worker's last known identity */ work_func_t last_func; /* K: last work's fn */ struct list_head scheduled; /* L: scheduled works */ struct task_struct *task; /* I: worker task */ struct worker_pool *pool; /* A: the associated pool */ /* L: for rescuers */ struct list_head node; /* A: anchored at pool->workers */ /* A: runs through worker->node */ unsigned long last_active; /* K: last active timestamp */ unsigned int flags; /* L: flags */ int id; /* I: worker id */ /* * Opaque string set with work_set_desc(). Printed out with task * dump for debugging - WARN, BUG, panic or sysrq. */ char desc[WORKER_DESC_LEN]; /* used only by rescuers to point to the target workqueue */ struct workqueue_struct *rescue_wq; /* I: the workqueue to rescue */ }; /** * current_wq_worker - return struct worker if %current is a workqueue worker */ static inline struct worker *current_wq_worker(void) { if (in_task() && (current->flags & PF_WQ_WORKER)) return kthread_data(current); return NULL; } /* * Scheduler hooks for concurrency managed workqueue. Only to be used from * sched/ and workqueue.c. */ void wq_worker_running(struct task_struct *task); void wq_worker_sleeping(struct task_struct *task); void wq_worker_tick(struct task_struct *task); work_func_t wq_worker_last_func(struct task_struct *task); #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ |
| 12 12 12 12 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_VIRTIO_NET_H #define _LINUX_VIRTIO_NET_H #include <linux/if_vlan.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/udp.h> #include <uapi/linux/tcp.h> #include <uapi/linux/virtio_net.h> static inline bool virtio_net_hdr_match_proto(__be16 protocol, __u8 gso_type) { switch (gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: return protocol == cpu_to_be16(ETH_P_IP); case VIRTIO_NET_HDR_GSO_TCPV6: return protocol == cpu_to_be16(ETH_P_IPV6); case VIRTIO_NET_HDR_GSO_UDP: case VIRTIO_NET_HDR_GSO_UDP_L4: return protocol == cpu_to_be16(ETH_P_IP) || protocol == cpu_to_be16(ETH_P_IPV6); default: return false; } } static inline int virtio_net_hdr_set_proto(struct sk_buff *skb, const struct virtio_net_hdr *hdr) { if (skb->protocol) return 0; switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: case VIRTIO_NET_HDR_GSO_UDP: case VIRTIO_NET_HDR_GSO_UDP_L4: skb->protocol = cpu_to_be16(ETH_P_IP); break; case VIRTIO_NET_HDR_GSO_TCPV6: skb->protocol = cpu_to_be16(ETH_P_IPV6); break; default: return -EINVAL; } return 0; } static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, const struct virtio_net_hdr *hdr, bool little_endian) { unsigned int nh_min_len = sizeof(struct iphdr); unsigned int gso_type = 0; unsigned int thlen = 0; unsigned int p_off = 0; unsigned int ip_proto; if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: gso_type = SKB_GSO_TCPV4; ip_proto = IPPROTO_TCP; thlen = sizeof(struct tcphdr); break; case VIRTIO_NET_HDR_GSO_TCPV6: gso_type = SKB_GSO_TCPV6; ip_proto = IPPROTO_TCP; thlen = sizeof(struct tcphdr); nh_min_len = sizeof(struct ipv6hdr); break; case VIRTIO_NET_HDR_GSO_UDP: gso_type = SKB_GSO_UDP; ip_proto = IPPROTO_UDP; thlen = sizeof(struct udphdr); break; case VIRTIO_NET_HDR_GSO_UDP_L4: gso_type = SKB_GSO_UDP_L4; ip_proto = IPPROTO_UDP; thlen = sizeof(struct udphdr); break; default: return -EINVAL; } if (hdr->gso_type & VIRTIO_NET_HDR_GSO_ECN) gso_type |= SKB_GSO_TCP_ECN; if (hdr->gso_size == 0) return -EINVAL; } skb_reset_mac_header(skb); if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { u32 start = __virtio16_to_cpu(little_endian, hdr->csum_start); u32 off = __virtio16_to_cpu(little_endian, hdr->csum_offset); u32 needed = start + max_t(u32, thlen, off + sizeof(__sum16)); if (!pskb_may_pull(skb, needed)) return -EINVAL; if (!skb_partial_csum_set(skb, start, off)) return -EINVAL; if (skb_transport_offset(skb) < nh_min_len) return -EINVAL; nh_min_len = skb_transport_offset(skb); p_off = nh_min_len + thlen; if (!pskb_may_pull(skb, p_off)) return -EINVAL; } else { /* gso packets without NEEDS_CSUM do not set transport_offset. * probe and drop if does not match one of the above types. */ if (gso_type && skb->network_header) { struct flow_keys_basic keys; if (!skb->protocol) { __be16 protocol = dev_parse_header_protocol(skb); if (!protocol) virtio_net_hdr_set_proto(skb, hdr); else if (!virtio_net_hdr_match_proto(protocol, hdr->gso_type)) return -EINVAL; else skb->protocol = protocol; } retry: if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, NULL, 0, 0, 0, 0)) { /* UFO does not specify ipv4 or 6: try both */ if (gso_type & SKB_GSO_UDP && skb->protocol == htons(ETH_P_IP)) { skb->protocol = htons(ETH_P_IPV6); goto retry; } return -EINVAL; } p_off = keys.control.thoff + thlen; if (!pskb_may_pull(skb, p_off) || keys.basic.ip_proto != ip_proto) return -EINVAL; skb_set_transport_header(skb, keys.control.thoff); } else if (gso_type) { p_off = nh_min_len + thlen; if (!pskb_may_pull(skb, p_off)) return -EINVAL; } } if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size); unsigned int nh_off = p_off; struct skb_shared_info *shinfo = skb_shinfo(skb); switch (gso_type & ~SKB_GSO_TCP_ECN) { case SKB_GSO_UDP: /* UFO may not include transport header in gso_size. */ nh_off -= thlen; break; case SKB_GSO_UDP_L4: if (!(hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM)) return -EINVAL; if (skb->csum_offset != offsetof(struct udphdr, check)) return -EINVAL; if (skb->len - p_off > gso_size * UDP_MAX_SEGMENTS) return -EINVAL; if (gso_type != SKB_GSO_UDP_L4) return -EINVAL; break; case SKB_GSO_TCPV4: case SKB_GSO_TCPV6: if (skb->ip_summed == CHECKSUM_PARTIAL && skb->csum_offset != offsetof(struct tcphdr, check)) return -EINVAL; break; } /* Kernel has a special handling for GSO_BY_FRAGS. */ if (gso_size == GSO_BY_FRAGS) return -EINVAL; /* Too small packets are not really GSO ones. */ if (skb->len - nh_off > gso_size) { shinfo->gso_size = gso_size; shinfo->gso_type = gso_type; /* Header must be checked, and gso_segs computed. */ shinfo->gso_type |= SKB_GSO_DODGY; shinfo->gso_segs = 0; } } return 0; } static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, struct virtio_net_hdr *hdr, bool little_endian, bool has_data_valid, int vlan_hlen) { memset(hdr, 0, sizeof(*hdr)); /* no info leak */ if (skb_is_gso(skb)) { struct skb_shared_info *sinfo = skb_shinfo(skb); /* This is a hint as to how much should be linear. */ hdr->hdr_len = __cpu_to_virtio16(little_endian, skb_headlen(skb)); hdr->gso_size = __cpu_to_virtio16(little_endian, sinfo->gso_size); if (sinfo->gso_type & SKB_GSO_TCPV4) hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (sinfo->gso_type & SKB_GSO_TCPV6) hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6; else if (sinfo->gso_type & SKB_GSO_UDP_L4) hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP_L4; else return -EINVAL; if (sinfo->gso_type & SKB_GSO_TCP_ECN) hdr->gso_type |= VIRTIO_NET_HDR_GSO_ECN; } else hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE; if (skb->ip_summed == CHECKSUM_PARTIAL) { hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; hdr->csum_start = __cpu_to_virtio16(little_endian, skb_checksum_start_offset(skb) + vlan_hlen); hdr->csum_offset = __cpu_to_virtio16(little_endian, skb->csum_offset); } else if (has_data_valid && skb->ip_summed == CHECKSUM_UNNECESSARY) { hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID; } /* else everything is zero */ return 0; } #endif /* _LINUX_VIRTIO_NET_H */ |
| 1 1 1 17 1 1 29 11 64 63 9 9 9 9 16 3 15 2 16 16 16 1 2 2 2 2 52 1 52 46 6 2 48 2 45 45 45 45 1 1 1 45 45 45 45 2 2 2 2 2 2 2 2 2 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 83 82 2 2 2 2 2 2 83 83 2 2 2 2 85 44 44 44 73 35 35 43 13 1 12 12 12 12 45 45 45 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2015, 2016 ARM Ltd. */ #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/kvm.h> #include <linux/kvm_host.h> #include <linux/list_sort.h> #include <linux/nospec.h> #include <asm/kvm_hyp.h> #include "vgic.h" #define CREATE_TRACE_POINTS #include "trace.h" struct vgic_global kvm_vgic_global_state __ro_after_init = { .gicv3_cpuif = STATIC_KEY_FALSE_INIT, }; /* * Locking order is always: * kvm->lock (mutex) * vcpu->mutex (mutex) * kvm->arch.config_lock (mutex) * its->cmd_lock (mutex) * its->its_lock (mutex) * vgic_cpu->ap_list_lock must be taken with IRQs disabled * vgic_dist->lpi_xa.xa_lock must be taken with IRQs disabled * vgic_irq->irq_lock must be taken with IRQs disabled * * As the ap_list_lock might be taken from the timer interrupt handler, * we have to disable IRQs before taking this lock and everything lower * than it. * * The config_lock has additional ordering requirements: * kvm->slots_lock * kvm->srcu * kvm->arch.config_lock * * If you need to take multiple locks, always take the upper lock first, * then the lower ones, e.g. first take the its_lock, then the irq_lock. * If you are already holding a lock and need to take a higher one, you * have to drop the lower ranking lock first and re-acquire it after having * taken the upper one. * * When taking more than one ap_list_lock at the same time, always take the * lowest numbered VCPU's ap_list_lock first, so: * vcpuX->vcpu_id < vcpuY->vcpu_id: * raw_spin_lock(vcpuX->arch.vgic_cpu.ap_list_lock); * raw_spin_lock(vcpuY->arch.vgic_cpu.ap_list_lock); * * Since the VGIC must support injecting virtual interrupts from ISRs, we have * to use the raw_spin_lock_irqsave/raw_spin_unlock_irqrestore versions of outer * spinlocks for any lock that may be taken while injecting an interrupt. */ /* * Index the VM's xarray of mapped LPIs and return a reference to the IRQ * structure. The caller is expected to call vgic_put_irq() later once it's * finished with the IRQ. */ static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid) { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq = NULL; rcu_read_lock(); irq = xa_load(&dist->lpi_xa, intid); if (!vgic_try_get_irq_kref(irq)) irq = NULL; rcu_read_unlock(); return irq; } /* * This looks up the virtual interrupt ID to get the corresponding * struct vgic_irq. It also increases the refcount, so any caller is expected * to call vgic_put_irq() once it's finished with this IRQ. */ struct vgic_irq *vgic_get_irq(struct kvm *kvm, u32 intid) { /* SPIs */ if (intid >= VGIC_NR_PRIVATE_IRQS && intid < (kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS)) { intid = array_index_nospec(intid, kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS); return &kvm->arch.vgic.spis[intid - VGIC_NR_PRIVATE_IRQS]; } /* LPIs */ if (intid >= VGIC_MIN_LPI) return vgic_get_lpi(kvm, intid); return NULL; } struct vgic_irq *vgic_get_vcpu_irq(struct kvm_vcpu *vcpu, u32 intid) { if (WARN_ON(!vcpu)) return NULL; /* SGIs and PPIs */ if (intid < VGIC_NR_PRIVATE_IRQS) { intid = array_index_nospec(intid, VGIC_NR_PRIVATE_IRQS); return &vcpu->arch.vgic_cpu.private_irqs[intid]; } return vgic_get_irq(vcpu->kvm, intid); } /* * We can't do anything in here, because we lack the kvm pointer to * lock and remove the item from the lpi_list. So we keep this function * empty and use the return value of kref_put() to trigger the freeing. */ static void vgic_irq_release(struct kref *ref) { } void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq) { struct vgic_dist *dist = &kvm->arch.vgic; unsigned long flags; if (irq->intid < VGIC_MIN_LPI) return; if (!kref_put(&irq->refcount, vgic_irq_release)) return; xa_lock_irqsave(&dist->lpi_xa, flags); __xa_erase(&dist->lpi_xa, irq->intid); xa_unlock_irqrestore(&dist->lpi_xa, flags); kfree_rcu(irq, rcu); } void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_irq *irq, *tmp; unsigned long flags; raw_spin_lock_irqsave(&vgic_cpu->ap_list_lock, flags); list_for_each_entry_safe(irq, tmp, &vgic_cpu->ap_list_head, ap_list) { if (irq->intid >= VGIC_MIN_LPI) { raw_spin_lock(&irq->irq_lock); list_del(&irq->ap_list); irq->vcpu = NULL; raw_spin_unlock(&irq->irq_lock); vgic_put_irq(vcpu->kvm, irq); } } raw_spin_unlock_irqrestore(&vgic_cpu->ap_list_lock, flags); } void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending) { WARN_ON(irq_set_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, pending)); } bool vgic_get_phys_line_level(struct vgic_irq *irq) { bool line_level; BUG_ON(!irq->hw); if (irq->ops && irq->ops->get_input_level) return irq->ops->get_input_level(irq->intid); WARN_ON(irq_get_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, &line_level)); return line_level; } /* Set/Clear the physical active state */ void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active) { BUG_ON(!irq->hw); WARN_ON(irq_set_irqchip_state(irq->host_irq, IRQCHIP_STATE_ACTIVE, active)); } /** * vgic_target_oracle - compute the target vcpu for an irq * * @irq: The irq to route. Must be already locked. * * Based on the current state of the interrupt (enabled, pending, * active, vcpu and target_vcpu), compute the next vcpu this should be * given to. Return NULL if this shouldn't be injected at all. * * Requires the IRQ lock to be held. */ static struct kvm_vcpu *vgic_target_oracle(struct vgic_irq *irq) { lockdep_assert_held(&irq->irq_lock); /* If the interrupt is active, it must stay on the current vcpu */ if (irq->active) return irq->vcpu ? : irq->target_vcpu; /* * If the IRQ is not active but enabled and pending, we should direct * it to its configured target VCPU. * If the distributor is disabled, pending interrupts shouldn't be * forwarded. */ if (irq->enabled && irq_is_pending(irq)) { if (unlikely(irq->target_vcpu && !irq->target_vcpu->kvm->arch.vgic.enabled)) return NULL; return irq->target_vcpu; } /* If neither active nor pending and enabled, then this IRQ should not * be queued to any VCPU. */ return NULL; } /* * The order of items in the ap_lists defines how we'll pack things in LRs as * well, the first items in the list being the first things populated in the * LRs. * * A hard rule is that active interrupts can never be pushed out of the LRs * (and therefore take priority) since we cannot reliably trap on deactivation * of IRQs and therefore they have to be present in the LRs. * * Otherwise things should be sorted by the priority field and the GIC * hardware support will take care of preemption of priority groups etc. * * Return negative if "a" sorts before "b", 0 to preserve order, and positive * to sort "b" before "a". */ static int vgic_irq_cmp(void *priv, const struct list_head *a, const struct list_head *b) { struct vgic_irq *irqa = container_of(a, struct vgic_irq, ap_list); struct vgic_irq *irqb = container_of(b, struct vgic_irq, ap_list); bool penda, pendb; int ret; /* * list_sort may call this function with the same element when * the list is fairly long. */ if (unlikely(irqa == irqb)) return 0; raw_spin_lock(&irqa->irq_lock); raw_spin_lock_nested(&irqb->irq_lock, SINGLE_DEPTH_NESTING); if (irqa->active || irqb->active) { ret = (int)irqb->active - (int)irqa->active; goto out; } penda = irqa->enabled && irq_is_pending(irqa); pendb = irqb->enabled && irq_is_pending(irqb); if (!penda || !pendb) { ret = (int)pendb - (int)penda; goto out; } /* Both pending and enabled, sort by priority */ ret = irqa->priority - irqb->priority; out: raw_spin_unlock(&irqb->irq_lock); raw_spin_unlock(&irqa->irq_lock); return ret; } /* Must be called with the ap_list_lock held */ static void vgic_sort_ap_list(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; lockdep_assert_held(&vgic_cpu->ap_list_lock); list_sort(NULL, &vgic_cpu->ap_list_head, vgic_irq_cmp); } /* * Only valid injection if changing level for level-triggered IRQs or for a * rising edge, and in-kernel connected IRQ lines can only be controlled by * their owner. */ static bool vgic_validate_injection(struct vgic_irq *irq, bool level, void *owner) { if (irq->owner != owner) return false; switch (irq->config) { case VGIC_CONFIG_LEVEL: return irq->line_level != level; case VGIC_CONFIG_EDGE: return level; } return false; } /* * Check whether an IRQ needs to (and can) be queued to a VCPU's ap list. * Do the queuing if necessary, taking the right locks in the right order. * Returns true when the IRQ was queued, false otherwise. * * Needs to be entered with the IRQ lock already held, but will return * with all locks dropped. */ bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq, unsigned long flags) __releases(&irq->irq_lock) { struct kvm_vcpu *vcpu; lockdep_assert_held(&irq->irq_lock); retry: vcpu = vgic_target_oracle(irq); if (irq->vcpu || !vcpu) { /* * If this IRQ is already on a VCPU's ap_list, then it * cannot be moved or modified and there is no more work for * us to do. * * Otherwise, if the irq is not pending and enabled, it does * not need to be inserted into an ap_list and there is also * no more work for us to do. */ raw_spin_unlock_irqrestore(&irq->irq_lock, flags); /* * We have to kick the VCPU here, because we could be * queueing an edge-triggered interrupt for which we * get no EOI maintenance interrupt. In that case, * while the IRQ is already on the VCPU's AP list, the * VCPU could have EOI'ed the original interrupt and * won't see this one until it exits for some other * reason. */ if (vcpu) { kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); kvm_vcpu_kick(vcpu); } return false; } /* * We must unlock the irq lock to take the ap_list_lock where * we are going to insert this new pending interrupt. */ raw_spin_unlock_irqrestore(&irq->irq_lock, flags); /* someone can do stuff here, which we re-check below */ raw_spin_lock_irqsave(&vcpu->arch.vgic_cpu.ap_list_lock, flags); raw_spin_lock(&irq->irq_lock); /* * Did something change behind our backs? * * There are two cases: * 1) The irq lost its pending state or was disabled behind our * backs and/or it was queued to another VCPU's ap_list. * 2) Someone changed the affinity on this irq behind our * backs and we are now holding the wrong ap_list_lock. * * In both cases, drop the locks and retry. */ if (unlikely(irq->vcpu || vcpu != vgic_target_oracle(irq))) { raw_spin_unlock(&irq->irq_lock); raw_spin_unlock_irqrestore(&vcpu->arch.vgic_cpu.ap_list_lock, flags); raw_spin_lock_irqsave(&irq->irq_lock, flags); goto retry; } /* * Grab a reference to the irq to reflect the fact that it is * now in the ap_list. This is safe as the caller must already hold a * reference on the irq. */ vgic_get_irq_kref(irq); list_add_tail(&irq->ap_list, &vcpu->arch.vgic_cpu.ap_list_head); irq->vcpu = vcpu; raw_spin_unlock(&irq->irq_lock); raw_spin_unlock_irqrestore(&vcpu->arch.vgic_cpu.ap_list_lock, flags); kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); kvm_vcpu_kick(vcpu); return true; } /** * kvm_vgic_inject_irq - Inject an IRQ from a device to the vgic * @kvm: The VM structure pointer * @vcpu: The CPU for PPIs or NULL for global interrupts * @intid: The INTID to inject a new state to. * @level: Edge-triggered: true: to trigger the interrupt * false: to ignore the call * Level-sensitive true: raise the input signal * false: lower the input signal * @owner: The opaque pointer to the owner of the IRQ being raised to verify * that the caller is allowed to inject this IRQ. Userspace * injections will have owner == NULL. * * The VGIC is not concerned with devices being active-LOW or active-HIGH for * level-sensitive interrupts. You can think of the level parameter as 1 * being HIGH and 0 being LOW and all devices being active-HIGH. */ int kvm_vgic_inject_irq(struct kvm *kvm, struct kvm_vcpu *vcpu, unsigned int intid, bool level, void *owner) { struct vgic_irq *irq; unsigned long flags; int ret; ret = vgic_lazy_init(kvm); if (ret) return ret; if (!vcpu && intid < VGIC_NR_PRIVATE_IRQS) return -EINVAL; trace_vgic_update_irq_pending(vcpu ? vcpu->vcpu_idx : 0, intid, level); if (intid < VGIC_NR_PRIVATE_IRQS) irq = vgic_get_vcpu_irq(vcpu, intid); else irq = vgic_get_irq(kvm, intid); if (!irq) return -EINVAL; raw_spin_lock_irqsave(&irq->irq_lock, flags); if (!vgic_validate_injection(irq, level, owner)) { /* Nothing to see here, move along... */ raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(kvm, irq); return 0; } if (irq->config == VGIC_CONFIG_LEVEL) irq->line_level = level; else irq->pending_latch = true; vgic_queue_irq_unlock(kvm, irq, flags); vgic_put_irq(kvm, irq); return 0; } /* @irq->irq_lock must be held */ static int kvm_vgic_map_irq(struct kvm_vcpu *vcpu, struct vgic_irq *irq, unsigned int host_irq, struct irq_ops *ops) { struct irq_desc *desc; struct irq_data *data; /* * Find the physical IRQ number corresponding to @host_irq */ desc = irq_to_desc(host_irq); if (!desc) { kvm_err("%s: no interrupt descriptor\n", __func__); return -EINVAL; } data = irq_desc_get_irq_data(desc); while (data->parent_data) data = data->parent_data; irq->hw = true; irq->host_irq = host_irq; irq->hwintid = data->hwirq; irq->ops = ops; return 0; } /* @irq->irq_lock must be held */ static inline void kvm_vgic_unmap_irq(struct vgic_irq *irq) { irq->hw = false; irq->hwintid = 0; irq->ops = NULL; } int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq, u32 vintid, struct irq_ops *ops) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, vintid); unsigned long flags; int ret; BUG_ON(!irq); raw_spin_lock_irqsave(&irq->irq_lock, flags); ret = kvm_vgic_map_irq(vcpu, irq, host_irq, ops); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); return ret; } /** * kvm_vgic_reset_mapped_irq - Reset a mapped IRQ * @vcpu: The VCPU pointer * @vintid: The INTID of the interrupt * * Reset the active and pending states of a mapped interrupt. Kernel * subsystems injecting mapped interrupts should reset their interrupt lines * when we are doing a reset of the VM. */ void kvm_vgic_reset_mapped_irq(struct kvm_vcpu *vcpu, u32 vintid) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, vintid); unsigned long flags; if (!irq->hw) goto out; raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->active = false; irq->pending_latch = false; irq->line_level = false; raw_spin_unlock_irqrestore(&irq->irq_lock, flags); out: vgic_put_irq(vcpu->kvm, irq); } int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int vintid) { struct vgic_irq *irq; unsigned long flags; if (!vgic_initialized(vcpu->kvm)) return -EAGAIN; irq = vgic_get_vcpu_irq(vcpu, vintid); BUG_ON(!irq); raw_spin_lock_irqsave(&irq->irq_lock, flags); kvm_vgic_unmap_irq(irq); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); return 0; } int kvm_vgic_get_map(struct kvm_vcpu *vcpu, unsigned int vintid) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, vintid); unsigned long flags; int ret = -1; raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->hw) ret = irq->hwintid; raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); return ret; } /** * kvm_vgic_set_owner - Set the owner of an interrupt for a VM * * @vcpu: Pointer to the VCPU (used for PPIs) * @intid: The virtual INTID identifying the interrupt (PPI or SPI) * @owner: Opaque pointer to the owner * * Returns 0 if intid is not already used by another in-kernel device and the * owner is set, otherwise returns an error code. */ int kvm_vgic_set_owner(struct kvm_vcpu *vcpu, unsigned int intid, void *owner) { struct vgic_irq *irq; unsigned long flags; int ret = 0; if (!vgic_initialized(vcpu->kvm)) return -EAGAIN; /* SGIs and LPIs cannot be wired up to any device */ if (!irq_is_ppi(intid) && !vgic_valid_spi(vcpu->kvm, intid)) return -EINVAL; irq = vgic_get_vcpu_irq(vcpu, intid); raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->owner && irq->owner != owner) ret = -EEXIST; else irq->owner = owner; raw_spin_unlock_irqrestore(&irq->irq_lock, flags); return ret; } /** * vgic_prune_ap_list - Remove non-relevant interrupts from the list * * @vcpu: The VCPU pointer * * Go over the list of "interesting" interrupts, and prune those that we * won't have to consider in the near future. */ static void vgic_prune_ap_list(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_irq *irq, *tmp; DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); retry: raw_spin_lock(&vgic_cpu->ap_list_lock); list_for_each_entry_safe(irq, tmp, &vgic_cpu->ap_list_head, ap_list) { struct kvm_vcpu *target_vcpu, *vcpuA, *vcpuB; bool target_vcpu_needs_kick = false; raw_spin_lock(&irq->irq_lock); BUG_ON(vcpu != irq->vcpu); target_vcpu = vgic_target_oracle(irq); if (!target_vcpu) { /* * We don't need to process this interrupt any * further, move it off the list. */ list_del(&irq->ap_list); irq->vcpu = NULL; raw_spin_unlock(&irq->irq_lock); /* * This vgic_put_irq call matches the * vgic_get_irq_kref in vgic_queue_irq_unlock, * where we added the LPI to the ap_list. As * we remove the irq from the list, we drop * also drop the refcount. */ vgic_put_irq(vcpu->kvm, irq); continue; } if (target_vcpu == vcpu) { /* We're on the right CPU */ raw_spin_unlock(&irq->irq_lock); continue; } /* This interrupt looks like it has to be migrated. */ raw_spin_unlock(&irq->irq_lock); raw_spin_unlock(&vgic_cpu->ap_list_lock); /* * Ensure locking order by always locking the smallest * ID first. */ if (vcpu->vcpu_id < target_vcpu->vcpu_id) { vcpuA = vcpu; vcpuB = target_vcpu; } else { vcpuA = target_vcpu; vcpuB = vcpu; } raw_spin_lock(&vcpuA->arch.vgic_cpu.ap_list_lock); raw_spin_lock_nested(&vcpuB->arch.vgic_cpu.ap_list_lock, SINGLE_DEPTH_NESTING); raw_spin_lock(&irq->irq_lock); /* * If the affinity has been preserved, move the * interrupt around. Otherwise, it means things have * changed while the interrupt was unlocked, and we * need to replay this. * * In all cases, we cannot trust the list not to have * changed, so we restart from the beginning. */ if (target_vcpu == vgic_target_oracle(irq)) { struct vgic_cpu *new_cpu = &target_vcpu->arch.vgic_cpu; list_del(&irq->ap_list); irq->vcpu = target_vcpu; list_add_tail(&irq->ap_list, &new_cpu->ap_list_head); target_vcpu_needs_kick = true; } raw_spin_unlock(&irq->irq_lock); raw_spin_unlock(&vcpuB->arch.vgic_cpu.ap_list_lock); raw_spin_unlock(&vcpuA->arch.vgic_cpu.ap_list_lock); if (target_vcpu_needs_kick) { kvm_make_request(KVM_REQ_IRQ_PENDING, target_vcpu); kvm_vcpu_kick(target_vcpu); } goto retry; } raw_spin_unlock(&vgic_cpu->ap_list_lock); } static inline void vgic_fold_lr_state(struct kvm_vcpu *vcpu) { if (kvm_vgic_global_state.type == VGIC_V2) vgic_v2_fold_lr_state(vcpu); else vgic_v3_fold_lr_state(vcpu); } /* Requires the irq_lock to be held. */ static inline void vgic_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr) { lockdep_assert_held(&irq->irq_lock); if (kvm_vgic_global_state.type == VGIC_V2) vgic_v2_populate_lr(vcpu, irq, lr); else vgic_v3_populate_lr(vcpu, irq, lr); } static inline void vgic_clear_lr(struct kvm_vcpu *vcpu, int lr) { if (kvm_vgic_global_state.type == VGIC_V2) vgic_v2_clear_lr(vcpu, lr); else vgic_v3_clear_lr(vcpu, lr); } static inline void vgic_set_underflow(struct kvm_vcpu *vcpu) { if (kvm_vgic_global_state.type == VGIC_V2) vgic_v2_set_underflow(vcpu); else vgic_v3_set_underflow(vcpu); } /* Requires the ap_list_lock to be held. */ static int compute_ap_list_depth(struct kvm_vcpu *vcpu, bool *multi_sgi) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_irq *irq; int count = 0; *multi_sgi = false; lockdep_assert_held(&vgic_cpu->ap_list_lock); list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { int w; raw_spin_lock(&irq->irq_lock); /* GICv2 SGIs can count for more than one... */ w = vgic_irq_get_lr_count(irq); raw_spin_unlock(&irq->irq_lock); count += w; *multi_sgi |= (w > 1); } return count; } /* Requires the VCPU's ap_list_lock to be held. */ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_irq *irq; int count; bool multi_sgi; u8 prio = 0xff; int i = 0; lockdep_assert_held(&vgic_cpu->ap_list_lock); count = compute_ap_list_depth(vcpu, &multi_sgi); if (count > kvm_vgic_global_state.nr_lr || multi_sgi) vgic_sort_ap_list(vcpu); count = 0; list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { raw_spin_lock(&irq->irq_lock); /* * If we have multi-SGIs in the pipeline, we need to * guarantee that they are all seen before any IRQ of * lower priority. In that case, we need to filter out * these interrupts by exiting early. This is easy as * the AP list has been sorted already. */ if (multi_sgi && irq->priority > prio) { _raw_spin_unlock(&irq->irq_lock); break; } if (likely(vgic_target_oracle(irq) == vcpu)) { vgic_populate_lr(vcpu, irq, count++); if (irq->source) prio = irq->priority; } raw_spin_unlock(&irq->irq_lock); if (count == kvm_vgic_global_state.nr_lr) { if (!list_is_last(&irq->ap_list, &vgic_cpu->ap_list_head)) vgic_set_underflow(vcpu); break; } } /* Nuke remaining LRs */ for (i = count ; i < kvm_vgic_global_state.nr_lr; i++) vgic_clear_lr(vcpu, i); if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) vcpu->arch.vgic_cpu.vgic_v2.used_lrs = count; else vcpu->arch.vgic_cpu.vgic_v3.used_lrs = count; } static inline bool can_access_vgic_from_kernel(void) { /* * GICv2 can always be accessed from the kernel because it is * memory-mapped, and VHE systems can access GICv3 EL2 system * registers. */ return !static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif) || has_vhe(); } static inline void vgic_save_state(struct kvm_vcpu *vcpu) { if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) vgic_v2_save_state(vcpu); else __vgic_v3_save_state(&vcpu->arch.vgic_cpu.vgic_v3); } /* Sync back the hardware VGIC state into our emulation after a guest's run. */ void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) { int used_lrs; /* An empty ap_list_head implies used_lrs == 0 */ if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head)) return; if (can_access_vgic_from_kernel()) vgic_save_state(vcpu); if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) used_lrs = vcpu->arch.vgic_cpu.vgic_v2.used_lrs; else used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs; if (used_lrs) vgic_fold_lr_state(vcpu); vgic_prune_ap_list(vcpu); } static inline void vgic_restore_state(struct kvm_vcpu *vcpu) { if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) vgic_v2_restore_state(vcpu); else __vgic_v3_restore_state(&vcpu->arch.vgic_cpu.vgic_v3); } /* Flush our emulation state into the GIC hardware before entering the guest. */ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) { /* * If there are no virtual interrupts active or pending for this * VCPU, then there is no work to do and we can bail out without * taking any lock. There is a potential race with someone injecting * interrupts to the VCPU, but it is a benign race as the VCPU will * either observe the new interrupt before or after doing this check, * and introducing additional synchronization mechanism doesn't change * this. * * Note that we still need to go through the whole thing if anything * can be directly injected (GICv4). */ if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head) && !vgic_supports_direct_msis(vcpu->kvm)) return; DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); if (!list_empty(&vcpu->arch.vgic_cpu.ap_list_head)) { raw_spin_lock(&vcpu->arch.vgic_cpu.ap_list_lock); vgic_flush_lr_state(vcpu); raw_spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock); } if (can_access_vgic_from_kernel()) vgic_restore_state(vcpu); if (vgic_supports_direct_msis(vcpu->kvm)) vgic_v4_commit(vcpu); } void kvm_vgic_load(struct kvm_vcpu *vcpu) { if (unlikely(!irqchip_in_kernel(vcpu->kvm) || !vgic_initialized(vcpu->kvm))) { if (has_vhe() && static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) __vgic_v3_activate_traps(&vcpu->arch.vgic_cpu.vgic_v3); return; } if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) vgic_v2_load(vcpu); else vgic_v3_load(vcpu); } void kvm_vgic_put(struct kvm_vcpu *vcpu) { if (unlikely(!irqchip_in_kernel(vcpu->kvm) || !vgic_initialized(vcpu->kvm))) { if (has_vhe() && static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) __vgic_v3_deactivate_traps(&vcpu->arch.vgic_cpu.vgic_v3); return; } if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) vgic_v2_put(vcpu); else vgic_v3_put(vcpu); } int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_irq *irq; bool pending = false; unsigned long flags; struct vgic_vmcr vmcr; if (!vcpu->kvm->arch.vgic.enabled) return false; if (vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last) return true; vgic_get_vmcr(vcpu, &vmcr); raw_spin_lock_irqsave(&vgic_cpu->ap_list_lock, flags); list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { raw_spin_lock(&irq->irq_lock); pending = irq_is_pending(irq) && irq->enabled && !irq->active && irq->priority < vmcr.pmr; raw_spin_unlock(&irq->irq_lock); if (pending) break; } raw_spin_unlock_irqrestore(&vgic_cpu->ap_list_lock, flags); return pending; } void vgic_kick_vcpus(struct kvm *kvm) { struct kvm_vcpu *vcpu; unsigned long c; /* * We've injected an interrupt, time to find out who deserves * a good kick... */ kvm_for_each_vcpu(c, vcpu, kvm) { if (kvm_vgic_vcpu_pending_irq(vcpu)) { kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); kvm_vcpu_kick(vcpu); } } } bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int vintid) { struct vgic_irq *irq; bool map_is_active; unsigned long flags; if (!vgic_initialized(vcpu->kvm)) return false; irq = vgic_get_vcpu_irq(vcpu, vintid); raw_spin_lock_irqsave(&irq->irq_lock, flags); map_is_active = irq->hw && irq->active; raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); return map_is_active; } /* * Level-triggered mapped IRQs are special because we only observe rising * edges as input to the VGIC. * * If the guest never acked the interrupt we have to sample the physical * line and set the line level, because the device state could have changed * or we simply need to process the still pending interrupt later. * * We could also have entered the guest with the interrupt active+pending. * On the next exit, we need to re-evaluate the pending state, as it could * otherwise result in a spurious interrupt by injecting a now potentially * stale pending state. * * If this causes us to lower the level, we have to also clear the physical * active state, since we will otherwise never be told when the interrupt * becomes asserted again. * * Another case is when the interrupt requires a helping hand on * deactivation (no HW deactivation, for example). */ void vgic_irq_handle_resampling(struct vgic_irq *irq, bool lr_deactivated, bool lr_pending) { if (vgic_irq_is_mapped_level(irq)) { bool resample = false; if (unlikely(vgic_irq_needs_resampling(irq))) { resample = !(irq->active || irq->pending_latch); } else if (lr_pending || (lr_deactivated && irq->line_level)) { irq->line_level = vgic_get_phys_line_level(irq); resample = !irq->line_level; } if (resample) vgic_irq_set_phys_active(irq, false); } } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 | // SPDX-License-Identifier: GPL-2.0 /* * device.h - generic, centralized driver model * * Copyright (c) 2001-2003 Patrick Mochel <mochel@osdl.org> * Copyright (c) 2004-2009 Greg Kroah-Hartman <gregkh@suse.de> * Copyright (c) 2008-2009 Novell Inc. * * See Documentation/driver-api/driver-model/ for more information. */ #ifndef _DEVICE_H_ #define _DEVICE_H_ #include <linux/dev_printk.h> #include <linux/energy_model.h> #include <linux/ioport.h> #include <linux/kobject.h> #include <linux/klist.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/compiler.h> #include <linux/types.h> #include <linux/mutex.h> #include <linux/pm.h> #include <linux/atomic.h> #include <linux/uidgid.h> #include <linux/gfp.h> #include <linux/overflow.h> #include <linux/device/bus.h> #include <linux/device/class.h> #include <linux/device/driver.h> #include <linux/cleanup.h> #include <asm/device.h> struct device; struct device_private; struct device_driver; struct driver_private; struct module; struct class; struct subsys_private; struct device_node; struct fwnode_handle; struct iommu_group; struct dev_pin_info; struct dev_iommu; struct msi_device_data; /** * struct subsys_interface - interfaces to device functions * @name: name of the device function * @subsys: subsystem of the devices to attach to * @node: the list of functions registered at the subsystem * @add_dev: device hookup to device function handler * @remove_dev: device hookup to device function handler * * Simple interfaces attached to a subsystem. Multiple interfaces can * attach to a subsystem and its devices. Unlike drivers, they do not * exclusively claim or control devices. Interfaces usually represent * a specific functionality of a subsystem/class of devices. */ struct subsys_interface { const char *name; const struct bus_type *subsys; struct list_head node; int (*add_dev)(struct device *dev, struct subsys_interface *sif); void (*remove_dev)(struct device *dev, struct subsys_interface *sif); }; int subsys_interface_register(struct subsys_interface *sif); void subsys_interface_unregister(struct subsys_interface *sif); int subsys_system_register(const struct bus_type *subsys, const struct attribute_group **groups); int subsys_virtual_register(const struct bus_type *subsys, const struct attribute_group **groups); /* * The type of device, "struct device" is embedded in. A class * or bus can contain devices of different types * like "partitions" and "disks", "mouse" and "event". * This identifies the device type and carries type-specific * information, equivalent to the kobj_type of a kobject. * If "name" is specified, the uevent will contain it in * the DEVTYPE variable. */ struct device_type { const char *name; const struct attribute_group **groups; int (*uevent)(const struct device *dev, struct kobj_uevent_env *env); char *(*devnode)(const struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid); void (*release)(struct device *dev); const struct dev_pm_ops *pm; }; /** * struct device_attribute - Interface for exporting device attributes. * @attr: sysfs attribute definition. * @show: Show handler. * @store: Store handler. */ struct device_attribute { struct attribute attr; ssize_t (*show)(struct device *dev, struct device_attribute *attr, char *buf); ssize_t (*store)(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); }; /** * struct dev_ext_attribute - Exported device attribute with extra context. * @attr: Exported device attribute. * @var: Pointer to context. */ struct dev_ext_attribute { struct device_attribute attr; void *var; }; ssize_t device_show_ulong(struct device *dev, struct device_attribute *attr, char *buf); ssize_t device_store_ulong(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); ssize_t device_show_int(struct device *dev, struct device_attribute *attr, char *buf); ssize_t device_store_int(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); ssize_t device_show_bool(struct device *dev, struct device_attribute *attr, char *buf); ssize_t device_store_bool(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); ssize_t device_show_string(struct device *dev, struct device_attribute *attr, char *buf); /** * DEVICE_ATTR - Define a device attribute. * @_name: Attribute name. * @_mode: File mode. * @_show: Show handler. Optional, but mandatory if attribute is readable. * @_store: Store handler. Optional, but mandatory if attribute is writable. * * Convenience macro for defining a struct device_attribute. * * For example, ``DEVICE_ATTR(foo, 0644, foo_show, foo_store);`` expands to: * * .. code-block:: c * * struct device_attribute dev_attr_foo = { * .attr = { .name = "foo", .mode = 0644 }, * .show = foo_show, * .store = foo_store, * }; */ #define DEVICE_ATTR(_name, _mode, _show, _store) \ struct device_attribute dev_attr_##_name = __ATTR(_name, _mode, _show, _store) /** * DEVICE_ATTR_PREALLOC - Define a preallocated device attribute. * @_name: Attribute name. * @_mode: File mode. * @_show: Show handler. Optional, but mandatory if attribute is readable. * @_store: Store handler. Optional, but mandatory if attribute is writable. * * Like DEVICE_ATTR(), but ``SYSFS_PREALLOC`` is set on @_mode. */ #define DEVICE_ATTR_PREALLOC(_name, _mode, _show, _store) \ struct device_attribute dev_attr_##_name = \ __ATTR_PREALLOC(_name, _mode, _show, _store) /** * DEVICE_ATTR_RW - Define a read-write device attribute. * @_name: Attribute name. * * Like DEVICE_ATTR(), but @_mode is 0644, @_show is <_name>_show, * and @_store is <_name>_store. */ #define DEVICE_ATTR_RW(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RW(_name) /** * DEVICE_ATTR_ADMIN_RW - Define an admin-only read-write device attribute. * @_name: Attribute name. * * Like DEVICE_ATTR_RW(), but @_mode is 0600. */ #define DEVICE_ATTR_ADMIN_RW(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RW_MODE(_name, 0600) /** * DEVICE_ATTR_RO - Define a readable device attribute. * @_name: Attribute name. * * Like DEVICE_ATTR(), but @_mode is 0444 and @_show is <_name>_show. */ #define DEVICE_ATTR_RO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RO(_name) /** * DEVICE_ATTR_ADMIN_RO - Define an admin-only readable device attribute. * @_name: Attribute name. * * Like DEVICE_ATTR_RO(), but @_mode is 0400. */ #define DEVICE_ATTR_ADMIN_RO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RO_MODE(_name, 0400) /** * DEVICE_ATTR_WO - Define an admin-only writable device attribute. * @_name: Attribute name. * * Like DEVICE_ATTR(), but @_mode is 0200 and @_store is <_name>_store. */ #define DEVICE_ATTR_WO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_WO(_name) /** * DEVICE_ULONG_ATTR - Define a device attribute backed by an unsigned long. * @_name: Attribute name. * @_mode: File mode. * @_var: Identifier of unsigned long. * * Like DEVICE_ATTR(), but @_show and @_store are automatically provided * such that reads and writes to the attribute from userspace affect @_var. */ #define DEVICE_ULONG_ATTR(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, _mode, device_show_ulong, device_store_ulong), &(_var) } /** * DEVICE_INT_ATTR - Define a device attribute backed by an int. * @_name: Attribute name. * @_mode: File mode. * @_var: Identifier of int. * * Like DEVICE_ULONG_ATTR(), but @_var is an int. */ #define DEVICE_INT_ATTR(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, _mode, device_show_int, device_store_int), &(_var) } /** * DEVICE_BOOL_ATTR - Define a device attribute backed by a bool. * @_name: Attribute name. * @_mode: File mode. * @_var: Identifier of bool. * * Like DEVICE_ULONG_ATTR(), but @_var is a bool. */ #define DEVICE_BOOL_ATTR(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, _mode, device_show_bool, device_store_bool), &(_var) } /** * DEVICE_STRING_ATTR_RO - Define a device attribute backed by a r/o string. * @_name: Attribute name. * @_mode: File mode. * @_var: Identifier of string. * * Like DEVICE_ULONG_ATTR(), but @_var is a string. Because the length of the * string allocation is unknown, the attribute must be read-only. */ #define DEVICE_STRING_ATTR_RO(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, (_mode) & ~0222, device_show_string, NULL), (_var) } #define DEVICE_ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) \ struct device_attribute dev_attr_##_name = \ __ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) int device_create_file(struct device *device, const struct device_attribute *entry); void device_remove_file(struct device *dev, const struct device_attribute *attr); bool device_remove_file_self(struct device *dev, const struct device_attribute *attr); int __must_check device_create_bin_file(struct device *dev, const struct bin_attribute *attr); void device_remove_bin_file(struct device *dev, const struct bin_attribute *attr); /* device resource management */ typedef void (*dr_release_t)(struct device *dev, void *res); typedef int (*dr_match_t)(struct device *dev, void *res, void *match_data); void *__devres_alloc_node(dr_release_t release, size_t size, gfp_t gfp, int nid, const char *name) __malloc; #define devres_alloc(release, size, gfp) \ __devres_alloc_node(release, size, gfp, NUMA_NO_NODE, #release) #define devres_alloc_node(release, size, gfp, nid) \ __devres_alloc_node(release, size, gfp, nid, #release) void devres_for_each_res(struct device *dev, dr_release_t release, dr_match_t match, void *match_data, void (*fn)(struct device *, void *, void *), void *data); void devres_free(void *res); void devres_add(struct device *dev, void *res); void *devres_find(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); void *devres_get(struct device *dev, void *new_res, dr_match_t match, void *match_data); void *devres_remove(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); int devres_destroy(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); int devres_release(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); /* devres group */ void * __must_check devres_open_group(struct device *dev, void *id, gfp_t gfp); void devres_close_group(struct device *dev, void *id); void devres_remove_group(struct device *dev, void *id); int devres_release_group(struct device *dev, void *id); /* managed devm_k.alloc/kfree for device drivers */ void *devm_kmalloc(struct device *dev, size_t size, gfp_t gfp) __alloc_size(2); void *devm_krealloc(struct device *dev, void *ptr, size_t size, gfp_t gfp) __must_check __realloc_size(3); __printf(3, 0) char *devm_kvasprintf(struct device *dev, gfp_t gfp, const char *fmt, va_list ap) __malloc; __printf(3, 4) char *devm_kasprintf(struct device *dev, gfp_t gfp, const char *fmt, ...) __malloc; static inline void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp) { return devm_kmalloc(dev, size, gfp | __GFP_ZERO); } static inline void *devm_kmalloc_array(struct device *dev, size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; return devm_kmalloc(dev, bytes, flags); } static inline void *devm_kcalloc(struct device *dev, size_t n, size_t size, gfp_t flags) { return devm_kmalloc_array(dev, n, size, flags | __GFP_ZERO); } static inline __realloc_size(3, 4) void * __must_check devm_krealloc_array(struct device *dev, void *p, size_t new_n, size_t new_size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(new_n, new_size, &bytes))) return NULL; return devm_krealloc(dev, p, bytes, flags); } void devm_kfree(struct device *dev, const void *p); char *devm_kstrdup(struct device *dev, const char *s, gfp_t gfp) __malloc; const char *devm_kstrdup_const(struct device *dev, const char *s, gfp_t gfp); void *devm_kmemdup(struct device *dev, const void *src, size_t len, gfp_t gfp) __realloc_size(3); unsigned long devm_get_free_pages(struct device *dev, gfp_t gfp_mask, unsigned int order); void devm_free_pages(struct device *dev, unsigned long addr); #ifdef CONFIG_HAS_IOMEM void __iomem *devm_ioremap_resource(struct device *dev, const struct resource *res); void __iomem *devm_ioremap_resource_wc(struct device *dev, const struct resource *res); void __iomem *devm_of_iomap(struct device *dev, struct device_node *node, int index, resource_size_t *size); #else static inline void __iomem *devm_ioremap_resource(struct device *dev, const struct resource *res) { return ERR_PTR(-EINVAL); } static inline void __iomem *devm_ioremap_resource_wc(struct device *dev, const struct resource *res) { return ERR_PTR(-EINVAL); } static inline void __iomem *devm_of_iomap(struct device *dev, struct device_node *node, int index, resource_size_t *size) { return ERR_PTR(-EINVAL); } #endif /* allows to add/remove a custom action to devres stack */ void devm_remove_action(struct device *dev, void (*action)(void *), void *data); void devm_release_action(struct device *dev, void (*action)(void *), void *data); int __devm_add_action(struct device *dev, void (*action)(void *), void *data, const char *name); #define devm_add_action(dev, action, data) \ __devm_add_action(dev, action, data, #action) static inline int __devm_add_action_or_reset(struct device *dev, void (*action)(void *), void *data, const char *name) { int ret; ret = __devm_add_action(dev, action, data, name); if (ret) action(data); return ret; } #define devm_add_action_or_reset(dev, action, data) \ __devm_add_action_or_reset(dev, action, data, #action) /** * devm_alloc_percpu - Resource-managed alloc_percpu * @dev: Device to allocate per-cpu memory for * @type: Type to allocate per-cpu memory for * * Managed alloc_percpu. Per-cpu memory allocated with this function is * automatically freed on driver detach. * * RETURNS: * Pointer to allocated memory on success, NULL on failure. */ #define devm_alloc_percpu(dev, type) \ ((typeof(type) __percpu *)__devm_alloc_percpu((dev), sizeof(type), \ __alignof__(type))) void __percpu *__devm_alloc_percpu(struct device *dev, size_t size, size_t align); void devm_free_percpu(struct device *dev, void __percpu *pdata); struct device_dma_parameters { /* * a low level driver may set these to teach IOMMU code about * sg limitations. */ unsigned int max_segment_size; unsigned int min_align_mask; unsigned long segment_boundary_mask; }; /** * enum device_link_state - Device link states. * @DL_STATE_NONE: The presence of the drivers is not being tracked. * @DL_STATE_DORMANT: None of the supplier/consumer drivers is present. * @DL_STATE_AVAILABLE: The supplier driver is present, but the consumer is not. * @DL_STATE_CONSUMER_PROBE: The consumer is probing (supplier driver present). * @DL_STATE_ACTIVE: Both the supplier and consumer drivers are present. * @DL_STATE_SUPPLIER_UNBIND: The supplier driver is unbinding. */ enum device_link_state { DL_STATE_NONE = -1, DL_STATE_DORMANT = 0, DL_STATE_AVAILABLE, DL_STATE_CONSUMER_PROBE, DL_STATE_ACTIVE, DL_STATE_SUPPLIER_UNBIND, }; /* * Device link flags. * * STATELESS: The core will not remove this link automatically. * AUTOREMOVE_CONSUMER: Remove the link automatically on consumer driver unbind. * PM_RUNTIME: If set, the runtime PM framework will use this link. * RPM_ACTIVE: Run pm_runtime_get_sync() on the supplier during link creation. * AUTOREMOVE_SUPPLIER: Remove the link automatically on supplier driver unbind. * AUTOPROBE_CONSUMER: Probe consumer driver automatically after supplier binds. * MANAGED: The core tracks presence of supplier/consumer drivers (internal). * SYNC_STATE_ONLY: Link only affects sync_state() behavior. * INFERRED: Inferred from data (eg: firmware) and not from driver actions. */ #define DL_FLAG_STATELESS BIT(0) #define DL_FLAG_AUTOREMOVE_CONSUMER BIT(1) #define DL_FLAG_PM_RUNTIME BIT(2) #define DL_FLAG_RPM_ACTIVE BIT(3) #define DL_FLAG_AUTOREMOVE_SUPPLIER BIT(4) #define DL_FLAG_AUTOPROBE_CONSUMER BIT(5) #define DL_FLAG_MANAGED BIT(6) #define DL_FLAG_SYNC_STATE_ONLY BIT(7) #define DL_FLAG_INFERRED BIT(8) #define DL_FLAG_CYCLE BIT(9) /** * enum dl_dev_state - Device driver presence tracking information. * @DL_DEV_NO_DRIVER: There is no driver attached to the device. * @DL_DEV_PROBING: A driver is probing. * @DL_DEV_DRIVER_BOUND: The driver has been bound to the device. * @DL_DEV_UNBINDING: The driver is unbinding from the device. */ enum dl_dev_state { DL_DEV_NO_DRIVER = 0, DL_DEV_PROBING, DL_DEV_DRIVER_BOUND, DL_DEV_UNBINDING, }; /** * enum device_removable - Whether the device is removable. The criteria for a * device to be classified as removable is determined by its subsystem or bus. * @DEVICE_REMOVABLE_NOT_SUPPORTED: This attribute is not supported for this * device (default). * @DEVICE_REMOVABLE_UNKNOWN: Device location is Unknown. * @DEVICE_FIXED: Device is not removable by the user. * @DEVICE_REMOVABLE: Device is removable by the user. */ enum device_removable { DEVICE_REMOVABLE_NOT_SUPPORTED = 0, /* must be 0 */ DEVICE_REMOVABLE_UNKNOWN, DEVICE_FIXED, DEVICE_REMOVABLE, }; /** * struct dev_links_info - Device data related to device links. * @suppliers: List of links to supplier devices. * @consumers: List of links to consumer devices. * @defer_sync: Hook to global list of devices that have deferred sync_state. * @status: Driver status information. */ struct dev_links_info { struct list_head suppliers; struct list_head consumers; struct list_head defer_sync; enum dl_dev_state status; }; /** * struct dev_msi_info - Device data related to MSI * @domain: The MSI interrupt domain associated to the device * @data: Pointer to MSI device data */ struct dev_msi_info { #ifdef CONFIG_GENERIC_MSI_IRQ struct irq_domain *domain; struct msi_device_data *data; #endif }; /** * enum device_physical_location_panel - Describes which panel surface of the * system's housing the device connection point resides on. * @DEVICE_PANEL_TOP: Device connection point is on the top panel. * @DEVICE_PANEL_BOTTOM: Device connection point is on the bottom panel. * @DEVICE_PANEL_LEFT: Device connection point is on the left panel. * @DEVICE_PANEL_RIGHT: Device connection point is on the right panel. * @DEVICE_PANEL_FRONT: Device connection point is on the front panel. * @DEVICE_PANEL_BACK: Device connection point is on the back panel. * @DEVICE_PANEL_UNKNOWN: The panel with device connection point is unknown. */ enum device_physical_location_panel { DEVICE_PANEL_TOP, DEVICE_PANEL_BOTTOM, DEVICE_PANEL_LEFT, DEVICE_PANEL_RIGHT, DEVICE_PANEL_FRONT, DEVICE_PANEL_BACK, DEVICE_PANEL_UNKNOWN, }; /** * enum device_physical_location_vertical_position - Describes vertical * position of the device connection point on the panel surface. * @DEVICE_VERT_POS_UPPER: Device connection point is at upper part of panel. * @DEVICE_VERT_POS_CENTER: Device connection point is at center part of panel. * @DEVICE_VERT_POS_LOWER: Device connection point is at lower part of panel. */ enum device_physical_location_vertical_position { DEVICE_VERT_POS_UPPER, DEVICE_VERT_POS_CENTER, DEVICE_VERT_POS_LOWER, }; /** * enum device_physical_location_horizontal_position - Describes horizontal * position of the device connection point on the panel surface. * @DEVICE_HORI_POS_LEFT: Device connection point is at left part of panel. * @DEVICE_HORI_POS_CENTER: Device connection point is at center part of panel. * @DEVICE_HORI_POS_RIGHT: Device connection point is at right part of panel. */ enum device_physical_location_horizontal_position { DEVICE_HORI_POS_LEFT, DEVICE_HORI_POS_CENTER, DEVICE_HORI_POS_RIGHT, }; /** * struct device_physical_location - Device data related to physical location * of the device connection point. * @panel: Panel surface of the system's housing that the device connection * point resides on. * @vertical_position: Vertical position of the device connection point within * the panel. * @horizontal_position: Horizontal position of the device connection point * within the panel. * @dock: Set if the device connection point resides in a docking station or * port replicator. * @lid: Set if this device connection point resides on the lid of laptop * system. */ struct device_physical_location { enum device_physical_location_panel panel; enum device_physical_location_vertical_position vertical_position; enum device_physical_location_horizontal_position horizontal_position; bool dock; bool lid; }; /** * struct device - The basic device structure * @parent: The device's "parent" device, the device to which it is attached. * In most cases, a parent device is some sort of bus or host * controller. If parent is NULL, the device, is a top-level device, * which is not usually what you want. * @p: Holds the private data of the driver core portions of the device. * See the comment of the struct device_private for detail. * @kobj: A top-level, abstract class from which other classes are derived. * @init_name: Initial name of the device. * @type: The type of device. * This identifies the device type and carries type-specific * information. * @mutex: Mutex to synchronize calls to its driver. * @bus: Type of bus device is on. * @driver: Which driver has allocated this * @platform_data: Platform data specific to the device. * Example: For devices on custom boards, as typical of embedded * and SOC based hardware, Linux often uses platform_data to point * to board-specific structures describing devices and how they * are wired. That can include what ports are available, chip * variants, which GPIO pins act in what additional roles, and so * on. This shrinks the "Board Support Packages" (BSPs) and * minimizes board-specific #ifdefs in drivers. * @driver_data: Private pointer for driver specific info. * @links: Links to suppliers and consumers of this device. * @power: For device power management. * See Documentation/driver-api/pm/devices.rst for details. * @pm_domain: Provide callbacks that are executed during system suspend, * hibernation, system resume and during runtime PM transitions * along with subsystem-level and driver-level callbacks. * @em_pd: device's energy model performance domain * @pins: For device pin management. * See Documentation/driver-api/pin-control.rst for details. * @msi: MSI related data * @numa_node: NUMA node this device is close to. * @dma_ops: DMA mapping operations for this device. * @dma_mask: Dma mask (if dma'ble device). * @coherent_dma_mask: Like dma_mask, but for alloc_coherent mapping as not all * hardware supports 64-bit addresses for consistent allocations * such descriptors. * @bus_dma_limit: Limit of an upstream bridge or bus which imposes a smaller * DMA limit than the device itself supports. * @dma_range_map: map for DMA memory ranges relative to that of RAM * @dma_parms: A low level driver may set these to teach IOMMU code about * segment limitations. * @dma_pools: Dma pools (if dma'ble device). * @dma_mem: Internal for coherent mem override. * @cma_area: Contiguous memory area for dma allocations * @dma_io_tlb_mem: Software IO TLB allocator. Not for driver use. * @dma_io_tlb_pools: List of transient swiotlb memory pools. * @dma_io_tlb_lock: Protects changes to the list of active pools. * @dma_uses_io_tlb: %true if device has used the software IO TLB. * @archdata: For arch-specific additions. * @of_node: Associated device tree node. * @fwnode: Associated device node supplied by platform firmware. * @devt: For creating the sysfs "dev". * @id: device instance * @devres_lock: Spinlock to protect the resource of the device. * @devres_head: The resources list of the device. * @class: The class of the device. * @groups: Optional attribute groups. * @release: Callback to free the device after all references have * gone away. This should be set by the allocator of the * device (i.e. the bus driver that discovered the device). * @iommu_group: IOMMU group the device belongs to. * @iommu: Per device generic IOMMU runtime data * @physical_location: Describes physical location of the device connection * point in the system housing. * @removable: Whether the device can be removed from the system. This * should be set by the subsystem / bus driver that discovered * the device. * * @offline_disabled: If set, the device is permanently online. * @offline: Set after successful invocation of bus type's .offline(). * @of_node_reused: Set if the device-tree node is shared with an ancestor * device. * @state_synced: The hardware state of this device has been synced to match * the software state of this device by calling the driver/bus * sync_state() callback. * @can_match: The device has matched with a driver at least once or it is in * a bus (like AMBA) which can't check for matching drivers until * other devices probe successfully. * @dma_coherent: this particular device is dma coherent, even if the * architecture supports non-coherent devices. * @dma_ops_bypass: If set to %true then the dma_ops are bypassed for the * streaming DMA operations (->map_* / ->unmap_* / ->sync_*), * and optionall (if the coherent mask is large enough) also * for dma allocations. This flag is managed by the dma ops * instance from ->dma_supported. * @dma_skip_sync: DMA sync operations can be skipped for coherent buffers. * @dma_iommu: Device is using default IOMMU implementation for DMA and * doesn't rely on dma_ops structure. * * At the lowest level, every device in a Linux system is represented by an * instance of struct device. The device structure contains the information * that the device model core needs to model the system. Most subsystems, * however, track additional information about the devices they host. As a * result, it is rare for devices to be represented by bare device structures; * instead, that structure, like kobject structures, is usually embedded within * a higher-level representation of the device. */ struct device { struct kobject kobj; struct device *parent; struct device_private *p; const char *init_name; /* initial name of the device */ const struct device_type *type; const struct bus_type *bus; /* type of bus device is on */ struct device_driver *driver; /* which driver has allocated this device */ void *platform_data; /* Platform specific data, device core doesn't touch it */ void *driver_data; /* Driver data, set and get with dev_set_drvdata/dev_get_drvdata */ struct mutex mutex; /* mutex to synchronize calls to * its driver. */ struct dev_links_info links; struct dev_pm_info power; struct dev_pm_domain *pm_domain; #ifdef CONFIG_ENERGY_MODEL struct em_perf_domain *em_pd; #endif #ifdef CONFIG_PINCTRL struct dev_pin_info *pins; #endif struct dev_msi_info msi; #ifdef CONFIG_ARCH_HAS_DMA_OPS const struct dma_map_ops *dma_ops; #endif u64 *dma_mask; /* dma mask (if dma'able device) */ u64 coherent_dma_mask;/* Like dma_mask, but for alloc_coherent mappings as not all hardware supports 64 bit addresses for consistent allocations such descriptors. */ u64 bus_dma_limit; /* upstream dma constraint */ const struct bus_dma_region *dma_range_map; struct device_dma_parameters *dma_parms; struct list_head dma_pools; /* dma pools (if dma'ble) */ #ifdef CONFIG_DMA_DECLARE_COHERENT struct dma_coherent_mem *dma_mem; /* internal for coherent mem override */ #endif #ifdef CONFIG_DMA_CMA struct cma *cma_area; /* contiguous memory area for dma allocations */ #endif #ifdef CONFIG_SWIOTLB struct io_tlb_mem *dma_io_tlb_mem; #endif #ifdef CONFIG_SWIOTLB_DYNAMIC struct list_head dma_io_tlb_pools; spinlock_t dma_io_tlb_lock; bool dma_uses_io_tlb; #endif /* arch specific additions */ struct dev_archdata archdata; struct device_node *of_node; /* associated device tree node */ struct fwnode_handle *fwnode; /* firmware device node */ #ifdef CONFIG_NUMA int numa_node; /* NUMA node this device is close to */ #endif dev_t devt; /* dev_t, creates the sysfs "dev" */ u32 id; /* device instance */ spinlock_t devres_lock; struct list_head devres_head; const struct class *class; const struct attribute_group **groups; /* optional groups */ void (*release)(struct device *dev); struct iommu_group *iommu_group; struct dev_iommu *iommu; struct device_physical_location *physical_location; enum device_removable removable; bool offline_disabled:1; bool offline:1; bool of_node_reused:1; bool state_synced:1; bool can_match:1; #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) bool dma_coherent:1; #endif #ifdef CONFIG_DMA_OPS_BYPASS bool dma_ops_bypass : 1; #endif #ifdef CONFIG_DMA_NEED_SYNC bool dma_skip_sync:1; #endif #ifdef CONFIG_IOMMU_DMA bool dma_iommu:1; #endif }; /** * struct device_link - Device link representation. * @supplier: The device on the supplier end of the link. * @s_node: Hook to the supplier device's list of links to consumers. * @consumer: The device on the consumer end of the link. * @c_node: Hook to the consumer device's list of links to suppliers. * @link_dev: device used to expose link details in sysfs * @status: The state of the link (with respect to the presence of drivers). * @flags: Link flags. * @rpm_active: Whether or not the consumer device is runtime-PM-active. * @kref: Count repeated addition of the same link. * @rm_work: Work structure used for removing the link. * @supplier_preactivated: Supplier has been made active before consumer probe. */ struct device_link { struct device *supplier; struct list_head s_node; struct device *consumer; struct list_head c_node; struct device link_dev; enum device_link_state status; u32 flags; refcount_t rpm_active; struct kref kref; struct work_struct rm_work; bool supplier_preactivated; /* Owned by consumer probe. */ }; #define kobj_to_dev(__kobj) container_of_const(__kobj, struct device, kobj) /** * device_iommu_mapped - Returns true when the device DMA is translated * by an IOMMU * @dev: Device to perform the check on */ static inline bool device_iommu_mapped(struct device *dev) { return (dev->iommu_group != NULL); } /* Get the wakeup routines, which depend on struct device */ #include <linux/pm_wakeup.h> /** * dev_name - Return a device's name. * @dev: Device with name to get. * Return: The kobject name of the device, or its initial name if unavailable. */ static inline const char *dev_name(const struct device *dev) { /* Use the init name until the kobject becomes available */ if (dev->init_name) return dev->init_name; return kobject_name(&dev->kobj); } /** * dev_bus_name - Return a device's bus/class name, if at all possible * @dev: struct device to get the bus/class name of * * Will return the name of the bus/class the device is attached to. If it is * not attached to a bus/class, an empty string will be returned. */ static inline const char *dev_bus_name(const struct device *dev) { return dev->bus ? dev->bus->name : (dev->class ? dev->class->name : ""); } __printf(2, 3) int dev_set_name(struct device *dev, const char *name, ...); #ifdef CONFIG_NUMA static inline int dev_to_node(struct device *dev) { return dev->numa_node; } static inline void set_dev_node(struct device *dev, int node) { dev->numa_node = node; } #else static inline int dev_to_node(struct device *dev) { return NUMA_NO_NODE; } static inline void set_dev_node(struct device *dev, int node) { } #endif static inline struct irq_domain *dev_get_msi_domain(const struct device *dev) { #ifdef CONFIG_GENERIC_MSI_IRQ return dev->msi.domain; #else return NULL; #endif } static inline void dev_set_msi_domain(struct device *dev, struct irq_domain *d) { #ifdef CONFIG_GENERIC_MSI_IRQ dev->msi.domain = d; #endif } static inline void *dev_get_drvdata(const struct device *dev) { return dev->driver_data; } static inline void dev_set_drvdata(struct device *dev, void *data) { dev->driver_data = data; } static inline struct pm_subsys_data *dev_to_psd(struct device *dev) { return dev ? dev->power.subsys_data : NULL; } static inline unsigned int dev_get_uevent_suppress(const struct device *dev) { return dev->kobj.uevent_suppress; } static inline void dev_set_uevent_suppress(struct device *dev, int val) { dev->kobj.uevent_suppress = val; } static inline int device_is_registered(struct device *dev) { return dev->kobj.state_in_sysfs; } static inline void device_enable_async_suspend(struct device *dev) { if (!dev->power.is_prepared) dev->power.async_suspend = true; } static inline void device_disable_async_suspend(struct device *dev) { if (!dev->power.is_prepared) dev->power.async_suspend = false; } static inline bool device_async_suspend_enabled(struct device *dev) { return !!dev->power.async_suspend; } static inline bool device_pm_not_required(struct device *dev) { return dev->power.no_pm; } static inline void device_set_pm_not_required(struct device *dev) { dev->power.no_pm = true; } static inline void dev_pm_syscore_device(struct device *dev, bool val) { #ifdef CONFIG_PM_SLEEP dev->power.syscore = val; #endif } static inline void dev_pm_set_driver_flags(struct device *dev, u32 flags) { dev->power.driver_flags = flags; } static inline bool dev_pm_test_driver_flags(struct device *dev, u32 flags) { return !!(dev->power.driver_flags & flags); } static inline void device_lock(struct device *dev) { mutex_lock(&dev->mutex); } static inline int device_lock_interruptible(struct device *dev) { return mutex_lock_interruptible(&dev->mutex); } static inline int device_trylock(struct device *dev) { return mutex_trylock(&dev->mutex); } static inline void device_unlock(struct device *dev) { mutex_unlock(&dev->mutex); } DEFINE_GUARD(device, struct device *, device_lock(_T), device_unlock(_T)) static inline void device_lock_assert(struct device *dev) { lockdep_assert_held(&dev->mutex); } static inline bool dev_has_sync_state(struct device *dev) { if (!dev) return false; if (dev->driver && dev->driver->sync_state) return true; if (dev->bus && dev->bus->sync_state) return true; return false; } static inline void dev_set_removable(struct device *dev, enum device_removable removable) { dev->removable = removable; } static inline bool dev_is_removable(struct device *dev) { return dev->removable == DEVICE_REMOVABLE; } static inline bool dev_removable_is_valid(struct device *dev) { return dev->removable != DEVICE_REMOVABLE_NOT_SUPPORTED; } /* * High level routines for use by the bus drivers */ int __must_check device_register(struct device *dev); void device_unregister(struct device *dev); void device_initialize(struct device *dev); int __must_check device_add(struct device *dev); void device_del(struct device *dev); DEFINE_FREE(device_del, struct device *, if (_T) device_del(_T)) int device_for_each_child(struct device *dev, void *data, int (*fn)(struct device *dev, void *data)); int device_for_each_child_reverse(struct device *dev, void *data, int (*fn)(struct device *dev, void *data)); int device_for_each_child_reverse_from(struct device *parent, struct device *from, const void *data, int (*fn)(struct device *, const void *)); struct device *device_find_child(struct device *dev, void *data, int (*match)(struct device *dev, void *data)); struct device *device_find_child_by_name(struct device *parent, const char *name); struct device *device_find_any_child(struct device *parent); int device_rename(struct device *dev, const char *new_name); int device_move(struct device *dev, struct device *new_parent, enum dpm_order dpm_order); int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid); static inline bool device_supports_offline(struct device *dev) { return dev->bus && dev->bus->offline && dev->bus->online; } #define __device_lock_set_class(dev, name, key) \ do { \ struct device *__d2 __maybe_unused = dev; \ lock_set_class(&__d2->mutex.dep_map, name, key, 0, _THIS_IP_); \ } while (0) /** * device_lock_set_class - Specify a temporary lock class while a device * is attached to a driver * @dev: device to modify * @key: lock class key data * * This must be called with the device_lock() already held, for example * from driver ->probe(). Take care to only override the default * lockdep_no_validate class. */ #ifdef CONFIG_LOCKDEP #define device_lock_set_class(dev, key) \ do { \ struct device *__d = dev; \ dev_WARN_ONCE(__d, !lockdep_match_class(&__d->mutex, \ &__lockdep_no_validate__), \ "overriding existing custom lock class\n"); \ __device_lock_set_class(__d, #key, key); \ } while (0) #else #define device_lock_set_class(dev, key) __device_lock_set_class(dev, #key, key) #endif /** * device_lock_reset_class - Return a device to the default lockdep novalidate state * @dev: device to modify * * This must be called with the device_lock() already held, for example * from driver ->remove(). */ #define device_lock_reset_class(dev) \ do { \ struct device *__d __maybe_unused = dev; \ lock_set_novalidate_class(&__d->mutex.dep_map, "&dev->mutex", \ _THIS_IP_); \ } while (0) void lock_device_hotplug(void); void unlock_device_hotplug(void); int lock_device_hotplug_sysfs(void); int device_offline(struct device *dev); int device_online(struct device *dev); void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode); void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode); void device_set_node(struct device *dev, struct fwnode_handle *fwnode); void device_set_of_node_from_dev(struct device *dev, const struct device *dev2); static inline struct device_node *dev_of_node(struct device *dev) { if (!IS_ENABLED(CONFIG_OF) || !dev) return NULL; return dev->of_node; } static inline int dev_num_vf(struct device *dev) { if (dev->bus && dev->bus->num_vf) return dev->bus->num_vf(dev); return 0; } /* * Root device objects for grouping under /sys/devices */ struct device *__root_device_register(const char *name, struct module *owner); /* This is a macro to avoid include problems with THIS_MODULE */ #define root_device_register(name) \ __root_device_register(name, THIS_MODULE) void root_device_unregister(struct device *root); static inline void *dev_get_platdata(const struct device *dev) { return dev->platform_data; } /* * Manual binding of a device to driver. See drivers/base/bus.c * for information on use. */ int __must_check device_driver_attach(const struct device_driver *drv, struct device *dev); int __must_check device_bind_driver(struct device *dev); void device_release_driver(struct device *dev); int __must_check device_attach(struct device *dev); int __must_check driver_attach(const struct device_driver *drv); void device_initial_probe(struct device *dev); int __must_check device_reprobe(struct device *dev); bool device_is_bound(struct device *dev); /* * Easy functions for dynamically creating devices on the fly */ __printf(5, 6) struct device * device_create(const struct class *cls, struct device *parent, dev_t devt, void *drvdata, const char *fmt, ...); __printf(6, 7) struct device * device_create_with_groups(const struct class *cls, struct device *parent, dev_t devt, void *drvdata, const struct attribute_group **groups, const char *fmt, ...); void device_destroy(const struct class *cls, dev_t devt); int __must_check device_add_groups(struct device *dev, const struct attribute_group **groups); void device_remove_groups(struct device *dev, const struct attribute_group **groups); static inline int __must_check device_add_group(struct device *dev, const struct attribute_group *grp) { const struct attribute_group *groups[] = { grp, NULL }; return device_add_groups(dev, groups); } static inline void device_remove_group(struct device *dev, const struct attribute_group *grp) { const struct attribute_group *groups[] = { grp, NULL }; return device_remove_groups(dev, groups); } int __must_check devm_device_add_group(struct device *dev, const struct attribute_group *grp); /* * get_device - atomically increment the reference count for the device. * */ struct device *get_device(struct device *dev); void put_device(struct device *dev); DEFINE_FREE(put_device, struct device *, if (_T) put_device(_T)) bool kill_device(struct device *dev); #ifdef CONFIG_DEVTMPFS int devtmpfs_mount(void); #else static inline int devtmpfs_mount(void) { return 0; } #endif /* drivers/base/power/shutdown.c */ void device_shutdown(void); /* debugging and troubleshooting/diagnostic helpers. */ const char *dev_driver_string(const struct device *dev); /* Device links interface. */ struct device_link *device_link_add(struct device *consumer, struct device *supplier, u32 flags); void device_link_del(struct device_link *link); void device_link_remove(void *consumer, struct device *supplier); void device_links_supplier_sync_state_pause(void); void device_links_supplier_sync_state_resume(void); void device_link_wait_removal(void); /* Create alias, so I can be autoloaded. */ #define MODULE_ALIAS_CHARDEV(major,minor) \ MODULE_ALIAS("char-major-" __stringify(major) "-" __stringify(minor)) #define MODULE_ALIAS_CHARDEV_MAJOR(major) \ MODULE_ALIAS("char-major-" __stringify(major) "-*") #endif /* _DEVICE_H_ */ |
| 359 218 218 370 370 26 113 13 532 148 148 148 140 532 358 383 364 363 365 3 364 753 748 381 109 140 751 748 369 44 748 31 747 383 383 543 752 366 118 9 148 9 370 371 3 370 148 371 532 531 531 531 364 364 362 13 148 364 3 1 3 364 363 365 363 365 364 149 356 3 362 132 751 381 752 751 353 349 709 645 371 371 371 371 362 361 112 361 361 362 362 344 362 362 362 3 3 3 375 68 161 358 358 3 148 148 3 148 148 148 148 356 356 356 356 148 148 3 148 148 148 16 2 125 2 41 75 2 5 73 75 73 2 148 148 18 13 148 148 147 148 148 148 142 363 2 148 148 22 148 36 148 148 148 68 148 148 11 68 114 6 45 115 45 3 47 1 41 8 4 138 3 135 17 3 138 138 137 383 379 186 383 383 2 2 2 2 48 12 39 48 48 148 48 36 22 20 2 46 3 148 10 12 48 12 12 12 12 148 148 1 148 148 148 28 148 148 3 148 148 148 148 9 148 148 148 148 148 148 148 148 148 148 148 22 36 48 48 2 36 22 36 13 48 736 737 737 707 548 550 739 737 736 734 4 48 48 2 12 48 48 48 48 48 48 48 48 48 12 37 37 37 37 25 12 37 44 10 10 140 140 140 140 140 3 140 139 10 140 140 3 140 140 140 140 140 140 140 140 140 138 140 64 16 16 83 16 83 91 83 16 66 66 140 140 16 83 141 10 140 118 118 118 6 118 118 327 41 354 29 26 383 383 383 383 381 42 41 41 41 41 30 3 25 4 28 3 1 14 19 306 85 85 85 85 85 85 41 41 41 10 32 41 41 325 289 68 356 69 361 362 308 1 361 7 140 355 361 69 12 12 12 48 91 4 5 128 6 166 370 3 40 40 141 380 141 352 224 85 40 12 362 41 141 353 29 379 107 318 118 348 141 10 361 383 353 383 379 378 134 380 376 72 141 40 364 363 362 363 354 132 6 27 19 19 19 19 19 19 370 371 42 42 42 39 11 42 42 371 374 375 54 367 367 374 42 375 375 374 67 531 371 531 3 531 532 532 531 532 532 532 370 605 605 601 536 534 59 605 532 603 531 603 605 605 530 530 19 19 19 19 19 19 19 248 306 609 306 304 19 19 19 19 19 19 19 19 3 3 3 3 3 3 3 3 113 113 3 3 112 9 113 349 347 349 355 355 10 355 354 355 365 365 365 355 353 356 381 383 381 175 175 367 347 142 347 346 111 48 49 374 373 16 16 374 374 121 121 531 532 321 531 532 1 306 530 532 360 85 85 85 84 85 8 8 7 7 3 19 19 363 363 322 113 19 499 499 499 499 55 154 184 500 55 495 371 371 371 371 371 371 371 369 370 370 371 371 370 371 369 371 371 371 370 371 371 371 371 370 371 371 371 370 371 371 371 370 371 370 370 370 371 371 371 371 371 371 370 371 371 371 371 371 369 370 371 371 370 371 371 370 371 371 371 371 371 371 371 371 371 371 371 371 371 371 371 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 | // SPDX-License-Identifier: GPL-2.0+ /* * Maple Tree implementation * Copyright (c) 2018-2022 Oracle Corporation * Authors: Liam R. Howlett <Liam.Howlett@oracle.com> * Matthew Wilcox <willy@infradead.org> * Copyright (c) 2023 ByteDance * Author: Peng Zhang <zhangpeng.00@bytedance.com> */ /* * DOC: Interesting implementation details of the Maple Tree * * Each node type has a number of slots for entries and a number of slots for * pivots. In the case of dense nodes, the pivots are implied by the position * and are simply the slot index + the minimum of the node. * * In regular B-Tree terms, pivots are called keys. The term pivot is used to * indicate that the tree is specifying ranges. Pivots may appear in the * subtree with an entry attached to the value whereas keys are unique to a * specific position of a B-tree. Pivot values are inclusive of the slot with * the same index. * * * The following illustrates the layout of a range64 nodes slots and pivots. * * * Slots -> | 0 | 1 | 2 | ... | 12 | 13 | 14 | 15 | * ┬ ┬ ┬ ┬ ┬ ┬ ┬ ┬ ┬ * │ │ │ │ │ │ │ │ └─ Implied maximum * │ │ │ │ │ │ │ └─ Pivot 14 * │ │ │ │ │ │ └─ Pivot 13 * │ │ │ │ │ └─ Pivot 12 * │ │ │ │ └─ Pivot 11 * │ │ │ └─ Pivot 2 * │ │ └─ Pivot 1 * │ └─ Pivot 0 * └─ Implied minimum * * Slot contents: * Internal (non-leaf) nodes contain pointers to other nodes. * Leaf nodes contain entries. * * The location of interest is often referred to as an offset. All offsets have * a slot, but the last offset has an implied pivot from the node above (or * UINT_MAX for the root node. * * Ranges complicate certain write activities. When modifying any of * the B-tree variants, it is known that one entry will either be added or * deleted. When modifying the Maple Tree, one store operation may overwrite * the entire data set, or one half of the tree, or the middle half of the tree. * */ #include <linux/maple_tree.h> #include <linux/xarray.h> #include <linux/types.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/limits.h> #include <asm/barrier.h> #define CREATE_TRACE_POINTS #include <trace/events/maple_tree.h> /* * Kernel pointer hashing renders much of the maple tree dump useless as tagged * pointers get hashed to arbitrary values. * * If CONFIG_DEBUG_VM_MAPLE_TREE is set we are in a debug mode where it is * permissible to bypass this. Otherwise remain cautious and retain the hashing. * * Userland doesn't know about %px so also use %p there. */ #if defined(__KERNEL__) && defined(CONFIG_DEBUG_VM_MAPLE_TREE) #define PTR_FMT "%px" #else #define PTR_FMT "%p" #endif #define MA_ROOT_PARENT 1 /* * Maple state flags * * MA_STATE_BULK - Bulk insert mode * * MA_STATE_REBALANCE - Indicate a rebalance during bulk insert * * MA_STATE_PREALLOC - Preallocated nodes, WARN_ON allocation */ #define MA_STATE_BULK 1 #define MA_STATE_REBALANCE 2 #define MA_STATE_PREALLOC 4 #define ma_parent_ptr(x) ((struct maple_pnode *)(x)) #define mas_tree_parent(x) ((unsigned long)(x->tree) | MA_ROOT_PARENT) #define ma_mnode_ptr(x) ((struct maple_node *)(x)) #define ma_enode_ptr(x) ((struct maple_enode *)(x)) static struct kmem_cache *maple_node_cache; #ifdef CONFIG_DEBUG_MAPLE_TREE static const unsigned long mt_max[] = { [maple_dense] = MAPLE_NODE_SLOTS, [maple_leaf_64] = ULONG_MAX, [maple_range_64] = ULONG_MAX, [maple_arange_64] = ULONG_MAX, }; #define mt_node_max(x) mt_max[mte_node_type(x)] #endif static const unsigned char mt_slots[] = { [maple_dense] = MAPLE_NODE_SLOTS, [maple_leaf_64] = MAPLE_RANGE64_SLOTS, [maple_range_64] = MAPLE_RANGE64_SLOTS, [maple_arange_64] = MAPLE_ARANGE64_SLOTS, }; #define mt_slot_count(x) mt_slots[mte_node_type(x)] static const unsigned char mt_pivots[] = { [maple_dense] = 0, [maple_leaf_64] = MAPLE_RANGE64_SLOTS - 1, [maple_range_64] = MAPLE_RANGE64_SLOTS - 1, [maple_arange_64] = MAPLE_ARANGE64_SLOTS - 1, }; #define mt_pivot_count(x) mt_pivots[mte_node_type(x)] static const unsigned char mt_min_slots[] = { [maple_dense] = MAPLE_NODE_SLOTS / 2, [maple_leaf_64] = (MAPLE_RANGE64_SLOTS / 2) - 2, [maple_range_64] = (MAPLE_RANGE64_SLOTS / 2) - 2, [maple_arange_64] = (MAPLE_ARANGE64_SLOTS / 2) - 1, }; #define mt_min_slot_count(x) mt_min_slots[mte_node_type(x)] #define MAPLE_BIG_NODE_SLOTS (MAPLE_RANGE64_SLOTS * 2 + 2) #define MAPLE_BIG_NODE_GAPS (MAPLE_ARANGE64_SLOTS * 2 + 1) struct maple_big_node { unsigned long pivot[MAPLE_BIG_NODE_SLOTS - 1]; union { struct maple_enode *slot[MAPLE_BIG_NODE_SLOTS]; struct { unsigned long padding[MAPLE_BIG_NODE_GAPS]; unsigned long gap[MAPLE_BIG_NODE_GAPS]; }; }; unsigned char b_end; enum maple_type type; }; /* * The maple_subtree_state is used to build a tree to replace a segment of an * existing tree in a more atomic way. Any walkers of the older tree will hit a * dead node and restart on updates. */ struct maple_subtree_state { struct ma_state *orig_l; /* Original left side of subtree */ struct ma_state *orig_r; /* Original right side of subtree */ struct ma_state *l; /* New left side of subtree */ struct ma_state *m; /* New middle of subtree (rare) */ struct ma_state *r; /* New right side of subtree */ struct ma_topiary *free; /* nodes to be freed */ struct ma_topiary *destroy; /* Nodes to be destroyed (walked and freed) */ struct maple_big_node *bn; }; #ifdef CONFIG_KASAN_STACK /* Prevent mas_wr_bnode() from exceeding the stack frame limit */ #define noinline_for_kasan noinline_for_stack #else #define noinline_for_kasan inline #endif /* Functions */ static inline struct maple_node *mt_alloc_one(gfp_t gfp) { return kmem_cache_alloc(maple_node_cache, gfp); } static inline int mt_alloc_bulk(gfp_t gfp, size_t size, void **nodes) { return kmem_cache_alloc_bulk(maple_node_cache, gfp, size, nodes); } static inline void mt_free_one(struct maple_node *node) { kmem_cache_free(maple_node_cache, node); } static inline void mt_free_bulk(size_t size, void __rcu **nodes) { kmem_cache_free_bulk(maple_node_cache, size, (void **)nodes); } static void mt_free_rcu(struct rcu_head *head) { struct maple_node *node = container_of(head, struct maple_node, rcu); kmem_cache_free(maple_node_cache, node); } /* * ma_free_rcu() - Use rcu callback to free a maple node * @node: The node to free * * The maple tree uses the parent pointer to indicate this node is no longer in * use and will be freed. */ static void ma_free_rcu(struct maple_node *node) { WARN_ON(node->parent != ma_parent_ptr(node)); call_rcu(&node->rcu, mt_free_rcu); } static void mas_set_height(struct ma_state *mas) { unsigned int new_flags = mas->tree->ma_flags; new_flags &= ~MT_FLAGS_HEIGHT_MASK; MAS_BUG_ON(mas, mas->depth > MAPLE_HEIGHT_MAX); new_flags |= mas->depth << MT_FLAGS_HEIGHT_OFFSET; mas->tree->ma_flags = new_flags; } static unsigned int mas_mt_height(struct ma_state *mas) { return mt_height(mas->tree); } static inline unsigned int mt_attr(struct maple_tree *mt) { return mt->ma_flags & ~MT_FLAGS_HEIGHT_MASK; } static __always_inline enum maple_type mte_node_type( const struct maple_enode *entry) { return ((unsigned long)entry >> MAPLE_NODE_TYPE_SHIFT) & MAPLE_NODE_TYPE_MASK; } static __always_inline bool ma_is_dense(const enum maple_type type) { return type < maple_leaf_64; } static __always_inline bool ma_is_leaf(const enum maple_type type) { return type < maple_range_64; } static __always_inline bool mte_is_leaf(const struct maple_enode *entry) { return ma_is_leaf(mte_node_type(entry)); } /* * We also reserve values with the bottom two bits set to '10' which are * below 4096 */ static __always_inline bool mt_is_reserved(const void *entry) { return ((unsigned long)entry < MAPLE_RESERVED_RANGE) && xa_is_internal(entry); } static __always_inline void mas_set_err(struct ma_state *mas, long err) { mas->node = MA_ERROR(err); mas->status = ma_error; } static __always_inline bool mas_is_ptr(const struct ma_state *mas) { return mas->status == ma_root; } static __always_inline bool mas_is_start(const struct ma_state *mas) { return mas->status == ma_start; } static __always_inline bool mas_is_none(const struct ma_state *mas) { return mas->status == ma_none; } static __always_inline bool mas_is_paused(const struct ma_state *mas) { return mas->status == ma_pause; } static __always_inline bool mas_is_overflow(struct ma_state *mas) { return mas->status == ma_overflow; } static inline bool mas_is_underflow(struct ma_state *mas) { return mas->status == ma_underflow; } static __always_inline struct maple_node *mte_to_node( const struct maple_enode *entry) { return (struct maple_node *)((unsigned long)entry & ~MAPLE_NODE_MASK); } /* * mte_to_mat() - Convert a maple encoded node to a maple topiary node. * @entry: The maple encoded node * * Return: a maple topiary pointer */ static inline struct maple_topiary *mte_to_mat(const struct maple_enode *entry) { return (struct maple_topiary *) ((unsigned long)entry & ~MAPLE_NODE_MASK); } /* * mas_mn() - Get the maple state node. * @mas: The maple state * * Return: the maple node (not encoded - bare pointer). */ static inline struct maple_node *mas_mn(const struct ma_state *mas) { return mte_to_node(mas->node); } /* * mte_set_node_dead() - Set a maple encoded node as dead. * @mn: The maple encoded node. */ static inline void mte_set_node_dead(struct maple_enode *mn) { mte_to_node(mn)->parent = ma_parent_ptr(mte_to_node(mn)); smp_wmb(); /* Needed for RCU */ } /* Bit 1 indicates the root is a node */ #define MAPLE_ROOT_NODE 0x02 /* maple_type stored bit 3-6 */ #define MAPLE_ENODE_TYPE_SHIFT 0x03 /* Bit 2 means a NULL somewhere below */ #define MAPLE_ENODE_NULL 0x04 static inline struct maple_enode *mt_mk_node(const struct maple_node *node, enum maple_type type) { return (void *)((unsigned long)node | (type << MAPLE_ENODE_TYPE_SHIFT) | MAPLE_ENODE_NULL); } static inline void *mte_mk_root(const struct maple_enode *node) { return (void *)((unsigned long)node | MAPLE_ROOT_NODE); } static inline void *mte_safe_root(const struct maple_enode *node) { return (void *)((unsigned long)node & ~MAPLE_ROOT_NODE); } static inline void __maybe_unused *mte_set_full(const struct maple_enode *node) { return (void *)((unsigned long)node & ~MAPLE_ENODE_NULL); } static inline void __maybe_unused *mte_clear_full(const struct maple_enode *node) { return (void *)((unsigned long)node | MAPLE_ENODE_NULL); } static inline bool __maybe_unused mte_has_null(const struct maple_enode *node) { return (unsigned long)node & MAPLE_ENODE_NULL; } static __always_inline bool ma_is_root(struct maple_node *node) { return ((unsigned long)node->parent & MA_ROOT_PARENT); } static __always_inline bool mte_is_root(const struct maple_enode *node) { return ma_is_root(mte_to_node(node)); } static inline bool mas_is_root_limits(const struct ma_state *mas) { return !mas->min && mas->max == ULONG_MAX; } static __always_inline bool mt_is_alloc(struct maple_tree *mt) { return (mt->ma_flags & MT_FLAGS_ALLOC_RANGE); } /* * The Parent Pointer * Excluding root, the parent pointer is 256B aligned like all other tree nodes. * When storing a 32 or 64 bit values, the offset can fit into 5 bits. The 16 * bit values need an extra bit to store the offset. This extra bit comes from * a reuse of the last bit in the node type. This is possible by using bit 1 to * indicate if bit 2 is part of the type or the slot. * * Note types: * 0x??1 = Root * 0x?00 = 16 bit nodes * 0x010 = 32 bit nodes * 0x110 = 64 bit nodes * * Slot size and alignment * 0b??1 : Root * 0b?00 : 16 bit values, type in 0-1, slot in 2-7 * 0b010 : 32 bit values, type in 0-2, slot in 3-7 * 0b110 : 64 bit values, type in 0-2, slot in 3-7 */ #define MAPLE_PARENT_ROOT 0x01 #define MAPLE_PARENT_SLOT_SHIFT 0x03 #define MAPLE_PARENT_SLOT_MASK 0xF8 #define MAPLE_PARENT_16B_SLOT_SHIFT 0x02 #define MAPLE_PARENT_16B_SLOT_MASK 0xFC #define MAPLE_PARENT_RANGE64 0x06 #define MAPLE_PARENT_RANGE32 0x04 #define MAPLE_PARENT_NOT_RANGE16 0x02 /* * mte_parent_shift() - Get the parent shift for the slot storage. * @parent: The parent pointer cast as an unsigned long * Return: The shift into that pointer to the star to of the slot */ static inline unsigned long mte_parent_shift(unsigned long parent) { /* Note bit 1 == 0 means 16B */ if (likely(parent & MAPLE_PARENT_NOT_RANGE16)) return MAPLE_PARENT_SLOT_SHIFT; return MAPLE_PARENT_16B_SLOT_SHIFT; } /* * mte_parent_slot_mask() - Get the slot mask for the parent. * @parent: The parent pointer cast as an unsigned long. * Return: The slot mask for that parent. */ static inline unsigned long mte_parent_slot_mask(unsigned long parent) { /* Note bit 1 == 0 means 16B */ if (likely(parent & MAPLE_PARENT_NOT_RANGE16)) return MAPLE_PARENT_SLOT_MASK; return MAPLE_PARENT_16B_SLOT_MASK; } /* * mas_parent_type() - Return the maple_type of the parent from the stored * parent type. * @mas: The maple state * @enode: The maple_enode to extract the parent's enum * Return: The node->parent maple_type */ static inline enum maple_type mas_parent_type(struct ma_state *mas, struct maple_enode *enode) { unsigned long p_type; p_type = (unsigned long)mte_to_node(enode)->parent; if (WARN_ON(p_type & MAPLE_PARENT_ROOT)) return 0; p_type &= MAPLE_NODE_MASK; p_type &= ~mte_parent_slot_mask(p_type); switch (p_type) { case MAPLE_PARENT_RANGE64: /* or MAPLE_PARENT_ARANGE64 */ if (mt_is_alloc(mas->tree)) return maple_arange_64; return maple_range_64; } return 0; } /* * mas_set_parent() - Set the parent node and encode the slot * @mas: The maple state * @enode: The encoded maple node. * @parent: The encoded maple node that is the parent of @enode. * @slot: The slot that @enode resides in @parent. * * Slot number is encoded in the enode->parent bit 3-6 or 2-6, depending on the * parent type. */ static inline void mas_set_parent(struct ma_state *mas, struct maple_enode *enode, const struct maple_enode *parent, unsigned char slot) { unsigned long val = (unsigned long)parent; unsigned long shift; unsigned long type; enum maple_type p_type = mte_node_type(parent); MAS_BUG_ON(mas, p_type == maple_dense); MAS_BUG_ON(mas, p_type == maple_leaf_64); switch (p_type) { case maple_range_64: case maple_arange_64: shift = MAPLE_PARENT_SLOT_SHIFT; type = MAPLE_PARENT_RANGE64; break; default: case maple_dense: case maple_leaf_64: shift = type = 0; break; } val &= ~MAPLE_NODE_MASK; /* Clear all node metadata in parent */ val |= (slot << shift) | type; mte_to_node(enode)->parent = ma_parent_ptr(val); } /* * mte_parent_slot() - get the parent slot of @enode. * @enode: The encoded maple node. * * Return: The slot in the parent node where @enode resides. */ static __always_inline unsigned int mte_parent_slot(const struct maple_enode *enode) { unsigned long val = (unsigned long)mte_to_node(enode)->parent; if (unlikely(val & MA_ROOT_PARENT)) return 0; /* * Okay to use MAPLE_PARENT_16B_SLOT_MASK as the last bit will be lost * by shift if the parent shift is MAPLE_PARENT_SLOT_SHIFT */ return (val & MAPLE_PARENT_16B_SLOT_MASK) >> mte_parent_shift(val); } /* * mte_parent() - Get the parent of @node. * @enode: The encoded maple node. * * Return: The parent maple node. */ static __always_inline struct maple_node *mte_parent(const struct maple_enode *enode) { return (void *)((unsigned long) (mte_to_node(enode)->parent) & ~MAPLE_NODE_MASK); } /* * ma_dead_node() - check if the @enode is dead. * @enode: The encoded maple node * * Return: true if dead, false otherwise. */ static __always_inline bool ma_dead_node(const struct maple_node *node) { struct maple_node *parent; /* Do not reorder reads from the node prior to the parent check */ smp_rmb(); parent = (void *)((unsigned long) node->parent & ~MAPLE_NODE_MASK); return (parent == node); } /* * mte_dead_node() - check if the @enode is dead. * @enode: The encoded maple node * * Return: true if dead, false otherwise. */ static __always_inline bool mte_dead_node(const struct maple_enode *enode) { struct maple_node *parent, *node; node = mte_to_node(enode); /* Do not reorder reads from the node prior to the parent check */ smp_rmb(); parent = mte_parent(enode); return (parent == node); } /* * mas_allocated() - Get the number of nodes allocated in a maple state. * @mas: The maple state * * The ma_state alloc member is overloaded to hold a pointer to the first * allocated node or to the number of requested nodes to allocate. If bit 0 is * set, then the alloc contains the number of requested nodes. If there is an * allocated node, then the total allocated nodes is in that node. * * Return: The total number of nodes allocated */ static inline unsigned long mas_allocated(const struct ma_state *mas) { if (!mas->alloc || ((unsigned long)mas->alloc & 0x1)) return 0; return mas->alloc->total; } /* * mas_set_alloc_req() - Set the requested number of allocations. * @mas: the maple state * @count: the number of allocations. * * The requested number of allocations is either in the first allocated node, * located in @mas->alloc->request_count, or directly in @mas->alloc if there is * no allocated node. Set the request either in the node or do the necessary * encoding to store in @mas->alloc directly. */ static inline void mas_set_alloc_req(struct ma_state *mas, unsigned long count) { if (!mas->alloc || ((unsigned long)mas->alloc & 0x1)) { if (!count) mas->alloc = NULL; else mas->alloc = (struct maple_alloc *)(((count) << 1U) | 1U); return; } mas->alloc->request_count = count; } /* * mas_alloc_req() - get the requested number of allocations. * @mas: The maple state * * The alloc count is either stored directly in @mas, or in * @mas->alloc->request_count if there is at least one node allocated. Decode * the request count if it's stored directly in @mas->alloc. * * Return: The allocation request count. */ static inline unsigned int mas_alloc_req(const struct ma_state *mas) { if ((unsigned long)mas->alloc & 0x1) return (unsigned long)(mas->alloc) >> 1; else if (mas->alloc) return mas->alloc->request_count; return 0; } /* * ma_pivots() - Get a pointer to the maple node pivots. * @node: the maple node * @type: the node type * * In the event of a dead node, this array may be %NULL * * Return: A pointer to the maple node pivots */ static inline unsigned long *ma_pivots(struct maple_node *node, enum maple_type type) { switch (type) { case maple_arange_64: return node->ma64.pivot; case maple_range_64: case maple_leaf_64: return node->mr64.pivot; case maple_dense: return NULL; } return NULL; } /* * ma_gaps() - Get a pointer to the maple node gaps. * @node: the maple node * @type: the node type * * Return: A pointer to the maple node gaps */ static inline unsigned long *ma_gaps(struct maple_node *node, enum maple_type type) { switch (type) { case maple_arange_64: return node->ma64.gap; case maple_range_64: case maple_leaf_64: case maple_dense: return NULL; } return NULL; } /* * mas_safe_pivot() - get the pivot at @piv or mas->max. * @mas: The maple state * @pivots: The pointer to the maple node pivots * @piv: The pivot to fetch * @type: The maple node type * * Return: The pivot at @piv within the limit of the @pivots array, @mas->max * otherwise. */ static __always_inline unsigned long mas_safe_pivot(const struct ma_state *mas, unsigned long *pivots, unsigned char piv, enum maple_type type) { if (piv >= mt_pivots[type]) return mas->max; return pivots[piv]; } /* * mas_safe_min() - Return the minimum for a given offset. * @mas: The maple state * @pivots: The pointer to the maple node pivots * @offset: The offset into the pivot array * * Return: The minimum range value that is contained in @offset. */ static inline unsigned long mas_safe_min(struct ma_state *mas, unsigned long *pivots, unsigned char offset) { if (likely(offset)) return pivots[offset - 1] + 1; return mas->min; } /* * mte_set_pivot() - Set a pivot to a value in an encoded maple node. * @mn: The encoded maple node * @piv: The pivot offset * @val: The value of the pivot */ static inline void mte_set_pivot(struct maple_enode *mn, unsigned char piv, unsigned long val) { struct maple_node *node = mte_to_node(mn); enum maple_type type = mte_node_type(mn); BUG_ON(piv >= mt_pivots[type]); switch (type) { case maple_range_64: case maple_leaf_64: node->mr64.pivot[piv] = val; break; case maple_arange_64: node->ma64.pivot[piv] = val; break; case maple_dense: break; } } /* * ma_slots() - Get a pointer to the maple node slots. * @mn: The maple node * @mt: The maple node type * * Return: A pointer to the maple node slots */ static inline void __rcu **ma_slots(struct maple_node *mn, enum maple_type mt) { switch (mt) { case maple_arange_64: return mn->ma64.slot; case maple_range_64: case maple_leaf_64: return mn->mr64.slot; case maple_dense: return mn->slot; } return NULL; } static inline bool mt_write_locked(const struct maple_tree *mt) { return mt_external_lock(mt) ? mt_write_lock_is_held(mt) : lockdep_is_held(&mt->ma_lock); } static __always_inline bool mt_locked(const struct maple_tree *mt) { return mt_external_lock(mt) ? mt_lock_is_held(mt) : lockdep_is_held(&mt->ma_lock); } static __always_inline void *mt_slot(const struct maple_tree *mt, void __rcu **slots, unsigned char offset) { return rcu_dereference_check(slots[offset], mt_locked(mt)); } static __always_inline void *mt_slot_locked(struct maple_tree *mt, void __rcu **slots, unsigned char offset) { return rcu_dereference_protected(slots[offset], mt_write_locked(mt)); } /* * mas_slot_locked() - Get the slot value when holding the maple tree lock. * @mas: The maple state * @slots: The pointer to the slots * @offset: The offset into the slots array to fetch * * Return: The entry stored in @slots at the @offset. */ static __always_inline void *mas_slot_locked(struct ma_state *mas, void __rcu **slots, unsigned char offset) { return mt_slot_locked(mas->tree, slots, offset); } /* * mas_slot() - Get the slot value when not holding the maple tree lock. * @mas: The maple state * @slots: The pointer to the slots * @offset: The offset into the slots array to fetch * * Return: The entry stored in @slots at the @offset */ static __always_inline void *mas_slot(struct ma_state *mas, void __rcu **slots, unsigned char offset) { return mt_slot(mas->tree, slots, offset); } /* * mas_root() - Get the maple tree root. * @mas: The maple state. * * Return: The pointer to the root of the tree */ static __always_inline void *mas_root(struct ma_state *mas) { return rcu_dereference_check(mas->tree->ma_root, mt_locked(mas->tree)); } static inline void *mt_root_locked(struct maple_tree *mt) { return rcu_dereference_protected(mt->ma_root, mt_write_locked(mt)); } /* * mas_root_locked() - Get the maple tree root when holding the maple tree lock. * @mas: The maple state. * * Return: The pointer to the root of the tree */ static inline void *mas_root_locked(struct ma_state *mas) { return mt_root_locked(mas->tree); } static inline struct maple_metadata *ma_meta(struct maple_node *mn, enum maple_type mt) { switch (mt) { case maple_arange_64: return &mn->ma64.meta; default: return &mn->mr64.meta; } } /* * ma_set_meta() - Set the metadata information of a node. * @mn: The maple node * @mt: The maple node type * @offset: The offset of the highest sub-gap in this node. * @end: The end of the data in this node. */ static inline void ma_set_meta(struct maple_node *mn, enum maple_type mt, unsigned char offset, unsigned char end) { struct maple_metadata *meta = ma_meta(mn, mt); meta->gap = offset; meta->end = end; } /* * mt_clear_meta() - clear the metadata information of a node, if it exists * @mt: The maple tree * @mn: The maple node * @type: The maple node type */ static inline void mt_clear_meta(struct maple_tree *mt, struct maple_node *mn, enum maple_type type) { struct maple_metadata *meta; unsigned long *pivots; void __rcu **slots; void *next; switch (type) { case maple_range_64: pivots = mn->mr64.pivot; if (unlikely(pivots[MAPLE_RANGE64_SLOTS - 2])) { slots = mn->mr64.slot; next = mt_slot_locked(mt, slots, MAPLE_RANGE64_SLOTS - 1); if (unlikely((mte_to_node(next) && mte_node_type(next)))) return; /* no metadata, could be node */ } fallthrough; case maple_arange_64: meta = ma_meta(mn, type); break; default: return; } meta->gap = 0; meta->end = 0; } /* * ma_meta_end() - Get the data end of a node from the metadata * @mn: The maple node * @mt: The maple node type */ static inline unsigned char ma_meta_end(struct maple_node *mn, enum maple_type mt) { struct maple_metadata *meta = ma_meta(mn, mt); return meta->end; } /* * ma_meta_gap() - Get the largest gap location of a node from the metadata * @mn: The maple node */ static inline unsigned char ma_meta_gap(struct maple_node *mn) { return mn->ma64.meta.gap; } /* * ma_set_meta_gap() - Set the largest gap location in a nodes metadata * @mn: The maple node * @mt: The maple node type * @offset: The location of the largest gap. */ static inline void ma_set_meta_gap(struct maple_node *mn, enum maple_type mt, unsigned char offset) { struct maple_metadata *meta = ma_meta(mn, mt); meta->gap = offset; } /* * mat_add() - Add a @dead_enode to the ma_topiary of a list of dead nodes. * @mat: the ma_topiary, a linked list of dead nodes. * @dead_enode: the node to be marked as dead and added to the tail of the list * * Add the @dead_enode to the linked list in @mat. */ static inline void mat_add(struct ma_topiary *mat, struct maple_enode *dead_enode) { mte_set_node_dead(dead_enode); mte_to_mat(dead_enode)->next = NULL; if (!mat->tail) { mat->tail = mat->head = dead_enode; return; } mte_to_mat(mat->tail)->next = dead_enode; mat->tail = dead_enode; } static void mt_free_walk(struct rcu_head *head); static void mt_destroy_walk(struct maple_enode *enode, struct maple_tree *mt, bool free); /* * mas_mat_destroy() - Free all nodes and subtrees in a dead list. * @mas: the maple state * @mat: the ma_topiary linked list of dead nodes to free. * * Destroy walk a dead list. */ static void mas_mat_destroy(struct ma_state *mas, struct ma_topiary *mat) { struct maple_enode *next; struct maple_node *node; bool in_rcu = mt_in_rcu(mas->tree); while (mat->head) { next = mte_to_mat(mat->head)->next; node = mte_to_node(mat->head); mt_destroy_walk(mat->head, mas->tree, !in_rcu); if (in_rcu) call_rcu(&node->rcu, mt_free_walk); mat->head = next; } } /* * mas_descend() - Descend into the slot stored in the ma_state. * @mas: the maple state. * * Note: Not RCU safe, only use in write side or debug code. */ static inline void mas_descend(struct ma_state *mas) { enum maple_type type; unsigned long *pivots; struct maple_node *node; void __rcu **slots; node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); slots = ma_slots(node, type); if (mas->offset) mas->min = pivots[mas->offset - 1] + 1; mas->max = mas_safe_pivot(mas, pivots, mas->offset, type); mas->node = mas_slot(mas, slots, mas->offset); } /* * mte_set_gap() - Set a maple node gap. * @mn: The encoded maple node * @gap: The offset of the gap to set * @val: The gap value */ static inline void mte_set_gap(const struct maple_enode *mn, unsigned char gap, unsigned long val) { switch (mte_node_type(mn)) { default: break; case maple_arange_64: mte_to_node(mn)->ma64.gap[gap] = val; break; } } /* * mas_ascend() - Walk up a level of the tree. * @mas: The maple state * * Sets the @mas->max and @mas->min to the correct values when walking up. This * may cause several levels of walking up to find the correct min and max. * May find a dead node which will cause a premature return. * Return: 1 on dead node, 0 otherwise */ static int mas_ascend(struct ma_state *mas) { struct maple_enode *p_enode; /* parent enode. */ struct maple_enode *a_enode; /* ancestor enode. */ struct maple_node *a_node; /* ancestor node. */ struct maple_node *p_node; /* parent node. */ unsigned char a_slot; enum maple_type a_type; unsigned long min, max; unsigned long *pivots; bool set_max = false, set_min = false; a_node = mas_mn(mas); if (ma_is_root(a_node)) { mas->offset = 0; return 0; } p_node = mte_parent(mas->node); if (unlikely(a_node == p_node)) return 1; a_type = mas_parent_type(mas, mas->node); mas->offset = mte_parent_slot(mas->node); a_enode = mt_mk_node(p_node, a_type); /* Check to make sure all parent information is still accurate */ if (p_node != mte_parent(mas->node)) return 1; mas->node = a_enode; if (mte_is_root(a_enode)) { mas->max = ULONG_MAX; mas->min = 0; return 0; } min = 0; max = ULONG_MAX; if (!mas->offset) { min = mas->min; set_min = true; } if (mas->max == ULONG_MAX) set_max = true; do { p_enode = a_enode; a_type = mas_parent_type(mas, p_enode); a_node = mte_parent(p_enode); a_slot = mte_parent_slot(p_enode); a_enode = mt_mk_node(a_node, a_type); pivots = ma_pivots(a_node, a_type); if (unlikely(ma_dead_node(a_node))) return 1; if (!set_min && a_slot) { set_min = true; min = pivots[a_slot - 1] + 1; } if (!set_max && a_slot < mt_pivots[a_type]) { set_max = true; max = pivots[a_slot]; } if (unlikely(ma_dead_node(a_node))) return 1; if (unlikely(ma_is_root(a_node))) break; } while (!set_min || !set_max); mas->max = max; mas->min = min; return 0; } /* * mas_pop_node() - Get a previously allocated maple node from the maple state. * @mas: The maple state * * Return: A pointer to a maple node. */ static inline struct maple_node *mas_pop_node(struct ma_state *mas) { struct maple_alloc *ret, *node = mas->alloc; unsigned long total = mas_allocated(mas); unsigned int req = mas_alloc_req(mas); /* nothing or a request pending. */ if (WARN_ON(!total)) return NULL; if (total == 1) { /* single allocation in this ma_state */ mas->alloc = NULL; ret = node; goto single_node; } if (node->node_count == 1) { /* Single allocation in this node. */ mas->alloc = node->slot[0]; mas->alloc->total = node->total - 1; ret = node; goto new_head; } node->total--; ret = node->slot[--node->node_count]; node->slot[node->node_count] = NULL; single_node: new_head: if (req) { req++; mas_set_alloc_req(mas, req); } memset(ret, 0, sizeof(*ret)); return (struct maple_node *)ret; } /* * mas_push_node() - Push a node back on the maple state allocation. * @mas: The maple state * @used: The used maple node * * Stores the maple node back into @mas->alloc for reuse. Updates allocated and * requested node count as necessary. */ static inline void mas_push_node(struct ma_state *mas, struct maple_node *used) { struct maple_alloc *reuse = (struct maple_alloc *)used; struct maple_alloc *head = mas->alloc; unsigned long count; unsigned int requested = mas_alloc_req(mas); count = mas_allocated(mas); reuse->request_count = 0; reuse->node_count = 0; if (count) { if (head->node_count < MAPLE_ALLOC_SLOTS) { head->slot[head->node_count++] = reuse; head->total++; goto done; } reuse->slot[0] = head; reuse->node_count = 1; } reuse->total = count + 1; mas->alloc = reuse; done: if (requested > 1) mas_set_alloc_req(mas, requested - 1); } /* * mas_alloc_nodes() - Allocate nodes into a maple state * @mas: The maple state * @gfp: The GFP Flags */ static inline void mas_alloc_nodes(struct ma_state *mas, gfp_t gfp) { struct maple_alloc *node; unsigned long allocated = mas_allocated(mas); unsigned int requested = mas_alloc_req(mas); unsigned int count; void **slots = NULL; unsigned int max_req = 0; if (!requested) return; mas_set_alloc_req(mas, 0); if (mas->mas_flags & MA_STATE_PREALLOC) { if (allocated) return; BUG_ON(!allocated); WARN_ON(!allocated); } if (!allocated || mas->alloc->node_count == MAPLE_ALLOC_SLOTS) { node = (struct maple_alloc *)mt_alloc_one(gfp); if (!node) goto nomem_one; if (allocated) { node->slot[0] = mas->alloc; node->node_count = 1; } else { node->node_count = 0; } mas->alloc = node; node->total = ++allocated; node->request_count = 0; requested--; } node = mas->alloc; while (requested) { max_req = MAPLE_ALLOC_SLOTS - node->node_count; slots = (void **)&node->slot[node->node_count]; max_req = min(requested, max_req); count = mt_alloc_bulk(gfp, max_req, slots); if (!count) goto nomem_bulk; if (node->node_count == 0) { node->slot[0]->node_count = 0; node->slot[0]->request_count = 0; } node->node_count += count; allocated += count; /* find a non-full node*/ do { node = node->slot[0]; } while (unlikely(node->node_count == MAPLE_ALLOC_SLOTS)); requested -= count; } mas->alloc->total = allocated; return; nomem_bulk: /* Clean up potential freed allocations on bulk failure */ memset(slots, 0, max_req * sizeof(unsigned long)); mas->alloc->total = allocated; nomem_one: mas_set_alloc_req(mas, requested); mas_set_err(mas, -ENOMEM); } /* * mas_free() - Free an encoded maple node * @mas: The maple state * @used: The encoded maple node to free. * * Uses rcu free if necessary, pushes @used back on the maple state allocations * otherwise. */ static inline void mas_free(struct ma_state *mas, struct maple_enode *used) { struct maple_node *tmp = mte_to_node(used); if (mt_in_rcu(mas->tree)) ma_free_rcu(tmp); else mas_push_node(mas, tmp); } /* * mas_node_count_gfp() - Check if enough nodes are allocated and request more * if there is not enough nodes. * @mas: The maple state * @count: The number of nodes needed * @gfp: the gfp flags */ static void mas_node_count_gfp(struct ma_state *mas, int count, gfp_t gfp) { unsigned long allocated = mas_allocated(mas); if (allocated < count) { mas_set_alloc_req(mas, count - allocated); mas_alloc_nodes(mas, gfp); } } /* * mas_node_count() - Check if enough nodes are allocated and request more if * there is not enough nodes. * @mas: The maple state * @count: The number of nodes needed * * Note: Uses GFP_NOWAIT | __GFP_NOWARN for gfp flags. */ static void mas_node_count(struct ma_state *mas, int count) { return mas_node_count_gfp(mas, count, GFP_NOWAIT | __GFP_NOWARN); } /* * mas_start() - Sets up maple state for operations. * @mas: The maple state. * * If mas->status == mas_start, then set the min, max and depth to * defaults. * * Return: * - If mas->node is an error or not mas_start, return NULL. * - If it's an empty tree: NULL & mas->status == ma_none * - If it's a single entry: The entry & mas->status == ma_root * - If it's a tree: NULL & mas->status == ma_active */ static inline struct maple_enode *mas_start(struct ma_state *mas) { if (likely(mas_is_start(mas))) { struct maple_enode *root; mas->min = 0; mas->max = ULONG_MAX; retry: mas->depth = 0; root = mas_root(mas); /* Tree with nodes */ if (likely(xa_is_node(root))) { mas->depth = 1; mas->status = ma_active; mas->node = mte_safe_root(root); mas->offset = 0; if (mte_dead_node(mas->node)) goto retry; return NULL; } mas->node = NULL; /* empty tree */ if (unlikely(!root)) { mas->status = ma_none; mas->offset = MAPLE_NODE_SLOTS; return NULL; } /* Single entry tree */ mas->status = ma_root; mas->offset = MAPLE_NODE_SLOTS; /* Single entry tree. */ if (mas->index > 0) return NULL; return root; } return NULL; } /* * ma_data_end() - Find the end of the data in a node. * @node: The maple node * @type: The maple node type * @pivots: The array of pivots in the node * @max: The maximum value in the node * * Uses metadata to find the end of the data when possible. * Return: The zero indexed last slot with data (may be null). */ static __always_inline unsigned char ma_data_end(struct maple_node *node, enum maple_type type, unsigned long *pivots, unsigned long max) { unsigned char offset; if (!pivots) return 0; if (type == maple_arange_64) return ma_meta_end(node, type); offset = mt_pivots[type] - 1; if (likely(!pivots[offset])) return ma_meta_end(node, type); if (likely(pivots[offset] == max)) return offset; return mt_pivots[type]; } /* * mas_data_end() - Find the end of the data (slot). * @mas: the maple state * * This method is optimized to check the metadata of a node if the node type * supports data end metadata. * * Return: The zero indexed last slot with data (may be null). */ static inline unsigned char mas_data_end(struct ma_state *mas) { enum maple_type type; struct maple_node *node; unsigned char offset; unsigned long *pivots; type = mte_node_type(mas->node); node = mas_mn(mas); if (type == maple_arange_64) return ma_meta_end(node, type); pivots = ma_pivots(node, type); if (unlikely(ma_dead_node(node))) return 0; offset = mt_pivots[type] - 1; if (likely(!pivots[offset])) return ma_meta_end(node, type); if (likely(pivots[offset] == mas->max)) return offset; return mt_pivots[type]; } /* * mas_leaf_max_gap() - Returns the largest gap in a leaf node * @mas: the maple state * * Return: The maximum gap in the leaf. */ static unsigned long mas_leaf_max_gap(struct ma_state *mas) { enum maple_type mt; unsigned long pstart, gap, max_gap; struct maple_node *mn; unsigned long *pivots; void __rcu **slots; unsigned char i; unsigned char max_piv; mt = mte_node_type(mas->node); mn = mas_mn(mas); slots = ma_slots(mn, mt); max_gap = 0; if (unlikely(ma_is_dense(mt))) { gap = 0; for (i = 0; i < mt_slots[mt]; i++) { if (slots[i]) { if (gap > max_gap) max_gap = gap; gap = 0; } else { gap++; } } if (gap > max_gap) max_gap = gap; return max_gap; } /* * Check the first implied pivot optimizes the loop below and slot 1 may * be skipped if there is a gap in slot 0. */ pivots = ma_pivots(mn, mt); if (likely(!slots[0])) { max_gap = pivots[0] - mas->min + 1; i = 2; } else { i = 1; } /* reduce max_piv as the special case is checked before the loop */ max_piv = ma_data_end(mn, mt, pivots, mas->max) - 1; /* * Check end implied pivot which can only be a gap on the right most * node. */ if (unlikely(mas->max == ULONG_MAX) && !slots[max_piv + 1]) { gap = ULONG_MAX - pivots[max_piv]; if (gap > max_gap) max_gap = gap; if (max_gap > pivots[max_piv] - mas->min) return max_gap; } for (; i <= max_piv; i++) { /* data == no gap. */ if (likely(slots[i])) continue; pstart = pivots[i - 1]; gap = pivots[i] - pstart; if (gap > max_gap) max_gap = gap; /* There cannot be two gaps in a row. */ i++; } return max_gap; } /* * ma_max_gap() - Get the maximum gap in a maple node (non-leaf) * @node: The maple node * @gaps: The pointer to the gaps * @mt: The maple node type * @off: Pointer to store the offset location of the gap. * * Uses the metadata data end to scan backwards across set gaps. * * Return: The maximum gap value */ static inline unsigned long ma_max_gap(struct maple_node *node, unsigned long *gaps, enum maple_type mt, unsigned char *off) { unsigned char offset, i; unsigned long max_gap = 0; i = offset = ma_meta_end(node, mt); do { if (gaps[i] > max_gap) { max_gap = gaps[i]; offset = i; } } while (i--); *off = offset; return max_gap; } /* * mas_max_gap() - find the largest gap in a non-leaf node and set the slot. * @mas: The maple state. * * Return: The gap value. */ static inline unsigned long mas_max_gap(struct ma_state *mas) { unsigned long *gaps; unsigned char offset; enum maple_type mt; struct maple_node *node; mt = mte_node_type(mas->node); if (ma_is_leaf(mt)) return mas_leaf_max_gap(mas); node = mas_mn(mas); MAS_BUG_ON(mas, mt != maple_arange_64); offset = ma_meta_gap(node); gaps = ma_gaps(node, mt); return gaps[offset]; } /* * mas_parent_gap() - Set the parent gap and any gaps above, as needed * @mas: The maple state * @offset: The gap offset in the parent to set * @new: The new gap value. * * Set the parent gap then continue to set the gap upwards, using the metadata * of the parent to see if it is necessary to check the node above. */ static inline void mas_parent_gap(struct ma_state *mas, unsigned char offset, unsigned long new) { unsigned long meta_gap = 0; struct maple_node *pnode; struct maple_enode *penode; unsigned long *pgaps; unsigned char meta_offset; enum maple_type pmt; pnode = mte_parent(mas->node); pmt = mas_parent_type(mas, mas->node); penode = mt_mk_node(pnode, pmt); pgaps = ma_gaps(pnode, pmt); ascend: MAS_BUG_ON(mas, pmt != maple_arange_64); meta_offset = ma_meta_gap(pnode); meta_gap = pgaps[meta_offset]; pgaps[offset] = new; if (meta_gap == new) return; if (offset != meta_offset) { if (meta_gap > new) return; ma_set_meta_gap(pnode, pmt, offset); } else if (new < meta_gap) { new = ma_max_gap(pnode, pgaps, pmt, &meta_offset); ma_set_meta_gap(pnode, pmt, meta_offset); } if (ma_is_root(pnode)) return; /* Go to the parent node. */ pnode = mte_parent(penode); pmt = mas_parent_type(mas, penode); pgaps = ma_gaps(pnode, pmt); offset = mte_parent_slot(penode); penode = mt_mk_node(pnode, pmt); goto ascend; } /* * mas_update_gap() - Update a nodes gaps and propagate up if necessary. * @mas: the maple state. */ static inline void mas_update_gap(struct ma_state *mas) { unsigned char pslot; unsigned long p_gap; unsigned long max_gap; if (!mt_is_alloc(mas->tree)) return; if (mte_is_root(mas->node)) return; max_gap = mas_max_gap(mas); pslot = mte_parent_slot(mas->node); p_gap = ma_gaps(mte_parent(mas->node), mas_parent_type(mas, mas->node))[pslot]; if (p_gap != max_gap) mas_parent_gap(mas, pslot, max_gap); } /* * mas_adopt_children() - Set the parent pointer of all nodes in @parent to * @parent with the slot encoded. * @mas: the maple state (for the tree) * @parent: the maple encoded node containing the children. */ static inline void mas_adopt_children(struct ma_state *mas, struct maple_enode *parent) { enum maple_type type = mte_node_type(parent); struct maple_node *node = mte_to_node(parent); void __rcu **slots = ma_slots(node, type); unsigned long *pivots = ma_pivots(node, type); struct maple_enode *child; unsigned char offset; offset = ma_data_end(node, type, pivots, mas->max); do { child = mas_slot_locked(mas, slots, offset); mas_set_parent(mas, child, parent, offset); } while (offset--); } /* * mas_put_in_tree() - Put a new node in the tree, smp_wmb(), and mark the old * node as dead. * @mas: the maple state with the new node * @old_enode: The old maple encoded node to replace. */ static inline void mas_put_in_tree(struct ma_state *mas, struct maple_enode *old_enode) __must_hold(mas->tree->ma_lock) { unsigned char offset; void __rcu **slots; if (mte_is_root(mas->node)) { mas_mn(mas)->parent = ma_parent_ptr(mas_tree_parent(mas)); rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node)); mas_set_height(mas); } else { offset = mte_parent_slot(mas->node); slots = ma_slots(mte_parent(mas->node), mas_parent_type(mas, mas->node)); rcu_assign_pointer(slots[offset], mas->node); } mte_set_node_dead(old_enode); } /* * mas_replace_node() - Replace a node by putting it in the tree, marking it * dead, and freeing it. * the parent encoding to locate the maple node in the tree. * @mas: the ma_state with @mas->node pointing to the new node. * @old_enode: The old maple encoded node. */ static inline void mas_replace_node(struct ma_state *mas, struct maple_enode *old_enode) __must_hold(mas->tree->ma_lock) { mas_put_in_tree(mas, old_enode); mas_free(mas, old_enode); } /* * mas_find_child() - Find a child who has the parent @mas->node. * @mas: the maple state with the parent. * @child: the maple state to store the child. */ static inline bool mas_find_child(struct ma_state *mas, struct ma_state *child) __must_hold(mas->tree->ma_lock) { enum maple_type mt; unsigned char offset; unsigned char end; unsigned long *pivots; struct maple_enode *entry; struct maple_node *node; void __rcu **slots; mt = mte_node_type(mas->node); node = mas_mn(mas); slots = ma_slots(node, mt); pivots = ma_pivots(node, mt); end = ma_data_end(node, mt, pivots, mas->max); for (offset = mas->offset; offset <= end; offset++) { entry = mas_slot_locked(mas, slots, offset); if (mte_parent(entry) == node) { *child = *mas; mas->offset = offset + 1; child->offset = offset; mas_descend(child); child->offset = 0; return true; } } return false; } /* * mab_shift_right() - Shift the data in mab right. Note, does not clean out the * old data or set b_node->b_end. * @b_node: the maple_big_node * @shift: the shift count */ static inline void mab_shift_right(struct maple_big_node *b_node, unsigned char shift) { unsigned long size = b_node->b_end * sizeof(unsigned long); memmove(b_node->pivot + shift, b_node->pivot, size); memmove(b_node->slot + shift, b_node->slot, size); if (b_node->type == maple_arange_64) memmove(b_node->gap + shift, b_node->gap, size); } /* * mab_middle_node() - Check if a middle node is needed (unlikely) * @b_node: the maple_big_node that contains the data. * @split: the potential split location * @slot_count: the size that can be stored in a single node being considered. * * Return: true if a middle node is required. */ static inline bool mab_middle_node(struct maple_big_node *b_node, int split, unsigned char slot_count) { unsigned char size = b_node->b_end; if (size >= 2 * slot_count) return true; if (!b_node->slot[split] && (size >= 2 * slot_count - 1)) return true; return false; } /* * mab_no_null_split() - ensure the split doesn't fall on a NULL * @b_node: the maple_big_node with the data * @split: the suggested split location * @slot_count: the number of slots in the node being considered. * * Return: the split location. */ static inline int mab_no_null_split(struct maple_big_node *b_node, unsigned char split, unsigned char slot_count) { if (!b_node->slot[split]) { /* * If the split is less than the max slot && the right side will * still be sufficient, then increment the split on NULL. */ if ((split < slot_count - 1) && (b_node->b_end - split) > (mt_min_slots[b_node->type])) split++; else split--; } return split; } /* * mab_calc_split() - Calculate the split location and if there needs to be two * splits. * @mas: The maple state * @bn: The maple_big_node with the data * @mid_split: The second split, if required. 0 otherwise. * * Return: The first split location. The middle split is set in @mid_split. */ static inline int mab_calc_split(struct ma_state *mas, struct maple_big_node *bn, unsigned char *mid_split, unsigned long min) { unsigned char b_end = bn->b_end; int split = b_end / 2; /* Assume equal split. */ unsigned char slot_min, slot_count = mt_slots[bn->type]; /* * To support gap tracking, all NULL entries are kept together and a node cannot * end on a NULL entry, with the exception of the left-most leaf. The * limitation means that the split of a node must be checked for this condition * and be able to put more data in one direction or the other. */ if (unlikely((mas->mas_flags & MA_STATE_BULK))) { *mid_split = 0; split = b_end - mt_min_slots[bn->type]; if (!ma_is_leaf(bn->type)) return split; mas->mas_flags |= MA_STATE_REBALANCE; if (!bn->slot[split]) split--; return split; } /* * Although extremely rare, it is possible to enter what is known as the 3-way * split scenario. The 3-way split comes about by means of a store of a range * that overwrites the end and beginning of two full nodes. The result is a set * of entries that cannot be stored in 2 nodes. Sometimes, these two nodes can * also be located in different parent nodes which are also full. This can * carry upwards all the way to the root in the worst case. */ if (unlikely(mab_middle_node(bn, split, slot_count))) { split = b_end / 3; *mid_split = split * 2; } else { slot_min = mt_min_slots[bn->type]; *mid_split = 0; /* * Avoid having a range less than the slot count unless it * causes one node to be deficient. * NOTE: mt_min_slots is 1 based, b_end and split are zero. */ while ((split < slot_count - 1) && ((bn->pivot[split] - min) < slot_count - 1) && (b_end - split > slot_min)) split++; } /* Avoid ending a node on a NULL entry */ split = mab_no_null_split(bn, split, slot_count); if (unlikely(*mid_split)) *mid_split = mab_no_null_split(bn, *mid_split, slot_count); return split; } /* * mas_mab_cp() - Copy data from a maple state inclusively to a maple_big_node * and set @b_node->b_end to the next free slot. * @mas: The maple state * @mas_start: The starting slot to copy * @mas_end: The end slot to copy (inclusively) * @b_node: The maple_big_node to place the data * @mab_start: The starting location in maple_big_node to store the data. */ static inline void mas_mab_cp(struct ma_state *mas, unsigned char mas_start, unsigned char mas_end, struct maple_big_node *b_node, unsigned char mab_start) { enum maple_type mt; struct maple_node *node; void __rcu **slots; unsigned long *pivots, *gaps; int i = mas_start, j = mab_start; unsigned char piv_end; node = mas_mn(mas); mt = mte_node_type(mas->node); pivots = ma_pivots(node, mt); if (!i) { b_node->pivot[j] = pivots[i++]; if (unlikely(i > mas_end)) goto complete; j++; } piv_end = min(mas_end, mt_pivots[mt]); for (; i < piv_end; i++, j++) { b_node->pivot[j] = pivots[i]; if (unlikely(!b_node->pivot[j])) goto complete; if (unlikely(mas->max == b_node->pivot[j])) goto complete; } b_node->pivot[j] = mas_safe_pivot(mas, pivots, i, mt); complete: b_node->b_end = ++j; j -= mab_start; slots = ma_slots(node, mt); memcpy(b_node->slot + mab_start, slots + mas_start, sizeof(void *) * j); if (!ma_is_leaf(mt) && mt_is_alloc(mas->tree)) { gaps = ma_gaps(node, mt); memcpy(b_node->gap + mab_start, gaps + mas_start, sizeof(unsigned long) * j); } } /* * mas_leaf_set_meta() - Set the metadata of a leaf if possible. * @node: The maple node * @mt: The maple type * @end: The node end */ static inline void mas_leaf_set_meta(struct maple_node *node, enum maple_type mt, unsigned char end) { if (end < mt_slots[mt] - 1) ma_set_meta(node, mt, 0, end); } /* * mab_mas_cp() - Copy data from maple_big_node to a maple encoded node. * @b_node: the maple_big_node that has the data * @mab_start: the start location in @b_node. * @mab_end: The end location in @b_node (inclusively) * @mas: The maple state with the maple encoded node. */ static inline void mab_mas_cp(struct maple_big_node *b_node, unsigned char mab_start, unsigned char mab_end, struct ma_state *mas, bool new_max) { int i, j = 0; enum maple_type mt = mte_node_type(mas->node); struct maple_node *node = mte_to_node(mas->node); void __rcu **slots = ma_slots(node, mt); unsigned long *pivots = ma_pivots(node, mt); unsigned long *gaps = NULL; unsigned char end; if (mab_end - mab_start > mt_pivots[mt]) mab_end--; if (!pivots[mt_pivots[mt] - 1]) slots[mt_pivots[mt]] = NULL; i = mab_start; do { pivots[j++] = b_node->pivot[i++]; } while (i <= mab_end && likely(b_node->pivot[i])); memcpy(slots, b_node->slot + mab_start, sizeof(void *) * (i - mab_start)); if (new_max) mas->max = b_node->pivot[i - 1]; end = j - 1; if (likely(!ma_is_leaf(mt) && mt_is_alloc(mas->tree))) { unsigned long max_gap = 0; unsigned char offset = 0; gaps = ma_gaps(node, mt); do { gaps[--j] = b_node->gap[--i]; if (gaps[j] > max_gap) { offset = j; max_gap = gaps[j]; } } while (j); ma_set_meta(node, mt, offset, end); } else { mas_leaf_set_meta(node, mt, end); } } /* * mas_bulk_rebalance() - Rebalance the end of a tree after a bulk insert. * @mas: The maple state * @end: The maple node end * @mt: The maple node type */ static inline void mas_bulk_rebalance(struct ma_state *mas, unsigned char end, enum maple_type mt) { if (!(mas->mas_flags & MA_STATE_BULK)) return; if (mte_is_root(mas->node)) return; if (end > mt_min_slots[mt]) { mas->mas_flags &= ~MA_STATE_REBALANCE; return; } } /* * mas_store_b_node() - Store an @entry into the b_node while also copying the * data from a maple encoded node. * @wr_mas: the maple write state * @b_node: the maple_big_node to fill with data * @offset_end: the offset to end copying * * Return: The actual end of the data stored in @b_node */ static noinline_for_kasan void mas_store_b_node(struct ma_wr_state *wr_mas, struct maple_big_node *b_node, unsigned char offset_end) { unsigned char slot; unsigned char b_end; /* Possible underflow of piv will wrap back to 0 before use. */ unsigned long piv; struct ma_state *mas = wr_mas->mas; b_node->type = wr_mas->type; b_end = 0; slot = mas->offset; if (slot) { /* Copy start data up to insert. */ mas_mab_cp(mas, 0, slot - 1, b_node, 0); b_end = b_node->b_end; piv = b_node->pivot[b_end - 1]; } else piv = mas->min - 1; if (piv + 1 < mas->index) { /* Handle range starting after old range */ b_node->slot[b_end] = wr_mas->content; if (!wr_mas->content) b_node->gap[b_end] = mas->index - 1 - piv; b_node->pivot[b_end++] = mas->index - 1; } /* Store the new entry. */ mas->offset = b_end; b_node->slot[b_end] = wr_mas->entry; b_node->pivot[b_end] = mas->last; /* Appended. */ if (mas->last >= mas->max) goto b_end; /* Handle new range ending before old range ends */ piv = mas_safe_pivot(mas, wr_mas->pivots, offset_end, wr_mas->type); if (piv > mas->last) { if (piv == ULONG_MAX) mas_bulk_rebalance(mas, b_node->b_end, wr_mas->type); if (offset_end != slot) wr_mas->content = mas_slot_locked(mas, wr_mas->slots, offset_end); b_node->slot[++b_end] = wr_mas->content; if (!wr_mas->content) b_node->gap[b_end] = piv - mas->last + 1; b_node->pivot[b_end] = piv; } slot = offset_end + 1; if (slot > mas->end) goto b_end; /* Copy end data to the end of the node. */ mas_mab_cp(mas, slot, mas->end + 1, b_node, ++b_end); b_node->b_end--; return; b_end: b_node->b_end = b_end; } /* * mas_prev_sibling() - Find the previous node with the same parent. * @mas: the maple state * * Return: True if there is a previous sibling, false otherwise. */ static inline bool mas_prev_sibling(struct ma_state *mas) { unsigned int p_slot = mte_parent_slot(mas->node); /* For root node, p_slot is set to 0 by mte_parent_slot(). */ if (!p_slot) return false; mas_ascend(mas); mas->offset = p_slot - 1; mas_descend(mas); return true; } /* * mas_next_sibling() - Find the next node with the same parent. * @mas: the maple state * * Return: true if there is a next sibling, false otherwise. */ static inline bool mas_next_sibling(struct ma_state *mas) { MA_STATE(parent, mas->tree, mas->index, mas->last); if (mte_is_root(mas->node)) return false; parent = *mas; mas_ascend(&parent); parent.offset = mte_parent_slot(mas->node) + 1; if (parent.offset > mas_data_end(&parent)) return false; *mas = parent; mas_descend(mas); return true; } /* * mas_node_or_none() - Set the enode and state. * @mas: the maple state * @enode: The encoded maple node. * * Set the node to the enode and the status. */ static inline void mas_node_or_none(struct ma_state *mas, struct maple_enode *enode) { if (enode) { mas->node = enode; mas->status = ma_active; } else { mas->node = NULL; mas->status = ma_none; } } /* * mas_wr_node_walk() - Find the correct offset for the index in the @mas. * If @mas->index cannot be found within the containing * node, we traverse to the last entry in the node. * @wr_mas: The maple write state * * Uses mas_slot_locked() and does not need to worry about dead nodes. */ static inline void mas_wr_node_walk(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char count, offset; if (unlikely(ma_is_dense(wr_mas->type))) { wr_mas->r_max = wr_mas->r_min = mas->index; mas->offset = mas->index = mas->min; return; } wr_mas->node = mas_mn(wr_mas->mas); wr_mas->pivots = ma_pivots(wr_mas->node, wr_mas->type); count = mas->end = ma_data_end(wr_mas->node, wr_mas->type, wr_mas->pivots, mas->max); offset = mas->offset; while (offset < count && mas->index > wr_mas->pivots[offset]) offset++; wr_mas->r_max = offset < count ? wr_mas->pivots[offset] : mas->max; wr_mas->r_min = mas_safe_min(mas, wr_mas->pivots, offset); wr_mas->offset_end = mas->offset = offset; } /* * mast_rebalance_next() - Rebalance against the next node * @mast: The maple subtree state */ static inline void mast_rebalance_next(struct maple_subtree_state *mast) { unsigned char b_end = mast->bn->b_end; mas_mab_cp(mast->orig_r, 0, mt_slot_count(mast->orig_r->node), mast->bn, b_end); mast->orig_r->last = mast->orig_r->max; } /* * mast_rebalance_prev() - Rebalance against the previous node * @mast: The maple subtree state */ static inline void mast_rebalance_prev(struct maple_subtree_state *mast) { unsigned char end = mas_data_end(mast->orig_l) + 1; unsigned char b_end = mast->bn->b_end; mab_shift_right(mast->bn, end); mas_mab_cp(mast->orig_l, 0, end - 1, mast->bn, 0); mast->l->min = mast->orig_l->min; mast->orig_l->index = mast->orig_l->min; mast->bn->b_end = end + b_end; mast->l->offset += end; } /* * mast_spanning_rebalance() - Rebalance nodes with nearest neighbour favouring * the node to the right. Checking the nodes to the right then the left at each * level upwards until root is reached. * Data is copied into the @mast->bn. * @mast: The maple_subtree_state. */ static inline bool mast_spanning_rebalance(struct maple_subtree_state *mast) { struct ma_state r_tmp = *mast->orig_r; struct ma_state l_tmp = *mast->orig_l; unsigned char depth = 0; do { mas_ascend(mast->orig_r); mas_ascend(mast->orig_l); depth++; if (mast->orig_r->offset < mas_data_end(mast->orig_r)) { mast->orig_r->offset++; do { mas_descend(mast->orig_r); mast->orig_r->offset = 0; } while (--depth); mast_rebalance_next(mast); *mast->orig_l = l_tmp; return true; } else if (mast->orig_l->offset != 0) { mast->orig_l->offset--; do { mas_descend(mast->orig_l); mast->orig_l->offset = mas_data_end(mast->orig_l); } while (--depth); mast_rebalance_prev(mast); *mast->orig_r = r_tmp; return true; } } while (!mte_is_root(mast->orig_r->node)); *mast->orig_r = r_tmp; *mast->orig_l = l_tmp; return false; } /* * mast_ascend() - Ascend the original left and right maple states. * @mast: the maple subtree state. * * Ascend the original left and right sides. Set the offsets to point to the * data already in the new tree (@mast->l and @mast->r). */ static inline void mast_ascend(struct maple_subtree_state *mast) { MA_WR_STATE(wr_mas, mast->orig_r, NULL); mas_ascend(mast->orig_l); mas_ascend(mast->orig_r); mast->orig_r->offset = 0; mast->orig_r->index = mast->r->max; /* last should be larger than or equal to index */ if (mast->orig_r->last < mast->orig_r->index) mast->orig_r->last = mast->orig_r->index; wr_mas.type = mte_node_type(mast->orig_r->node); mas_wr_node_walk(&wr_mas); /* Set up the left side of things */ mast->orig_l->offset = 0; mast->orig_l->index = mast->l->min; wr_mas.mas = mast->orig_l; wr_mas.type = mte_node_type(mast->orig_l->node); mas_wr_node_walk(&wr_mas); mast->bn->type = wr_mas.type; } /* * mas_new_ma_node() - Create and return a new maple node. Helper function. * @mas: the maple state with the allocations. * @b_node: the maple_big_node with the type encoding. * * Use the node type from the maple_big_node to allocate a new node from the * ma_state. This function exists mainly for code readability. * * Return: A new maple encoded node */ static inline struct maple_enode *mas_new_ma_node(struct ma_state *mas, struct maple_big_node *b_node) { return mt_mk_node(ma_mnode_ptr(mas_pop_node(mas)), b_node->type); } /* * mas_mab_to_node() - Set up right and middle nodes * * @mas: the maple state that contains the allocations. * @b_node: the node which contains the data. * @left: The pointer which will have the left node * @right: The pointer which may have the right node * @middle: the pointer which may have the middle node (rare) * @mid_split: the split location for the middle node * * Return: the split of left. */ static inline unsigned char mas_mab_to_node(struct ma_state *mas, struct maple_big_node *b_node, struct maple_enode **left, struct maple_enode **right, struct maple_enode **middle, unsigned char *mid_split, unsigned long min) { unsigned char split = 0; unsigned char slot_count = mt_slots[b_node->type]; *left = mas_new_ma_node(mas, b_node); *right = NULL; *middle = NULL; *mid_split = 0; if (b_node->b_end < slot_count) { split = b_node->b_end; } else { split = mab_calc_split(mas, b_node, mid_split, min); *right = mas_new_ma_node(mas, b_node); } if (*mid_split) *middle = mas_new_ma_node(mas, b_node); return split; } /* * mab_set_b_end() - Add entry to b_node at b_node->b_end and increment the end * pointer. * @b_node: the big node to add the entry * @mas: the maple state to get the pivot (mas->max) * @entry: the entry to add, if NULL nothing happens. */ static inline void mab_set_b_end(struct maple_big_node *b_node, struct ma_state *mas, void *entry) { if (!entry) return; b_node->slot[b_node->b_end] = entry; if (mt_is_alloc(mas->tree)) b_node->gap[b_node->b_end] = mas_max_gap(mas); b_node->pivot[b_node->b_end++] = mas->max; } /* * mas_set_split_parent() - combine_then_separate helper function. Sets the parent * of @mas->node to either @left or @right, depending on @slot and @split * * @mas: the maple state with the node that needs a parent * @left: possible parent 1 * @right: possible parent 2 * @slot: the slot the mas->node was placed * @split: the split location between @left and @right */ static inline void mas_set_split_parent(struct ma_state *mas, struct maple_enode *left, struct maple_enode *right, unsigned char *slot, unsigned char split) { if (mas_is_none(mas)) return; if ((*slot) <= split) mas_set_parent(mas, mas->node, left, *slot); else if (right) mas_set_parent(mas, mas->node, right, (*slot) - split - 1); (*slot)++; } /* * mte_mid_split_check() - Check if the next node passes the mid-split * @l: Pointer to left encoded maple node. * @m: Pointer to middle encoded maple node. * @r: Pointer to right encoded maple node. * @slot: The offset * @split: The split location. * @mid_split: The middle split. */ static inline void mte_mid_split_check(struct maple_enode **l, struct maple_enode **r, struct maple_enode *right, unsigned char slot, unsigned char *split, unsigned char mid_split) { if (*r == right) return; if (slot < mid_split) return; *l = *r; *r = right; *split = mid_split; } /* * mast_set_split_parents() - Helper function to set three nodes parents. Slot * is taken from @mast->l. * @mast: the maple subtree state * @left: the left node * @right: the right node * @split: the split location. */ static inline void mast_set_split_parents(struct maple_subtree_state *mast, struct maple_enode *left, struct maple_enode *middle, struct maple_enode *right, unsigned char split, unsigned char mid_split) { unsigned char slot; struct maple_enode *l = left; struct maple_enode *r = right; if (mas_is_none(mast->l)) return; if (middle) r = middle; slot = mast->l->offset; mte_mid_split_check(&l, &r, right, slot, &split, mid_split); mas_set_split_parent(mast->l, l, r, &slot, split); mte_mid_split_check(&l, &r, right, slot, &split, mid_split); mas_set_split_parent(mast->m, l, r, &slot, split); mte_mid_split_check(&l, &r, right, slot, &split, mid_split); mas_set_split_parent(mast->r, l, r, &slot, split); } /* * mas_topiary_node() - Dispose of a single node * @mas: The maple state for pushing nodes * @in_rcu: If the tree is in rcu mode * * The node will either be RCU freed or pushed back on the maple state. */ static inline void mas_topiary_node(struct ma_state *mas, struct ma_state *tmp_mas, bool in_rcu) { struct maple_node *tmp; struct maple_enode *enode; if (mas_is_none(tmp_mas)) return; enode = tmp_mas->node; tmp = mte_to_node(enode); mte_set_node_dead(enode); if (in_rcu) ma_free_rcu(tmp); else mas_push_node(mas, tmp); } /* * mas_topiary_replace() - Replace the data with new data, then repair the * parent links within the new tree. Iterate over the dead sub-tree and collect * the dead subtrees and topiary the nodes that are no longer of use. * * The new tree will have up to three children with the correct parent. Keep * track of the new entries as they need to be followed to find the next level * of new entries. * * The old tree will have up to three children with the old parent. Keep track * of the old entries as they may have more nodes below replaced. Nodes within * [index, last] are dead subtrees, others need to be freed and followed. * * @mas: The maple state pointing at the new data * @old_enode: The maple encoded node being replaced * */ static inline void mas_topiary_replace(struct ma_state *mas, struct maple_enode *old_enode) { struct ma_state tmp[3], tmp_next[3]; MA_TOPIARY(subtrees, mas->tree); bool in_rcu; int i, n; /* Place data in tree & then mark node as old */ mas_put_in_tree(mas, old_enode); /* Update the parent pointers in the tree */ tmp[0] = *mas; tmp[0].offset = 0; tmp[1].status = ma_none; tmp[2].status = ma_none; while (!mte_is_leaf(tmp[0].node)) { n = 0; for (i = 0; i < 3; i++) { if (mas_is_none(&tmp[i])) continue; while (n < 3) { if (!mas_find_child(&tmp[i], &tmp_next[n])) break; n++; } mas_adopt_children(&tmp[i], tmp[i].node); } if (MAS_WARN_ON(mas, n == 0)) break; while (n < 3) tmp_next[n++].status = ma_none; for (i = 0; i < 3; i++) tmp[i] = tmp_next[i]; } /* Collect the old nodes that need to be discarded */ if (mte_is_leaf(old_enode)) return mas_free(mas, old_enode); tmp[0] = *mas; tmp[0].offset = 0; tmp[0].node = old_enode; tmp[1].status = ma_none; tmp[2].status = ma_none; in_rcu = mt_in_rcu(mas->tree); do { n = 0; for (i = 0; i < 3; i++) { if (mas_is_none(&tmp[i])) continue; while (n < 3) { if (!mas_find_child(&tmp[i], &tmp_next[n])) break; if ((tmp_next[n].min >= tmp_next->index) && (tmp_next[n].max <= tmp_next->last)) { mat_add(&subtrees, tmp_next[n].node); tmp_next[n].status = ma_none; } else { n++; } } } if (MAS_WARN_ON(mas, n == 0)) break; while (n < 3) tmp_next[n++].status = ma_none; for (i = 0; i < 3; i++) { mas_topiary_node(mas, &tmp[i], in_rcu); tmp[i] = tmp_next[i]; } } while (!mte_is_leaf(tmp[0].node)); for (i = 0; i < 3; i++) mas_topiary_node(mas, &tmp[i], in_rcu); mas_mat_destroy(mas, &subtrees); } /* * mas_wmb_replace() - Write memory barrier and replace * @mas: The maple state * @old_enode: The old maple encoded node that is being replaced. * * Updates gap as necessary. */ static inline void mas_wmb_replace(struct ma_state *mas, struct maple_enode *old_enode) { /* Insert the new data in the tree */ mas_topiary_replace(mas, old_enode); if (mte_is_leaf(mas->node)) return; mas_update_gap(mas); } /* * mast_cp_to_nodes() - Copy data out to nodes. * @mast: The maple subtree state * @left: The left encoded maple node * @middle: The middle encoded maple node * @right: The right encoded maple node * @split: The location to split between left and (middle ? middle : right) * @mid_split: The location to split between middle and right. */ static inline void mast_cp_to_nodes(struct maple_subtree_state *mast, struct maple_enode *left, struct maple_enode *middle, struct maple_enode *right, unsigned char split, unsigned char mid_split) { bool new_lmax = true; mas_node_or_none(mast->l, left); mas_node_or_none(mast->m, middle); mas_node_or_none(mast->r, right); mast->l->min = mast->orig_l->min; if (split == mast->bn->b_end) { mast->l->max = mast->orig_r->max; new_lmax = false; } mab_mas_cp(mast->bn, 0, split, mast->l, new_lmax); if (middle) { mab_mas_cp(mast->bn, 1 + split, mid_split, mast->m, true); mast->m->min = mast->bn->pivot[split] + 1; split = mid_split; } mast->r->max = mast->orig_r->max; if (right) { mab_mas_cp(mast->bn, 1 + split, mast->bn->b_end, mast->r, false); mast->r->min = mast->bn->pivot[split] + 1; } } /* * mast_combine_cp_left - Copy in the original left side of the tree into the * combined data set in the maple subtree state big node. * @mast: The maple subtree state */ static inline void mast_combine_cp_left(struct maple_subtree_state *mast) { unsigned char l_slot = mast->orig_l->offset; if (!l_slot) return; mas_mab_cp(mast->orig_l, 0, l_slot - 1, mast->bn, 0); } /* * mast_combine_cp_right: Copy in the original right side of the tree into the * combined data set in the maple subtree state big node. * @mast: The maple subtree state */ static inline void mast_combine_cp_right(struct maple_subtree_state *mast) { if (mast->bn->pivot[mast->bn->b_end - 1] >= mast->orig_r->max) return; mas_mab_cp(mast->orig_r, mast->orig_r->offset + 1, mt_slot_count(mast->orig_r->node), mast->bn, mast->bn->b_end); mast->orig_r->last = mast->orig_r->max; } /* * mast_sufficient: Check if the maple subtree state has enough data in the big * node to create at least one sufficient node * @mast: the maple subtree state */ static inline bool mast_sufficient(struct maple_subtree_state *mast) { if (mast->bn->b_end > mt_min_slot_count(mast->orig_l->node)) return true; return false; } /* * mast_overflow: Check if there is too much data in the subtree state for a * single node. * @mast: The maple subtree state */ static inline bool mast_overflow(struct maple_subtree_state *mast) { if (mast->bn->b_end >= mt_slot_count(mast->orig_l->node)) return true; return false; } static inline void *mtree_range_walk(struct ma_state *mas) { unsigned long *pivots; unsigned char offset; struct maple_node *node; struct maple_enode *next, *last; enum maple_type type; void __rcu **slots; unsigned char end; unsigned long max, min; unsigned long prev_max, prev_min; next = mas->node; min = mas->min; max = mas->max; do { last = next; node = mte_to_node(next); type = mte_node_type(next); pivots = ma_pivots(node, type); end = ma_data_end(node, type, pivots, max); prev_min = min; prev_max = max; if (pivots[0] >= mas->index) { offset = 0; max = pivots[0]; goto next; } offset = 1; while (offset < end) { if (pivots[offset] >= mas->index) { max = pivots[offset]; break; } offset++; } min = pivots[offset - 1] + 1; next: slots = ma_slots(node, type); next = mt_slot(mas->tree, slots, offset); if (unlikely(ma_dead_node(node))) goto dead_node; } while (!ma_is_leaf(type)); mas->end = end; mas->offset = offset; mas->index = min; mas->last = max; mas->min = prev_min; mas->max = prev_max; mas->node = last; return (void *)next; dead_node: mas_reset(mas); return NULL; } /* * mas_spanning_rebalance() - Rebalance across two nodes which may not be peers. * @mas: The starting maple state * @mast: The maple_subtree_state, keeps track of 4 maple states. * @count: The estimated count of iterations needed. * * Follow the tree upwards from @l_mas and @r_mas for @count, or until the root * is hit. First @b_node is split into two entries which are inserted into the * next iteration of the loop. @b_node is returned populated with the final * iteration. @mas is used to obtain allocations. orig_l_mas keeps track of the * nodes that will remain active by using orig_l_mas->index and orig_l_mas->last * to account of what has been copied into the new sub-tree. The update of * orig_l_mas->last is used in mas_consume to find the slots that will need to * be either freed or destroyed. orig_l_mas->depth keeps track of the height of * the new sub-tree in case the sub-tree becomes the full tree. */ static void mas_spanning_rebalance(struct ma_state *mas, struct maple_subtree_state *mast, unsigned char count) { unsigned char split, mid_split; unsigned char slot = 0; struct maple_enode *left = NULL, *middle = NULL, *right = NULL; struct maple_enode *old_enode; MA_STATE(l_mas, mas->tree, mas->index, mas->index); MA_STATE(r_mas, mas->tree, mas->index, mas->last); MA_STATE(m_mas, mas->tree, mas->index, mas->index); /* * The tree needs to be rebalanced and leaves need to be kept at the same level. * Rebalancing is done by use of the ``struct maple_topiary``. */ mast->l = &l_mas; mast->m = &m_mas; mast->r = &r_mas; l_mas.status = r_mas.status = m_mas.status = ma_none; /* Check if this is not root and has sufficient data. */ if (((mast->orig_l->min != 0) || (mast->orig_r->max != ULONG_MAX)) && unlikely(mast->bn->b_end <= mt_min_slots[mast->bn->type])) mast_spanning_rebalance(mast); l_mas.depth = 0; /* * Each level of the tree is examined and balanced, pushing data to the left or * right, or rebalancing against left or right nodes is employed to avoid * rippling up the tree to limit the amount of churn. Once a new sub-section of * the tree is created, there may be a mix of new and old nodes. The old nodes * will have the incorrect parent pointers and currently be in two trees: the * original tree and the partially new tree. To remedy the parent pointers in * the old tree, the new data is swapped into the active tree and a walk down * the tree is performed and the parent pointers are updated. * See mas_topiary_replace() for more information. */ while (count--) { mast->bn->b_end--; mast->bn->type = mte_node_type(mast->orig_l->node); split = mas_mab_to_node(mas, mast->bn, &left, &right, &middle, &mid_split, mast->orig_l->min); mast_set_split_parents(mast, left, middle, right, split, mid_split); mast_cp_to_nodes(mast, left, middle, right, split, mid_split); /* * Copy data from next level in the tree to mast->bn from next * iteration */ memset(mast->bn, 0, sizeof(struct maple_big_node)); mast->bn->type = mte_node_type(left); l_mas.depth++; /* Root already stored in l->node. */ if (mas_is_root_limits(mast->l)) goto new_root; mast_ascend(mast); mast_combine_cp_left(mast); l_mas.offset = mast->bn->b_end; mab_set_b_end(mast->bn, &l_mas, left); mab_set_b_end(mast->bn, &m_mas, middle); mab_set_b_end(mast->bn, &r_mas, right); /* Copy anything necessary out of the right node. */ mast_combine_cp_right(mast); mast->orig_l->last = mast->orig_l->max; if (mast_sufficient(mast)) continue; if (mast_overflow(mast)) continue; /* May be a new root stored in mast->bn */ if (mas_is_root_limits(mast->orig_l)) break; mast_spanning_rebalance(mast); /* rebalancing from other nodes may require another loop. */ if (!count) count++; } l_mas.node = mt_mk_node(ma_mnode_ptr(mas_pop_node(mas)), mte_node_type(mast->orig_l->node)); l_mas.depth++; mab_mas_cp(mast->bn, 0, mt_slots[mast->bn->type] - 1, &l_mas, true); mas_set_parent(mas, left, l_mas.node, slot); if (middle) mas_set_parent(mas, middle, l_mas.node, ++slot); if (right) mas_set_parent(mas, right, l_mas.node, ++slot); if (mas_is_root_limits(mast->l)) { new_root: mas_mn(mast->l)->parent = ma_parent_ptr(mas_tree_parent(mas)); while (!mte_is_root(mast->orig_l->node)) mast_ascend(mast); } else { mas_mn(&l_mas)->parent = mas_mn(mast->orig_l)->parent; } old_enode = mast->orig_l->node; mas->depth = l_mas.depth; mas->node = l_mas.node; mas->min = l_mas.min; mas->max = l_mas.max; mas->offset = l_mas.offset; mas_wmb_replace(mas, old_enode); mtree_range_walk(mas); return; } /* * mas_rebalance() - Rebalance a given node. * @mas: The maple state * @b_node: The big maple node. * * Rebalance two nodes into a single node or two new nodes that are sufficient. * Continue upwards until tree is sufficient. */ static inline void mas_rebalance(struct ma_state *mas, struct maple_big_node *b_node) { char empty_count = mas_mt_height(mas); struct maple_subtree_state mast; unsigned char shift, b_end = ++b_node->b_end; MA_STATE(l_mas, mas->tree, mas->index, mas->last); MA_STATE(r_mas, mas->tree, mas->index, mas->last); trace_ma_op(__func__, mas); /* * Rebalancing occurs if a node is insufficient. Data is rebalanced * against the node to the right if it exists, otherwise the node to the * left of this node is rebalanced against this node. If rebalancing * causes just one node to be produced instead of two, then the parent * is also examined and rebalanced if it is insufficient. Every level * tries to combine the data in the same way. If one node contains the * entire range of the tree, then that node is used as a new root node. */ mast.orig_l = &l_mas; mast.orig_r = &r_mas; mast.bn = b_node; mast.bn->type = mte_node_type(mas->node); l_mas = r_mas = *mas; if (mas_next_sibling(&r_mas)) { mas_mab_cp(&r_mas, 0, mt_slot_count(r_mas.node), b_node, b_end); r_mas.last = r_mas.index = r_mas.max; } else { mas_prev_sibling(&l_mas); shift = mas_data_end(&l_mas) + 1; mab_shift_right(b_node, shift); mas->offset += shift; mas_mab_cp(&l_mas, 0, shift - 1, b_node, 0); b_node->b_end = shift + b_end; l_mas.index = l_mas.last = l_mas.min; } return mas_spanning_rebalance(mas, &mast, empty_count); } /* * mas_destroy_rebalance() - Rebalance left-most node while destroying the maple * state. * @mas: The maple state * @end: The end of the left-most node. * * During a mass-insert event (such as forking), it may be necessary to * rebalance the left-most node when it is not sufficient. */ static inline void mas_destroy_rebalance(struct ma_state *mas, unsigned char end) { enum maple_type mt = mte_node_type(mas->node); struct maple_node reuse, *newnode, *parent, *new_left, *left, *node; struct maple_enode *eparent, *old_eparent; unsigned char offset, tmp, split = mt_slots[mt] / 2; void __rcu **l_slots, **slots; unsigned long *l_pivs, *pivs, gap; bool in_rcu = mt_in_rcu(mas->tree); MA_STATE(l_mas, mas->tree, mas->index, mas->last); l_mas = *mas; mas_prev_sibling(&l_mas); /* set up node. */ if (in_rcu) { newnode = mas_pop_node(mas); } else { newnode = &reuse; } node = mas_mn(mas); newnode->parent = node->parent; slots = ma_slots(newnode, mt); pivs = ma_pivots(newnode, mt); left = mas_mn(&l_mas); l_slots = ma_slots(left, mt); l_pivs = ma_pivots(left, mt); if (!l_slots[split]) split++; tmp = mas_data_end(&l_mas) - split; memcpy(slots, l_slots + split + 1, sizeof(void *) * tmp); memcpy(pivs, l_pivs + split + 1, sizeof(unsigned long) * tmp); pivs[tmp] = l_mas.max; memcpy(slots + tmp, ma_slots(node, mt), sizeof(void *) * end); memcpy(pivs + tmp, ma_pivots(node, mt), sizeof(unsigned long) * end); l_mas.max = l_pivs[split]; mas->min = l_mas.max + 1; old_eparent = mt_mk_node(mte_parent(l_mas.node), mas_parent_type(&l_mas, l_mas.node)); tmp += end; if (!in_rcu) { unsigned char max_p = mt_pivots[mt]; unsigned char max_s = mt_slots[mt]; if (tmp < max_p) memset(pivs + tmp, 0, sizeof(unsigned long) * (max_p - tmp)); if (tmp < mt_slots[mt]) memset(slots + tmp, 0, sizeof(void *) * (max_s - tmp)); memcpy(node, newnode, sizeof(struct maple_node)); ma_set_meta(node, mt, 0, tmp - 1); mte_set_pivot(old_eparent, mte_parent_slot(l_mas.node), l_pivs[split]); /* Remove data from l_pivs. */ tmp = split + 1; memset(l_pivs + tmp, 0, sizeof(unsigned long) * (max_p - tmp)); memset(l_slots + tmp, 0, sizeof(void *) * (max_s - tmp)); ma_set_meta(left, mt, 0, split); eparent = old_eparent; goto done; } /* RCU requires replacing both l_mas, mas, and parent. */ mas->node = mt_mk_node(newnode, mt); ma_set_meta(newnode, mt, 0, tmp); new_left = mas_pop_node(mas); new_left->parent = left->parent; mt = mte_node_type(l_mas.node); slots = ma_slots(new_left, mt); pivs = ma_pivots(new_left, mt); memcpy(slots, l_slots, sizeof(void *) * split); memcpy(pivs, l_pivs, sizeof(unsigned long) * split); ma_set_meta(new_left, mt, 0, split); l_mas.node = mt_mk_node(new_left, mt); /* replace parent. */ offset = mte_parent_slot(mas->node); mt = mas_parent_type(&l_mas, l_mas.node); parent = mas_pop_node(mas); slots = ma_slots(parent, mt); pivs = ma_pivots(parent, mt); memcpy(parent, mte_to_node(old_eparent), sizeof(struct maple_node)); rcu_assign_pointer(slots[offset], mas->node); rcu_assign_pointer(slots[offset - 1], l_mas.node); pivs[offset - 1] = l_mas.max; eparent = mt_mk_node(parent, mt); done: gap = mas_leaf_max_gap(mas); mte_set_gap(eparent, mte_parent_slot(mas->node), gap); gap = mas_leaf_max_gap(&l_mas); mte_set_gap(eparent, mte_parent_slot(l_mas.node), gap); mas_ascend(mas); if (in_rcu) { mas_replace_node(mas, old_eparent); mas_adopt_children(mas, mas->node); } mas_update_gap(mas); } /* * mas_split_final_node() - Split the final node in a subtree operation. * @mast: the maple subtree state * @mas: The maple state * @height: The height of the tree in case it's a new root. */ static inline void mas_split_final_node(struct maple_subtree_state *mast, struct ma_state *mas, int height) { struct maple_enode *ancestor; if (mte_is_root(mas->node)) { if (mt_is_alloc(mas->tree)) mast->bn->type = maple_arange_64; else mast->bn->type = maple_range_64; mas->depth = height; } /* * Only a single node is used here, could be root. * The Big_node data should just fit in a single node. */ ancestor = mas_new_ma_node(mas, mast->bn); mas_set_parent(mas, mast->l->node, ancestor, mast->l->offset); mas_set_parent(mas, mast->r->node, ancestor, mast->r->offset); mte_to_node(ancestor)->parent = mas_mn(mas)->parent; mast->l->node = ancestor; mab_mas_cp(mast->bn, 0, mt_slots[mast->bn->type] - 1, mast->l, true); mas->offset = mast->bn->b_end - 1; } /* * mast_fill_bnode() - Copy data into the big node in the subtree state * @mast: The maple subtree state * @mas: the maple state * @skip: The number of entries to skip for new nodes insertion. */ static inline void mast_fill_bnode(struct maple_subtree_state *mast, struct ma_state *mas, unsigned char skip) { bool cp = true; unsigned char split; memset(mast->bn, 0, sizeof(struct maple_big_node)); if (mte_is_root(mas->node)) { cp = false; } else { mas_ascend(mas); mas->offset = mte_parent_slot(mas->node); } if (cp && mast->l->offset) mas_mab_cp(mas, 0, mast->l->offset - 1, mast->bn, 0); split = mast->bn->b_end; mab_set_b_end(mast->bn, mast->l, mast->l->node); mast->r->offset = mast->bn->b_end; mab_set_b_end(mast->bn, mast->r, mast->r->node); if (mast->bn->pivot[mast->bn->b_end - 1] == mas->max) cp = false; if (cp) mas_mab_cp(mas, split + skip, mt_slot_count(mas->node) - 1, mast->bn, mast->bn->b_end); mast->bn->b_end--; mast->bn->type = mte_node_type(mas->node); } /* * mast_split_data() - Split the data in the subtree state big node into regular * nodes. * @mast: The maple subtree state * @mas: The maple state * @split: The location to split the big node */ static inline void mast_split_data(struct maple_subtree_state *mast, struct ma_state *mas, unsigned char split) { unsigned char p_slot; mab_mas_cp(mast->bn, 0, split, mast->l, true); mte_set_pivot(mast->r->node, 0, mast->r->max); mab_mas_cp(mast->bn, split + 1, mast->bn->b_end, mast->r, false); mast->l->offset = mte_parent_slot(mas->node); mast->l->max = mast->bn->pivot[split]; mast->r->min = mast->l->max + 1; if (mte_is_leaf(mas->node)) return; p_slot = mast->orig_l->offset; mas_set_split_parent(mast->orig_l, mast->l->node, mast->r->node, &p_slot, split); mas_set_split_parent(mast->orig_r, mast->l->node, mast->r->node, &p_slot, split); } /* * mas_push_data() - Instead of splitting a node, it is beneficial to push the * data to the right or left node if there is room. * @mas: The maple state * @height: The current height of the maple state * @mast: The maple subtree state * @left: Push left or not. * * Keeping the height of the tree low means faster lookups. * * Return: True if pushed, false otherwise. */ static inline bool mas_push_data(struct ma_state *mas, int height, struct maple_subtree_state *mast, bool left) { unsigned char slot_total = mast->bn->b_end; unsigned char end, space, split; MA_STATE(tmp_mas, mas->tree, mas->index, mas->last); tmp_mas = *mas; tmp_mas.depth = mast->l->depth; if (left && !mas_prev_sibling(&tmp_mas)) return false; else if (!left && !mas_next_sibling(&tmp_mas)) return false; end = mas_data_end(&tmp_mas); slot_total += end; space = 2 * mt_slot_count(mas->node) - 2; /* -2 instead of -1 to ensure there isn't a triple split */ if (ma_is_leaf(mast->bn->type)) space--; if (mas->max == ULONG_MAX) space--; if (slot_total >= space) return false; /* Get the data; Fill mast->bn */ mast->bn->b_end++; if (left) { mab_shift_right(mast->bn, end + 1); mas_mab_cp(&tmp_mas, 0, end, mast->bn, 0); mast->bn->b_end = slot_total + 1; } else { mas_mab_cp(&tmp_mas, 0, end, mast->bn, mast->bn->b_end); } /* Configure mast for splitting of mast->bn */ split = mt_slots[mast->bn->type] - 2; if (left) { /* Switch mas to prev node */ *mas = tmp_mas; /* Start using mast->l for the left side. */ tmp_mas.node = mast->l->node; *mast->l = tmp_mas; } else { tmp_mas.node = mast->r->node; *mast->r = tmp_mas; split = slot_total - split; } split = mab_no_null_split(mast->bn, split, mt_slots[mast->bn->type]); /* Update parent slot for split calculation. */ if (left) mast->orig_l->offset += end + 1; mast_split_data(mast, mas, split); mast_fill_bnode(mast, mas, 2); mas_split_final_node(mast, mas, height + 1); return true; } /* * mas_split() - Split data that is too big for one node into two. * @mas: The maple state * @b_node: The maple big node */ static void mas_split(struct ma_state *mas, struct maple_big_node *b_node) { struct maple_subtree_state mast; int height = 0; unsigned char mid_split, split = 0; struct maple_enode *old; /* * Splitting is handled differently from any other B-tree; the Maple * Tree splits upwards. Splitting up means that the split operation * occurs when the walk of the tree hits the leaves and not on the way * down. The reason for splitting up is that it is impossible to know * how much space will be needed until the leaf is (or leaves are) * reached. Since overwriting data is allowed and a range could * overwrite more than one range or result in changing one entry into 3 * entries, it is impossible to know if a split is required until the * data is examined. * * Splitting is a balancing act between keeping allocations to a minimum * and avoiding a 'jitter' event where a tree is expanded to make room * for an entry followed by a contraction when the entry is removed. To * accomplish the balance, there are empty slots remaining in both left * and right nodes after a split. */ MA_STATE(l_mas, mas->tree, mas->index, mas->last); MA_STATE(r_mas, mas->tree, mas->index, mas->last); MA_STATE(prev_l_mas, mas->tree, mas->index, mas->last); MA_STATE(prev_r_mas, mas->tree, mas->index, mas->last); trace_ma_op(__func__, mas); mas->depth = mas_mt_height(mas); mast.l = &l_mas; mast.r = &r_mas; mast.orig_l = &prev_l_mas; mast.orig_r = &prev_r_mas; mast.bn = b_node; while (height++ <= mas->depth) { if (mt_slots[b_node->type] > b_node->b_end) { mas_split_final_node(&mast, mas, height); break; } l_mas = r_mas = *mas; l_mas.node = mas_new_ma_node(mas, b_node); r_mas.node = mas_new_ma_node(mas, b_node); /* * Another way that 'jitter' is avoided is to terminate a split up early if the * left or right node has space to spare. This is referred to as "pushing left" * or "pushing right" and is similar to the B* tree, except the nodes left or * right can rarely be reused due to RCU, but the ripple upwards is halted which * is a significant savings. */ /* Try to push left. */ if (mas_push_data(mas, height, &mast, true)) break; /* Try to push right. */ if (mas_push_data(mas, height, &mast, false)) break; split = mab_calc_split(mas, b_node, &mid_split, prev_l_mas.min); mast_split_data(&mast, mas, split); /* * Usually correct, mab_mas_cp in the above call overwrites * r->max. */ mast.r->max = mas->max; mast_fill_bnode(&mast, mas, 1); prev_l_mas = *mast.l; prev_r_mas = *mast.r; } /* Set the original node as dead */ old = mas->node; mas->node = l_mas.node; mas_wmb_replace(mas, old); mtree_range_walk(mas); return; } /* * mas_commit_b_node() - Commit the big node into the tree. * @wr_mas: The maple write state * @b_node: The maple big node */ static noinline_for_kasan void mas_commit_b_node(struct ma_wr_state *wr_mas, struct maple_big_node *b_node) { enum store_type type = wr_mas->mas->store_type; WARN_ON_ONCE(type != wr_rebalance && type != wr_split_store); if (type == wr_rebalance) return mas_rebalance(wr_mas->mas, b_node); return mas_split(wr_mas->mas, b_node); } /* * mas_root_expand() - Expand a root to a node * @mas: The maple state * @entry: The entry to store into the tree */ static inline void mas_root_expand(struct ma_state *mas, void *entry) { void *contents = mas_root_locked(mas); enum maple_type type = maple_leaf_64; struct maple_node *node; void __rcu **slots; unsigned long *pivots; int slot = 0; node = mas_pop_node(mas); pivots = ma_pivots(node, type); slots = ma_slots(node, type); node->parent = ma_parent_ptr(mas_tree_parent(mas)); mas->node = mt_mk_node(node, type); mas->status = ma_active; if (mas->index) { if (contents) { rcu_assign_pointer(slots[slot], contents); if (likely(mas->index > 1)) slot++; } pivots[slot++] = mas->index - 1; } rcu_assign_pointer(slots[slot], entry); mas->offset = slot; pivots[slot] = mas->last; if (mas->last != ULONG_MAX) pivots[++slot] = ULONG_MAX; mas->depth = 1; mas_set_height(mas); ma_set_meta(node, maple_leaf_64, 0, slot); /* swap the new root into the tree */ rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node)); return; } /* * mas_store_root() - Storing value into root. * @mas: The maple state * @entry: The entry to store. * * There is no root node now and we are storing a value into the root - this * function either assigns the pointer or expands into a node. */ static inline void mas_store_root(struct ma_state *mas, void *entry) { if (!entry) { if (!mas->index) rcu_assign_pointer(mas->tree->ma_root, NULL); } else if (likely((mas->last != 0) || (mas->index != 0))) mas_root_expand(mas, entry); else if (((unsigned long) (entry) & 3) == 2) mas_root_expand(mas, entry); else { rcu_assign_pointer(mas->tree->ma_root, entry); mas->status = ma_start; } } /* * mas_is_span_wr() - Check if the write needs to be treated as a write that * spans the node. * @wr_mas: The maple write state * * Spanning writes are writes that start in one node and end in another OR if * the write of a %NULL will cause the node to end with a %NULL. * * Return: True if this is a spanning write, false otherwise. */ static bool mas_is_span_wr(struct ma_wr_state *wr_mas) { unsigned long max = wr_mas->r_max; unsigned long last = wr_mas->mas->last; enum maple_type type = wr_mas->type; void *entry = wr_mas->entry; /* Contained in this pivot, fast path */ if (last < max) return false; if (ma_is_leaf(type)) { max = wr_mas->mas->max; if (last < max) return false; } if (last == max) { /* * The last entry of leaf node cannot be NULL unless it is the * rightmost node (writing ULONG_MAX), otherwise it spans slots. */ if (entry || last == ULONG_MAX) return false; } trace_ma_write(__func__, wr_mas->mas, wr_mas->r_max, entry); return true; } static inline void mas_wr_walk_descend(struct ma_wr_state *wr_mas) { wr_mas->type = mte_node_type(wr_mas->mas->node); mas_wr_node_walk(wr_mas); wr_mas->slots = ma_slots(wr_mas->node, wr_mas->type); } static inline void mas_wr_walk_traverse(struct ma_wr_state *wr_mas) { wr_mas->mas->max = wr_mas->r_max; wr_mas->mas->min = wr_mas->r_min; wr_mas->mas->node = wr_mas->content; wr_mas->mas->offset = 0; wr_mas->mas->depth++; } /* * mas_wr_walk() - Walk the tree for a write. * @wr_mas: The maple write state * * Uses mas_slot_locked() and does not need to worry about dead nodes. * * Return: True if it's contained in a node, false on spanning write. */ static bool mas_wr_walk(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; while (true) { mas_wr_walk_descend(wr_mas); if (unlikely(mas_is_span_wr(wr_mas))) return false; wr_mas->content = mas_slot_locked(mas, wr_mas->slots, mas->offset); if (ma_is_leaf(wr_mas->type)) return true; mas_wr_walk_traverse(wr_mas); } return true; } static void mas_wr_walk_index(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; while (true) { mas_wr_walk_descend(wr_mas); wr_mas->content = mas_slot_locked(mas, wr_mas->slots, mas->offset); if (ma_is_leaf(wr_mas->type)) return; mas_wr_walk_traverse(wr_mas); } } /* * mas_extend_spanning_null() - Extend a store of a %NULL to include surrounding %NULLs. * @l_wr_mas: The left maple write state * @r_wr_mas: The right maple write state */ static inline void mas_extend_spanning_null(struct ma_wr_state *l_wr_mas, struct ma_wr_state *r_wr_mas) { struct ma_state *r_mas = r_wr_mas->mas; struct ma_state *l_mas = l_wr_mas->mas; unsigned char l_slot; l_slot = l_mas->offset; if (!l_wr_mas->content) l_mas->index = l_wr_mas->r_min; if ((l_mas->index == l_wr_mas->r_min) && (l_slot && !mas_slot_locked(l_mas, l_wr_mas->slots, l_slot - 1))) { if (l_slot > 1) l_mas->index = l_wr_mas->pivots[l_slot - 2] + 1; else l_mas->index = l_mas->min; l_mas->offset = l_slot - 1; } if (!r_wr_mas->content) { if (r_mas->last < r_wr_mas->r_max) r_mas->last = r_wr_mas->r_max; r_mas->offset++; } else if ((r_mas->last == r_wr_mas->r_max) && (r_mas->last < r_mas->max) && !mas_slot_locked(r_mas, r_wr_mas->slots, r_mas->offset + 1)) { r_mas->last = mas_safe_pivot(r_mas, r_wr_mas->pivots, r_wr_mas->type, r_mas->offset + 1); r_mas->offset++; } } static inline void *mas_state_walk(struct ma_state *mas) { void *entry; entry = mas_start(mas); if (mas_is_none(mas)) return NULL; if (mas_is_ptr(mas)) return entry; return mtree_range_walk(mas); } /* * mtree_lookup_walk() - Internal quick lookup that does not keep maple state up * to date. * * @mas: The maple state. * * Note: Leaves mas in undesirable state. * Return: The entry for @mas->index or %NULL on dead node. */ static inline void *mtree_lookup_walk(struct ma_state *mas) { unsigned long *pivots; unsigned char offset; struct maple_node *node; struct maple_enode *next; enum maple_type type; void __rcu **slots; unsigned char end; next = mas->node; do { node = mte_to_node(next); type = mte_node_type(next); pivots = ma_pivots(node, type); end = mt_pivots[type]; offset = 0; do { if (pivots[offset] >= mas->index) break; } while (++offset < end); slots = ma_slots(node, type); next = mt_slot(mas->tree, slots, offset); if (unlikely(ma_dead_node(node))) goto dead_node; } while (!ma_is_leaf(type)); return (void *)next; dead_node: mas_reset(mas); return NULL; } static void mte_destroy_walk(struct maple_enode *, struct maple_tree *); /* * mas_new_root() - Create a new root node that only contains the entry passed * in. * @mas: The maple state * @entry: The entry to store. * * Only valid when the index == 0 and the last == ULONG_MAX */ static inline void mas_new_root(struct ma_state *mas, void *entry) { struct maple_enode *root = mas_root_locked(mas); enum maple_type type = maple_leaf_64; struct maple_node *node; void __rcu **slots; unsigned long *pivots; WARN_ON_ONCE(mas->index || mas->last != ULONG_MAX); if (!entry) { mas->depth = 0; mas_set_height(mas); rcu_assign_pointer(mas->tree->ma_root, entry); mas->status = ma_start; goto done; } node = mas_pop_node(mas); pivots = ma_pivots(node, type); slots = ma_slots(node, type); node->parent = ma_parent_ptr(mas_tree_parent(mas)); mas->node = mt_mk_node(node, type); mas->status = ma_active; rcu_assign_pointer(slots[0], entry); pivots[0] = mas->last; mas->depth = 1; mas_set_height(mas); rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node)); done: if (xa_is_node(root)) mte_destroy_walk(root, mas->tree); return; } /* * mas_wr_spanning_store() - Create a subtree with the store operation completed * and new nodes where necessary, then place the sub-tree in the actual tree. * Note that mas is expected to point to the node which caused the store to * span. * @wr_mas: The maple write state */ static noinline void mas_wr_spanning_store(struct ma_wr_state *wr_mas) { struct maple_subtree_state mast; struct maple_big_node b_node; struct ma_state *mas; unsigned char height; /* Left and Right side of spanning store */ MA_STATE(l_mas, NULL, 0, 0); MA_STATE(r_mas, NULL, 0, 0); MA_WR_STATE(r_wr_mas, &r_mas, wr_mas->entry); MA_WR_STATE(l_wr_mas, &l_mas, wr_mas->entry); /* * A store operation that spans multiple nodes is called a spanning * store and is handled early in the store call stack by the function * mas_is_span_wr(). When a spanning store is identified, the maple * state is duplicated. The first maple state walks the left tree path * to ``index``, the duplicate walks the right tree path to ``last``. * The data in the two nodes are combined into a single node, two nodes, * or possibly three nodes (see the 3-way split above). A ``NULL`` * written to the last entry of a node is considered a spanning store as * a rebalance is required for the operation to complete and an overflow * of data may happen. */ mas = wr_mas->mas; trace_ma_op(__func__, mas); if (unlikely(!mas->index && mas->last == ULONG_MAX)) return mas_new_root(mas, wr_mas->entry); /* * Node rebalancing may occur due to this store, so there may be three new * entries per level plus a new root. */ height = mas_mt_height(mas); /* * Set up right side. Need to get to the next offset after the spanning * store to ensure it's not NULL and to combine both the next node and * the node with the start together. */ r_mas = *mas; /* Avoid overflow, walk to next slot in the tree. */ if (r_mas.last + 1) r_mas.last++; r_mas.index = r_mas.last; mas_wr_walk_index(&r_wr_mas); r_mas.last = r_mas.index = mas->last; /* Set up left side. */ l_mas = *mas; mas_wr_walk_index(&l_wr_mas); if (!wr_mas->entry) { mas_extend_spanning_null(&l_wr_mas, &r_wr_mas); mas->offset = l_mas.offset; mas->index = l_mas.index; mas->last = l_mas.last = r_mas.last; } /* expanding NULLs may make this cover the entire range */ if (!l_mas.index && r_mas.last == ULONG_MAX) { mas_set_range(mas, 0, ULONG_MAX); return mas_new_root(mas, wr_mas->entry); } memset(&b_node, 0, sizeof(struct maple_big_node)); /* Copy l_mas and store the value in b_node. */ mas_store_b_node(&l_wr_mas, &b_node, l_mas.end); /* Copy r_mas into b_node if there is anything to copy. */ if (r_mas.max > r_mas.last) mas_mab_cp(&r_mas, r_mas.offset, r_mas.end, &b_node, b_node.b_end + 1); else b_node.b_end++; /* Stop spanning searches by searching for just index. */ l_mas.index = l_mas.last = mas->index; mast.bn = &b_node; mast.orig_l = &l_mas; mast.orig_r = &r_mas; /* Combine l_mas and r_mas and split them up evenly again. */ return mas_spanning_rebalance(mas, &mast, height + 1); } /* * mas_wr_node_store() - Attempt to store the value in a node * @wr_mas: The maple write state * * Attempts to reuse the node, but may allocate. */ static inline void mas_wr_node_store(struct ma_wr_state *wr_mas, unsigned char new_end) { struct ma_state *mas = wr_mas->mas; void __rcu **dst_slots; unsigned long *dst_pivots; unsigned char dst_offset, offset_end = wr_mas->offset_end; struct maple_node reuse, *newnode; unsigned char copy_size, node_pivots = mt_pivots[wr_mas->type]; bool in_rcu = mt_in_rcu(mas->tree); if (mas->last == wr_mas->end_piv) offset_end++; /* don't copy this offset */ else if (unlikely(wr_mas->r_max == ULONG_MAX)) mas_bulk_rebalance(mas, mas->end, wr_mas->type); /* set up node. */ if (in_rcu) { newnode = mas_pop_node(mas); } else { memset(&reuse, 0, sizeof(struct maple_node)); newnode = &reuse; } newnode->parent = mas_mn(mas)->parent; dst_pivots = ma_pivots(newnode, wr_mas->type); dst_slots = ma_slots(newnode, wr_mas->type); /* Copy from start to insert point */ memcpy(dst_pivots, wr_mas->pivots, sizeof(unsigned long) * mas->offset); memcpy(dst_slots, wr_mas->slots, sizeof(void *) * mas->offset); /* Handle insert of new range starting after old range */ if (wr_mas->r_min < mas->index) { rcu_assign_pointer(dst_slots[mas->offset], wr_mas->content); dst_pivots[mas->offset++] = mas->index - 1; } /* Store the new entry and range end. */ if (mas->offset < node_pivots) dst_pivots[mas->offset] = mas->last; rcu_assign_pointer(dst_slots[mas->offset], wr_mas->entry); /* * this range wrote to the end of the node or it overwrote the rest of * the data */ if (offset_end > mas->end) goto done; dst_offset = mas->offset + 1; /* Copy to the end of node if necessary. */ copy_size = mas->end - offset_end + 1; memcpy(dst_slots + dst_offset, wr_mas->slots + offset_end, sizeof(void *) * copy_size); memcpy(dst_pivots + dst_offset, wr_mas->pivots + offset_end, sizeof(unsigned long) * (copy_size - 1)); if (new_end < node_pivots) dst_pivots[new_end] = mas->max; done: mas_leaf_set_meta(newnode, maple_leaf_64, new_end); if (in_rcu) { struct maple_enode *old_enode = mas->node; mas->node = mt_mk_node(newnode, wr_mas->type); mas_replace_node(mas, old_enode); } else { memcpy(wr_mas->node, newnode, sizeof(struct maple_node)); } trace_ma_write(__func__, mas, 0, wr_mas->entry); mas_update_gap(mas); mas->end = new_end; return; } /* * mas_wr_slot_store: Attempt to store a value in a slot. * @wr_mas: the maple write state */ static inline void mas_wr_slot_store(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char offset = mas->offset; void __rcu **slots = wr_mas->slots; bool gap = false; gap |= !mt_slot_locked(mas->tree, slots, offset); gap |= !mt_slot_locked(mas->tree, slots, offset + 1); if (wr_mas->offset_end - offset == 1) { if (mas->index == wr_mas->r_min) { /* Overwriting the range and a part of the next one */ rcu_assign_pointer(slots[offset], wr_mas->entry); wr_mas->pivots[offset] = mas->last; } else { /* Overwriting a part of the range and the next one */ rcu_assign_pointer(slots[offset + 1], wr_mas->entry); wr_mas->pivots[offset] = mas->index - 1; mas->offset++; /* Keep mas accurate. */ } } else { WARN_ON_ONCE(mt_in_rcu(mas->tree)); /* * Expand the range, only partially overwriting the previous and * next ranges */ gap |= !mt_slot_locked(mas->tree, slots, offset + 2); rcu_assign_pointer(slots[offset + 1], wr_mas->entry); wr_mas->pivots[offset] = mas->index - 1; wr_mas->pivots[offset + 1] = mas->last; mas->offset++; /* Keep mas accurate. */ } trace_ma_write(__func__, mas, 0, wr_mas->entry); /* * Only update gap when the new entry is empty or there is an empty * entry in the original two ranges. */ if (!wr_mas->entry || gap) mas_update_gap(mas); return; } static inline void mas_wr_extend_null(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; if (!wr_mas->slots[wr_mas->offset_end]) { /* If this one is null, the next and prev are not */ mas->last = wr_mas->end_piv; } else { /* Check next slot(s) if we are overwriting the end */ if ((mas->last == wr_mas->end_piv) && (mas->end != wr_mas->offset_end) && !wr_mas->slots[wr_mas->offset_end + 1]) { wr_mas->offset_end++; if (wr_mas->offset_end == mas->end) mas->last = mas->max; else mas->last = wr_mas->pivots[wr_mas->offset_end]; wr_mas->end_piv = mas->last; } } if (!wr_mas->content) { /* If this one is null, the next and prev are not */ mas->index = wr_mas->r_min; } else { /* Check prev slot if we are overwriting the start */ if (mas->index == wr_mas->r_min && mas->offset && !wr_mas->slots[mas->offset - 1]) { mas->offset--; wr_mas->r_min = mas->index = mas_safe_min(mas, wr_mas->pivots, mas->offset); wr_mas->r_max = wr_mas->pivots[mas->offset]; } } } static inline void mas_wr_end_piv(struct ma_wr_state *wr_mas) { while ((wr_mas->offset_end < wr_mas->mas->end) && (wr_mas->mas->last > wr_mas->pivots[wr_mas->offset_end])) wr_mas->offset_end++; if (wr_mas->offset_end < wr_mas->mas->end) wr_mas->end_piv = wr_mas->pivots[wr_mas->offset_end]; else wr_mas->end_piv = wr_mas->mas->max; } static inline unsigned char mas_wr_new_end(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char new_end = mas->end + 2; new_end -= wr_mas->offset_end - mas->offset; if (wr_mas->r_min == mas->index) new_end--; if (wr_mas->end_piv == mas->last) new_end--; return new_end; } /* * mas_wr_append: Attempt to append * @wr_mas: the maple write state * @new_end: The end of the node after the modification * * This is currently unsafe in rcu mode since the end of the node may be cached * by readers while the node contents may be updated which could result in * inaccurate information. */ static inline void mas_wr_append(struct ma_wr_state *wr_mas, unsigned char new_end) { struct ma_state *mas = wr_mas->mas; void __rcu **slots; unsigned char end = mas->end; if (new_end < mt_pivots[wr_mas->type]) { wr_mas->pivots[new_end] = wr_mas->pivots[end]; ma_set_meta(wr_mas->node, wr_mas->type, 0, new_end); } slots = wr_mas->slots; if (new_end == end + 1) { if (mas->last == wr_mas->r_max) { /* Append to end of range */ rcu_assign_pointer(slots[new_end], wr_mas->entry); wr_mas->pivots[end] = mas->index - 1; mas->offset = new_end; } else { /* Append to start of range */ rcu_assign_pointer(slots[new_end], wr_mas->content); wr_mas->pivots[end] = mas->last; rcu_assign_pointer(slots[end], wr_mas->entry); } } else { /* Append to the range without touching any boundaries. */ rcu_assign_pointer(slots[new_end], wr_mas->content); wr_mas->pivots[end + 1] = mas->last; rcu_assign_pointer(slots[end + 1], wr_mas->entry); wr_mas->pivots[end] = mas->index - 1; mas->offset = end + 1; } if (!wr_mas->content || !wr_mas->entry) mas_update_gap(mas); mas->end = new_end; trace_ma_write(__func__, mas, new_end, wr_mas->entry); return; } /* * mas_wr_bnode() - Slow path for a modification. * @wr_mas: The write maple state * * This is where split, rebalance end up. */ static void mas_wr_bnode(struct ma_wr_state *wr_mas) { struct maple_big_node b_node; trace_ma_write(__func__, wr_mas->mas, 0, wr_mas->entry); memset(&b_node, 0, sizeof(struct maple_big_node)); mas_store_b_node(wr_mas, &b_node, wr_mas->offset_end); mas_commit_b_node(wr_mas, &b_node); } /* * mas_wr_store_entry() - Internal call to store a value * @wr_mas: The maple write state */ static inline void mas_wr_store_entry(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char new_end = mas_wr_new_end(wr_mas); switch (mas->store_type) { case wr_invalid: MT_BUG_ON(mas->tree, 1); return; case wr_new_root: mas_new_root(mas, wr_mas->entry); break; case wr_store_root: mas_store_root(mas, wr_mas->entry); break; case wr_exact_fit: rcu_assign_pointer(wr_mas->slots[mas->offset], wr_mas->entry); if (!!wr_mas->entry ^ !!wr_mas->content) mas_update_gap(mas); break; case wr_append: mas_wr_append(wr_mas, new_end); break; case wr_slot_store: mas_wr_slot_store(wr_mas); break; case wr_node_store: mas_wr_node_store(wr_mas, new_end); break; case wr_spanning_store: mas_wr_spanning_store(wr_mas); break; case wr_split_store: case wr_rebalance: mas_wr_bnode(wr_mas); break; } return; } static inline void mas_wr_prealloc_setup(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; if (!mas_is_active(mas)) { if (mas_is_start(mas)) goto set_content; if (unlikely(mas_is_paused(mas))) goto reset; if (unlikely(mas_is_none(mas))) goto reset; if (unlikely(mas_is_overflow(mas))) goto reset; if (unlikely(mas_is_underflow(mas))) goto reset; } /* * A less strict version of mas_is_span_wr() where we allow spanning * writes within this node. This is to stop partial walks in * mas_prealloc() from being reset. */ if (mas->last > mas->max) goto reset; if (wr_mas->entry) goto set_content; if (mte_is_leaf(mas->node) && mas->last == mas->max) goto reset; goto set_content; reset: mas_reset(mas); set_content: wr_mas->content = mas_start(mas); } /** * mas_prealloc_calc() - Calculate number of nodes needed for a * given store oepration * @mas: The maple state * @entry: The entry to store into the tree * * Return: Number of nodes required for preallocation. */ static inline int mas_prealloc_calc(struct ma_state *mas, void *entry) { int ret = mas_mt_height(mas) * 3 + 1; switch (mas->store_type) { case wr_invalid: WARN_ON_ONCE(1); break; case wr_new_root: ret = 1; break; case wr_store_root: if (likely((mas->last != 0) || (mas->index != 0))) ret = 1; else if (((unsigned long) (entry) & 3) == 2) ret = 1; else ret = 0; break; case wr_spanning_store: ret = mas_mt_height(mas) * 3 + 1; break; case wr_split_store: ret = mas_mt_height(mas) * 2 + 1; break; case wr_rebalance: ret = mas_mt_height(mas) * 2 - 1; break; case wr_node_store: ret = mt_in_rcu(mas->tree) ? 1 : 0; break; case wr_append: case wr_exact_fit: case wr_slot_store: ret = 0; } return ret; } /* * mas_wr_store_type() - Determine the store type for a given * store operation. * @wr_mas: The maple write state * * Return: the type of store needed for the operation */ static inline enum store_type mas_wr_store_type(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char new_end; if (unlikely(mas_is_none(mas) || mas_is_ptr(mas))) return wr_store_root; if (unlikely(!mas_wr_walk(wr_mas))) return wr_spanning_store; /* At this point, we are at the leaf node that needs to be altered. */ mas_wr_end_piv(wr_mas); if (!wr_mas->entry) mas_wr_extend_null(wr_mas); if ((wr_mas->r_min == mas->index) && (wr_mas->r_max == mas->last)) return wr_exact_fit; if (unlikely(!mas->index && mas->last == ULONG_MAX)) return wr_new_root; new_end = mas_wr_new_end(wr_mas); /* Potential spanning rebalance collapsing a node */ if (new_end < mt_min_slots[wr_mas->type]) { if (!mte_is_root(mas->node) && !(mas->mas_flags & MA_STATE_BULK)) return wr_rebalance; return wr_node_store; } if (new_end >= mt_slots[wr_mas->type]) return wr_split_store; if (!mt_in_rcu(mas->tree) && (mas->offset == mas->end)) return wr_append; if ((new_end == mas->end) && (!mt_in_rcu(mas->tree) || (wr_mas->offset_end - mas->offset == 1))) return wr_slot_store; return wr_node_store; } /** * mas_wr_preallocate() - Preallocate enough nodes for a store operation * @wr_mas: The maple write state * @entry: The entry that will be stored * */ static inline void mas_wr_preallocate(struct ma_wr_state *wr_mas, void *entry) { struct ma_state *mas = wr_mas->mas; int request; mas_wr_prealloc_setup(wr_mas); mas->store_type = mas_wr_store_type(wr_mas); request = mas_prealloc_calc(mas, entry); if (!request) return; mas_node_count(mas, request); } /** * mas_insert() - Internal call to insert a value * @mas: The maple state * @entry: The entry to store * * Return: %NULL or the contents that already exists at the requested index * otherwise. The maple state needs to be checked for error conditions. */ static inline void *mas_insert(struct ma_state *mas, void *entry) { MA_WR_STATE(wr_mas, mas, entry); /* * Inserting a new range inserts either 0, 1, or 2 pivots within the * tree. If the insert fits exactly into an existing gap with a value * of NULL, then the slot only needs to be written with the new value. * If the range being inserted is adjacent to another range, then only a * single pivot needs to be inserted (as well as writing the entry). If * the new range is within a gap but does not touch any other ranges, * then two pivots need to be inserted: the start - 1, and the end. As * usual, the entry must be written. Most operations require a new node * to be allocated and replace an existing node to ensure RCU safety, * when in RCU mode. The exception to requiring a newly allocated node * is when inserting at the end of a node (appending). When done * carefully, appending can reuse the node in place. */ wr_mas.content = mas_start(mas); if (wr_mas.content) goto exists; mas_wr_preallocate(&wr_mas, entry); if (mas_is_err(mas)) return NULL; /* spanning writes always overwrite something */ if (mas->store_type == wr_spanning_store) goto exists; /* At this point, we are at the leaf node that needs to be altered. */ if (mas->store_type != wr_new_root && mas->store_type != wr_store_root) { wr_mas.offset_end = mas->offset; wr_mas.end_piv = wr_mas.r_max; if (wr_mas.content || (mas->last > wr_mas.r_max)) goto exists; } mas_wr_store_entry(&wr_mas); return wr_mas.content; exists: mas_set_err(mas, -EEXIST); return wr_mas.content; } /** * mas_alloc_cyclic() - Internal call to find somewhere to store an entry * @mas: The maple state. * @startp: Pointer to ID. * @range_lo: Lower bound of range to search. * @range_hi: Upper bound of range to search. * @entry: The entry to store. * @next: Pointer to next ID to allocate. * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 if the allocation succeeded without wrapping, 1 if the * allocation succeeded after wrapping, or -EBUSY if there are no * free entries. */ int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp, void *entry, unsigned long range_lo, unsigned long range_hi, unsigned long *next, gfp_t gfp) { unsigned long min = range_lo; int ret = 0; range_lo = max(min, *next); ret = mas_empty_area(mas, range_lo, range_hi, 1); if ((mas->tree->ma_flags & MT_FLAGS_ALLOC_WRAPPED) && ret == 0) { mas->tree->ma_flags &= ~MT_FLAGS_ALLOC_WRAPPED; ret = 1; } if (ret < 0 && range_lo > min) { ret = mas_empty_area(mas, min, range_hi, 1); if (ret == 0) ret = 1; } if (ret < 0) return ret; do { mas_insert(mas, entry); } while (mas_nomem(mas, gfp)); if (mas_is_err(mas)) return xa_err(mas->node); *startp = mas->index; *next = *startp + 1; if (*next == 0) mas->tree->ma_flags |= MT_FLAGS_ALLOC_WRAPPED; mas_destroy(mas); return ret; } EXPORT_SYMBOL(mas_alloc_cyclic); static __always_inline void mas_rewalk(struct ma_state *mas, unsigned long index) { retry: mas_set(mas, index); mas_state_walk(mas); if (mas_is_start(mas)) goto retry; } static __always_inline bool mas_rewalk_if_dead(struct ma_state *mas, struct maple_node *node, const unsigned long index) { if (unlikely(ma_dead_node(node))) { mas_rewalk(mas, index); return true; } return false; } /* * mas_prev_node() - Find the prev non-null entry at the same level in the * tree. The prev value will be mas->node[mas->offset] or the status will be * ma_none. * @mas: The maple state * @min: The lower limit to search * * The prev node value will be mas->node[mas->offset] or the status will be * ma_none. * Return: 1 if the node is dead, 0 otherwise. */ static int mas_prev_node(struct ma_state *mas, unsigned long min) { enum maple_type mt; int offset, level; void __rcu **slots; struct maple_node *node; unsigned long *pivots; unsigned long max; node = mas_mn(mas); if (!mas->min) goto no_entry; max = mas->min - 1; if (max < min) goto no_entry; level = 0; do { if (ma_is_root(node)) goto no_entry; /* Walk up. */ if (unlikely(mas_ascend(mas))) return 1; offset = mas->offset; level++; node = mas_mn(mas); } while (!offset); offset--; mt = mte_node_type(mas->node); while (level > 1) { level--; slots = ma_slots(node, mt); mas->node = mas_slot(mas, slots, offset); if (unlikely(ma_dead_node(node))) return 1; mt = mte_node_type(mas->node); node = mas_mn(mas); pivots = ma_pivots(node, mt); offset = ma_data_end(node, mt, pivots, max); if (unlikely(ma_dead_node(node))) return 1; } slots = ma_slots(node, mt); mas->node = mas_slot(mas, slots, offset); pivots = ma_pivots(node, mt); if (unlikely(ma_dead_node(node))) return 1; if (likely(offset)) mas->min = pivots[offset - 1] + 1; mas->max = max; mas->offset = mas_data_end(mas); if (unlikely(mte_dead_node(mas->node))) return 1; mas->end = mas->offset; return 0; no_entry: if (unlikely(ma_dead_node(node))) return 1; mas->status = ma_underflow; return 0; } /* * mas_prev_slot() - Get the entry in the previous slot * * @mas: The maple state * @min: The minimum starting range * @empty: Can be empty * * Return: The entry in the previous slot which is possibly NULL */ static void *mas_prev_slot(struct ma_state *mas, unsigned long min, bool empty) { void *entry; void __rcu **slots; unsigned long pivot; enum maple_type type; unsigned long *pivots; struct maple_node *node; unsigned long save_point = mas->index; retry: node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (mas->min <= min) { pivot = mas_safe_min(mas, pivots, mas->offset); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (pivot <= min) goto underflow; } again: if (likely(mas->offset)) { mas->offset--; mas->last = mas->index - 1; mas->index = mas_safe_min(mas, pivots, mas->offset); } else { if (mas->index <= min) goto underflow; if (mas_prev_node(mas, min)) { mas_rewalk(mas, save_point); goto retry; } if (WARN_ON_ONCE(mas_is_underflow(mas))) return NULL; mas->last = mas->max; node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); mas->index = pivots[mas->offset - 1] + 1; } slots = ma_slots(node, type); entry = mas_slot(mas, slots, mas->offset); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (likely(entry)) return entry; if (!empty) { if (mas->index <= min) { mas->status = ma_underflow; return NULL; } goto again; } return entry; underflow: mas->status = ma_underflow; return NULL; } /* * mas_next_node() - Get the next node at the same level in the tree. * @mas: The maple state * @node: The maple node * @max: The maximum pivot value to check. * * The next value will be mas->node[mas->offset] or the status will have * overflowed. * Return: 1 on dead node, 0 otherwise. */ static int mas_next_node(struct ma_state *mas, struct maple_node *node, unsigned long max) { unsigned long min; unsigned long *pivots; struct maple_enode *enode; struct maple_node *tmp; int level = 0; unsigned char node_end; enum maple_type mt; void __rcu **slots; if (mas->max >= max) goto overflow; min = mas->max + 1; level = 0; do { if (ma_is_root(node)) goto overflow; /* Walk up. */ if (unlikely(mas_ascend(mas))) return 1; level++; node = mas_mn(mas); mt = mte_node_type(mas->node); pivots = ma_pivots(node, mt); node_end = ma_data_end(node, mt, pivots, mas->max); if (unlikely(ma_dead_node(node))) return 1; } while (unlikely(mas->offset == node_end)); slots = ma_slots(node, mt); mas->offset++; enode = mas_slot(mas, slots, mas->offset); if (unlikely(ma_dead_node(node))) return 1; if (level > 1) mas->offset = 0; while (unlikely(level > 1)) { level--; mas->node = enode; node = mas_mn(mas); mt = mte_node_type(mas->node); slots = ma_slots(node, mt); enode = mas_slot(mas, slots, 0); if (unlikely(ma_dead_node(node))) return 1; } if (!mas->offset) pivots = ma_pivots(node, mt); mas->max = mas_safe_pivot(mas, pivots, mas->offset, mt); tmp = mte_to_node(enode); mt = mte_node_type(enode); pivots = ma_pivots(tmp, mt); mas->end = ma_data_end(tmp, mt, pivots, mas->max); if (unlikely(ma_dead_node(node))) return 1; mas->node = enode; mas->min = min; return 0; overflow: if (unlikely(ma_dead_node(node))) return 1; mas->status = ma_overflow; return 0; } /* * mas_next_slot() - Get the entry in the next slot * * @mas: The maple state * @max: The maximum starting range * @empty: Can be empty * * Return: The entry in the next slot which is possibly NULL */ static void *mas_next_slot(struct ma_state *mas, unsigned long max, bool empty) { void __rcu **slots; unsigned long *pivots; unsigned long pivot; enum maple_type type; struct maple_node *node; unsigned long save_point = mas->last; void *entry; retry: node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (mas->max >= max) { if (likely(mas->offset < mas->end)) pivot = pivots[mas->offset]; else pivot = mas->max; if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (pivot >= max) { /* Was at the limit, next will extend beyond */ mas->status = ma_overflow; return NULL; } } if (likely(mas->offset < mas->end)) { mas->index = pivots[mas->offset] + 1; again: mas->offset++; if (likely(mas->offset < mas->end)) mas->last = pivots[mas->offset]; else mas->last = mas->max; } else { if (mas->last >= max) { mas->status = ma_overflow; return NULL; } if (mas_next_node(mas, node, max)) { mas_rewalk(mas, save_point); goto retry; } if (WARN_ON_ONCE(mas_is_overflow(mas))) return NULL; mas->offset = 0; mas->index = mas->min; node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); mas->last = pivots[0]; } slots = ma_slots(node, type); entry = mt_slot(mas->tree, slots, mas->offset); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (entry) return entry; if (!empty) { if (mas->last >= max) { mas->status = ma_overflow; return NULL; } mas->index = mas->last + 1; goto again; } return entry; } /* * mas_next_entry() - Internal function to get the next entry. * @mas: The maple state * @limit: The maximum range start. * * Set the @mas->node to the next entry and the range_start to * the beginning value for the entry. Does not check beyond @limit. * Sets @mas->index and @mas->last to the range, Does not update @mas->index and * @mas->last on overflow. * Restarts on dead nodes. * * Return: the next entry or %NULL. */ static inline void *mas_next_entry(struct ma_state *mas, unsigned long limit) { if (mas->last >= limit) { mas->status = ma_overflow; return NULL; } return mas_next_slot(mas, limit, false); } /* * mas_rev_awalk() - Internal function. Reverse allocation walk. Find the * highest gap address of a given size in a given node and descend. * @mas: The maple state * @size: The needed size. * * Return: True if found in a leaf, false otherwise. * */ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size, unsigned long *gap_min, unsigned long *gap_max) { enum maple_type type = mte_node_type(mas->node); struct maple_node *node = mas_mn(mas); unsigned long *pivots, *gaps; void __rcu **slots; unsigned long gap = 0; unsigned long max, min; unsigned char offset; if (unlikely(mas_is_err(mas))) return true; if (ma_is_dense(type)) { /* dense nodes. */ mas->offset = (unsigned char)(mas->index - mas->min); return true; } pivots = ma_pivots(node, type); slots = ma_slots(node, type); gaps = ma_gaps(node, type); offset = mas->offset; min = mas_safe_min(mas, pivots, offset); /* Skip out of bounds. */ while (mas->last < min) min = mas_safe_min(mas, pivots, --offset); max = mas_safe_pivot(mas, pivots, offset, type); while (mas->index <= max) { gap = 0; if (gaps) gap = gaps[offset]; else if (!mas_slot(mas, slots, offset)) gap = max - min + 1; if (gap) { if ((size <= gap) && (size <= mas->last - min + 1)) break; if (!gaps) { /* Skip the next slot, it cannot be a gap. */ if (offset < 2) goto ascend; offset -= 2; max = pivots[offset]; min = mas_safe_min(mas, pivots, offset); continue; } } if (!offset) goto ascend; offset--; max = min - 1; min = mas_safe_min(mas, pivots, offset); } if (unlikely((mas->index > max) || (size - 1 > max - mas->index))) goto no_space; if (unlikely(ma_is_leaf(type))) { mas->offset = offset; *gap_min = min; *gap_max = min + gap - 1; return true; } /* descend, only happens under lock. */ mas->node = mas_slot(mas, slots, offset); mas->min = min; mas->max = max; mas->offset = mas_data_end(mas); return false; ascend: if (!mte_is_root(mas->node)) return false; no_space: mas_set_err(mas, -EBUSY); return false; } static inline bool mas_anode_descend(struct ma_state *mas, unsigned long size) { enum maple_type type = mte_node_type(mas->node); unsigned long pivot, min, gap = 0; unsigned char offset, data_end; unsigned long *gaps, *pivots; void __rcu **slots; struct maple_node *node; bool found = false; if (ma_is_dense(type)) { mas->offset = (unsigned char)(mas->index - mas->min); return true; } node = mas_mn(mas); pivots = ma_pivots(node, type); slots = ma_slots(node, type); gaps = ma_gaps(node, type); offset = mas->offset; min = mas_safe_min(mas, pivots, offset); data_end = ma_data_end(node, type, pivots, mas->max); for (; offset <= data_end; offset++) { pivot = mas_safe_pivot(mas, pivots, offset, type); /* Not within lower bounds */ if (mas->index > pivot) goto next_slot; if (gaps) gap = gaps[offset]; else if (!mas_slot(mas, slots, offset)) gap = min(pivot, mas->last) - max(mas->index, min) + 1; else goto next_slot; if (gap >= size) { if (ma_is_leaf(type)) { found = true; goto done; } if (mas->index <= pivot) { mas->node = mas_slot(mas, slots, offset); mas->min = min; mas->max = pivot; offset = 0; break; } } next_slot: min = pivot + 1; if (mas->last <= pivot) { mas_set_err(mas, -EBUSY); return true; } } if (mte_is_root(mas->node)) found = true; done: mas->offset = offset; return found; } /** * mas_walk() - Search for @mas->index in the tree. * @mas: The maple state. * * mas->index and mas->last will be set to the range if there is a value. If * mas->status is ma_none, reset to ma_start * * Return: the entry at the location or %NULL. */ void *mas_walk(struct ma_state *mas) { void *entry; if (!mas_is_active(mas) || !mas_is_start(mas)) mas->status = ma_start; retry: entry = mas_state_walk(mas); if (mas_is_start(mas)) { goto retry; } else if (mas_is_none(mas)) { mas->index = 0; mas->last = ULONG_MAX; } else if (mas_is_ptr(mas)) { if (!mas->index) { mas->last = 0; return entry; } mas->index = 1; mas->last = ULONG_MAX; mas->status = ma_none; return NULL; } return entry; } EXPORT_SYMBOL_GPL(mas_walk); static inline bool mas_rewind_node(struct ma_state *mas) { unsigned char slot; do { if (mte_is_root(mas->node)) { slot = mas->offset; if (!slot) return false; } else { mas_ascend(mas); slot = mas->offset; } } while (!slot); mas->offset = --slot; return true; } /* * mas_skip_node() - Internal function. Skip over a node. * @mas: The maple state. * * Return: true if there is another node, false otherwise. */ static inline bool mas_skip_node(struct ma_state *mas) { if (mas_is_err(mas)) return false; do { if (mte_is_root(mas->node)) { if (mas->offset >= mas_data_end(mas)) { mas_set_err(mas, -EBUSY); return false; } } else { mas_ascend(mas); } } while (mas->offset >= mas_data_end(mas)); mas->offset++; return true; } /* * mas_awalk() - Allocation walk. Search from low address to high, for a gap of * @size * @mas: The maple state * @size: The size of the gap required * * Search between @mas->index and @mas->last for a gap of @size. */ static inline void mas_awalk(struct ma_state *mas, unsigned long size) { struct maple_enode *last = NULL; /* * There are 4 options: * go to child (descend) * go back to parent (ascend) * no gap found. (return, slot == MAPLE_NODE_SLOTS) * found the gap. (return, slot != MAPLE_NODE_SLOTS) */ while (!mas_is_err(mas) && !mas_anode_descend(mas, size)) { if (last == mas->node) mas_skip_node(mas); else last = mas->node; } } /* * mas_sparse_area() - Internal function. Return upper or lower limit when * searching for a gap in an empty tree. * @mas: The maple state * @min: the minimum range * @max: The maximum range * @size: The size of the gap * @fwd: Searching forward or back */ static inline int mas_sparse_area(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size, bool fwd) { if (!unlikely(mas_is_none(mas)) && min == 0) { min++; /* * At this time, min is increased, we need to recheck whether * the size is satisfied. */ if (min > max || max - min + 1 < size) return -EBUSY; } /* mas_is_ptr */ if (fwd) { mas->index = min; mas->last = min + size - 1; } else { mas->last = max; mas->index = max - size + 1; } return 0; } /* * mas_empty_area() - Get the lowest address within the range that is * sufficient for the size requested. * @mas: The maple state * @min: The lowest value of the range * @max: The highest value of the range * @size: The size needed */ int mas_empty_area(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size) { unsigned char offset; unsigned long *pivots; enum maple_type mt; struct maple_node *node; if (min > max) return -EINVAL; if (size == 0 || max - min < size - 1) return -EINVAL; if (mas_is_start(mas)) mas_start(mas); else if (mas->offset >= 2) mas->offset -= 2; else if (!mas_skip_node(mas)) return -EBUSY; /* Empty set */ if (mas_is_none(mas) || mas_is_ptr(mas)) return mas_sparse_area(mas, min, max, size, true); /* The start of the window can only be within these values */ mas->index = min; mas->last = max; mas_awalk(mas, size); if (unlikely(mas_is_err(mas))) return xa_err(mas->node); offset = mas->offset; if (unlikely(offset == MAPLE_NODE_SLOTS)) return -EBUSY; node = mas_mn(mas); mt = mte_node_type(mas->node); pivots = ma_pivots(node, mt); min = mas_safe_min(mas, pivots, offset); if (mas->index < min) mas->index = min; mas->last = mas->index + size - 1; mas->end = ma_data_end(node, mt, pivots, mas->max); return 0; } EXPORT_SYMBOL_GPL(mas_empty_area); /* * mas_empty_area_rev() - Get the highest address within the range that is * sufficient for the size requested. * @mas: The maple state * @min: The lowest value of the range * @max: The highest value of the range * @size: The size needed */ int mas_empty_area_rev(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size) { struct maple_enode *last = mas->node; if (min > max) return -EINVAL; if (size == 0 || max - min < size - 1) return -EINVAL; if (mas_is_start(mas)) mas_start(mas); else if ((mas->offset < 2) && (!mas_rewind_node(mas))) return -EBUSY; if (unlikely(mas_is_none(mas) || mas_is_ptr(mas))) return mas_sparse_area(mas, min, max, size, false); else if (mas->offset >= 2) mas->offset -= 2; else mas->offset = mas_data_end(mas); /* The start of the window can only be within these values. */ mas->index = min; mas->last = max; while (!mas_rev_awalk(mas, size, &min, &max)) { if (last == mas->node) { if (!mas_rewind_node(mas)) return -EBUSY; } else { last = mas->node; } } if (mas_is_err(mas)) return xa_err(mas->node); if (unlikely(mas->offset == MAPLE_NODE_SLOTS)) return -EBUSY; /* Trim the upper limit to the max. */ if (max < mas->last) mas->last = max; mas->index = mas->last - size + 1; mas->end = mas_data_end(mas); return 0; } EXPORT_SYMBOL_GPL(mas_empty_area_rev); /* * mte_dead_leaves() - Mark all leaves of a node as dead. * @enode: the encoded node * @mt: the maple tree * @slots: Pointer to the slot array * * Must hold the write lock. * * Return: The number of leaves marked as dead. */ static inline unsigned char mte_dead_leaves(struct maple_enode *enode, struct maple_tree *mt, void __rcu **slots) { struct maple_node *node; enum maple_type type; void *entry; int offset; for (offset = 0; offset < mt_slot_count(enode); offset++) { entry = mt_slot(mt, slots, offset); type = mte_node_type(entry); node = mte_to_node(entry); /* Use both node and type to catch LE & BE metadata */ if (!node || !type) break; mte_set_node_dead(entry); node->type = type; rcu_assign_pointer(slots[offset], node); } return offset; } /** * mte_dead_walk() - Walk down a dead tree to just before the leaves * @enode: The maple encoded node * @offset: The starting offset * * Note: This can only be used from the RCU callback context. */ static void __rcu **mte_dead_walk(struct maple_enode **enode, unsigned char offset) { struct maple_node *node, *next; void __rcu **slots = NULL; next = mte_to_node(*enode); do { *enode = ma_enode_ptr(next); node = mte_to_node(*enode); slots = ma_slots(node, node->type); next = rcu_dereference_protected(slots[offset], lock_is_held(&rcu_callback_map)); offset = 0; } while (!ma_is_leaf(next->type)); return slots; } /** * mt_free_walk() - Walk & free a tree in the RCU callback context * @head: The RCU head that's within the node. * * Note: This can only be used from the RCU callback context. */ static void mt_free_walk(struct rcu_head *head) { void __rcu **slots; struct maple_node *node, *start; struct maple_enode *enode; unsigned char offset; enum maple_type type; node = container_of(head, struct maple_node, rcu); if (ma_is_leaf(node->type)) goto free_leaf; start = node; enode = mt_mk_node(node, node->type); slots = mte_dead_walk(&enode, 0); node = mte_to_node(enode); do { mt_free_bulk(node->slot_len, slots); offset = node->parent_slot + 1; enode = node->piv_parent; if (mte_to_node(enode) == node) goto free_leaf; type = mte_node_type(enode); slots = ma_slots(mte_to_node(enode), type); if ((offset < mt_slots[type]) && rcu_dereference_protected(slots[offset], lock_is_held(&rcu_callback_map))) slots = mte_dead_walk(&enode, offset); node = mte_to_node(enode); } while ((node != start) || (node->slot_len < offset)); slots = ma_slots(node, node->type); mt_free_bulk(node->slot_len, slots); free_leaf: mt_free_rcu(&node->rcu); } static inline void __rcu **mte_destroy_descend(struct maple_enode **enode, struct maple_tree *mt, struct maple_enode *prev, unsigned char offset) { struct maple_node *node; struct maple_enode *next = *enode; void __rcu **slots = NULL; enum maple_type type; unsigned char next_offset = 0; do { *enode = next; node = mte_to_node(*enode); type = mte_node_type(*enode); slots = ma_slots(node, type); next = mt_slot_locked(mt, slots, next_offset); if ((mte_dead_node(next))) next = mt_slot_locked(mt, slots, ++next_offset); mte_set_node_dead(*enode); node->type = type; node->piv_parent = prev; node->parent_slot = offset; offset = next_offset; next_offset = 0; prev = *enode; } while (!mte_is_leaf(next)); return slots; } static void mt_destroy_walk(struct maple_enode *enode, struct maple_tree *mt, bool free) { void __rcu **slots; struct maple_node *node = mte_to_node(enode); struct maple_enode *start; if (mte_is_leaf(enode)) { node->type = mte_node_type(enode); goto free_leaf; } start = enode; slots = mte_destroy_descend(&enode, mt, start, 0); node = mte_to_node(enode); // Updated in the above call. do { enum maple_type type; unsigned char offset; struct maple_enode *parent, *tmp; node->slot_len = mte_dead_leaves(enode, mt, slots); if (free) mt_free_bulk(node->slot_len, slots); offset = node->parent_slot + 1; enode = node->piv_parent; if (mte_to_node(enode) == node) goto free_leaf; type = mte_node_type(enode); slots = ma_slots(mte_to_node(enode), type); if (offset >= mt_slots[type]) goto next; tmp = mt_slot_locked(mt, slots, offset); if (mte_node_type(tmp) && mte_to_node(tmp)) { parent = enode; enode = tmp; slots = mte_destroy_descend(&enode, mt, parent, offset); } next: node = mte_to_node(enode); } while (start != enode); node = mte_to_node(enode); node->slot_len = mte_dead_leaves(enode, mt, slots); if (free) mt_free_bulk(node->slot_len, slots); free_leaf: if (free) mt_free_rcu(&node->rcu); else mt_clear_meta(mt, node, node->type); } /* * mte_destroy_walk() - Free a tree or sub-tree. * @enode: the encoded maple node (maple_enode) to start * @mt: the tree to free - needed for node types. * * Must hold the write lock. */ static inline void mte_destroy_walk(struct maple_enode *enode, struct maple_tree *mt) { struct maple_node *node = mte_to_node(enode); if (mt_in_rcu(mt)) { mt_destroy_walk(enode, mt, false); call_rcu(&node->rcu, mt_free_walk); } else { mt_destroy_walk(enode, mt, true); } } /* Interface */ /** * mas_store() - Store an @entry. * @mas: The maple state. * @entry: The entry to store. * * The @mas->index and @mas->last is used to set the range for the @entry. * * Return: the first entry between mas->index and mas->last or %NULL. */ void *mas_store(struct ma_state *mas, void *entry) { int request; MA_WR_STATE(wr_mas, mas, entry); trace_ma_write(__func__, mas, 0, entry); #ifdef CONFIG_DEBUG_MAPLE_TREE if (MAS_WARN_ON(mas, mas->index > mas->last)) pr_err("Error %lX > %lX " PTR_FMT "\n", mas->index, mas->last, entry); if (mas->index > mas->last) { mas_set_err(mas, -EINVAL); return NULL; } #endif /* * Storing is the same operation as insert with the added caveat that it * can overwrite entries. Although this seems simple enough, one may * want to examine what happens if a single store operation was to * overwrite multiple entries within a self-balancing B-Tree. */ mas_wr_prealloc_setup(&wr_mas); mas->store_type = mas_wr_store_type(&wr_mas); if (mas->mas_flags & MA_STATE_PREALLOC) { mas_wr_store_entry(&wr_mas); MAS_WR_BUG_ON(&wr_mas, mas_is_err(mas)); return wr_mas.content; } request = mas_prealloc_calc(mas, entry); if (!request) goto store; mas_node_count(mas, request); if (mas_is_err(mas)) return NULL; store: mas_wr_store_entry(&wr_mas); mas_destroy(mas); return wr_mas.content; } EXPORT_SYMBOL_GPL(mas_store); /** * mas_store_gfp() - Store a value into the tree. * @mas: The maple state * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations if necessary. * * Return: 0 on success, -EINVAL on invalid request, -ENOMEM if memory could not * be allocated. */ int mas_store_gfp(struct ma_state *mas, void *entry, gfp_t gfp) { unsigned long index = mas->index; unsigned long last = mas->last; MA_WR_STATE(wr_mas, mas, entry); int ret = 0; retry: mas_wr_preallocate(&wr_mas, entry); if (unlikely(mas_nomem(mas, gfp))) { if (!entry) __mas_set_range(mas, index, last); goto retry; } if (mas_is_err(mas)) { ret = xa_err(mas->node); goto out; } mas_wr_store_entry(&wr_mas); out: mas_destroy(mas); return ret; } EXPORT_SYMBOL_GPL(mas_store_gfp); /** * mas_store_prealloc() - Store a value into the tree using memory * preallocated in the maple state. * @mas: The maple state * @entry: The entry to store. */ void mas_store_prealloc(struct ma_state *mas, void *entry) { MA_WR_STATE(wr_mas, mas, entry); if (mas->store_type == wr_store_root) { mas_wr_prealloc_setup(&wr_mas); goto store; } mas_wr_walk_descend(&wr_mas); if (mas->store_type != wr_spanning_store) { /* set wr_mas->content to current slot */ wr_mas.content = mas_slot_locked(mas, wr_mas.slots, mas->offset); mas_wr_end_piv(&wr_mas); } store: trace_ma_write(__func__, mas, 0, entry); mas_wr_store_entry(&wr_mas); MAS_WR_BUG_ON(&wr_mas, mas_is_err(mas)); mas_destroy(mas); } EXPORT_SYMBOL_GPL(mas_store_prealloc); /** * mas_preallocate() - Preallocate enough nodes for a store operation * @mas: The maple state * @entry: The entry that will be stored * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 on success, -ENOMEM if memory could not be allocated. */ int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp) { MA_WR_STATE(wr_mas, mas, entry); int ret = 0; int request; mas_wr_prealloc_setup(&wr_mas); mas->store_type = mas_wr_store_type(&wr_mas); request = mas_prealloc_calc(mas, entry); if (!request) return ret; mas_node_count_gfp(mas, request, gfp); if (mas_is_err(mas)) { mas_set_alloc_req(mas, 0); ret = xa_err(mas->node); mas_destroy(mas); mas_reset(mas); return ret; } mas->mas_flags |= MA_STATE_PREALLOC; return ret; } EXPORT_SYMBOL_GPL(mas_preallocate); /* * mas_destroy() - destroy a maple state. * @mas: The maple state * * Upon completion, check the left-most node and rebalance against the node to * the right if necessary. Frees any allocated nodes associated with this maple * state. */ void mas_destroy(struct ma_state *mas) { struct maple_alloc *node; unsigned long total; /* * When using mas_for_each() to insert an expected number of elements, * it is possible that the number inserted is less than the expected * number. To fix an invalid final node, a check is performed here to * rebalance the previous node with the final node. */ if (mas->mas_flags & MA_STATE_REBALANCE) { unsigned char end; if (mas_is_err(mas)) mas_reset(mas); mas_start(mas); mtree_range_walk(mas); end = mas->end + 1; if (end < mt_min_slot_count(mas->node) - 1) mas_destroy_rebalance(mas, end); mas->mas_flags &= ~MA_STATE_REBALANCE; } mas->mas_flags &= ~(MA_STATE_BULK|MA_STATE_PREALLOC); total = mas_allocated(mas); while (total) { node = mas->alloc; mas->alloc = node->slot[0]; if (node->node_count > 1) { size_t count = node->node_count - 1; mt_free_bulk(count, (void __rcu **)&node->slot[1]); total -= count; } mt_free_one(ma_mnode_ptr(node)); total--; } mas->alloc = NULL; } EXPORT_SYMBOL_GPL(mas_destroy); /* * mas_expected_entries() - Set the expected number of entries that will be inserted. * @mas: The maple state * @nr_entries: The number of expected entries. * * This will attempt to pre-allocate enough nodes to store the expected number * of entries. The allocations will occur using the bulk allocator interface * for speed. Please call mas_destroy() on the @mas after inserting the entries * to ensure any unused nodes are freed. * * Return: 0 on success, -ENOMEM if memory could not be allocated. */ int mas_expected_entries(struct ma_state *mas, unsigned long nr_entries) { int nonleaf_cap = MAPLE_ARANGE64_SLOTS - 2; struct maple_enode *enode = mas->node; int nr_nodes; int ret; /* * Sometimes it is necessary to duplicate a tree to a new tree, such as * forking a process and duplicating the VMAs from one tree to a new * tree. When such a situation arises, it is known that the new tree is * not going to be used until the entire tree is populated. For * performance reasons, it is best to use a bulk load with RCU disabled. * This allows for optimistic splitting that favours the left and reuse * of nodes during the operation. */ /* Optimize splitting for bulk insert in-order */ mas->mas_flags |= MA_STATE_BULK; /* * Avoid overflow, assume a gap between each entry and a trailing null. * If this is wrong, it just means allocation can happen during * insertion of entries. */ nr_nodes = max(nr_entries, nr_entries * 2 + 1); if (!mt_is_alloc(mas->tree)) nonleaf_cap = MAPLE_RANGE64_SLOTS - 2; /* Leaves; reduce slots to keep space for expansion */ nr_nodes = DIV_ROUND_UP(nr_nodes, MAPLE_RANGE64_SLOTS - 2); /* Internal nodes */ nr_nodes += DIV_ROUND_UP(nr_nodes, nonleaf_cap); /* Add working room for split (2 nodes) + new parents */ mas_node_count_gfp(mas, nr_nodes + 3, GFP_KERNEL); /* Detect if allocations run out */ mas->mas_flags |= MA_STATE_PREALLOC; if (!mas_is_err(mas)) return 0; ret = xa_err(mas->node); mas->node = enode; mas_destroy(mas); return ret; } EXPORT_SYMBOL_GPL(mas_expected_entries); static bool mas_next_setup(struct ma_state *mas, unsigned long max, void **entry) { bool was_none = mas_is_none(mas); if (unlikely(mas->last >= max)) { mas->status = ma_overflow; return true; } switch (mas->status) { case ma_active: return false; case ma_none: fallthrough; case ma_pause: mas->status = ma_start; fallthrough; case ma_start: mas_walk(mas); /* Retries on dead nodes handled by mas_walk */ break; case ma_overflow: /* Overflowed before, but the max changed */ mas->status = ma_active; break; case ma_underflow: /* The user expects the mas to be one before where it is */ mas->status = ma_active; *entry = mas_walk(mas); if (*entry) return true; break; case ma_root: break; case ma_error: return true; } if (likely(mas_is_active(mas))) /* Fast path */ return false; if (mas_is_ptr(mas)) { *entry = NULL; if (was_none && mas->index == 0) { mas->index = mas->last = 0; return true; } mas->index = 1; mas->last = ULONG_MAX; mas->status = ma_none; return true; } if (mas_is_none(mas)) return true; return false; } /** * mas_next() - Get the next entry. * @mas: The maple state * @max: The maximum index to check. * * Returns the next entry after @mas->index. * Must hold rcu_read_lock or the write lock. * Can return the zero entry. * * Return: The next entry or %NULL */ void *mas_next(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_next_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ return mas_next_slot(mas, max, false); } EXPORT_SYMBOL_GPL(mas_next); /** * mas_next_range() - Advance the maple state to the next range * @mas: The maple state * @max: The maximum index to check. * * Sets @mas->index and @mas->last to the range. * Must hold rcu_read_lock or the write lock. * Can return the zero entry. * * Return: The next entry or %NULL */ void *mas_next_range(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_next_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ return mas_next_slot(mas, max, true); } EXPORT_SYMBOL_GPL(mas_next_range); /** * mt_next() - get the next value in the maple tree * @mt: The maple tree * @index: The start index * @max: The maximum index to check * * Takes RCU read lock internally to protect the search, which does not * protect the returned pointer after dropping RCU read lock. * See also: Documentation/core-api/maple_tree.rst * * Return: The entry higher than @index or %NULL if nothing is found. */ void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max) { void *entry = NULL; MA_STATE(mas, mt, index, index); rcu_read_lock(); entry = mas_next(&mas, max); rcu_read_unlock(); return entry; } EXPORT_SYMBOL_GPL(mt_next); static bool mas_prev_setup(struct ma_state *mas, unsigned long min, void **entry) { if (unlikely(mas->index <= min)) { mas->status = ma_underflow; return true; } switch (mas->status) { case ma_active: return false; case ma_start: break; case ma_none: fallthrough; case ma_pause: mas->status = ma_start; break; case ma_underflow: /* underflowed before but the min changed */ mas->status = ma_active; break; case ma_overflow: /* User expects mas to be one after where it is */ mas->status = ma_active; *entry = mas_walk(mas); if (*entry) return true; break; case ma_root: break; case ma_error: return true; } if (mas_is_start(mas)) mas_walk(mas); if (unlikely(mas_is_ptr(mas))) { if (!mas->index) { mas->status = ma_none; return true; } mas->index = mas->last = 0; *entry = mas_root(mas); return true; } if (mas_is_none(mas)) { if (mas->index) { /* Walked to out-of-range pointer? */ mas->index = mas->last = 0; mas->status = ma_root; *entry = mas_root(mas); return true; } return true; } return false; } /** * mas_prev() - Get the previous entry * @mas: The maple state * @min: The minimum value to check. * * Must hold rcu_read_lock or the write lock. * Will reset mas to ma_start if the status is ma_none. Will stop on not * searchable nodes. * * Return: the previous value or %NULL. */ void *mas_prev(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_prev_setup(mas, min, &entry)) return entry; return mas_prev_slot(mas, min, false); } EXPORT_SYMBOL_GPL(mas_prev); /** * mas_prev_range() - Advance to the previous range * @mas: The maple state * @min: The minimum value to check. * * Sets @mas->index and @mas->last to the range. * Must hold rcu_read_lock or the write lock. * Will reset mas to ma_start if the node is ma_none. Will stop on not * searchable nodes. * * Return: the previous value or %NULL. */ void *mas_prev_range(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_prev_setup(mas, min, &entry)) return entry; return mas_prev_slot(mas, min, true); } EXPORT_SYMBOL_GPL(mas_prev_range); /** * mt_prev() - get the previous value in the maple tree * @mt: The maple tree * @index: The start index * @min: The minimum index to check * * Takes RCU read lock internally to protect the search, which does not * protect the returned pointer after dropping RCU read lock. * See also: Documentation/core-api/maple_tree.rst * * Return: The entry before @index or %NULL if nothing is found. */ void *mt_prev(struct maple_tree *mt, unsigned long index, unsigned long min) { void *entry = NULL; MA_STATE(mas, mt, index, index); rcu_read_lock(); entry = mas_prev(&mas, min); rcu_read_unlock(); return entry; } EXPORT_SYMBOL_GPL(mt_prev); /** * mas_pause() - Pause a mas_find/mas_for_each to drop the lock. * @mas: The maple state to pause * * Some users need to pause a walk and drop the lock they're holding in * order to yield to a higher priority thread or carry out an operation * on an entry. Those users should call this function before they drop * the lock. It resets the @mas to be suitable for the next iteration * of the loop after the user has reacquired the lock. If most entries * found during a walk require you to call mas_pause(), the mt_for_each() * iterator may be more appropriate. * */ void mas_pause(struct ma_state *mas) { mas->status = ma_pause; mas->node = NULL; } EXPORT_SYMBOL_GPL(mas_pause); /** * mas_find_setup() - Internal function to set up mas_find*(). * @mas: The maple state * @max: The maximum index * @entry: Pointer to the entry * * Returns: True if entry is the answer, false otherwise. */ static __always_inline bool mas_find_setup(struct ma_state *mas, unsigned long max, void **entry) { switch (mas->status) { case ma_active: if (mas->last < max) return false; return true; case ma_start: break; case ma_pause: if (unlikely(mas->last >= max)) return true; mas->index = ++mas->last; mas->status = ma_start; break; case ma_none: if (unlikely(mas->last >= max)) return true; mas->index = mas->last; mas->status = ma_start; break; case ma_underflow: /* mas is pointing at entry before unable to go lower */ if (unlikely(mas->index >= max)) { mas->status = ma_overflow; return true; } mas->status = ma_active; *entry = mas_walk(mas); if (*entry) return true; break; case ma_overflow: if (unlikely(mas->last >= max)) return true; mas->status = ma_active; *entry = mas_walk(mas); if (*entry) return true; break; case ma_root: break; case ma_error: return true; } if (mas_is_start(mas)) { /* First run or continue */ if (mas->index > max) return true; *entry = mas_walk(mas); if (*entry) return true; } if (unlikely(mas_is_ptr(mas))) goto ptr_out_of_range; if (unlikely(mas_is_none(mas))) return true; if (mas->index == max) return true; return false; ptr_out_of_range: mas->status = ma_none; mas->index = 1; mas->last = ULONG_MAX; return true; } /** * mas_find() - On the first call, find the entry at or after mas->index up to * %max. Otherwise, find the entry after mas->index. * @mas: The maple state * @max: The maximum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_overflow. * * Return: The entry or %NULL. */ void *mas_find(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_find_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ entry = mas_next_slot(mas, max, false); /* Ignore overflow */ mas->status = ma_active; return entry; } EXPORT_SYMBOL_GPL(mas_find); /** * mas_find_range() - On the first call, find the entry at or after * mas->index up to %max. Otherwise, advance to the next slot mas->index. * @mas: The maple state * @max: The maximum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_overflow. * * Return: The entry or %NULL. */ void *mas_find_range(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_find_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ return mas_next_slot(mas, max, true); } EXPORT_SYMBOL_GPL(mas_find_range); /** * mas_find_rev_setup() - Internal function to set up mas_find_*_rev() * @mas: The maple state * @min: The minimum index * @entry: Pointer to the entry * * Returns: True if entry is the answer, false otherwise. */ static bool mas_find_rev_setup(struct ma_state *mas, unsigned long min, void **entry) { switch (mas->status) { case ma_active: goto active; case ma_start: break; case ma_pause: if (unlikely(mas->index <= min)) { mas->status = ma_underflow; return true; } mas->last = --mas->index; mas->status = ma_start; break; case ma_none: if (mas->index <= min) goto none; mas->last = mas->index; mas->status = ma_start; break; case ma_overflow: /* user expects the mas to be one after where it is */ if (unlikely(mas->index <= min)) { mas->status = ma_underflow; return true; } mas->status = ma_active; break; case ma_underflow: /* user expects the mas to be one before where it is */ if (unlikely(mas->index <= min)) return true; mas->status = ma_active; break; case ma_root: break; case ma_error: return true; } if (mas_is_start(mas)) { /* First run or continue */ if (mas->index < min) return true; *entry = mas_walk(mas); if (*entry) return true; } if (unlikely(mas_is_ptr(mas))) goto none; if (unlikely(mas_is_none(mas))) { /* * Walked to the location, and there was nothing so the previous * location is 0. */ mas->last = mas->index = 0; mas->status = ma_root; *entry = mas_root(mas); return true; } active: if (mas->index < min) return true; return false; none: mas->status = ma_none; return true; } /** * mas_find_rev: On the first call, find the first non-null entry at or below * mas->index down to %min. Otherwise find the first non-null entry below * mas->index down to %min. * @mas: The maple state * @min: The minimum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_underflow. * * Return: The entry or %NULL. */ void *mas_find_rev(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_find_rev_setup(mas, min, &entry)) return entry; /* Retries on dead nodes handled by mas_prev_slot */ return mas_prev_slot(mas, min, false); } EXPORT_SYMBOL_GPL(mas_find_rev); /** * mas_find_range_rev: On the first call, find the first non-null entry at or * below mas->index down to %min. Otherwise advance to the previous slot after * mas->index down to %min. * @mas: The maple state * @min: The minimum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_underflow. * * Return: The entry or %NULL. */ void *mas_find_range_rev(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_find_rev_setup(mas, min, &entry)) return entry; /* Retries on dead nodes handled by mas_prev_slot */ return mas_prev_slot(mas, min, true); } EXPORT_SYMBOL_GPL(mas_find_range_rev); /** * mas_erase() - Find the range in which index resides and erase the entire * range. * @mas: The maple state * * Must hold the write lock. * Searches for @mas->index, sets @mas->index and @mas->last to the range and * erases that range. * * Return: the entry that was erased or %NULL, @mas->index and @mas->last are updated. */ void *mas_erase(struct ma_state *mas) { void *entry; unsigned long index = mas->index; MA_WR_STATE(wr_mas, mas, NULL); if (!mas_is_active(mas) || !mas_is_start(mas)) mas->status = ma_start; write_retry: entry = mas_state_walk(mas); if (!entry) return NULL; /* Must reset to ensure spanning writes of last slot are detected */ mas_reset(mas); mas_wr_preallocate(&wr_mas, NULL); if (mas_nomem(mas, GFP_KERNEL)) { /* in case the range of entry changed when unlocked */ mas->index = mas->last = index; goto write_retry; } if (mas_is_err(mas)) goto out; mas_wr_store_entry(&wr_mas); out: mas_destroy(mas); return entry; } EXPORT_SYMBOL_GPL(mas_erase); /** * mas_nomem() - Check if there was an error allocating and do the allocation * if necessary If there are allocations, then free them. * @mas: The maple state * @gfp: The GFP_FLAGS to use for allocations * Return: true on allocation, false otherwise. */ bool mas_nomem(struct ma_state *mas, gfp_t gfp) __must_hold(mas->tree->ma_lock) { if (likely(mas->node != MA_ERROR(-ENOMEM))) return false; if (gfpflags_allow_blocking(gfp) && !mt_external_lock(mas->tree)) { mtree_unlock(mas->tree); mas_alloc_nodes(mas, gfp); mtree_lock(mas->tree); } else { mas_alloc_nodes(mas, gfp); } if (!mas_allocated(mas)) return false; mas->status = ma_start; return true; } void __init maple_tree_init(void) { maple_node_cache = kmem_cache_create("maple_node", sizeof(struct maple_node), sizeof(struct maple_node), SLAB_PANIC, NULL); } /** * mtree_load() - Load a value stored in a maple tree * @mt: The maple tree * @index: The index to load * * Return: the entry or %NULL */ void *mtree_load(struct maple_tree *mt, unsigned long index) { MA_STATE(mas, mt, index, index); void *entry; trace_ma_read(__func__, &mas); rcu_read_lock(); retry: entry = mas_start(&mas); if (unlikely(mas_is_none(&mas))) goto unlock; if (unlikely(mas_is_ptr(&mas))) { if (index) entry = NULL; goto unlock; } entry = mtree_lookup_walk(&mas); if (!entry && unlikely(mas_is_start(&mas))) goto retry; unlock: rcu_read_unlock(); if (xa_is_zero(entry)) return NULL; return entry; } EXPORT_SYMBOL(mtree_load); /** * mtree_store_range() - Store an entry at a given range. * @mt: The maple tree * @index: The start of the range * @last: The end of the range * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations * * Return: 0 on success, -EINVAL on invalid request, -ENOMEM if memory could not * be allocated. */ int mtree_store_range(struct maple_tree *mt, unsigned long index, unsigned long last, void *entry, gfp_t gfp) { MA_STATE(mas, mt, index, last); int ret = 0; trace_ma_write(__func__, &mas, 0, entry); if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (index > last) return -EINVAL; mtree_lock(mt); ret = mas_store_gfp(&mas, entry, gfp); mtree_unlock(mt); return ret; } EXPORT_SYMBOL(mtree_store_range); /** * mtree_store() - Store an entry at a given index. * @mt: The maple tree * @index: The index to store the value * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations * * Return: 0 on success, -EINVAL on invalid request, -ENOMEM if memory could not * be allocated. */ int mtree_store(struct maple_tree *mt, unsigned long index, void *entry, gfp_t gfp) { return mtree_store_range(mt, index, index, entry, gfp); } EXPORT_SYMBOL(mtree_store); /** * mtree_insert_range() - Insert an entry at a given range if there is no value. * @mt: The maple tree * @first: The start of the range * @last: The end of the range * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 on success, -EEXISTS if the range is occupied, -EINVAL on invalid * request, -ENOMEM if memory could not be allocated. */ int mtree_insert_range(struct maple_tree *mt, unsigned long first, unsigned long last, void *entry, gfp_t gfp) { MA_STATE(ms, mt, first, last); int ret = 0; if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (first > last) return -EINVAL; mtree_lock(mt); retry: mas_insert(&ms, entry); if (mas_nomem(&ms, gfp)) goto retry; mtree_unlock(mt); if (mas_is_err(&ms)) ret = xa_err(ms.node); mas_destroy(&ms); return ret; } EXPORT_SYMBOL(mtree_insert_range); /** * mtree_insert() - Insert an entry at a given index if there is no value. * @mt: The maple tree * @index : The index to store the value * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 on success, -EEXISTS if the range is occupied, -EINVAL on invalid * request, -ENOMEM if memory could not be allocated. */ int mtree_insert(struct maple_tree *mt, unsigned long index, void *entry, gfp_t gfp) { return mtree_insert_range(mt, index, index, entry, gfp); } EXPORT_SYMBOL(mtree_insert); int mtree_alloc_range(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); if (!mt_is_alloc(mt)) return -EINVAL; if (WARN_ON_ONCE(mt_is_reserved(entry))) return -EINVAL; mtree_lock(mt); retry: ret = mas_empty_area(&mas, min, max, size); if (ret) goto unlock; mas_insert(&mas, entry); /* * mas_nomem() may release the lock, causing the allocated area * to be unavailable, so try to allocate a free area again. */ if (mas_nomem(&mas, gfp)) goto retry; if (mas_is_err(&mas)) ret = xa_err(mas.node); else *startp = mas.index; unlock: mtree_unlock(mt); mas_destroy(&mas); return ret; } EXPORT_SYMBOL(mtree_alloc_range); /** * mtree_alloc_cyclic() - Find somewhere to store this entry in the tree. * @mt: The maple tree. * @startp: Pointer to ID. * @range_lo: Lower bound of range to search. * @range_hi: Upper bound of range to search. * @entry: The entry to store. * @next: Pointer to next ID to allocate. * @gfp: The GFP_FLAGS to use for allocations. * * Finds an empty entry in @mt after @next, stores the new index into * the @id pointer, stores the entry at that index, then updates @next. * * @mt must be initialized with the MT_FLAGS_ALLOC_RANGE flag. * * Context: Any context. Takes and releases the mt.lock. May sleep if * the @gfp flags permit. * * Return: 0 if the allocation succeeded without wrapping, 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated, -EINVAL if @mt cannot be used, or -EBUSY if there are no * free entries. */ int mtree_alloc_cyclic(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long range_lo, unsigned long range_hi, unsigned long *next, gfp_t gfp) { int ret; MA_STATE(mas, mt, 0, 0); if (!mt_is_alloc(mt)) return -EINVAL; if (WARN_ON_ONCE(mt_is_reserved(entry))) return -EINVAL; mtree_lock(mt); ret = mas_alloc_cyclic(&mas, startp, entry, range_lo, range_hi, next, gfp); mtree_unlock(mt); return ret; } EXPORT_SYMBOL(mtree_alloc_cyclic); int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); if (!mt_is_alloc(mt)) return -EINVAL; if (WARN_ON_ONCE(mt_is_reserved(entry))) return -EINVAL; mtree_lock(mt); retry: ret = mas_empty_area_rev(&mas, min, max, size); if (ret) goto unlock; mas_insert(&mas, entry); /* * mas_nomem() may release the lock, causing the allocated area * to be unavailable, so try to allocate a free area again. */ if (mas_nomem(&mas, gfp)) goto retry; if (mas_is_err(&mas)) ret = xa_err(mas.node); else *startp = mas.index; unlock: mtree_unlock(mt); mas_destroy(&mas); return ret; } EXPORT_SYMBOL(mtree_alloc_rrange); /** * mtree_erase() - Find an index and erase the entire range. * @mt: The maple tree * @index: The index to erase * * Erasing is the same as a walk to an entry then a store of a NULL to that * ENTIRE range. In fact, it is implemented as such using the advanced API. * * Return: The entry stored at the @index or %NULL */ void *mtree_erase(struct maple_tree *mt, unsigned long index) { void *entry = NULL; MA_STATE(mas, mt, index, index); trace_ma_op(__func__, &mas); mtree_lock(mt); entry = mas_erase(&mas); mtree_unlock(mt); return entry; } EXPORT_SYMBOL(mtree_erase); /* * mas_dup_free() - Free an incomplete duplication of a tree. * @mas: The maple state of a incomplete tree. * * The parameter @mas->node passed in indicates that the allocation failed on * this node. This function frees all nodes starting from @mas->node in the * reverse order of mas_dup_build(). There is no need to hold the source tree * lock at this time. */ static void mas_dup_free(struct ma_state *mas) { struct maple_node *node; enum maple_type type; void __rcu **slots; unsigned char count, i; /* Maybe the first node allocation failed. */ if (mas_is_none(mas)) return; while (!mte_is_root(mas->node)) { mas_ascend(mas); if (mas->offset) { mas->offset--; do { mas_descend(mas); mas->offset = mas_data_end(mas); } while (!mte_is_leaf(mas->node)); mas_ascend(mas); } node = mte_to_node(mas->node); type = mte_node_type(mas->node); slots = ma_slots(node, type); count = mas_data_end(mas) + 1; for (i = 0; i < count; i++) ((unsigned long *)slots)[i] &= ~MAPLE_NODE_MASK; mt_free_bulk(count, slots); } node = mte_to_node(mas->node); mt_free_one(node); } /* * mas_copy_node() - Copy a maple node and replace the parent. * @mas: The maple state of source tree. * @new_mas: The maple state of new tree. * @parent: The parent of the new node. * * Copy @mas->node to @new_mas->node, set @parent to be the parent of * @new_mas->node. If memory allocation fails, @mas is set to -ENOMEM. */ static inline void mas_copy_node(struct ma_state *mas, struct ma_state *new_mas, struct maple_pnode *parent) { struct maple_node *node = mte_to_node(mas->node); struct maple_node *new_node = mte_to_node(new_mas->node); unsigned long val; /* Copy the node completely. */ memcpy(new_node, node, sizeof(struct maple_node)); /* Update the parent node pointer. */ val = (unsigned long)node->parent & MAPLE_NODE_MASK; new_node->parent = ma_parent_ptr(val | (unsigned long)parent); } /* * mas_dup_alloc() - Allocate child nodes for a maple node. * @mas: The maple state of source tree. * @new_mas: The maple state of new tree. * @gfp: The GFP_FLAGS to use for allocations. * * This function allocates child nodes for @new_mas->node during the duplication * process. If memory allocation fails, @mas is set to -ENOMEM. */ static inline void mas_dup_alloc(struct ma_state *mas, struct ma_state *new_mas, gfp_t gfp) { struct maple_node *node = mte_to_node(mas->node); struct maple_node *new_node = mte_to_node(new_mas->node); enum maple_type type; unsigned char request, count, i; void __rcu **slots; void __rcu **new_slots; unsigned long val; /* Allocate memory for child nodes. */ type = mte_node_type(mas->node); new_slots = ma_slots(new_node, type); request = mas_data_end(mas) + 1; count = mt_alloc_bulk(gfp, request, (void **)new_slots); if (unlikely(count < request)) { memset(new_slots, 0, request * sizeof(void *)); mas_set_err(mas, -ENOMEM); return; } /* Restore node type information in slots. */ slots = ma_slots(node, type); for (i = 0; i < count; i++) { val = (unsigned long)mt_slot_locked(mas->tree, slots, i); val &= MAPLE_NODE_MASK; ((unsigned long *)new_slots)[i] |= val; } } /* * mas_dup_build() - Build a new maple tree from a source tree * @mas: The maple state of source tree, need to be in MAS_START state. * @new_mas: The maple state of new tree, need to be in MAS_START state. * @gfp: The GFP_FLAGS to use for allocations. * * This function builds a new tree in DFS preorder. If the memory allocation * fails, the error code -ENOMEM will be set in @mas, and @new_mas points to the * last node. mas_dup_free() will free the incomplete duplication of a tree. * * Note that the attributes of the two trees need to be exactly the same, and the * new tree needs to be empty, otherwise -EINVAL will be set in @mas. */ static inline void mas_dup_build(struct ma_state *mas, struct ma_state *new_mas, gfp_t gfp) { struct maple_node *node; struct maple_pnode *parent = NULL; struct maple_enode *root; enum maple_type type; if (unlikely(mt_attr(mas->tree) != mt_attr(new_mas->tree)) || unlikely(!mtree_empty(new_mas->tree))) { mas_set_err(mas, -EINVAL); return; } root = mas_start(mas); if (mas_is_ptr(mas) || mas_is_none(mas)) goto set_new_tree; node = mt_alloc_one(gfp); if (!node) { new_mas->status = ma_none; mas_set_err(mas, -ENOMEM); return; } type = mte_node_type(mas->node); root = mt_mk_node(node, type); new_mas->node = root; new_mas->min = 0; new_mas->max = ULONG_MAX; root = mte_mk_root(root); while (1) { mas_copy_node(mas, new_mas, parent); if (!mte_is_leaf(mas->node)) { /* Only allocate child nodes for non-leaf nodes. */ mas_dup_alloc(mas, new_mas, gfp); if (unlikely(mas_is_err(mas))) return; } else { /* * This is the last leaf node and duplication is * completed. */ if (mas->max == ULONG_MAX) goto done; /* This is not the last leaf node and needs to go up. */ do { mas_ascend(mas); mas_ascend(new_mas); } while (mas->offset == mas_data_end(mas)); /* Move to the next subtree. */ mas->offset++; new_mas->offset++; } mas_descend(mas); parent = ma_parent_ptr(mte_to_node(new_mas->node)); mas_descend(new_mas); mas->offset = 0; new_mas->offset = 0; } done: /* Specially handle the parent of the root node. */ mte_to_node(root)->parent = ma_parent_ptr(mas_tree_parent(new_mas)); set_new_tree: /* Make them the same height */ new_mas->tree->ma_flags = mas->tree->ma_flags; rcu_assign_pointer(new_mas->tree->ma_root, root); } /** * __mt_dup(): Duplicate an entire maple tree * @mt: The source maple tree * @new: The new maple tree * @gfp: The GFP_FLAGS to use for allocations * * This function duplicates a maple tree in Depth-First Search (DFS) pre-order * traversal. It uses memcpy() to copy nodes in the source tree and allocate * new child nodes in non-leaf nodes. The new node is exactly the same as the * source node except for all the addresses stored in it. It will be faster than * traversing all elements in the source tree and inserting them one by one into * the new tree. * The user needs to ensure that the attributes of the source tree and the new * tree are the same, and the new tree needs to be an empty tree, otherwise * -EINVAL will be returned. * Note that the user needs to manually lock the source tree and the new tree. * * Return: 0 on success, -ENOMEM if memory could not be allocated, -EINVAL If * the attributes of the two trees are different or the new tree is not an empty * tree. */ int __mt_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); MA_STATE(new_mas, new, 0, 0); mas_dup_build(&mas, &new_mas, gfp); if (unlikely(mas_is_err(&mas))) { ret = xa_err(mas.node); if (ret == -ENOMEM) mas_dup_free(&new_mas); } return ret; } EXPORT_SYMBOL(__mt_dup); /** * mtree_dup(): Duplicate an entire maple tree * @mt: The source maple tree * @new: The new maple tree * @gfp: The GFP_FLAGS to use for allocations * * This function duplicates a maple tree in Depth-First Search (DFS) pre-order * traversal. It uses memcpy() to copy nodes in the source tree and allocate * new child nodes in non-leaf nodes. The new node is exactly the same as the * source node except for all the addresses stored in it. It will be faster than * traversing all elements in the source tree and inserting them one by one into * the new tree. * The user needs to ensure that the attributes of the source tree and the new * tree are the same, and the new tree needs to be an empty tree, otherwise * -EINVAL will be returned. * * Return: 0 on success, -ENOMEM if memory could not be allocated, -EINVAL If * the attributes of the two trees are different or the new tree is not an empty * tree. */ int mtree_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); MA_STATE(new_mas, new, 0, 0); mas_lock(&new_mas); mas_lock_nested(&mas, SINGLE_DEPTH_NESTING); mas_dup_build(&mas, &new_mas, gfp); mas_unlock(&mas); if (unlikely(mas_is_err(&mas))) { ret = xa_err(mas.node); if (ret == -ENOMEM) mas_dup_free(&new_mas); } mas_unlock(&new_mas); return ret; } EXPORT_SYMBOL(mtree_dup); /** * __mt_destroy() - Walk and free all nodes of a locked maple tree. * @mt: The maple tree * * Note: Does not handle locking. */ void __mt_destroy(struct maple_tree *mt) { void *root = mt_root_locked(mt); rcu_assign_pointer(mt->ma_root, NULL); if (xa_is_node(root)) mte_destroy_walk(root, mt); mt->ma_flags = mt_attr(mt); } EXPORT_SYMBOL_GPL(__mt_destroy); /** * mtree_destroy() - Destroy a maple tree * @mt: The maple tree * * Frees all resources used by the tree. Handles locking. */ void mtree_destroy(struct maple_tree *mt) { mtree_lock(mt); __mt_destroy(mt); mtree_unlock(mt); } EXPORT_SYMBOL(mtree_destroy); /** * mt_find() - Search from the start up until an entry is found. * @mt: The maple tree * @index: Pointer which contains the start location of the search * @max: The maximum value of the search range * * Takes RCU read lock internally to protect the search, which does not * protect the returned pointer after dropping RCU read lock. * See also: Documentation/core-api/maple_tree.rst * * In case that an entry is found @index is updated to point to the next * possible entry independent whether the found entry is occupying a * single index or a range if indices. * * Return: The entry at or after the @index or %NULL */ void *mt_find(struct maple_tree *mt, unsigned long *index, unsigned long max) { MA_STATE(mas, mt, *index, *index); void *entry; #ifdef CONFIG_DEBUG_MAPLE_TREE unsigned long copy = *index; #endif trace_ma_read(__func__, &mas); if ((*index) > max) return NULL; rcu_read_lock(); retry: entry = mas_state_walk(&mas); if (mas_is_start(&mas)) goto retry; if (unlikely(xa_is_zero(entry))) entry = NULL; if (entry) goto unlock; while (mas_is_active(&mas) && (mas.last < max)) { entry = mas_next_entry(&mas, max); if (likely(entry && !xa_is_zero(entry))) break; } if (unlikely(xa_is_zero(entry))) entry = NULL; unlock: rcu_read_unlock(); if (likely(entry)) { *index = mas.last + 1; #ifdef CONFIG_DEBUG_MAPLE_TREE if (MT_WARN_ON(mt, (*index) && ((*index) <= copy))) pr_err("index not increased! %lx <= %lx\n", *index, copy); #endif } return entry; } EXPORT_SYMBOL(mt_find); /** * mt_find_after() - Search from the start up until an entry is found. * @mt: The maple tree * @index: Pointer which contains the start location of the search * @max: The maximum value to check * * Same as mt_find() except that it checks @index for 0 before * searching. If @index == 0, the search is aborted. This covers a wrap * around of @index to 0 in an iterator loop. * * Return: The entry at or after the @index or %NULL */ void *mt_find_after(struct maple_tree *mt, unsigned long *index, unsigned long max) { if (!(*index)) return NULL; return mt_find(mt, index, max); } EXPORT_SYMBOL(mt_find_after); #ifdef CONFIG_DEBUG_MAPLE_TREE atomic_t maple_tree_tests_run; EXPORT_SYMBOL_GPL(maple_tree_tests_run); atomic_t maple_tree_tests_passed; EXPORT_SYMBOL_GPL(maple_tree_tests_passed); #ifndef __KERNEL__ extern void kmem_cache_set_non_kernel(struct kmem_cache *, unsigned int); void mt_set_non_kernel(unsigned int val) { kmem_cache_set_non_kernel(maple_node_cache, val); } extern void kmem_cache_set_callback(struct kmem_cache *cachep, void (*callback)(void *)); void mt_set_callback(void (*callback)(void *)) { kmem_cache_set_callback(maple_node_cache, callback); } extern void kmem_cache_set_private(struct kmem_cache *cachep, void *private); void mt_set_private(void *private) { kmem_cache_set_private(maple_node_cache, private); } extern unsigned long kmem_cache_get_alloc(struct kmem_cache *); unsigned long mt_get_alloc_size(void) { return kmem_cache_get_alloc(maple_node_cache); } extern void kmem_cache_zero_nr_tallocated(struct kmem_cache *); void mt_zero_nr_tallocated(void) { kmem_cache_zero_nr_tallocated(maple_node_cache); } extern unsigned int kmem_cache_nr_tallocated(struct kmem_cache *); unsigned int mt_nr_tallocated(void) { return kmem_cache_nr_tallocated(maple_node_cache); } extern unsigned int kmem_cache_nr_allocated(struct kmem_cache *); unsigned int mt_nr_allocated(void) { return kmem_cache_nr_allocated(maple_node_cache); } void mt_cache_shrink(void) { } #else /* * mt_cache_shrink() - For testing, don't use this. * * Certain testcases can trigger an OOM when combined with other memory * debugging configuration options. This function is used to reduce the * possibility of an out of memory even due to kmem_cache objects remaining * around for longer than usual. */ void mt_cache_shrink(void) { kmem_cache_shrink(maple_node_cache); } EXPORT_SYMBOL_GPL(mt_cache_shrink); #endif /* not defined __KERNEL__ */ /* * mas_get_slot() - Get the entry in the maple state node stored at @offset. * @mas: The maple state * @offset: The offset into the slot array to fetch. * * Return: The entry stored at @offset. */ static inline struct maple_enode *mas_get_slot(struct ma_state *mas, unsigned char offset) { return mas_slot(mas, ma_slots(mas_mn(mas), mte_node_type(mas->node)), offset); } /* Depth first search, post-order */ static void mas_dfs_postorder(struct ma_state *mas, unsigned long max) { struct maple_enode *p, *mn = mas->node; unsigned long p_min, p_max; mas_next_node(mas, mas_mn(mas), max); if (!mas_is_overflow(mas)) return; if (mte_is_root(mn)) return; mas->node = mn; mas_ascend(mas); do { p = mas->node; p_min = mas->min; p_max = mas->max; mas_prev_node(mas, 0); } while (!mas_is_underflow(mas)); mas->node = p; mas->max = p_max; mas->min = p_min; } /* Tree validations */ static void mt_dump_node(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format); static void mt_dump_range(unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { static const char spaces[] = " "; switch(format) { case mt_dump_hex: if (min == max) pr_info("%.*s%lx: ", depth * 2, spaces, min); else pr_info("%.*s%lx-%lx: ", depth * 2, spaces, min, max); break; case mt_dump_dec: if (min == max) pr_info("%.*s%lu: ", depth * 2, spaces, min); else pr_info("%.*s%lu-%lu: ", depth * 2, spaces, min, max); } } static void mt_dump_entry(void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { mt_dump_range(min, max, depth, format); if (xa_is_value(entry)) pr_cont("value %ld (0x%lx) [" PTR_FMT "]\n", xa_to_value(entry), xa_to_value(entry), entry); else if (xa_is_zero(entry)) pr_cont("zero (%ld)\n", xa_to_internal(entry)); else if (mt_is_reserved(entry)) pr_cont("UNKNOWN ENTRY (" PTR_FMT ")\n", entry); else pr_cont(PTR_FMT "\n", entry); } static void mt_dump_range64(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { struct maple_range_64 *node = &mte_to_node(entry)->mr64; bool leaf = mte_is_leaf(entry); unsigned long first = min; int i; pr_cont(" contents: "); for (i = 0; i < MAPLE_RANGE64_SLOTS - 1; i++) { switch(format) { case mt_dump_hex: pr_cont(PTR_FMT " %lX ", node->slot[i], node->pivot[i]); break; case mt_dump_dec: pr_cont(PTR_FMT " %lu ", node->slot[i], node->pivot[i]); } } pr_cont(PTR_FMT "\n", node->slot[i]); for (i = 0; i < MAPLE_RANGE64_SLOTS; i++) { unsigned long last = max; if (i < (MAPLE_RANGE64_SLOTS - 1)) last = node->pivot[i]; else if (!node->slot[i] && max != mt_node_max(entry)) break; if (last == 0 && i > 0) break; if (leaf) mt_dump_entry(mt_slot(mt, node->slot, i), first, last, depth + 1, format); else if (node->slot[i]) mt_dump_node(mt, mt_slot(mt, node->slot, i), first, last, depth + 1, format); if (last == max) break; if (last > max) { switch(format) { case mt_dump_hex: pr_err("node " PTR_FMT " last (%lx) > max (%lx) at pivot %d!\n", node, last, max, i); break; case mt_dump_dec: pr_err("node " PTR_FMT " last (%lu) > max (%lu) at pivot %d!\n", node, last, max, i); } } first = last + 1; } } static void mt_dump_arange64(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { struct maple_arange_64 *node = &mte_to_node(entry)->ma64; unsigned long first = min; int i; pr_cont(" contents: "); for (i = 0; i < MAPLE_ARANGE64_SLOTS; i++) { switch (format) { case mt_dump_hex: pr_cont("%lx ", node->gap[i]); break; case mt_dump_dec: pr_cont("%lu ", node->gap[i]); } } pr_cont("| %02X %02X| ", node->meta.end, node->meta.gap); for (i = 0; i < MAPLE_ARANGE64_SLOTS - 1; i++) { switch (format) { case mt_dump_hex: pr_cont(PTR_FMT " %lX ", node->slot[i], node->pivot[i]); break; case mt_dump_dec: pr_cont(PTR_FMT " %lu ", node->slot[i], node->pivot[i]); } } pr_cont(PTR_FMT "\n", node->slot[i]); for (i = 0; i < MAPLE_ARANGE64_SLOTS; i++) { unsigned long last = max; if (i < (MAPLE_ARANGE64_SLOTS - 1)) last = node->pivot[i]; else if (!node->slot[i]) break; if (last == 0 && i > 0) break; if (node->slot[i]) mt_dump_node(mt, mt_slot(mt, node->slot, i), first, last, depth + 1, format); if (last == max) break; if (last > max) { switch(format) { case mt_dump_hex: pr_err("node " PTR_FMT " last (%lx) > max (%lx) at pivot %d!\n", node, last, max, i); break; case mt_dump_dec: pr_err("node " PTR_FMT " last (%lu) > max (%lu) at pivot %d!\n", node, last, max, i); } } first = last + 1; } } static void mt_dump_node(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { struct maple_node *node = mte_to_node(entry); unsigned int type = mte_node_type(entry); unsigned int i; mt_dump_range(min, max, depth, format); pr_cont("node " PTR_FMT " depth %d type %d parent " PTR_FMT, node, depth, type, node ? node->parent : NULL); switch (type) { case maple_dense: pr_cont("\n"); for (i = 0; i < MAPLE_NODE_SLOTS; i++) { if (min + i > max) pr_cont("OUT OF RANGE: "); mt_dump_entry(mt_slot(mt, node->slot, i), min + i, min + i, depth, format); } break; case maple_leaf_64: case maple_range_64: mt_dump_range64(mt, entry, min, max, depth, format); break; case maple_arange_64: mt_dump_arange64(mt, entry, min, max, depth, format); break; default: pr_cont(" UNKNOWN TYPE\n"); } } void mt_dump(const struct maple_tree *mt, enum mt_dump_format format) { void *entry = rcu_dereference_check(mt->ma_root, mt_locked(mt)); pr_info("maple_tree(" PTR_FMT ") flags %X, height %u root " PTR_FMT "\n", mt, mt->ma_flags, mt_height(mt), entry); if (xa_is_node(entry)) mt_dump_node(mt, entry, 0, mt_node_max(entry), 0, format); else if (entry) mt_dump_entry(entry, 0, 0, 0, format); else pr_info("(empty)\n"); } EXPORT_SYMBOL_GPL(mt_dump); /* * Calculate the maximum gap in a node and check if that's what is reported in * the parent (unless root). */ static void mas_validate_gaps(struct ma_state *mas) { struct maple_enode *mte = mas->node; struct maple_node *p_mn, *node = mte_to_node(mte); enum maple_type mt = mte_node_type(mas->node); unsigned long gap = 0, max_gap = 0; unsigned long p_end, p_start = mas->min; unsigned char p_slot, offset; unsigned long *gaps = NULL; unsigned long *pivots = ma_pivots(node, mt); unsigned int i; if (ma_is_dense(mt)) { for (i = 0; i < mt_slot_count(mte); i++) { if (mas_get_slot(mas, i)) { if (gap > max_gap) max_gap = gap; gap = 0; continue; } gap++; } goto counted; } gaps = ma_gaps(node, mt); for (i = 0; i < mt_slot_count(mte); i++) { p_end = mas_safe_pivot(mas, pivots, i, mt); if (!gaps) { if (!mas_get_slot(mas, i)) gap = p_end - p_start + 1; } else { void *entry = mas_get_slot(mas, i); gap = gaps[i]; MT_BUG_ON(mas->tree, !entry); if (gap > p_end - p_start + 1) { pr_err(PTR_FMT "[%u] %lu >= %lu - %lu + 1 (%lu)\n", mas_mn(mas), i, gap, p_end, p_start, p_end - p_start + 1); MT_BUG_ON(mas->tree, gap > p_end - p_start + 1); } } if (gap > max_gap) max_gap = gap; p_start = p_end + 1; if (p_end >= mas->max) break; } counted: if (mt == maple_arange_64) { MT_BUG_ON(mas->tree, !gaps); offset = ma_meta_gap(node); if (offset > i) { pr_err("gap offset " PTR_FMT "[%u] is invalid\n", node, offset); MT_BUG_ON(mas->tree, 1); } if (gaps[offset] != max_gap) { pr_err("gap " PTR_FMT "[%u] is not the largest gap %lu\n", node, offset, max_gap); MT_BUG_ON(mas->tree, 1); } for (i++ ; i < mt_slot_count(mte); i++) { if (gaps[i] != 0) { pr_err("gap " PTR_FMT "[%u] beyond node limit != 0\n", node, i); MT_BUG_ON(mas->tree, 1); } } } if (mte_is_root(mte)) return; p_slot = mte_parent_slot(mas->node); p_mn = mte_parent(mte); MT_BUG_ON(mas->tree, max_gap > mas->max); if (ma_gaps(p_mn, mas_parent_type(mas, mte))[p_slot] != max_gap) { pr_err("gap " PTR_FMT "[%u] != %lu\n", p_mn, p_slot, max_gap); mt_dump(mas->tree, mt_dump_hex); MT_BUG_ON(mas->tree, 1); } } static void mas_validate_parent_slot(struct ma_state *mas) { struct maple_node *parent; struct maple_enode *node; enum maple_type p_type; unsigned char p_slot; void __rcu **slots; int i; if (mte_is_root(mas->node)) return; p_slot = mte_parent_slot(mas->node); p_type = mas_parent_type(mas, mas->node); parent = mte_parent(mas->node); slots = ma_slots(parent, p_type); MT_BUG_ON(mas->tree, mas_mn(mas) == parent); /* Check prev/next parent slot for duplicate node entry */ for (i = 0; i < mt_slots[p_type]; i++) { node = mas_slot(mas, slots, i); if (i == p_slot) { if (node != mas->node) pr_err("parent " PTR_FMT "[%u] does not have " PTR_FMT "\n", parent, i, mas_mn(mas)); MT_BUG_ON(mas->tree, node != mas->node); } else if (node == mas->node) { pr_err("Invalid child " PTR_FMT " at parent " PTR_FMT "[%u] p_slot %u\n", mas_mn(mas), parent, i, p_slot); MT_BUG_ON(mas->tree, node == mas->node); } } } static void mas_validate_child_slot(struct ma_state *mas) { enum maple_type type = mte_node_type(mas->node); void __rcu **slots = ma_slots(mte_to_node(mas->node), type); unsigned long *pivots = ma_pivots(mte_to_node(mas->node), type); struct maple_enode *child; unsigned char i; if (mte_is_leaf(mas->node)) return; for (i = 0; i < mt_slots[type]; i++) { child = mas_slot(mas, slots, i); if (!child) { pr_err("Non-leaf node lacks child at " PTR_FMT "[%u]\n", mas_mn(mas), i); MT_BUG_ON(mas->tree, 1); } if (mte_parent_slot(child) != i) { pr_err("Slot error at " PTR_FMT "[%u]: child " PTR_FMT " has pslot %u\n", mas_mn(mas), i, mte_to_node(child), mte_parent_slot(child)); MT_BUG_ON(mas->tree, 1); } if (mte_parent(child) != mte_to_node(mas->node)) { pr_err("child " PTR_FMT " has parent " PTR_FMT " not " PTR_FMT "\n", mte_to_node(child), mte_parent(child), mte_to_node(mas->node)); MT_BUG_ON(mas->tree, 1); } if (i < mt_pivots[type] && pivots[i] == mas->max) break; } } /* * Validate all pivots are within mas->min and mas->max, check metadata ends * where the maximum ends and ensure there is no slots or pivots set outside of * the end of the data. */ static void mas_validate_limits(struct ma_state *mas) { int i; unsigned long prev_piv = 0; enum maple_type type = mte_node_type(mas->node); void __rcu **slots = ma_slots(mte_to_node(mas->node), type); unsigned long *pivots = ma_pivots(mas_mn(mas), type); for (i = 0; i < mt_slots[type]; i++) { unsigned long piv; piv = mas_safe_pivot(mas, pivots, i, type); if (!piv && (i != 0)) { pr_err("Missing node limit pivot at " PTR_FMT "[%u]", mas_mn(mas), i); MAS_WARN_ON(mas, 1); } if (prev_piv > piv) { pr_err(PTR_FMT "[%u] piv %lu < prev_piv %lu\n", mas_mn(mas), i, piv, prev_piv); MAS_WARN_ON(mas, piv < prev_piv); } if (piv < mas->min) { pr_err(PTR_FMT "[%u] %lu < %lu\n", mas_mn(mas), i, piv, mas->min); MAS_WARN_ON(mas, piv < mas->min); } if (piv > mas->max) { pr_err(PTR_FMT "[%u] %lu > %lu\n", mas_mn(mas), i, piv, mas->max); MAS_WARN_ON(mas, piv > mas->max); } prev_piv = piv; if (piv == mas->max) break; } if (mas_data_end(mas) != i) { pr_err("node" PTR_FMT ": data_end %u != the last slot offset %u\n", mas_mn(mas), mas_data_end(mas), i); MT_BUG_ON(mas->tree, 1); } for (i += 1; i < mt_slots[type]; i++) { void *entry = mas_slot(mas, slots, i); if (entry && (i != mt_slots[type] - 1)) { pr_err(PTR_FMT "[%u] should not have entry " PTR_FMT "\n", mas_mn(mas), i, entry); MT_BUG_ON(mas->tree, entry != NULL); } if (i < mt_pivots[type]) { unsigned long piv = pivots[i]; if (!piv) continue; pr_err(PTR_FMT "[%u] should not have piv %lu\n", mas_mn(mas), i, piv); MAS_WARN_ON(mas, i < mt_pivots[type] - 1); } } } static void mt_validate_nulls(struct maple_tree *mt) { void *entry, *last = (void *)1; unsigned char offset = 0; void __rcu **slots; MA_STATE(mas, mt, 0, 0); mas_start(&mas); if (mas_is_none(&mas) || (mas_is_ptr(&mas))) return; while (!mte_is_leaf(mas.node)) mas_descend(&mas); slots = ma_slots(mte_to_node(mas.node), mte_node_type(mas.node)); do { entry = mas_slot(&mas, slots, offset); if (!last && !entry) { pr_err("Sequential nulls end at " PTR_FMT "[%u]\n", mas_mn(&mas), offset); } MT_BUG_ON(mt, !last && !entry); last = entry; if (offset == mas_data_end(&mas)) { mas_next_node(&mas, mas_mn(&mas), ULONG_MAX); if (mas_is_overflow(&mas)) return; offset = 0; slots = ma_slots(mte_to_node(mas.node), mte_node_type(mas.node)); } else { offset++; } } while (!mas_is_overflow(&mas)); } /* * validate a maple tree by checking: * 1. The limits (pivots are within mas->min to mas->max) * 2. The gap is correctly set in the parents */ void mt_validate(struct maple_tree *mt) __must_hold(mas->tree->ma_lock) { unsigned char end; MA_STATE(mas, mt, 0, 0); mas_start(&mas); if (!mas_is_active(&mas)) return; while (!mte_is_leaf(mas.node)) mas_descend(&mas); while (!mas_is_overflow(&mas)) { MAS_WARN_ON(&mas, mte_dead_node(mas.node)); end = mas_data_end(&mas); if (MAS_WARN_ON(&mas, (end < mt_min_slot_count(mas.node)) && (mas.max != ULONG_MAX))) { pr_err("Invalid size %u of " PTR_FMT "\n", end, mas_mn(&mas)); } mas_validate_parent_slot(&mas); mas_validate_limits(&mas); mas_validate_child_slot(&mas); if (mt_is_alloc(mt)) mas_validate_gaps(&mas); mas_dfs_postorder(&mas, ULONG_MAX); } mt_validate_nulls(mt); } EXPORT_SYMBOL_GPL(mt_validate); void mas_dump(const struct ma_state *mas) { pr_err("MAS: tree=" PTR_FMT " enode=" PTR_FMT " ", mas->tree, mas->node); switch (mas->status) { case ma_active: pr_err("(ma_active)"); break; case ma_none: pr_err("(ma_none)"); break; case ma_root: pr_err("(ma_root)"); break; case ma_start: pr_err("(ma_start) "); break; case ma_pause: pr_err("(ma_pause) "); break; case ma_overflow: pr_err("(ma_overflow) "); break; case ma_underflow: pr_err("(ma_underflow) "); break; case ma_error: pr_err("(ma_error) "); break; } pr_err("Store Type: "); switch (mas->store_type) { case wr_invalid: pr_err("invalid store type\n"); break; case wr_new_root: pr_err("new_root\n"); break; case wr_store_root: pr_err("store_root\n"); break; case wr_exact_fit: pr_err("exact_fit\n"); break; case wr_split_store: pr_err("split_store\n"); break; case wr_slot_store: pr_err("slot_store\n"); break; case wr_append: pr_err("append\n"); break; case wr_node_store: pr_err("node_store\n"); break; case wr_spanning_store: pr_err("spanning_store\n"); break; case wr_rebalance: pr_err("rebalance\n"); break; } pr_err("[%u/%u] index=%lx last=%lx\n", mas->offset, mas->end, mas->index, mas->last); pr_err(" min=%lx max=%lx alloc=" PTR_FMT ", depth=%u, flags=%x\n", mas->min, mas->max, mas->alloc, mas->depth, mas->mas_flags); if (mas->index > mas->last) pr_err("Check index & last\n"); } EXPORT_SYMBOL_GPL(mas_dump); void mas_wr_dump(const struct ma_wr_state *wr_mas) { pr_err("WR_MAS: node=" PTR_FMT " r_min=%lx r_max=%lx\n", wr_mas->node, wr_mas->r_min, wr_mas->r_max); pr_err(" type=%u off_end=%u, node_end=%u, end_piv=%lx\n", wr_mas->type, wr_mas->offset_end, wr_mas->mas->end, wr_mas->end_piv); } EXPORT_SYMBOL_GPL(mas_wr_dump); #endif /* CONFIG_DEBUG_MAPLE_TREE */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Linux Socket Filter Data Structures */ #ifndef __LINUX_FILTER_H__ #define __LINUX_FILTER_H__ #include <linux/atomic.h> #include <linux/bpf.h> #include <linux/refcount.h> #include <linux/compat.h> #include <linux/skbuff.h> #include <linux/linkage.h> #include <linux/printk.h> #include <linux/workqueue.h> #include <linux/sched.h> #include <linux/sched/clock.h> #include <linux/capability.h> #include <linux/set_memory.h> #include <linux/kallsyms.h> #include <linux/if_vlan.h> #include <linux/vmalloc.h> #include <linux/sockptr.h> #include <crypto/sha1.h> #include <linux/u64_stats_sync.h> #include <net/sch_generic.h> #include <asm/byteorder.h> #include <uapi/linux/filter.h> struct sk_buff; struct sock; struct seccomp_data; struct bpf_prog_aux; struct xdp_rxq_info; struct xdp_buff; struct sock_reuseport; struct ctl_table; struct ctl_table_header; /* ArgX, context and stack frame pointer register positions. Note, * Arg1, Arg2, Arg3, etc are used as argument mappings of function * calls in BPF_CALL instruction. */ #define BPF_REG_ARG1 BPF_REG_1 #define BPF_REG_ARG2 BPF_REG_2 #define BPF_REG_ARG3 BPF_REG_3 #define BPF_REG_ARG4 BPF_REG_4 #define BPF_REG_ARG5 BPF_REG_5 #define BPF_REG_CTX BPF_REG_6 #define BPF_REG_FP BPF_REG_10 /* Additional register mappings for converted user programs. */ #define BPF_REG_A BPF_REG_0 #define BPF_REG_X BPF_REG_7 #define BPF_REG_TMP BPF_REG_2 /* scratch reg */ #define BPF_REG_D BPF_REG_8 /* data, callee-saved */ #define BPF_REG_H BPF_REG_9 /* hlen, callee-saved */ /* Kernel hidden auxiliary/helper register. */ #define BPF_REG_AX MAX_BPF_REG #define MAX_BPF_EXT_REG (MAX_BPF_REG + 1) #define MAX_BPF_JIT_REG MAX_BPF_EXT_REG /* unused opcode to mark special call to bpf_tail_call() helper */ #define BPF_TAIL_CALL 0xf0 /* unused opcode to mark special load instruction. Same as BPF_ABS */ #define BPF_PROBE_MEM 0x20 /* unused opcode to mark special ldsx instruction. Same as BPF_IND */ #define BPF_PROBE_MEMSX 0x40 /* unused opcode to mark special load instruction. Same as BPF_MSH */ #define BPF_PROBE_MEM32 0xa0 /* unused opcode to mark special atomic instruction */ #define BPF_PROBE_ATOMIC 0xe0 /* unused opcode to mark call to interpreter with arguments */ #define BPF_CALL_ARGS 0xe0 /* unused opcode to mark speculation barrier for mitigating * Speculative Store Bypass */ #define BPF_NOSPEC 0xc0 /* As per nm, we expose JITed images as text (code) section for * kallsyms. That way, tools like perf can find it to match * addresses. */ #define BPF_SYM_ELF_TYPE 't' /* BPF program can access up to 512 bytes of stack space. */ #define MAX_BPF_STACK 512 /* Helper macros for filter block array initializers. */ /* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */ #define BPF_ALU64_REG_OFF(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) #define BPF_ALU64_REG(OP, DST, SRC) \ BPF_ALU64_REG_OFF(OP, DST, SRC, 0) #define BPF_ALU32_REG_OFF(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) #define BPF_ALU32_REG(OP, DST, SRC) \ BPF_ALU32_REG_OFF(OP, DST, SRC, 0) /* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */ #define BPF_ALU64_IMM_OFF(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) #define BPF_ALU64_IMM(OP, DST, IMM) \ BPF_ALU64_IMM_OFF(OP, DST, IMM, 0) #define BPF_ALU32_IMM_OFF(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) #define BPF_ALU32_IMM(OP, DST, IMM) \ BPF_ALU32_IMM_OFF(OP, DST, IMM, 0) /* Endianess conversion, cpu_to_{l,b}e(), {l,b}e_to_cpu() */ #define BPF_ENDIAN(TYPE, DST, LEN) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_END | BPF_SRC(TYPE), \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = LEN }) /* Byte Swap, bswap16/32/64 */ #define BPF_BSWAP(DST, LEN) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_END | BPF_SRC(BPF_TO_LE), \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = LEN }) /* Short form of mov, dst_reg = src_reg */ #define BPF_MOV64_REG(DST, SRC) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = 0 }) #define BPF_MOV32_REG(DST, SRC) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = 0 }) /* Special (internal-only) form of mov, used to resolve per-CPU addrs: * dst_reg = src_reg + <percpu_base_off> * BPF_ADDR_PERCPU is used as a special insn->off value. */ #define BPF_ADDR_PERCPU (-1) #define BPF_MOV64_PERCPU_REG(DST, SRC) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = BPF_ADDR_PERCPU, \ .imm = 0 }) static inline bool insn_is_mov_percpu_addr(const struct bpf_insn *insn) { return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->off == BPF_ADDR_PERCPU; } /* Short form of mov, dst_reg = imm32 */ #define BPF_MOV64_IMM(DST, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = IMM }) #define BPF_MOV32_IMM(DST, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = IMM }) /* Short form of movsx, dst_reg = (s8,s16,s32)src_reg */ #define BPF_MOVSX64_REG(DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) #define BPF_MOVSX32_REG(DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Special form of mov32, used for doing explicit zero extension on dst. */ #define BPF_ZEXT_REG(DST) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = DST, \ .off = 0, \ .imm = 1 }) static inline bool insn_is_zext(const struct bpf_insn *insn) { return insn->code == (BPF_ALU | BPF_MOV | BPF_X) && insn->imm == 1; } /* addr_space_cast from as(0) to as(1) is for converting bpf arena pointers * to pointers in user vma. */ static inline bool insn_is_cast_user(const struct bpf_insn *insn) { return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->off == BPF_ADDR_SPACE_CAST && insn->imm == 1U << 16; } /* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */ #define BPF_LD_IMM64(DST, IMM) \ BPF_LD_IMM64_RAW(DST, 0, IMM) #define BPF_LD_IMM64_RAW(DST, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_LD | BPF_DW | BPF_IMM, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = (__u32) (IMM) }), \ ((struct bpf_insn) { \ .code = 0, /* zero is reserved opcode */ \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = ((__u64) (IMM)) >> 32 }) /* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */ #define BPF_LD_MAP_FD(DST, MAP_FD) \ BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD) /* Short form of mov based on type, BPF_X: dst_reg = src_reg, BPF_K: dst_reg = imm32 */ #define BPF_MOV64_RAW(TYPE, DST, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_SRC(TYPE), \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = IMM }) #define BPF_MOV32_RAW(TYPE, DST, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_SRC(TYPE), \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = IMM }) /* Direct packet access, R0 = *(uint *) (skb->data + imm32) */ #define BPF_LD_ABS(SIZE, IMM) \ ((struct bpf_insn) { \ .code = BPF_LD | BPF_SIZE(SIZE) | BPF_ABS, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = IMM }) /* Indirect packet access, R0 = *(uint *) (skb->data + src_reg + imm32) */ #define BPF_LD_IND(SIZE, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_LD | BPF_SIZE(SIZE) | BPF_IND, \ .dst_reg = 0, \ .src_reg = SRC, \ .off = 0, \ .imm = IMM }) /* Memory load, dst_reg = *(uint *) (src_reg + off16) */ #define BPF_LDX_MEM(SIZE, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEM, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Memory load, dst_reg = *(signed size *) (src_reg + off16) */ #define BPF_LDX_MEMSX(SIZE, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEMSX, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Memory store, *(uint *) (dst_reg + off16) = src_reg */ #define BPF_STX_MEM(SIZE, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_STX | BPF_SIZE(SIZE) | BPF_MEM, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* * Atomic operations: * * BPF_ADD *(uint *) (dst_reg + off16) += src_reg * BPF_AND *(uint *) (dst_reg + off16) &= src_reg * BPF_OR *(uint *) (dst_reg + off16) |= src_reg * BPF_XOR *(uint *) (dst_reg + off16) ^= src_reg * BPF_ADD | BPF_FETCH src_reg = atomic_fetch_add(dst_reg + off16, src_reg); * BPF_AND | BPF_FETCH src_reg = atomic_fetch_and(dst_reg + off16, src_reg); * BPF_OR | BPF_FETCH src_reg = atomic_fetch_or(dst_reg + off16, src_reg); * BPF_XOR | BPF_FETCH src_reg = atomic_fetch_xor(dst_reg + off16, src_reg); * BPF_XCHG src_reg = atomic_xchg(dst_reg + off16, src_reg) * BPF_CMPXCHG r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg) */ #define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_STX | BPF_SIZE(SIZE) | BPF_ATOMIC, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = OP }) /* Legacy alias */ #define BPF_STX_XADD(SIZE, DST, SRC, OFF) BPF_ATOMIC_OP(SIZE, BPF_ADD, DST, SRC, OFF) /* Memory store, *(uint *) (dst_reg + off16) = imm32 */ #define BPF_ST_MEM(SIZE, DST, OFF, IMM) \ ((struct bpf_insn) { \ .code = BPF_ST | BPF_SIZE(SIZE) | BPF_MEM, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) /* Conditional jumps against registers, if (dst_reg 'op' src_reg) goto pc + off16 */ #define BPF_JMP_REG(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Conditional jumps against immediates, if (dst_reg 'op' imm32) goto pc + off16 */ #define BPF_JMP_IMM(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) /* Like BPF_JMP_REG, but with 32-bit wide operands for comparison. */ #define BPF_JMP32_REG(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP32 | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Like BPF_JMP_IMM, but with 32-bit wide operands for comparison. */ #define BPF_JMP32_IMM(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP32 | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) /* Unconditional jumps, goto pc + off16 */ #define BPF_JMP_A(OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_JA, \ .dst_reg = 0, \ .src_reg = 0, \ .off = OFF, \ .imm = 0 }) /* Unconditional jumps, gotol pc + imm32 */ #define BPF_JMP32_A(IMM) \ ((struct bpf_insn) { \ .code = BPF_JMP32 | BPF_JA, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = IMM }) /* Relative call */ #define BPF_CALL_REL(TGT) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_CALL, \ .dst_reg = 0, \ .src_reg = BPF_PSEUDO_CALL, \ .off = 0, \ .imm = TGT }) /* Convert function address to BPF immediate */ #define BPF_CALL_IMM(x) ((void *)(x) - (void *)__bpf_call_base) #define BPF_EMIT_CALL(FUNC) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_CALL, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = BPF_CALL_IMM(FUNC) }) /* Raw code statement block */ #define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM) \ ((struct bpf_insn) { \ .code = CODE, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = IMM }) /* Program exit */ #define BPF_EXIT_INSN() \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_EXIT, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = 0 }) /* Speculation barrier */ #define BPF_ST_NOSPEC() \ ((struct bpf_insn) { \ .code = BPF_ST | BPF_NOSPEC, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = 0 }) /* Internal classic blocks for direct assignment */ #define __BPF_STMT(CODE, K) \ ((struct sock_filter) BPF_STMT(CODE, K)) #define __BPF_JUMP(CODE, K, JT, JF) \ ((struct sock_filter) BPF_JUMP(CODE, K, JT, JF)) #define bytes_to_bpf_size(bytes) \ ({ \ int bpf_size = -EINVAL; \ \ if (bytes == sizeof(u8)) \ bpf_size = BPF_B; \ else if (bytes == sizeof(u16)) \ bpf_size = BPF_H; \ else if (bytes == sizeof(u32)) \ bpf_size = BPF_W; \ else if (bytes == sizeof(u64)) \ bpf_size = BPF_DW; \ \ bpf_size; \ }) #define bpf_size_to_bytes(bpf_size) \ ({ \ int bytes = -EINVAL; \ \ if (bpf_size == BPF_B) \ bytes = sizeof(u8); \ else if (bpf_size == BPF_H) \ bytes = sizeof(u16); \ else if (bpf_size == BPF_W) \ bytes = sizeof(u32); \ else if (bpf_size == BPF_DW) \ bytes = sizeof(u64); \ \ bytes; \ }) #define BPF_SIZEOF(type) \ ({ \ const int __size = bytes_to_bpf_size(sizeof(type)); \ BUILD_BUG_ON(__size < 0); \ __size; \ }) #define BPF_FIELD_SIZEOF(type, field) \ ({ \ const int __size = bytes_to_bpf_size(sizeof_field(type, field)); \ BUILD_BUG_ON(__size < 0); \ __size; \ }) #define BPF_LDST_BYTES(insn) \ ({ \ const int __size = bpf_size_to_bytes(BPF_SIZE((insn)->code)); \ WARN_ON(__size < 0); \ __size; \ }) #define __BPF_MAP_0(m, v, ...) v #define __BPF_MAP_1(m, v, t, a, ...) m(t, a) #define __BPF_MAP_2(m, v, t, a, ...) m(t, a), __BPF_MAP_1(m, v, __VA_ARGS__) #define __BPF_MAP_3(m, v, t, a, ...) m(t, a), __BPF_MAP_2(m, v, __VA_ARGS__) #define __BPF_MAP_4(m, v, t, a, ...) m(t, a), __BPF_MAP_3(m, v, __VA_ARGS__) #define __BPF_MAP_5(m, v, t, a, ...) m(t, a), __BPF_MAP_4(m, v, __VA_ARGS__) #define __BPF_REG_0(...) __BPF_PAD(5) #define __BPF_REG_1(...) __BPF_MAP(1, __VA_ARGS__), __BPF_PAD(4) #define __BPF_REG_2(...) __BPF_MAP(2, __VA_ARGS__), __BPF_PAD(3) #define __BPF_REG_3(...) __BPF_MAP(3, __VA_ARGS__), __BPF_PAD(2) #define __BPF_REG_4(...) __BPF_MAP(4, __VA_ARGS__), __BPF_PAD(1) #define __BPF_REG_5(...) __BPF_MAP(5, __VA_ARGS__) #define __BPF_MAP(n, ...) __BPF_MAP_##n(__VA_ARGS__) #define __BPF_REG(n, ...) __BPF_REG_##n(__VA_ARGS__) #define __BPF_CAST(t, a) \ (__force t) \ (__force \ typeof(__builtin_choose_expr(sizeof(t) == sizeof(unsigned long), \ (unsigned long)0, (t)0))) a #define __BPF_V void #define __BPF_N #define __BPF_DECL_ARGS(t, a) t a #define __BPF_DECL_REGS(t, a) u64 a #define __BPF_PAD(n) \ __BPF_MAP(n, __BPF_DECL_ARGS, __BPF_N, u64, __ur_1, u64, __ur_2, \ u64, __ur_3, u64, __ur_4, u64, __ur_5) #define BPF_CALL_x(x, attr, name, ...) \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ typedef u64 (*btf_##name)(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ attr u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)); \ attr u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)) \ { \ return ((btf_##name)____##name)(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\ } \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)) #define __NOATTR #define BPF_CALL_0(name, ...) BPF_CALL_x(0, __NOATTR, name, __VA_ARGS__) #define BPF_CALL_1(name, ...) BPF_CALL_x(1, __NOATTR, name, __VA_ARGS__) #define BPF_CALL_2(name, ...) BPF_CALL_x(2, __NOATTR, name, __VA_ARGS__) #define BPF_CALL_3(name, ...) BPF_CALL_x(3, __NOATTR, name, __VA_ARGS__) #define BPF_CALL_4(name, ...) BPF_CALL_x(4, __NOATTR, name, __VA_ARGS__) #define BPF_CALL_5(name, ...) BPF_CALL_x(5, __NOATTR, name, __VA_ARGS__) #define NOTRACE_BPF_CALL_1(name, ...) BPF_CALL_x(1, notrace, name, __VA_ARGS__) #define bpf_ctx_range(TYPE, MEMBER) \ offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 #define bpf_ctx_range_till(TYPE, MEMBER1, MEMBER2) \ offsetof(TYPE, MEMBER1) ... offsetofend(TYPE, MEMBER2) - 1 #if BITS_PER_LONG == 64 # define bpf_ctx_range_ptr(TYPE, MEMBER) \ offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 #else # define bpf_ctx_range_ptr(TYPE, MEMBER) \ offsetof(TYPE, MEMBER) ... offsetof(TYPE, MEMBER) + 8 - 1 #endif /* BITS_PER_LONG == 64 */ #define bpf_target_off(TYPE, MEMBER, SIZE, PTR_SIZE) \ ({ \ BUILD_BUG_ON(sizeof_field(TYPE, MEMBER) != (SIZE)); \ *(PTR_SIZE) = (SIZE); \ offsetof(TYPE, MEMBER); \ }) /* A struct sock_filter is architecture independent. */ struct compat_sock_fprog { u16 len; compat_uptr_t filter; /* struct sock_filter * */ }; struct sock_fprog_kern { u16 len; struct sock_filter *filter; }; /* Some arches need doubleword alignment for their instructions and/or data */ #define BPF_IMAGE_ALIGNMENT 8 struct bpf_binary_header { u32 size; u8 image[] __aligned(BPF_IMAGE_ALIGNMENT); }; struct bpf_prog_stats { u64_stats_t cnt; u64_stats_t nsecs; u64_stats_t misses; struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); struct sk_filter { refcount_t refcnt; struct rcu_head rcu; struct bpf_prog *prog; }; DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key); extern struct mutex nf_conn_btf_access_lock; extern int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size); typedef unsigned int (*bpf_dispatcher_fn)(const void *ctx, const struct bpf_insn *insnsi, unsigned int (*bpf_func)(const void *, const struct bpf_insn *)); static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog, const void *ctx, bpf_dispatcher_fn dfunc) { u32 ret; cant_migrate(); if (static_branch_unlikely(&bpf_stats_enabled_key)) { struct bpf_prog_stats *stats; u64 duration, start = sched_clock(); unsigned long flags; ret = dfunc(ctx, prog->insnsi, prog->bpf_func); duration = sched_clock() - start; stats = this_cpu_ptr(prog->stats); flags = u64_stats_update_begin_irqsave(&stats->syncp); u64_stats_inc(&stats->cnt); u64_stats_add(&stats->nsecs, duration); u64_stats_update_end_irqrestore(&stats->syncp, flags); } else { ret = dfunc(ctx, prog->insnsi, prog->bpf_func); } return ret; } static __always_inline u32 bpf_prog_run(const struct bpf_prog *prog, const void *ctx) { return __bpf_prog_run(prog, ctx, bpf_dispatcher_nop_func); } /* * Use in preemptible and therefore migratable context to make sure that * the execution of the BPF program runs on one CPU. * * This uses migrate_disable/enable() explicitly to document that the * invocation of a BPF program does not require reentrancy protection * against a BPF program which is invoked from a preempting task. */ static inline u32 bpf_prog_run_pin_on_cpu(const struct bpf_prog *prog, const void *ctx) { u32 ret; migrate_disable(); ret = bpf_prog_run(prog, ctx); migrate_enable(); return ret; } #define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN struct bpf_skb_data_end { struct qdisc_skb_cb qdisc_cb; void *data_meta; void *data_end; }; struct bpf_nh_params { u32 nh_family; union { u32 ipv4_nh; struct in6_addr ipv6_nh; }; }; /* flags for bpf_redirect_info kern_flags */ #define BPF_RI_F_RF_NO_DIRECT BIT(0) /* no napi_direct on return_frame */ #define BPF_RI_F_RI_INIT BIT(1) #define BPF_RI_F_CPU_MAP_INIT BIT(2) #define BPF_RI_F_DEV_MAP_INIT BIT(3) #define BPF_RI_F_XSK_MAP_INIT BIT(4) struct bpf_redirect_info { u64 tgt_index; void *tgt_value; struct bpf_map *map; u32 flags; u32 map_id; enum bpf_map_type map_type; struct bpf_nh_params nh; u32 kern_flags; }; struct bpf_net_context { struct bpf_redirect_info ri; struct list_head cpu_map_flush_list; struct list_head dev_map_flush_list; struct list_head xskmap_map_flush_list; }; static inline struct bpf_net_context *bpf_net_ctx_set(struct bpf_net_context *bpf_net_ctx) { struct task_struct *tsk = current; if (tsk->bpf_net_context != NULL) return NULL; bpf_net_ctx->ri.kern_flags = 0; tsk->bpf_net_context = bpf_net_ctx; return bpf_net_ctx; } static inline void bpf_net_ctx_clear(struct bpf_net_context *bpf_net_ctx) { if (bpf_net_ctx) current->bpf_net_context = NULL; } static inline struct bpf_net_context *bpf_net_ctx_get(void) { return current->bpf_net_context; } static inline struct bpf_redirect_info *bpf_net_ctx_get_ri(void) { struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_RI_INIT)) { memset(&bpf_net_ctx->ri, 0, offsetof(struct bpf_net_context, ri.nh)); bpf_net_ctx->ri.kern_flags |= BPF_RI_F_RI_INIT; } return &bpf_net_ctx->ri; } static inline struct list_head *bpf_net_ctx_get_cpu_map_flush_list(void) { struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_CPU_MAP_INIT)) { INIT_LIST_HEAD(&bpf_net_ctx->cpu_map_flush_list); bpf_net_ctx->ri.kern_flags |= BPF_RI_F_CPU_MAP_INIT; } return &bpf_net_ctx->cpu_map_flush_list; } static inline struct list_head *bpf_net_ctx_get_dev_flush_list(void) { struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_DEV_MAP_INIT)) { INIT_LIST_HEAD(&bpf_net_ctx->dev_map_flush_list); bpf_net_ctx->ri.kern_flags |= BPF_RI_F_DEV_MAP_INIT; } return &bpf_net_ctx->dev_map_flush_list; } static inline struct list_head *bpf_net_ctx_get_xskmap_flush_list(void) { struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_XSK_MAP_INIT)) { INIT_LIST_HEAD(&bpf_net_ctx->xskmap_map_flush_list); bpf_net_ctx->ri.kern_flags |= BPF_RI_F_XSK_MAP_INIT; } return &bpf_net_ctx->xskmap_map_flush_list; } static inline void bpf_net_ctx_get_all_used_flush_lists(struct list_head **lh_map, struct list_head **lh_dev, struct list_head **lh_xsk) { struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); u32 kern_flags = bpf_net_ctx->ri.kern_flags; struct list_head *lh; *lh_map = *lh_dev = *lh_xsk = NULL; if (!IS_ENABLED(CONFIG_BPF_SYSCALL)) return; lh = &bpf_net_ctx->dev_map_flush_list; if (kern_flags & BPF_RI_F_DEV_MAP_INIT && !list_empty(lh)) *lh_dev = lh; lh = &bpf_net_ctx->cpu_map_flush_list; if (kern_flags & BPF_RI_F_CPU_MAP_INIT && !list_empty(lh)) *lh_map = lh; lh = &bpf_net_ctx->xskmap_map_flush_list; if (IS_ENABLED(CONFIG_XDP_SOCKETS) && kern_flags & BPF_RI_F_XSK_MAP_INIT && !list_empty(lh)) *lh_xsk = lh; } /* Compute the linear packet data range [data, data_end) which * will be accessed by various program types (cls_bpf, act_bpf, * lwt, ...). Subsystems allowing direct data access must (!) * ensure that cb[] area can be written to when BPF program is * invoked (otherwise cb[] save/restore is necessary). */ static inline void bpf_compute_data_pointers(struct sk_buff *skb) { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; BUILD_BUG_ON(sizeof(*cb) > sizeof_field(struct sk_buff, cb)); cb->data_meta = skb->data - skb_metadata_len(skb); cb->data_end = skb->data + skb_headlen(skb); } /* Similar to bpf_compute_data_pointers(), except that save orginal * data in cb->data and cb->meta_data for restore. */ static inline void bpf_compute_and_save_data_end( struct sk_buff *skb, void **saved_data_end) { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; *saved_data_end = cb->data_end; cb->data_end = skb->data + skb_headlen(skb); } /* Restore data saved by bpf_compute_and_save_data_end(). */ static inline void bpf_restore_data_end( struct sk_buff *skb, void *saved_data_end) { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; cb->data_end = saved_data_end; } static inline u8 *bpf_skb_cb(const struct sk_buff *skb) { /* eBPF programs may read/write skb->cb[] area to transfer meta * data between tail calls. Since this also needs to work with * tc, that scratch memory is mapped to qdisc_skb_cb's data area. * * In some socket filter cases, the cb unfortunately needs to be * saved/restored so that protocol specific skb->cb[] data won't * be lost. In any case, due to unpriviledged eBPF programs * attached to sockets, we need to clear the bpf_skb_cb() area * to not leak previous contents to user space. */ BUILD_BUG_ON(sizeof_field(struct __sk_buff, cb) != BPF_SKB_CB_LEN); BUILD_BUG_ON(sizeof_field(struct __sk_buff, cb) != sizeof_field(struct qdisc_skb_cb, data)); return qdisc_skb_cb(skb)->data; } /* Must be invoked with migration disabled */ static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog, const void *ctx) { const struct sk_buff *skb = ctx; u8 *cb_data = bpf_skb_cb(skb); u8 cb_saved[BPF_SKB_CB_LEN]; u32 res; if (unlikely(prog->cb_access)) { memcpy(cb_saved, cb_data, sizeof(cb_saved)); memset(cb_data, 0, sizeof(cb_saved)); } res = bpf_prog_run(prog, skb); if (unlikely(prog->cb_access)) memcpy(cb_data, cb_saved, sizeof(cb_saved)); return res; } static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, struct sk_buff *skb) { u32 res; migrate_disable(); res = __bpf_prog_run_save_cb(prog, skb); migrate_enable(); return res; } static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, struct sk_buff *skb) { u8 *cb_data = bpf_skb_cb(skb); u32 res; if (unlikely(prog->cb_access)) memset(cb_data, 0, BPF_SKB_CB_LEN); res = bpf_prog_run_pin_on_cpu(prog, skb); return res; } DECLARE_BPF_DISPATCHER(xdp) DECLARE_STATIC_KEY_FALSE(bpf_master_redirect_enabled_key); u32 xdp_master_redirect(struct xdp_buff *xdp); void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog); static inline u32 bpf_prog_insn_size(const struct bpf_prog *prog) { return prog->len * sizeof(struct bpf_insn); } static inline u32 bpf_prog_tag_scratch_size(const struct bpf_prog *prog) { return round_up(bpf_prog_insn_size(prog) + sizeof(__be64) + 1, SHA1_BLOCK_SIZE); } static inline unsigned int bpf_prog_size(unsigned int proglen) { return max(sizeof(struct bpf_prog), offsetof(struct bpf_prog, insns[proglen])); } static inline bool bpf_prog_was_classic(const struct bpf_prog *prog) { /* When classic BPF programs have been loaded and the arch * does not have a classic BPF JIT (anymore), they have been * converted via bpf_migrate_filter() to eBPF and thus always * have an unspec program type. */ return prog->type == BPF_PROG_TYPE_UNSPEC; } static inline u32 bpf_ctx_off_adjust_machine(u32 size) { const u32 size_machine = sizeof(unsigned long); if (size > size_machine && size % size_machine == 0) size = size_machine; return size; } static inline bool bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) { return size <= size_default && (size & (size - 1)) == 0; } static inline u8 bpf_ctx_narrow_access_offset(u32 off, u32 size, u32 size_default) { u8 access_off = off & (size_default - 1); #ifdef __LITTLE_ENDIAN return access_off; #else return size_default - (access_off + size); #endif } #define bpf_ctx_wide_access_ok(off, size, type, field) \ (size == sizeof(__u64) && \ off >= offsetof(type, field) && \ off + sizeof(__u64) <= offsetofend(type, field) && \ off % sizeof(__u64) == 0) #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) static inline int __must_check bpf_prog_lock_ro(struct bpf_prog *fp) { #ifndef CONFIG_BPF_JIT_ALWAYS_ON if (!fp->jited) { set_vm_flush_reset_perms(fp); return set_memory_ro((unsigned long)fp, fp->pages); } #endif return 0; } static inline int __must_check bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { set_vm_flush_reset_perms(hdr); return set_memory_rox((unsigned long)hdr, hdr->size >> PAGE_SHIFT); } int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); static inline int sk_filter(struct sock *sk, struct sk_buff *skb) { return sk_filter_trim_cap(sk, skb, 1); } struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err); void bpf_prog_free(struct bpf_prog *fp); bool bpf_opcode_in_insntable(u8 code); void bpf_prog_fill_jited_linfo(struct bpf_prog *prog, const u32 *insn_to_jit_off); int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog); void bpf_prog_jit_attempt_done(struct bpf_prog *prog); struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags); struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags); struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_extra_flags); void __bpf_prog_free(struct bpf_prog *fp); static inline void bpf_prog_unlock_free(struct bpf_prog *fp) { __bpf_prog_free(fp); } typedef int (*bpf_aux_classic_check_t)(struct sock_filter *filter, unsigned int flen); int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog); int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, bpf_aux_classic_check_t trans, bool save_orig); void bpf_prog_destroy(struct bpf_prog *fp); int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_attach_bpf(u32 ufd, struct sock *sk); int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk); void sk_reuseport_prog_free(struct bpf_prog *prog); int sk_detach_filter(struct sock *sk); int sk_get_filter(struct sock *sk, sockptr_t optval, unsigned int len); bool sk_filter_charge(struct sock *sk, struct sk_filter *fp); void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp); u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); #define __bpf_call_base_args \ ((u64 (*)(u64, u64, u64, u64, u64, const struct bpf_insn *)) \ (void *)__bpf_call_base) struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog); void bpf_jit_compile(struct bpf_prog *prog); bool bpf_jit_needs_zext(void); bool bpf_jit_inlines_helper_call(s32 imm); bool bpf_jit_supports_subprog_tailcalls(void); bool bpf_jit_supports_percpu_insn(void); bool bpf_jit_supports_kfunc_call(void); bool bpf_jit_supports_far_kfunc_call(void); bool bpf_jit_supports_exceptions(void); bool bpf_jit_supports_ptr_xchg(void); bool bpf_jit_supports_arena(void); bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena); bool bpf_jit_supports_private_stack(void); u64 bpf_arch_uaddress_limit(void); void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie); bool bpf_helper_changes_pkt_data(enum bpf_func_id func_id); static inline bool bpf_dump_raw_ok(const struct cred *cred) { /* Reconstruction of call-sites is dependent on kallsyms, * thus make dump the same restriction. */ return kallsyms_show_value(cred); } struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt); static inline bool xdp_return_frame_no_direct(void) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); return ri->kern_flags & BPF_RI_F_RF_NO_DIRECT; } static inline void xdp_set_return_frame_no_direct(void) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); ri->kern_flags |= BPF_RI_F_RF_NO_DIRECT; } static inline void xdp_clear_return_frame_no_direct(void) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); ri->kern_flags &= ~BPF_RI_F_RF_NO_DIRECT; } static inline int xdp_ok_fwd_dev(const struct net_device *fwd, unsigned int pktlen) { unsigned int len; if (unlikely(!(fwd->flags & IFF_UP))) return -ENETDOWN; len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN; if (pktlen > len) return -EMSGSIZE; return 0; } /* The pair of xdp_do_redirect and xdp_do_flush MUST be called in the * same cpu context. Further for best results no more than a single map * for the do_redirect/do_flush pair should be used. This limitation is * because we only track one map and force a flush when the map changes. * This does not appear to be a real limitation for existing software. */ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, struct bpf_prog *prog); int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *prog); int xdp_do_redirect_frame(struct net_device *dev, struct xdp_buff *xdp, struct xdp_frame *xdpf, struct bpf_prog *prog); void xdp_do_flush(void); void bpf_warn_invalid_xdp_action(struct net_device *dev, struct bpf_prog *prog, u32 act); #ifdef CONFIG_INET struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, struct sock *migrating_sk, u32 hash); #else static inline struct sock * bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, struct sock *migrating_sk, u32 hash) { return NULL; } #endif #ifdef CONFIG_BPF_JIT extern int bpf_jit_enable; extern int bpf_jit_harden; extern int bpf_jit_kallsyms; extern long bpf_jit_limit; extern long bpf_jit_limit_max; typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size); void bpf_jit_fill_hole_with_zero(void *area, unsigned int size); struct bpf_binary_header * bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, unsigned int alignment, bpf_jit_fill_hole_t bpf_fill_ill_insns); void bpf_jit_binary_free(struct bpf_binary_header *hdr); u64 bpf_jit_alloc_exec_limit(void); void *bpf_jit_alloc_exec(unsigned long size); void bpf_jit_free_exec(void *addr); void bpf_jit_free(struct bpf_prog *fp); struct bpf_binary_header * bpf_jit_binary_pack_hdr(const struct bpf_prog *fp); void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns); void bpf_prog_pack_free(void *ptr, u32 size); static inline bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp) { return list_empty(&fp->aux->ksym.lnode) || fp->aux->ksym.lnode.prev == LIST_POISON2; } struct bpf_binary_header * bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **ro_image, unsigned int alignment, struct bpf_binary_header **rw_hdr, u8 **rw_image, bpf_jit_fill_hole_t bpf_fill_ill_insns); int bpf_jit_binary_pack_finalize(struct bpf_binary_header *ro_header, struct bpf_binary_header *rw_header); void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header, struct bpf_binary_header *rw_header); int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, struct bpf_jit_poke_descriptor *poke); int bpf_jit_get_func_addr(const struct bpf_prog *prog, const struct bpf_insn *insn, bool extra_pass, u64 *func_addr, bool *func_addr_fixed); struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *fp); void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other); static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen, u32 pass, void *image) { pr_err("flen=%u proglen=%u pass=%u image=%pK from=%s pid=%d\n", flen, proglen, pass, image, current->comm, task_pid_nr(current)); if (image) print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET, 16, 1, image, proglen, false); } static inline bool bpf_jit_is_ebpf(void) { # ifdef CONFIG_HAVE_EBPF_JIT return true; # else return false; # endif } static inline bool ebpf_jit_enabled(void) { return bpf_jit_enable && bpf_jit_is_ebpf(); } static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp) { return fp->jited && bpf_jit_is_ebpf(); } static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog) { /* These are the prerequisites, should someone ever have the * idea to call blinding outside of them, we make sure to * bail out. */ if (!bpf_jit_is_ebpf()) return false; if (!prog->jit_requested) return false; if (!bpf_jit_harden) return false; if (bpf_jit_harden == 1 && bpf_token_capable(prog->aux->token, CAP_BPF)) return false; return true; } static inline bool bpf_jit_kallsyms_enabled(void) { /* There are a couple of corner cases where kallsyms should * not be enabled f.e. on hardening. */ if (bpf_jit_harden) return false; if (!bpf_jit_kallsyms) return false; if (bpf_jit_kallsyms == 1) return true; return false; } int __bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym); bool is_bpf_text_address(unsigned long addr); int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym); struct bpf_prog *bpf_prog_ksym_find(unsigned long addr); static inline int bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char **modname, char *sym) { int ret = __bpf_address_lookup(addr, size, off, sym); if (ret && modname) *modname = NULL; return ret; } void bpf_prog_kallsyms_add(struct bpf_prog *fp); void bpf_prog_kallsyms_del(struct bpf_prog *fp); #else /* CONFIG_BPF_JIT */ static inline bool ebpf_jit_enabled(void) { return false; } static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog) { return false; } static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp) { return false; } static inline int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, struct bpf_jit_poke_descriptor *poke) { return -ENOTSUPP; } static inline void bpf_jit_free(struct bpf_prog *fp) { bpf_prog_unlock_free(fp); } static inline bool bpf_jit_kallsyms_enabled(void) { return false; } static inline int __bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym) { return 0; } static inline bool is_bpf_text_address(unsigned long addr) { return false; } static inline int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym) { return -ERANGE; } static inline struct bpf_prog *bpf_prog_ksym_find(unsigned long addr) { return NULL; } static inline int bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char **modname, char *sym) { return 0; } static inline void bpf_prog_kallsyms_add(struct bpf_prog *fp) { } static inline void bpf_prog_kallsyms_del(struct bpf_prog *fp) { } #endif /* CONFIG_BPF_JIT */ void bpf_prog_kallsyms_del_all(struct bpf_prog *fp); #define BPF_ANC BIT(15) static inline bool bpf_needs_clear_a(const struct sock_filter *first) { switch (first->code) { case BPF_RET | BPF_K: case BPF_LD | BPF_W | BPF_LEN: return false; case BPF_LD | BPF_W | BPF_ABS: case BPF_LD | BPF_H | BPF_ABS: case BPF_LD | BPF_B | BPF_ABS: if (first->k == SKF_AD_OFF + SKF_AD_ALU_XOR_X) return true; return false; default: return true; } } static inline u16 bpf_anc_helper(const struct sock_filter *ftest) { BUG_ON(ftest->code & BPF_ANC); switch (ftest->code) { case BPF_LD | BPF_W | BPF_ABS: case BPF_LD | BPF_H | BPF_ABS: case BPF_LD | BPF_B | BPF_ABS: #define BPF_ANCILLARY(CODE) case SKF_AD_OFF + SKF_AD_##CODE: \ return BPF_ANC | SKF_AD_##CODE switch (ftest->k) { BPF_ANCILLARY(PROTOCOL); BPF_ANCILLARY(PKTTYPE); BPF_ANCILLARY(IFINDEX); BPF_ANCILLARY(NLATTR); BPF_ANCILLARY(NLATTR_NEST); BPF_ANCILLARY(MARK); BPF_ANCILLARY(QUEUE); BPF_ANCILLARY(HATYPE); BPF_ANCILLARY(RXHASH); BPF_ANCILLARY(CPU); BPF_ANCILLARY(ALU_XOR_X); BPF_ANCILLARY(VLAN_TAG); BPF_ANCILLARY(VLAN_TAG_PRESENT); BPF_ANCILLARY(PAY_OFFSET); BPF_ANCILLARY(RANDOM); BPF_ANCILLARY(VLAN_TPID); } fallthrough; default: return ftest->code; } } void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size); static inline int bpf_tell_extensions(void) { return SKF_AD_MAX; } struct bpf_sock_addr_kern { struct sock *sk; struct sockaddr *uaddr; /* Temporary "register" to make indirect stores to nested structures * defined above. We need three registers to make such a store, but * only two (src and dst) are available at convert_ctx_access time */ u64 tmp_reg; void *t_ctx; /* Attach type specific context. */ u32 uaddrlen; }; struct bpf_sock_ops_kern { struct sock *sk; union { u32 args[4]; u32 reply; u32 replylong[4]; }; struct sk_buff *syn_skb; struct sk_buff *skb; void *skb_data_end; u8 op; u8 is_fullsock; u8 remaining_opt_len; u64 temp; /* temp and everything after is not * initialized to 0 before calling * the BPF program. New fields that * should be initialized to 0 should * be inserted before temp. * temp is scratch storage used by * sock_ops_convert_ctx_access * as temporary storage of a register. */ }; struct bpf_sysctl_kern { struct ctl_table_header *head; const struct ctl_table *table; void *cur_val; size_t cur_len; void *new_val; size_t new_len; int new_updated; int write; loff_t *ppos; /* Temporary "register" for indirect stores to ppos. */ u64 tmp_reg; }; #define BPF_SOCKOPT_KERN_BUF_SIZE 32 struct bpf_sockopt_buf { u8 data[BPF_SOCKOPT_KERN_BUF_SIZE]; }; struct bpf_sockopt_kern { struct sock *sk; u8 *optval; u8 *optval_end; s32 level; s32 optname; s32 optlen; /* for retval in struct bpf_cg_run_ctx */ struct task_struct *current_task; /* Temporary "register" for indirect stores to ppos. */ u64 tmp_reg; }; int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len); struct bpf_sk_lookup_kern { u16 family; u16 protocol; __be16 sport; u16 dport; struct { __be32 saddr; __be32 daddr; } v4; struct { const struct in6_addr *saddr; const struct in6_addr *daddr; } v6; struct sock *selected_sk; u32 ingress_ifindex; bool no_reuseport; }; extern struct static_key_false bpf_sk_lookup_enabled; /* Runners for BPF_SK_LOOKUP programs to invoke on socket lookup. * * Allowed return values for a BPF SK_LOOKUP program are SK_PASS and * SK_DROP. Their meaning is as follows: * * SK_PASS && ctx.selected_sk != NULL: use selected_sk as lookup result * SK_PASS && ctx.selected_sk == NULL: continue to htable-based socket lookup * SK_DROP : terminate lookup with -ECONNREFUSED * * This macro aggregates return values and selected sockets from * multiple BPF programs according to following rules in order: * * 1. If any program returned SK_PASS and a non-NULL ctx.selected_sk, * macro result is SK_PASS and last ctx.selected_sk is used. * 2. If any program returned SK_DROP return value, * macro result is SK_DROP. * 3. Otherwise result is SK_PASS and ctx.selected_sk is NULL. * * Caller must ensure that the prog array is non-NULL, and that the * array as well as the programs it contains remain valid. */ #define BPF_PROG_SK_LOOKUP_RUN_ARRAY(array, ctx, func) \ ({ \ struct bpf_sk_lookup_kern *_ctx = &(ctx); \ struct bpf_prog_array_item *_item; \ struct sock *_selected_sk = NULL; \ bool _no_reuseport = false; \ struct bpf_prog *_prog; \ bool _all_pass = true; \ u32 _ret; \ \ migrate_disable(); \ _item = &(array)->items[0]; \ while ((_prog = READ_ONCE(_item->prog))) { \ /* restore most recent selection */ \ _ctx->selected_sk = _selected_sk; \ _ctx->no_reuseport = _no_reuseport; \ \ _ret = func(_prog, _ctx); \ if (_ret == SK_PASS && _ctx->selected_sk) { \ /* remember last non-NULL socket */ \ _selected_sk = _ctx->selected_sk; \ _no_reuseport = _ctx->no_reuseport; \ } else if (_ret == SK_DROP && _all_pass) { \ _all_pass = false; \ } \ _item++; \ } \ _ctx->selected_sk = _selected_sk; \ _ctx->no_reuseport = _no_reuseport; \ migrate_enable(); \ _all_pass || _selected_sk ? SK_PASS : SK_DROP; \ }) static inline bool bpf_sk_lookup_run_v4(const struct net *net, int protocol, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 dport, const int ifindex, struct sock **psk) { struct bpf_prog_array *run_array; struct sock *selected_sk = NULL; bool no_reuseport = false; rcu_read_lock(); run_array = rcu_dereference(net->bpf.run_array[NETNS_BPF_SK_LOOKUP]); if (run_array) { struct bpf_sk_lookup_kern ctx = { .family = AF_INET, .protocol = protocol, .v4.saddr = saddr, .v4.daddr = daddr, .sport = sport, .dport = dport, .ingress_ifindex = ifindex, }; u32 act; act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, bpf_prog_run); if (act == SK_PASS) { selected_sk = ctx.selected_sk; no_reuseport = ctx.no_reuseport; } else { selected_sk = ERR_PTR(-ECONNREFUSED); } } rcu_read_unlock(); *psk = selected_sk; return no_reuseport; } #if IS_ENABLED(CONFIG_IPV6) static inline bool bpf_sk_lookup_run_v6(const struct net *net, int protocol, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const u16 dport, const int ifindex, struct sock **psk) { struct bpf_prog_array *run_array; struct sock *selected_sk = NULL; bool no_reuseport = false; rcu_read_lock(); run_array = rcu_dereference(net->bpf.run_array[NETNS_BPF_SK_LOOKUP]); if (run_array) { struct bpf_sk_lookup_kern ctx = { .family = AF_INET6, .protocol = protocol, .v6.saddr = saddr, .v6.daddr = daddr, .sport = sport, .dport = dport, .ingress_ifindex = ifindex, }; u32 act; act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, bpf_prog_run); if (act == SK_PASS) { selected_sk = ctx.selected_sk; no_reuseport = ctx.no_reuseport; } else { selected_sk = ERR_PTR(-ECONNREFUSED); } } rcu_read_unlock(); *psk = selected_sk; return no_reuseport; } #endif /* IS_ENABLED(CONFIG_IPV6) */ static __always_inline long __bpf_xdp_redirect_map(struct bpf_map *map, u64 index, u64 flags, const u64 flag_mask, void *lookup_elem(struct bpf_map *map, u32 key)) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); const u64 action_mask = XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX; /* Lower bits of the flags are used as return code on lookup failure */ if (unlikely(flags & ~(action_mask | flag_mask))) return XDP_ABORTED; ri->tgt_value = lookup_elem(map, index); if (unlikely(!ri->tgt_value) && !(flags & BPF_F_BROADCAST)) { /* If the lookup fails we want to clear out the state in the * redirect_info struct completely, so that if an eBPF program * performs multiple lookups, the last one always takes * precedence. */ ri->map_id = INT_MAX; /* Valid map id idr range: [1,INT_MAX[ */ ri->map_type = BPF_MAP_TYPE_UNSPEC; return flags & action_mask; } ri->tgt_index = index; ri->map_id = map->id; ri->map_type = map->map_type; if (flags & BPF_F_BROADCAST) { WRITE_ONCE(ri->map, map); ri->flags = flags; } else { WRITE_ONCE(ri->map, NULL); ri->flags = 0; } return XDP_REDIRECT; } #ifdef CONFIG_NET int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len); int __bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags); int __bpf_xdp_load_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len); int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len); void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len); void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf, unsigned long len, bool flush); #else /* CONFIG_NET */ static inline int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len) { return -EOPNOTSUPP; } static inline int __bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) { return -EOPNOTSUPP; } static inline int __bpf_xdp_load_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len) { return -EOPNOTSUPP; } static inline int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len) { return -EOPNOTSUPP; } static inline void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len) { return NULL; } static inline void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf, unsigned long len, bool flush) { } #endif /* CONFIG_NET */ #endif /* __LINUX_FILTER_H__ */ |
| 159 159 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM workqueue #if !defined(_TRACE_WORKQUEUE_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_WORKQUEUE_H #include <linux/tracepoint.h> #include <linux/workqueue.h> struct pool_workqueue; /** * workqueue_queue_work - called when a work gets queued * @req_cpu: the requested cpu * @pwq: pointer to struct pool_workqueue * @work: pointer to struct work_struct * * This event occurs when a work is queued immediately or once a * delayed work is actually queued on a workqueue (ie: once the delay * has been reached). */ TRACE_EVENT(workqueue_queue_work, TP_PROTO(int req_cpu, struct pool_workqueue *pwq, struct work_struct *work), TP_ARGS(req_cpu, pwq, work), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) __string( workqueue, pwq->wq->name) __field( int, req_cpu ) __field( int, cpu ) ), TP_fast_assign( __entry->work = work; __entry->function = work->func; __assign_str(workqueue); __entry->req_cpu = req_cpu; __entry->cpu = pwq->pool->cpu; ), TP_printk("work struct=%p function=%ps workqueue=%s req_cpu=%d cpu=%d", __entry->work, __entry->function, __get_str(workqueue), __entry->req_cpu, __entry->cpu) ); /** * workqueue_activate_work - called when a work gets activated * @work: pointer to struct work_struct * * This event occurs when a queued work is put on the active queue, * which happens immediately after queueing unless @max_active limit * is reached. */ TRACE_EVENT(workqueue_activate_work, TP_PROTO(struct work_struct *work), TP_ARGS(work), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) ), TP_fast_assign( __entry->work = work; __entry->function = work->func; ), TP_printk("work struct %p function=%ps ", __entry->work, __entry->function) ); /** * workqueue_execute_start - called immediately before the workqueue callback * @work: pointer to struct work_struct * * Allows to track workqueue execution. */ TRACE_EVENT(workqueue_execute_start, TP_PROTO(struct work_struct *work), TP_ARGS(work), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) ), TP_fast_assign( __entry->work = work; __entry->function = work->func; ), TP_printk("work struct %p: function %ps", __entry->work, __entry->function) ); /** * workqueue_execute_end - called immediately after the workqueue callback * @work: pointer to struct work_struct * @function: pointer to worker function * * Allows to track workqueue execution. */ TRACE_EVENT(workqueue_execute_end, TP_PROTO(struct work_struct *work, work_func_t function), TP_ARGS(work, function), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) ), TP_fast_assign( __entry->work = work; __entry->function = function; ), TP_printk("work struct %p: function %ps", __entry->work, __entry->function) ); #endif /* _TRACE_WORKQUEUE_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 166 166 166 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 | // SPDX-License-Identifier: GPL-2.0-only /* * Fixmap manipulation code */ #include <linux/bug.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/libfdt.h> #include <linux/memory.h> #include <linux/mm.h> #include <linux/sizes.h> #include <asm/fixmap.h> #include <asm/kernel-pgtable.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> /* ensure that the fixmap region does not grow down into the PCI I/O region */ static_assert(FIXADDR_TOT_START > PCI_IO_END); #define NR_BM_PTE_TABLES \ SPAN_NR_ENTRIES(FIXADDR_TOT_START, FIXADDR_TOP, PMD_SHIFT) #define NR_BM_PMD_TABLES \ SPAN_NR_ENTRIES(FIXADDR_TOT_START, FIXADDR_TOP, PUD_SHIFT) static_assert(NR_BM_PMD_TABLES == 1); #define __BM_TABLE_IDX(addr, shift) \ (((addr) >> (shift)) - (FIXADDR_TOT_START >> (shift))) #define BM_PTE_TABLE_IDX(addr) __BM_TABLE_IDX(addr, PMD_SHIFT) static pte_t bm_pte[NR_BM_PTE_TABLES][PTRS_PER_PTE] __page_aligned_bss; static pmd_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss __maybe_unused; static pud_t bm_pud[PTRS_PER_PUD] __page_aligned_bss __maybe_unused; static inline pte_t *fixmap_pte(unsigned long addr) { return &bm_pte[BM_PTE_TABLE_IDX(addr)][pte_index(addr)]; } static void __init early_fixmap_init_pte(pmd_t *pmdp, unsigned long addr) { pmd_t pmd = READ_ONCE(*pmdp); pte_t *ptep; if (pmd_none(pmd)) { ptep = bm_pte[BM_PTE_TABLE_IDX(addr)]; __pmd_populate(pmdp, __pa_symbol(ptep), PMD_TYPE_TABLE | PMD_TABLE_AF); } } static void __init early_fixmap_init_pmd(pud_t *pudp, unsigned long addr, unsigned long end) { unsigned long next; pud_t pud = READ_ONCE(*pudp); pmd_t *pmdp; if (pud_none(pud)) __pud_populate(pudp, __pa_symbol(bm_pmd), PUD_TYPE_TABLE | PUD_TABLE_AF); pmdp = pmd_offset_kimg(pudp, addr); do { next = pmd_addr_end(addr, end); early_fixmap_init_pte(pmdp, addr); } while (pmdp++, addr = next, addr != end); } static void __init early_fixmap_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end) { p4d_t p4d = READ_ONCE(*p4dp); pud_t *pudp; if (CONFIG_PGTABLE_LEVELS > 3 && !p4d_none(p4d) && p4d_page_paddr(p4d) != __pa_symbol(bm_pud)) { /* * We only end up here if the kernel mapping and the fixmap * share the top level pgd entry, which should only happen on * 16k/4 levels configurations. */ BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES)); } if (p4d_none(p4d)) __p4d_populate(p4dp, __pa_symbol(bm_pud), P4D_TYPE_TABLE | P4D_TABLE_AF); pudp = pud_offset_kimg(p4dp, addr); early_fixmap_init_pmd(pudp, addr, end); } /* * The p*d_populate functions call virt_to_phys implicitly so they can't be used * directly on kernel symbols (bm_p*d). This function is called too early to use * lm_alias so __p*d_populate functions must be used to populate with the * physical address from __pa_symbol. */ void __init early_fixmap_init(void) { unsigned long addr = FIXADDR_TOT_START; unsigned long end = FIXADDR_TOP; pgd_t *pgdp = pgd_offset_k(addr); p4d_t *p4dp = p4d_offset_kimg(pgdp, addr); early_fixmap_init_pud(p4dp, addr, end); } /* * Unusually, this is also called in IRQ context (ghes_iounmap_irq) so if we * ever need to use IPIs for TLB broadcasting, then we're in trouble here. */ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags) { unsigned long addr = __fix_to_virt(idx); pte_t *ptep; BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses); ptep = fixmap_pte(addr); if (pgprot_val(flags)) { __set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, flags)); } else { __pte_clear(&init_mm, addr, ptep); flush_tlb_kernel_range(addr, addr+PAGE_SIZE); } } void *__init fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot) { const u64 dt_virt_base = __fix_to_virt(FIX_FDT); phys_addr_t dt_phys_base; int offset; void *dt_virt; /* * Check whether the physical FDT address is set and meets the minimum * alignment requirement. Since we are relying on MIN_FDT_ALIGN to be * at least 8 bytes so that we can always access the magic and size * fields of the FDT header after mapping the first chunk, double check * here if that is indeed the case. */ BUILD_BUG_ON(MIN_FDT_ALIGN < 8); if (!dt_phys || dt_phys % MIN_FDT_ALIGN) return NULL; dt_phys_base = round_down(dt_phys, PAGE_SIZE); offset = dt_phys % PAGE_SIZE; dt_virt = (void *)dt_virt_base + offset; /* map the first chunk so we can read the size from the header */ create_mapping_noalloc(dt_phys_base, dt_virt_base, PAGE_SIZE, prot); if (fdt_magic(dt_virt) != FDT_MAGIC) return NULL; *size = fdt_totalsize(dt_virt); if (*size > MAX_FDT_SIZE) return NULL; if (offset + *size > PAGE_SIZE) { create_mapping_noalloc(dt_phys_base, dt_virt_base, offset + *size, prot); } return dt_virt; } |
| 2 7 6 343 64 344 64 123 55 79 79 7 45 52 29 21 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HUGETLB_H #define _LINUX_HUGETLB_H #include <linux/mm.h> #include <linux/mm_types.h> #include <linux/mmdebug.h> #include <linux/fs.h> #include <linux/hugetlb_inline.h> #include <linux/cgroup.h> #include <linux/page_ref.h> #include <linux/list.h> #include <linux/kref.h> #include <linux/pgtable.h> #include <linux/gfp.h> #include <linux/userfaultfd_k.h> struct ctl_table; struct user_struct; struct mmu_gather; struct node; void free_huge_folio(struct folio *folio); #ifdef CONFIG_HUGETLB_PAGE #include <linux/pagemap.h> #include <linux/shm.h> #include <asm/tlbflush.h> /* * For HugeTLB page, there are more metadata to save in the struct page. But * the head struct page cannot meet our needs, so we have to abuse other tail * struct page to store the metadata. */ #define __NR_USED_SUBPAGE 3 struct hugepage_subpool { spinlock_t lock; long count; long max_hpages; /* Maximum huge pages or -1 if no maximum. */ long used_hpages; /* Used count against maximum, includes */ /* both allocated and reserved pages. */ struct hstate *hstate; long min_hpages; /* Minimum huge pages or -1 if no minimum. */ long rsv_hpages; /* Pages reserved against global pool to */ /* satisfy minimum size. */ }; struct resv_map { struct kref refs; spinlock_t lock; struct list_head regions; long adds_in_progress; struct list_head region_cache; long region_cache_count; struct rw_semaphore rw_sema; #ifdef CONFIG_CGROUP_HUGETLB /* * On private mappings, the counter to uncharge reservations is stored * here. If these fields are 0, then either the mapping is shared, or * cgroup accounting is disabled for this resv_map. */ struct page_counter *reservation_counter; unsigned long pages_per_hpage; struct cgroup_subsys_state *css; #endif }; /* * Region tracking -- allows tracking of reservations and instantiated pages * across the pages in a mapping. * * The region data structures are embedded into a resv_map and protected * by a resv_map's lock. The set of regions within the resv_map represent * reservations for huge pages, or huge pages that have already been * instantiated within the map. The from and to elements are huge page * indices into the associated mapping. from indicates the starting index * of the region. to represents the first index past the end of the region. * * For example, a file region structure with from == 0 and to == 4 represents * four huge pages in a mapping. It is important to note that the to element * represents the first element past the end of the region. This is used in * arithmetic as 4(to) - 0(from) = 4 huge pages in the region. * * Interval notation of the form [from, to) will be used to indicate that * the endpoint from is inclusive and to is exclusive. */ struct file_region { struct list_head link; long from; long to; #ifdef CONFIG_CGROUP_HUGETLB /* * On shared mappings, each reserved region appears as a struct * file_region in resv_map. These fields hold the info needed to * uncharge each reservation. */ struct page_counter *reservation_counter; struct cgroup_subsys_state *css; #endif }; struct hugetlb_vma_lock { struct kref refs; struct rw_semaphore rw_sema; struct vm_area_struct *vma; }; extern struct resv_map *resv_map_alloc(void); void resv_map_release(struct kref *ref); extern spinlock_t hugetlb_lock; extern int hugetlb_max_hstate __read_mostly; #define for_each_hstate(h) \ for ((h) = hstates; (h) < &hstates[hugetlb_max_hstate]; (h)++) struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, long min_hpages); void hugepage_put_subpool(struct hugepage_subpool *spool); void hugetlb_dup_vma_private(struct vm_area_struct *vma); void clear_vma_resv_huge_pages(struct vm_area_struct *vma); int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long len); int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *, struct vm_area_struct *); void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long, struct page *, zap_flags_t); void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page, zap_flags_t zap_flags); void hugetlb_report_meminfo(struct seq_file *); int hugetlb_report_node_meminfo(char *buf, int len, int nid); void hugetlb_show_meminfo_node(int nid); unsigned long hugetlb_total_pages(void); vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); #ifdef CONFIG_USERFAULTFD int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, struct folio **foliop); #endif /* CONFIG_USERFAULTFD */ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags); long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); bool isolate_hugetlb(struct folio *folio, struct list_head *list); int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison); int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); void folio_putback_active_hugetlb(struct folio *folio); void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason); void hugetlb_fix_reserve_counts(struct inode *inode); extern struct mutex *hugetlb_fault_mutex_table; u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx); pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud); bool hugetlbfs_pagecache_present(struct hstate *h, struct vm_area_struct *vma, unsigned long address); struct address_space *hugetlb_folio_mapping_lock_write(struct folio *folio); extern int sysctl_hugetlb_shm_group; extern struct list_head huge_boot_pages[MAX_NUMNODES]; /* arch callbacks */ #ifndef CONFIG_HIGHPTE /* * pte_offset_huge() and pte_alloc_huge() are helpers for those architectures * which may go down to the lowest PTE level in their huge_pte_offset() and * huge_pte_alloc(): to avoid reliance on pte_offset_map() without pte_unmap(). */ static inline pte_t *pte_offset_huge(pmd_t *pmd, unsigned long address) { return pte_offset_kernel(pmd, address); } static inline pte_t *pte_alloc_huge(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { return pte_alloc(mm, pmd) ? NULL : pte_offset_huge(pmd, address); } #endif pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz); /* * huge_pte_offset(): Walk the hugetlb pgtable until the last level PTE. * Returns the pte_t* if found, or NULL if the address is not mapped. * * IMPORTANT: we should normally not directly call this function, instead * this is only a common interface to implement arch-specific * walker. Please use hugetlb_walk() instead, because that will attempt to * verify the locking for you. * * Since this function will walk all the pgtable pages (including not only * high-level pgtable page, but also PUD entry that can be unshared * concurrently for VM_SHARED), the caller of this function should be * responsible of its thread safety. One can follow this rule: * * (1) For private mappings: pmd unsharing is not possible, so holding the * mmap_lock for either read or write is sufficient. Most callers * already hold the mmap_lock, so normally, no special action is * required. * * (2) For shared mappings: pmd unsharing is possible (so the PUD-ranged * pgtable page can go away from under us! It can be done by a pmd * unshare with a follow up munmap() on the other process), then we * need either: * * (2.1) hugetlb vma lock read or write held, to make sure pmd unshare * won't happen upon the range (it also makes sure the pte_t we * read is the right and stable one), or, * * (2.2) hugetlb mapping i_mmap_rwsem lock held read or write, to make * sure even if unshare happened the racy unmap() will wait until * i_mmap_rwsem is released. * * Option (2.1) is the safest, which guarantees pte stability from pmd * sharing pov, until the vma lock released. Option (2.2) doesn't protect * a concurrent pmd unshare, but it makes sure the pgtable page is safe to * access. */ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); unsigned long hugetlb_mask_last_page(struct hstate *h); int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end); extern void __hugetlb_zap_begin(struct vm_area_struct *vma, unsigned long *begin, unsigned long *end); extern void __hugetlb_zap_end(struct vm_area_struct *vma, struct zap_details *details); static inline void hugetlb_zap_begin(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { if (is_vm_hugetlb_page(vma)) __hugetlb_zap_begin(vma, start, end); } static inline void hugetlb_zap_end(struct vm_area_struct *vma, struct zap_details *details) { if (is_vm_hugetlb_page(vma)) __hugetlb_zap_end(vma, details); } void hugetlb_vma_lock_read(struct vm_area_struct *vma); void hugetlb_vma_unlock_read(struct vm_area_struct *vma); void hugetlb_vma_lock_write(struct vm_area_struct *vma); void hugetlb_vma_unlock_write(struct vm_area_struct *vma); int hugetlb_vma_trylock_write(struct vm_area_struct *vma); void hugetlb_vma_assert_locked(struct vm_area_struct *vma); void hugetlb_vma_lock_release(struct kref *kref); long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags); bool is_hugetlb_entry_migration(pte_t pte); bool is_hugetlb_entry_hwpoisoned(pte_t pte); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); #else /* !CONFIG_HUGETLB_PAGE */ static inline void hugetlb_dup_vma_private(struct vm_area_struct *vma) { } static inline void clear_vma_resv_huge_pages(struct vm_area_struct *vma) { } static inline unsigned long hugetlb_total_pages(void) { return 0; } static inline struct address_space *hugetlb_folio_mapping_lock_write( struct folio *folio) { return NULL; } static inline int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return 0; } static inline void adjust_range_if_pmd_sharing_possible( struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { } static inline void hugetlb_zap_begin( struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { } static inline void hugetlb_zap_end( struct vm_area_struct *vma, struct zap_details *details) { } static inline int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { BUG(); return 0; } static inline int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long len) { BUG(); return 0; } static inline void hugetlb_report_meminfo(struct seq_file *m) { } static inline int hugetlb_report_node_meminfo(char *buf, int len, int nid) { return 0; } static inline void hugetlb_show_meminfo_node(int nid) { } static inline int prepare_hugepage_range(struct file *file, unsigned long addr, unsigned long len) { return -EINVAL; } static inline void hugetlb_vma_lock_read(struct vm_area_struct *vma) { } static inline void hugetlb_vma_unlock_read(struct vm_area_struct *vma) { } static inline void hugetlb_vma_lock_write(struct vm_area_struct *vma) { } static inline void hugetlb_vma_unlock_write(struct vm_area_struct *vma) { } static inline int hugetlb_vma_trylock_write(struct vm_area_struct *vma) { return 1; } static inline void hugetlb_vma_assert_locked(struct vm_area_struct *vma) { } static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, unsigned long len) { return 0; } static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { BUG(); } #ifdef CONFIG_USERFAULTFD static inline int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, struct folio **foliop) { BUG(); return 0; } #endif /* CONFIG_USERFAULTFD */ static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { return NULL; } static inline bool isolate_hugetlb(struct folio *folio, struct list_head *list) { return false; } static inline int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison) { return 0; } static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared) { return 0; } static inline void folio_putback_active_hugetlb(struct folio *folio) { } static inline void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason) { } static inline long hugetlb_change_protection( struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags) { return 0; } static inline void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page, zap_flags_t zap_flags) { BUG(); } static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags) { BUG(); return 0; } static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { } #endif /* !CONFIG_HUGETLB_PAGE */ #ifndef pgd_write static inline int pgd_write(pgd_t pgd) { BUG(); return 0; } #endif #define HUGETLB_ANON_FILE "anon_hugepage" enum { /* * The file will be used as an shm file so shmfs accounting rules * apply */ HUGETLB_SHMFS_INODE = 1, /* * The file is being created on the internal vfs mount and shmfs * accounting rules do not apply */ HUGETLB_ANONHUGE_INODE = 2, }; #ifdef CONFIG_HUGETLBFS struct hugetlbfs_sb_info { long max_inodes; /* inodes allowed */ long free_inodes; /* inodes free */ spinlock_t stat_lock; struct hstate *hstate; struct hugepage_subpool *spool; kuid_t uid; kgid_t gid; umode_t mode; }; static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb) { return sb->s_fs_info; } struct hugetlbfs_inode_info { struct inode vfs_inode; unsigned int seals; }; static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode) { return container_of(inode, struct hugetlbfs_inode_info, vfs_inode); } extern const struct vm_operations_struct hugetlb_vm_ops; struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct, int creat_flags, int page_size_log); static inline bool is_file_hugepages(const struct file *file) { return file->f_op->fop_flags & FOP_HUGE_PAGES; } static inline struct hstate *hstate_inode(struct inode *i) { return HUGETLBFS_SB(i->i_sb)->hstate; } #else /* !CONFIG_HUGETLBFS */ #define is_file_hugepages(file) false static inline struct file * hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag, int creat_flags, int page_size_log) { return ERR_PTR(-ENOSYS); } static inline struct hstate *hstate_inode(struct inode *i) { return NULL; } #endif /* !CONFIG_HUGETLBFS */ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); /* * huegtlb page specific state flags. These flags are located in page.private * of the hugetlb head page. Functions created via the below macros should be * used to manipulate these flags. * * HPG_restore_reserve - Set when a hugetlb page consumes a reservation at * allocation time. Cleared when page is fully instantiated. Free * routine checks flag to restore a reservation on error paths. * Synchronization: Examined or modified by code that knows it has * the only reference to page. i.e. After allocation but before use * or when the page is being freed. * HPG_migratable - Set after a newly allocated page is added to the page * cache and/or page tables. Indicates the page is a candidate for * migration. * Synchronization: Initially set after new page allocation with no * locking. When examined and modified during migration processing * (isolate, migrate, putback) the hugetlb_lock is held. * HPG_temporary - Set on a page that is temporarily allocated from the buddy * allocator. Typically used for migration target pages when no pages * are available in the pool. The hugetlb free page path will * immediately free pages with this flag set to the buddy allocator. * Synchronization: Can be set after huge page allocation from buddy when * code knows it has only reference. All other examinations and * modifications require hugetlb_lock. * HPG_freed - Set when page is on the free lists. * Synchronization: hugetlb_lock held for examination and modification. * HPG_vmemmap_optimized - Set when the vmemmap pages of the page are freed. * HPG_raw_hwp_unreliable - Set when the hugetlb page has a hwpoison sub-page * that is not tracked by raw_hwp_page list. */ enum hugetlb_page_flags { HPG_restore_reserve = 0, HPG_migratable, HPG_temporary, HPG_freed, HPG_vmemmap_optimized, HPG_raw_hwp_unreliable, __NR_HPAGEFLAGS, }; /* * Macros to create test, set and clear function definitions for * hugetlb specific page flags. */ #ifdef CONFIG_HUGETLB_PAGE #define TESTHPAGEFLAG(uname, flname) \ static __always_inline \ bool folio_test_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ return test_bit(HPG_##flname, private); \ } #define SETHPAGEFLAG(uname, flname) \ static __always_inline \ void folio_set_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ set_bit(HPG_##flname, private); \ } #define CLEARHPAGEFLAG(uname, flname) \ static __always_inline \ void folio_clear_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ clear_bit(HPG_##flname, private); \ } #else #define TESTHPAGEFLAG(uname, flname) \ static inline bool \ folio_test_hugetlb_##flname(struct folio *folio) \ { return 0; } #define SETHPAGEFLAG(uname, flname) \ static inline void \ folio_set_hugetlb_##flname(struct folio *folio) \ { } #define CLEARHPAGEFLAG(uname, flname) \ static inline void \ folio_clear_hugetlb_##flname(struct folio *folio) \ { } #endif #define HPAGEFLAG(uname, flname) \ TESTHPAGEFLAG(uname, flname) \ SETHPAGEFLAG(uname, flname) \ CLEARHPAGEFLAG(uname, flname) \ /* * Create functions associated with hugetlb page flags */ HPAGEFLAG(RestoreReserve, restore_reserve) HPAGEFLAG(Migratable, migratable) HPAGEFLAG(Temporary, temporary) HPAGEFLAG(Freed, freed) HPAGEFLAG(VmemmapOptimized, vmemmap_optimized) HPAGEFLAG(RawHwpUnreliable, raw_hwp_unreliable) #ifdef CONFIG_HUGETLB_PAGE #define HSTATE_NAME_LEN 32 /* Defines one hugetlb page size */ struct hstate { struct mutex resize_lock; struct lock_class_key resize_key; int next_nid_to_alloc; int next_nid_to_free; unsigned int order; unsigned int demote_order; unsigned long mask; unsigned long max_huge_pages; unsigned long nr_huge_pages; unsigned long free_huge_pages; unsigned long resv_huge_pages; unsigned long surplus_huge_pages; unsigned long nr_overcommit_huge_pages; struct list_head hugepage_activelist; struct list_head hugepage_freelists[MAX_NUMNODES]; unsigned int max_huge_pages_node[MAX_NUMNODES]; unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; char name[HSTATE_NAME_LEN]; }; struct huge_bootmem_page { struct list_head list; struct hstate *hstate; }; int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list); struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve); struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback); struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask); int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping, pgoff_t idx); void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct folio *folio); /* arch callback */ int __init __alloc_bootmem_huge_page(struct hstate *h, int nid); int __init alloc_bootmem_huge_page(struct hstate *h, int nid); bool __init hugetlb_node_alloc_supported(void); void __init hugetlb_add_hstate(unsigned order); bool __init arch_hugetlb_valid_size(unsigned long size); struct hstate *size_to_hstate(unsigned long size); #ifndef HUGE_MAX_HSTATE #define HUGE_MAX_HSTATE 1 #endif extern struct hstate hstates[HUGE_MAX_HSTATE]; extern unsigned int default_hstate_idx; #define default_hstate (hstates[default_hstate_idx]) static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio) { return folio->_hugetlb_subpool; } static inline void hugetlb_set_folio_subpool(struct folio *folio, struct hugepage_subpool *subpool) { folio->_hugetlb_subpool = subpool; } static inline struct hstate *hstate_file(struct file *f) { return hstate_inode(file_inode(f)); } static inline struct hstate *hstate_sizelog(int page_size_log) { if (!page_size_log) return &default_hstate; if (page_size_log < BITS_PER_LONG) return size_to_hstate(1UL << page_size_log); return NULL; } static inline struct hstate *hstate_vma(struct vm_area_struct *vma) { return hstate_file(vma->vm_file); } static inline unsigned long huge_page_size(const struct hstate *h) { return (unsigned long)PAGE_SIZE << h->order; } extern unsigned long vma_kernel_pagesize(struct vm_area_struct *vma); extern unsigned long vma_mmu_pagesize(struct vm_area_struct *vma); static inline unsigned long huge_page_mask(struct hstate *h) { return h->mask; } static inline unsigned int huge_page_order(struct hstate *h) { return h->order; } static inline unsigned huge_page_shift(struct hstate *h) { return h->order + PAGE_SHIFT; } static inline bool hstate_is_gigantic(struct hstate *h) { return huge_page_order(h) > MAX_PAGE_ORDER; } static inline unsigned int pages_per_huge_page(const struct hstate *h) { return 1 << h->order; } static inline unsigned int blocks_per_huge_page(struct hstate *h) { return huge_page_size(h) / 512; } static inline struct folio *filemap_lock_hugetlb_folio(struct hstate *h, struct address_space *mapping, pgoff_t idx) { return filemap_lock_folio(mapping, idx << huge_page_order(h)); } #include <asm/hugetlb.h> #ifndef is_hugepage_only_range static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, unsigned long len) { return 0; } #define is_hugepage_only_range is_hugepage_only_range #endif #ifndef arch_clear_hugetlb_flags static inline void arch_clear_hugetlb_flags(struct folio *folio) { } #define arch_clear_hugetlb_flags arch_clear_hugetlb_flags #endif #ifndef arch_make_huge_pte static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) { return pte_mkhuge(entry); } #endif static inline struct hstate *folio_hstate(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio); return size_to_hstate(folio_size(folio)); } static inline unsigned hstate_index_to_shift(unsigned index) { return hstates[index].order + PAGE_SHIFT; } static inline int hstate_index(struct hstate *h) { return h - hstates; } int dissolve_free_hugetlb_folio(struct folio *folio); int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn); #ifdef CONFIG_MEMORY_FAILURE extern void folio_clear_hugetlb_hwpoison(struct folio *folio); #else static inline void folio_clear_hugetlb_hwpoison(struct folio *folio) { } #endif #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION #ifndef arch_hugetlb_migration_supported static inline bool arch_hugetlb_migration_supported(struct hstate *h) { if ((huge_page_shift(h) == PMD_SHIFT) || (huge_page_shift(h) == PUD_SHIFT) || (huge_page_shift(h) == PGDIR_SHIFT)) return true; else return false; } #endif #else static inline bool arch_hugetlb_migration_supported(struct hstate *h) { return false; } #endif static inline bool hugepage_migration_supported(struct hstate *h) { return arch_hugetlb_migration_supported(h); } /* * Movability check is different as compared to migration check. * It determines whether or not a huge page should be placed on * movable zone or not. Movability of any huge page should be * required only if huge page size is supported for migration. * There won't be any reason for the huge page to be movable if * it is not migratable to start with. Also the size of the huge * page should be large enough to be placed under a movable zone * and still feasible enough to be migratable. Just the presence * in movable zone does not make the migration feasible. * * So even though large huge page sizes like the gigantic ones * are migratable they should not be movable because its not * feasible to migrate them from movable zone. */ static inline bool hugepage_movable_supported(struct hstate *h) { if (!hugepage_migration_supported(h)) return false; if (hstate_is_gigantic(h)) return false; return true; } /* Movability of hugepages depends on migration support. */ static inline gfp_t htlb_alloc_mask(struct hstate *h) { gfp_t gfp = __GFP_COMP | __GFP_NOWARN; gfp |= hugepage_movable_supported(h) ? GFP_HIGHUSER_MOVABLE : GFP_HIGHUSER; return gfp; } static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) { gfp_t modified_mask = htlb_alloc_mask(h); /* Some callers might want to enforce node */ modified_mask |= (gfp_mask & __GFP_THISNODE); modified_mask |= (gfp_mask & __GFP_NOWARN); return modified_mask; } static inline bool htlb_allow_alloc_fallback(int reason) { bool allowed_fallback = false; /* * Note: the memory offline, memory failure and migration syscalls will * be allowed to fallback to other nodes due to lack of a better chioce, * that might break the per-node hugetlb pool. While other cases will * set the __GFP_THISNODE to avoid breaking the per-node hugetlb pool. */ switch (reason) { case MR_MEMORY_HOTPLUG: case MR_MEMORY_FAILURE: case MR_SYSCALL: case MR_MEMPOLICY_MBIND: allowed_fallback = true; break; default: break; } return allowed_fallback; } static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { const unsigned long size = huge_page_size(h); VM_WARN_ON(size == PAGE_SIZE); /* * hugetlb must use the exact same PT locks as core-mm page table * walkers would. When modifying a PTE table, hugetlb must take the * PTE PT lock, when modifying a PMD table, hugetlb must take the PMD * PT lock etc. * * The expectation is that any hugetlb folio smaller than a PMD is * always mapped into a single PTE table and that any hugetlb folio * smaller than a PUD (but at least as big as a PMD) is always mapped * into a single PMD table. * * If that does not hold for an architecture, then that architecture * must disable split PT locks such that all *_lockptr() functions * will give us the same result: the per-MM PT lock. * * Note that with e.g., CONFIG_PGTABLE_LEVELS=2 where * PGDIR_SIZE==P4D_SIZE==PUD_SIZE==PMD_SIZE, we'd use pud_lockptr() * and core-mm would use pmd_lockptr(). However, in such configurations * split PMD locks are disabled -- they don't make sense on a single * PGDIR page table -- and the end result is the same. */ if (size >= PUD_SIZE) return pud_lockptr(mm, (pud_t *) pte); else if (size >= PMD_SIZE || IS_ENABLED(CONFIG_HIGHPTE)) return pmd_lockptr(mm, (pmd_t *) pte); /* pte_alloc_huge() only applies with !CONFIG_HIGHPTE */ return ptep_lockptr(mm, pte); } #ifndef hugepages_supported /* * Some platform decide whether they support huge pages at boot * time. Some of them, such as powerpc, set HPAGE_SHIFT to 0 * when there is no such support */ #define hugepages_supported() (HPAGE_SHIFT != 0) #endif void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm); static inline void hugetlb_count_init(struct mm_struct *mm) { atomic_long_set(&mm->hugetlb_usage, 0); } static inline void hugetlb_count_add(long l, struct mm_struct *mm) { atomic_long_add(l, &mm->hugetlb_usage); } static inline void hugetlb_count_sub(long l, struct mm_struct *mm) { atomic_long_sub(l, &mm->hugetlb_usage); } #ifndef huge_ptep_modify_prot_start #define huge_ptep_modify_prot_start huge_ptep_modify_prot_start static inline pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); } #endif #ifndef huge_ptep_modify_prot_commit #define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { unsigned long psize = huge_page_size(hstate_vma(vma)); set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize); } #endif #ifdef CONFIG_NUMA void hugetlb_register_node(struct node *node); void hugetlb_unregister_node(struct node *node); #endif /* * Check if a given raw @page in a hugepage is HWPOISON. */ bool is_raw_hwpoison_page_in_hugepage(struct page *page); static inline unsigned long huge_page_mask_align(struct file *file) { return PAGE_MASK & ~huge_page_mask(hstate_file(file)); } #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; static inline unsigned long huge_page_mask_align(struct file *file) { return 0; } static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio) { return NULL; } static inline struct folio *filemap_lock_hugetlb_folio(struct hstate *h, struct address_space *mapping, pgoff_t idx) { return NULL; } static inline int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) { return -ENOMEM; } static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve) { return NULL; } static inline struct folio * alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask) { return NULL; } static inline struct folio * alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback) { return NULL; } static inline int __alloc_bootmem_huge_page(struct hstate *h) { return 0; } static inline struct hstate *hstate_file(struct file *f) { return NULL; } static inline struct hstate *hstate_sizelog(int page_size_log) { return NULL; } static inline struct hstate *hstate_vma(struct vm_area_struct *vma) { return NULL; } static inline struct hstate *folio_hstate(struct folio *folio) { return NULL; } static inline struct hstate *size_to_hstate(unsigned long size) { return NULL; } static inline unsigned long huge_page_size(struct hstate *h) { return PAGE_SIZE; } static inline unsigned long huge_page_mask(struct hstate *h) { return PAGE_MASK; } static inline unsigned long vma_kernel_pagesize(struct vm_area_struct *vma) { return PAGE_SIZE; } static inline unsigned long vma_mmu_pagesize(struct vm_area_struct *vma) { return PAGE_SIZE; } static inline unsigned int huge_page_order(struct hstate *h) { return 0; } static inline unsigned int huge_page_shift(struct hstate *h) { return PAGE_SHIFT; } static inline bool hstate_is_gigantic(struct hstate *h) { return false; } static inline unsigned int pages_per_huge_page(struct hstate *h) { return 1; } static inline unsigned hstate_index_to_shift(unsigned index) { return 0; } static inline int hstate_index(struct hstate *h) { return 0; } static inline int dissolve_free_hugetlb_folio(struct folio *folio) { return 0; } static inline int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn) { return 0; } static inline bool hugepage_migration_supported(struct hstate *h) { return false; } static inline bool hugepage_movable_supported(struct hstate *h) { return false; } static inline gfp_t htlb_alloc_mask(struct hstate *h) { return 0; } static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) { return 0; } static inline bool htlb_allow_alloc_fallback(int reason) { return false; } static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { return &mm->page_table_lock; } static inline void hugetlb_count_init(struct mm_struct *mm) { } static inline void hugetlb_report_usage(struct seq_file *f, struct mm_struct *m) { } static inline void hugetlb_count_sub(long l, struct mm_struct *mm) { } static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { #ifdef CONFIG_MMU return ptep_get(ptep); #else return *ptep; #endif } static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned long sz) { } static inline void hugetlb_register_node(struct node *node) { } static inline void hugetlb_unregister_node(struct node *node) { } static inline bool hugetlbfs_pagecache_present( struct hstate *h, struct vm_area_struct *vma, unsigned long address) { return false; } #endif /* CONFIG_HUGETLB_PAGE */ static inline spinlock_t *huge_pte_lock(struct hstate *h, struct mm_struct *mm, pte_t *pte) { spinlock_t *ptl; ptl = huge_pte_lockptr(h, mm, pte); spin_lock(ptl); return ptl; } #if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA) extern void __init hugetlb_cma_reserve(int order); #else static inline __init void hugetlb_cma_reserve(int order) { } #endif #ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING static inline bool hugetlb_pmd_shared(pte_t *pte) { return page_count(virt_to_page(pte)) > 1; } #else static inline bool hugetlb_pmd_shared(pte_t *pte) { return false; } #endif bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr); #ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE /* * ARCHes with special requirements for evicting HUGETLB backing TLB entries can * implement this. */ #define flush_hugetlb_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) #endif static inline bool __vma_shareable_lock(struct vm_area_struct *vma) { return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data; } bool __vma_private_lock(struct vm_area_struct *vma); /* * Safe version of huge_pte_offset() to check the locks. See comments * above huge_pte_offset(). */ static inline pte_t * hugetlb_walk(struct vm_area_struct *vma, unsigned long addr, unsigned long sz) { #if defined(CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING) && defined(CONFIG_LOCKDEP) struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; /* * If pmd sharing possible, locking needed to safely walk the * hugetlb pgtables. More information can be found at the comment * above huge_pte_offset() in the same file. * * NOTE: lockdep_is_held() is only defined with CONFIG_LOCKDEP. */ if (__vma_shareable_lock(vma)) WARN_ON_ONCE(!lockdep_is_held(&vma_lock->rw_sema) && !lockdep_is_held( &vma->vm_file->f_mapping->i_mmap_rwsem)); #endif return huge_pte_offset(vma->vm_mm, addr, sz); } #endif /* _LINUX_HUGETLB_H */ |
| 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/etherdevice.h> #include "ipvlan.h" #include <linux/if_vlan.h> #include <linux/if_tap.h> #include <linux/interrupt.h> #include <linux/nsproxy.h> #include <linux/compat.h> #include <linux/if_tun.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/cache.h> #include <linux/sched.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/wait.h> #include <linux/cdev.h> #include <linux/idr.h> #include <linux/fs.h> #include <linux/uio.h> #include <net/net_namespace.h> #include <net/rtnetlink.h> #include <net/sock.h> #include <linux/virtio_net.h> #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \ NETIF_F_TSO6) static dev_t ipvtap_major; static struct cdev ipvtap_cdev; static const void *ipvtap_net_namespace(const struct device *d) { const struct net_device *dev = to_net_dev(d->parent); return dev_net(dev); } static struct class ipvtap_class = { .name = "ipvtap", .ns_type = &net_ns_type_operations, .namespace = ipvtap_net_namespace, }; struct ipvtap_dev { struct ipvl_dev vlan; struct tap_dev tap; }; static void ipvtap_count_tx_dropped(struct tap_dev *tap) { struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap); struct ipvl_dev *vlan = &vlantap->vlan; this_cpu_inc(vlan->pcpu_stats->tx_drps); } static void ipvtap_count_rx_dropped(struct tap_dev *tap) { struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap); struct ipvl_dev *vlan = &vlantap->vlan; ipvlan_count_rx(vlan, 0, 0, 0); } static void ipvtap_update_features(struct tap_dev *tap, netdev_features_t features) { struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap); struct ipvl_dev *vlan = &vlantap->vlan; vlan->sfeatures = features; netdev_update_features(vlan->dev); } static int ipvtap_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ipvtap_dev *vlantap = netdev_priv(dev); int err; INIT_LIST_HEAD(&vlantap->tap.queue_list); /* Since macvlan supports all offloads by default, make * tap support all offloads also. */ vlantap->tap.tap_features = TUN_OFFLOADS; vlantap->tap.count_tx_dropped = ipvtap_count_tx_dropped; vlantap->tap.update_features = ipvtap_update_features; vlantap->tap.count_rx_dropped = ipvtap_count_rx_dropped; err = netdev_rx_handler_register(dev, tap_handle_frame, &vlantap->tap); if (err) return err; /* Don't put anything that may fail after macvlan_common_newlink * because we can't undo what it does. */ err = ipvlan_link_new(src_net, dev, tb, data, extack); if (err) { netdev_rx_handler_unregister(dev); return err; } vlantap->tap.dev = vlantap->vlan.dev; return err; } static void ipvtap_dellink(struct net_device *dev, struct list_head *head) { struct ipvtap_dev *vlan = netdev_priv(dev); netdev_rx_handler_unregister(dev); tap_del_queues(&vlan->tap); ipvlan_link_delete(dev, head); } static void ipvtap_setup(struct net_device *dev) { ipvlan_link_setup(dev); dev->tx_queue_len = TUN_READQ_SIZE; dev->priv_flags &= ~IFF_NO_QUEUE; } static struct rtnl_link_ops ipvtap_link_ops __read_mostly = { .kind = "ipvtap", .setup = ipvtap_setup, .newlink = ipvtap_newlink, .dellink = ipvtap_dellink, .priv_size = sizeof(struct ipvtap_dev), }; static int ipvtap_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct ipvtap_dev *vlantap; struct device *classdev; dev_t devt; int err; char tap_name[IFNAMSIZ]; if (dev->rtnl_link_ops != &ipvtap_link_ops) return NOTIFY_DONE; snprintf(tap_name, IFNAMSIZ, "tap%d", dev->ifindex); vlantap = netdev_priv(dev); switch (event) { case NETDEV_REGISTER: /* Create the device node here after the network device has * been registered but before register_netdevice has * finished running. */ err = tap_get_minor(ipvtap_major, &vlantap->tap); if (err) return notifier_from_errno(err); devt = MKDEV(MAJOR(ipvtap_major), vlantap->tap.minor); classdev = device_create(&ipvtap_class, &dev->dev, devt, dev, "%s", tap_name); if (IS_ERR(classdev)) { tap_free_minor(ipvtap_major, &vlantap->tap); return notifier_from_errno(PTR_ERR(classdev)); } err = sysfs_create_link(&dev->dev.kobj, &classdev->kobj, tap_name); if (err) return notifier_from_errno(err); break; case NETDEV_UNREGISTER: /* vlan->minor == 0 if NETDEV_REGISTER above failed */ if (vlantap->tap.minor == 0) break; sysfs_remove_link(&dev->dev.kobj, tap_name); devt = MKDEV(MAJOR(ipvtap_major), vlantap->tap.minor); device_destroy(&ipvtap_class, devt); tap_free_minor(ipvtap_major, &vlantap->tap); break; case NETDEV_CHANGE_TX_QUEUE_LEN: if (tap_queue_resize(&vlantap->tap)) return NOTIFY_BAD; break; } return NOTIFY_DONE; } static struct notifier_block ipvtap_notifier_block __read_mostly = { .notifier_call = ipvtap_device_event, }; static int __init ipvtap_init(void) { int err; err = tap_create_cdev(&ipvtap_cdev, &ipvtap_major, "ipvtap", THIS_MODULE); if (err) goto out1; err = class_register(&ipvtap_class); if (err) goto out2; err = register_netdevice_notifier(&ipvtap_notifier_block); if (err) goto out3; err = ipvlan_link_register(&ipvtap_link_ops); if (err) goto out4; return 0; out4: unregister_netdevice_notifier(&ipvtap_notifier_block); out3: class_unregister(&ipvtap_class); out2: tap_destroy_cdev(ipvtap_major, &ipvtap_cdev); out1: return err; } module_init(ipvtap_init); static void __exit ipvtap_exit(void) { rtnl_link_unregister(&ipvtap_link_ops); unregister_netdevice_notifier(&ipvtap_notifier_block); class_unregister(&ipvtap_class); tap_destroy_cdev(ipvtap_major, &ipvtap_cdev); } module_exit(ipvtap_exit); MODULE_ALIAS_RTNL_LINK("ipvtap"); MODULE_AUTHOR("Sainath Grandhi <sainath.grandhi@intel.com>"); MODULE_DESCRIPTION("IP-VLAN based tap driver"); MODULE_LICENSE("GPL"); |
| 29 29 729 28 728 726 729 729 727 29 29 29 29 29 29 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 | // SPDX-License-Identifier: GPL-2.0-or-later /* * printk_safe.c - Safe printk for printk-deadlock-prone contexts */ #include <linux/preempt.h> #include <linux/kdb.h> #include <linux/smp.h> #include <linux/cpumask.h> #include <linux/printk.h> #include <linux/kprobes.h> #include "internal.h" /* Context where printk messages are never suppressed */ static atomic_t force_con; void printk_force_console_enter(void) { atomic_inc(&force_con); } void printk_force_console_exit(void) { atomic_dec(&force_con); } bool is_printk_force_console(void) { return atomic_read(&force_con); } static DEFINE_PER_CPU(int, printk_context); /* Can be preempted by NMI. */ void __printk_safe_enter(void) { this_cpu_inc(printk_context); } /* Can be preempted by NMI. */ void __printk_safe_exit(void) { this_cpu_dec(printk_context); } void __printk_deferred_enter(void) { cant_migrate(); __printk_safe_enter(); } void __printk_deferred_exit(void) { cant_migrate(); __printk_safe_exit(); } bool is_printk_legacy_deferred(void) { /* * The per-CPU variable @printk_context can be read safely in any * context. CPU migration is always disabled when set. */ return (force_legacy_kthread() || this_cpu_read(printk_context) || in_nmi()); } asmlinkage int vprintk(const char *fmt, va_list args) { #ifdef CONFIG_KGDB_KDB /* Allow to pass printk() to kdb but avoid a recursion. */ if (unlikely(kdb_trap_printk && kdb_printf_cpu < 0)) return vkdb_printf(KDB_MSGSRC_PRINTK, fmt, args); #endif /* * Use the main logbuf even in NMI. But avoid calling console * drivers that might have their own locks. */ if (is_printk_legacy_deferred()) return vprintk_deferred(fmt, args); /* No obstacles. */ return vprintk_default(fmt, args); } EXPORT_SYMBOL(vprintk); |
| 180 179 23 18 1 1 1 1 1 18 21 21 21 21 20 20 19 20 20 4 19 19 19 19 50 11 23 21 20 7 47 359 354 50 359 22 22 22 22 22 22 21 20 20 20 20 20 20 19 20 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 | // SPDX-License-Identifier: GPL-2.0 /* * linux/mm/mlock.c * * (C) Copyright 1995 Linus Torvalds * (C) Copyright 2002 Christoph Hellwig */ #include <linux/capability.h> #include <linux/mman.h> #include <linux/mm.h> #include <linux/sched/user.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/pagemap.h> #include <linux/pagevec.h> #include <linux/pagewalk.h> #include <linux/mempolicy.h> #include <linux/syscalls.h> #include <linux/sched.h> #include <linux/export.h> #include <linux/rmap.h> #include <linux/mmzone.h> #include <linux/hugetlb.h> #include <linux/memcontrol.h> #include <linux/mm_inline.h> #include <linux/secretmem.h> #include "internal.h" struct mlock_fbatch { local_lock_t lock; struct folio_batch fbatch; }; static DEFINE_PER_CPU(struct mlock_fbatch, mlock_fbatch) = { .lock = INIT_LOCAL_LOCK(lock), }; bool can_do_mlock(void) { if (rlimit(RLIMIT_MEMLOCK) != 0) return true; if (capable(CAP_IPC_LOCK)) return true; return false; } EXPORT_SYMBOL(can_do_mlock); /* * Mlocked folios are marked with the PG_mlocked flag for efficient testing * in vmscan and, possibly, the fault path; and to support semi-accurate * statistics. * * An mlocked folio [folio_test_mlocked(folio)] is unevictable. As such, it * will be ostensibly placed on the LRU "unevictable" list (actually no such * list exists), rather than the [in]active lists. PG_unevictable is set to * indicate the unevictable state. */ static struct lruvec *__mlock_folio(struct folio *folio, struct lruvec *lruvec) { /* There is nothing more we can do while it's off LRU */ if (!folio_test_clear_lru(folio)) return lruvec; lruvec = folio_lruvec_relock_irq(folio, lruvec); if (unlikely(folio_evictable(folio))) { /* * This is a little surprising, but quite possible: PG_mlocked * must have got cleared already by another CPU. Could this * folio be unevictable? I'm not sure, but move it now if so. */ if (folio_test_unevictable(folio)) { lruvec_del_folio(lruvec, folio); folio_clear_unevictable(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(UNEVICTABLE_PGRESCUED, folio_nr_pages(folio)); } goto out; } if (folio_test_unevictable(folio)) { if (folio_test_mlocked(folio)) folio->mlock_count++; goto out; } lruvec_del_folio(lruvec, folio); folio_clear_active(folio); folio_set_unevictable(folio); folio->mlock_count = !!folio_test_mlocked(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(UNEVICTABLE_PGCULLED, folio_nr_pages(folio)); out: folio_set_lru(folio); return lruvec; } static struct lruvec *__mlock_new_folio(struct folio *folio, struct lruvec *lruvec) { VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); lruvec = folio_lruvec_relock_irq(folio, lruvec); /* As above, this is a little surprising, but possible */ if (unlikely(folio_evictable(folio))) goto out; folio_set_unevictable(folio); folio->mlock_count = !!folio_test_mlocked(folio); __count_vm_events(UNEVICTABLE_PGCULLED, folio_nr_pages(folio)); out: lruvec_add_folio(lruvec, folio); folio_set_lru(folio); return lruvec; } static struct lruvec *__munlock_folio(struct folio *folio, struct lruvec *lruvec) { int nr_pages = folio_nr_pages(folio); bool isolated = false; if (!folio_test_clear_lru(folio)) goto munlock; isolated = true; lruvec = folio_lruvec_relock_irq(folio, lruvec); if (folio_test_unevictable(folio)) { /* Then mlock_count is maintained, but might undercount */ if (folio->mlock_count) folio->mlock_count--; if (folio->mlock_count) goto out; } /* else assume that was the last mlock: reclaim will fix it if not */ munlock: if (folio_test_clear_mlocked(folio)) { __zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages); if (isolated || !folio_test_unevictable(folio)) __count_vm_events(UNEVICTABLE_PGMUNLOCKED, nr_pages); else __count_vm_events(UNEVICTABLE_PGSTRANDED, nr_pages); } /* folio_evictable() has to be checked *after* clearing Mlocked */ if (isolated && folio_test_unevictable(folio) && folio_evictable(folio)) { lruvec_del_folio(lruvec, folio); folio_clear_unevictable(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages); } out: if (isolated) folio_set_lru(folio); return lruvec; } /* * Flags held in the low bits of a struct folio pointer on the mlock_fbatch. */ #define LRU_FOLIO 0x1 #define NEW_FOLIO 0x2 static inline struct folio *mlock_lru(struct folio *folio) { return (struct folio *)((unsigned long)folio + LRU_FOLIO); } static inline struct folio *mlock_new(struct folio *folio) { return (struct folio *)((unsigned long)folio + NEW_FOLIO); } /* * mlock_folio_batch() is derived from folio_batch_move_lru(): perhaps that can * make use of such folio pointer flags in future, but for now just keep it for * mlock. We could use three separate folio batches instead, but one feels * better (munlocking a full folio batch does not need to drain mlocking folio * batches first). */ static void mlock_folio_batch(struct folio_batch *fbatch) { struct lruvec *lruvec = NULL; unsigned long mlock; struct folio *folio; int i; for (i = 0; i < folio_batch_count(fbatch); i++) { folio = fbatch->folios[i]; mlock = (unsigned long)folio & (LRU_FOLIO | NEW_FOLIO); folio = (struct folio *)((unsigned long)folio - mlock); fbatch->folios[i] = folio; if (mlock & LRU_FOLIO) lruvec = __mlock_folio(folio, lruvec); else if (mlock & NEW_FOLIO) lruvec = __mlock_new_folio(folio, lruvec); else lruvec = __munlock_folio(folio, lruvec); } if (lruvec) unlock_page_lruvec_irq(lruvec); folios_put(fbatch); } void mlock_drain_local(void) { struct folio_batch *fbatch; local_lock(&mlock_fbatch.lock); fbatch = this_cpu_ptr(&mlock_fbatch.fbatch); if (folio_batch_count(fbatch)) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } void mlock_drain_remote(int cpu) { struct folio_batch *fbatch; WARN_ON_ONCE(cpu_online(cpu)); fbatch = &per_cpu(mlock_fbatch.fbatch, cpu); if (folio_batch_count(fbatch)) mlock_folio_batch(fbatch); } bool need_mlock_drain(int cpu) { return folio_batch_count(&per_cpu(mlock_fbatch.fbatch, cpu)); } /** * mlock_folio - mlock a folio already on (or temporarily off) LRU * @folio: folio to be mlocked. */ void mlock_folio(struct folio *folio) { struct folio_batch *fbatch; local_lock(&mlock_fbatch.lock); fbatch = this_cpu_ptr(&mlock_fbatch.fbatch); if (!folio_test_set_mlocked(folio)) { int nr_pages = folio_nr_pages(folio); zone_stat_mod_folio(folio, NR_MLOCK, nr_pages); __count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages); } folio_get(folio); if (!folio_batch_add(fbatch, mlock_lru(folio)) || folio_test_large(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } /** * mlock_new_folio - mlock a newly allocated folio not yet on LRU * @folio: folio to be mlocked, either normal or a THP head. */ void mlock_new_folio(struct folio *folio) { struct folio_batch *fbatch; int nr_pages = folio_nr_pages(folio); local_lock(&mlock_fbatch.lock); fbatch = this_cpu_ptr(&mlock_fbatch.fbatch); folio_set_mlocked(folio); zone_stat_mod_folio(folio, NR_MLOCK, nr_pages); __count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages); folio_get(folio); if (!folio_batch_add(fbatch, mlock_new(folio)) || folio_test_large(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } /** * munlock_folio - munlock a folio * @folio: folio to be munlocked, either normal or a THP head. */ void munlock_folio(struct folio *folio) { struct folio_batch *fbatch; local_lock(&mlock_fbatch.lock); fbatch = this_cpu_ptr(&mlock_fbatch.fbatch); /* * folio_test_clear_mlocked(folio) must be left to __munlock_folio(), * which will check whether the folio is multiply mlocked. */ folio_get(folio); if (!folio_batch_add(fbatch, folio) || folio_test_large(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } static inline unsigned int folio_mlock_step(struct folio *folio, pte_t *pte, unsigned long addr, unsigned long end) { const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY; unsigned int count = (end - addr) >> PAGE_SHIFT; pte_t ptent = ptep_get(pte); if (!folio_test_large(folio)) return 1; return folio_pte_batch(folio, addr, pte, ptent, count, fpb_flags, NULL, NULL, NULL); } static inline bool allow_mlock_munlock(struct folio *folio, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned int step) { /* * For unlock, allow munlock large folio which is partially * mapped to VMA. As it's possible that large folio is * mlocked and VMA is split later. * * During memory pressure, such kind of large folio can * be split. And the pages are not in VM_LOCKed VMA * can be reclaimed. */ if (!(vma->vm_flags & VM_LOCKED)) return true; /* folio_within_range() cannot take KSM, but any small folio is OK */ if (!folio_test_large(folio)) return true; /* folio not in range [start, end), skip mlock */ if (!folio_within_range(folio, vma, start, end)) return false; /* folio is not fully mapped, skip mlock */ if (step != folio_nr_pages(folio)) return false; return true; } static int mlock_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; spinlock_t *ptl; pte_t *start_pte, *pte; pte_t ptent; struct folio *folio; unsigned int step = 1; unsigned long start = addr; ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { if (!pmd_present(*pmd)) goto out; if (is_huge_zero_pmd(*pmd)) goto out; folio = pmd_folio(*pmd); if (vma->vm_flags & VM_LOCKED) mlock_folio(folio); else munlock_folio(folio); goto out; } start_pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (!start_pte) { walk->action = ACTION_AGAIN; return 0; } for (pte = start_pte; addr != end; pte++, addr += PAGE_SIZE) { ptent = ptep_get(pte); if (!pte_present(ptent)) continue; folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; step = folio_mlock_step(folio, pte, addr, end); if (!allow_mlock_munlock(folio, vma, start, end, step)) goto next_entry; if (vma->vm_flags & VM_LOCKED) mlock_folio(folio); else munlock_folio(folio); next_entry: pte += step - 1; addr += (step - 1) << PAGE_SHIFT; } pte_unmap(start_pte); out: spin_unlock(ptl); cond_resched(); return 0; } /* * mlock_vma_pages_range() - mlock any pages already in the range, * or munlock all pages in the range. * @vma - vma containing range to be mlock()ed or munlock()ed * @start - start address in @vma of the range * @end - end of range in @vma * @newflags - the new set of flags for @vma. * * Called for mlock(), mlock2() and mlockall(), to set @vma VM_LOCKED; * called for munlock() and munlockall(), to clear VM_LOCKED from @vma. */ static void mlock_vma_pages_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, vm_flags_t newflags) { static const struct mm_walk_ops mlock_walk_ops = { .pmd_entry = mlock_pte_range, .walk_lock = PGWALK_WRLOCK_VERIFY, }; /* * There is a slight chance that concurrent page migration, * or page reclaim finding a page of this now-VM_LOCKED vma, * will call mlock_vma_folio() and raise page's mlock_count: * double counting, leaving the page unevictable indefinitely. * Communicate this danger to mlock_vma_folio() with VM_IO, * which is a VM_SPECIAL flag not allowed on VM_LOCKED vmas. * mmap_lock is held in write mode here, so this weird * combination should not be visible to other mmap_lock users; * but WRITE_ONCE so rmap walkers must see VM_IO if VM_LOCKED. */ if (newflags & VM_LOCKED) newflags |= VM_IO; vma_start_write(vma); vm_flags_reset_once(vma, newflags); lru_add_drain(); walk_page_range(vma->vm_mm, start, end, &mlock_walk_ops, NULL); lru_add_drain(); if (newflags & VM_IO) { newflags &= ~VM_IO; vm_flags_reset_once(vma, newflags); } } /* * mlock_fixup - handle mlock[all]/munlock[all] requests. * * Filters out "special" vmas -- VM_LOCKED never gets set for these, and * munlock is a no-op. However, for some special vmas, we go ahead and * populate the ptes. * * For vmas that pass the filters, merge/split as appropriate. */ static int mlock_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, vm_flags_t newflags) { struct mm_struct *mm = vma->vm_mm; int nr_pages; int ret = 0; vm_flags_t oldflags = vma->vm_flags; if (newflags == oldflags || (oldflags & VM_SPECIAL) || is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm) || vma_is_dax(vma) || vma_is_secretmem(vma) || (oldflags & VM_DROPPABLE)) /* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */ goto out; vma = vma_modify_flags(vmi, *prev, vma, start, end, newflags); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto out; } /* * Keep track of amount of locked VM. */ nr_pages = (end - start) >> PAGE_SHIFT; if (!(newflags & VM_LOCKED)) nr_pages = -nr_pages; else if (oldflags & VM_LOCKED) nr_pages = 0; mm->locked_vm += nr_pages; /* * vm_flags is protected by the mmap_lock held in write mode. * It's okay if try_to_unmap_one unmaps a page just after we * set VM_LOCKED, populate_vma_page_range will bring it back. */ if ((newflags & VM_LOCKED) && (oldflags & VM_LOCKED)) { /* No work to do, and mlocking twice would be wrong */ vma_start_write(vma); vm_flags_reset(vma, newflags); } else { mlock_vma_pages_range(vma, start, end, newflags); } out: *prev = vma; return ret; } static int apply_vma_lock_flags(unsigned long start, size_t len, vm_flags_t flags) { unsigned long nstart, end, tmp; struct vm_area_struct *vma, *prev; VMA_ITERATOR(vmi, current->mm, start); VM_BUG_ON(offset_in_page(start)); VM_BUG_ON(len != PAGE_ALIGN(len)); end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; vma = vma_iter_load(&vmi); if (!vma) return -ENOMEM; prev = vma_prev(&vmi); if (start > vma->vm_start) prev = vma; nstart = start; tmp = vma->vm_start; for_each_vma_range(vmi, vma, end) { int error; vm_flags_t newflags; if (vma->vm_start != tmp) return -ENOMEM; newflags = vma->vm_flags & ~VM_LOCKED_MASK; newflags |= flags; /* Here we know that vma->vm_start <= nstart < vma->vm_end. */ tmp = vma->vm_end; if (tmp > end) tmp = end; error = mlock_fixup(&vmi, vma, &prev, nstart, tmp, newflags); if (error) return error; tmp = vma_iter_end(&vmi); nstart = tmp; } if (tmp < end) return -ENOMEM; return 0; } /* * Go through vma areas and sum size of mlocked * vma pages, as return value. * Note deferred memory locking case(mlock2(,,MLOCK_ONFAULT) * is also counted. * Return value: previously mlocked page counts */ static unsigned long count_mm_mlocked_page_nr(struct mm_struct *mm, unsigned long start, size_t len) { struct vm_area_struct *vma; unsigned long count = 0; unsigned long end; VMA_ITERATOR(vmi, mm, start); /* Don't overflow past ULONG_MAX */ if (unlikely(ULONG_MAX - len < start)) end = ULONG_MAX; else end = start + len; for_each_vma_range(vmi, vma, end) { if (vma->vm_flags & VM_LOCKED) { if (start > vma->vm_start) count -= (start - vma->vm_start); if (end < vma->vm_end) { count += end - vma->vm_start; break; } count += vma->vm_end - vma->vm_start; } } return count >> PAGE_SHIFT; } /* * convert get_user_pages() return value to posix mlock() error */ static int __mlock_posix_error_return(long retval) { if (retval == -EFAULT) retval = -ENOMEM; else if (retval == -ENOMEM) retval = -EAGAIN; return retval; } static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t flags) { unsigned long locked; unsigned long lock_limit; int error = -ENOMEM; start = untagged_addr(start); if (!can_do_mlock()) return -EPERM; len = PAGE_ALIGN(len + (offset_in_page(start))); start &= PAGE_MASK; lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; locked = len >> PAGE_SHIFT; if (mmap_write_lock_killable(current->mm)) return -EINTR; locked += current->mm->locked_vm; if ((locked > lock_limit) && (!capable(CAP_IPC_LOCK))) { /* * It is possible that the regions requested intersect with * previously mlocked areas, that part area in "mm->locked_vm" * should not be counted to new mlock increment count. So check * and adjust locked count if necessary. */ locked -= count_mm_mlocked_page_nr(current->mm, start, len); } /* check against resource limits */ if ((locked <= lock_limit) || capable(CAP_IPC_LOCK)) error = apply_vma_lock_flags(start, len, flags); mmap_write_unlock(current->mm); if (error) return error; error = __mm_populate(start, len, 0); if (error) return __mlock_posix_error_return(error); return 0; } SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len) { return do_mlock(start, len, VM_LOCKED); } SYSCALL_DEFINE3(mlock2, unsigned long, start, size_t, len, int, flags) { vm_flags_t vm_flags = VM_LOCKED; if (flags & ~MLOCK_ONFAULT) return -EINVAL; if (flags & MLOCK_ONFAULT) vm_flags |= VM_LOCKONFAULT; return do_mlock(start, len, vm_flags); } SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) { int ret; start = untagged_addr(start); len = PAGE_ALIGN(len + (offset_in_page(start))); start &= PAGE_MASK; if (mmap_write_lock_killable(current->mm)) return -EINTR; ret = apply_vma_lock_flags(start, len, 0); mmap_write_unlock(current->mm); return ret; } /* * Take the MCL_* flags passed into mlockall (or 0 if called from munlockall) * and translate into the appropriate modifications to mm->def_flags and/or the * flags for all current VMAs. * * There are a couple of subtleties with this. If mlockall() is called multiple * times with different flags, the values do not necessarily stack. If mlockall * is called once including the MCL_FUTURE flag and then a second time without * it, VM_LOCKED and VM_LOCKONFAULT will be cleared from mm->def_flags. */ static int apply_mlockall_flags(int flags) { VMA_ITERATOR(vmi, current->mm, 0); struct vm_area_struct *vma, *prev = NULL; vm_flags_t to_add = 0; current->mm->def_flags &= ~VM_LOCKED_MASK; if (flags & MCL_FUTURE) { current->mm->def_flags |= VM_LOCKED; if (flags & MCL_ONFAULT) current->mm->def_flags |= VM_LOCKONFAULT; if (!(flags & MCL_CURRENT)) goto out; } if (flags & MCL_CURRENT) { to_add |= VM_LOCKED; if (flags & MCL_ONFAULT) to_add |= VM_LOCKONFAULT; } for_each_vma(vmi, vma) { int error; vm_flags_t newflags; newflags = vma->vm_flags & ~VM_LOCKED_MASK; newflags |= to_add; error = mlock_fixup(&vmi, vma, &prev, vma->vm_start, vma->vm_end, newflags); /* Ignore errors, but prev needs fixing up. */ if (error) prev = vma; cond_resched(); } out: return 0; } SYSCALL_DEFINE1(mlockall, int, flags) { unsigned long lock_limit; int ret; if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT)) || flags == MCL_ONFAULT) return -EINVAL; if (!can_do_mlock()) return -EPERM; lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; if (mmap_write_lock_killable(current->mm)) return -EINTR; ret = -ENOMEM; if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) || capable(CAP_IPC_LOCK)) ret = apply_mlockall_flags(flags); mmap_write_unlock(current->mm); if (!ret && (flags & MCL_CURRENT)) mm_populate(0, TASK_SIZE); return ret; } SYSCALL_DEFINE0(munlockall) { int ret; if (mmap_write_lock_killable(current->mm)) return -EINTR; ret = apply_mlockall_flags(0); mmap_write_unlock(current->mm); return ret; } /* * Objects with different lifetime than processes (SHM_LOCK and SHM_HUGETLB * shm segments) get accounted against the user_struct instead. */ static DEFINE_SPINLOCK(shmlock_user_lock); int user_shm_lock(size_t size, struct ucounts *ucounts) { unsigned long lock_limit, locked; long memlock; int allowed = 0; locked = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; lock_limit = rlimit(RLIMIT_MEMLOCK); if (lock_limit != RLIM_INFINITY) lock_limit >>= PAGE_SHIFT; spin_lock(&shmlock_user_lock); memlock = inc_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked); if ((memlock == LONG_MAX || memlock > lock_limit) && !capable(CAP_IPC_LOCK)) { dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked); goto out; } if (!get_ucounts(ucounts)) { dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked); allowed = 0; goto out; } allowed = 1; out: spin_unlock(&shmlock_user_lock); return allowed; } void user_shm_unlock(size_t size, struct ucounts *ucounts) { spin_lock(&shmlock_user_lock); dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, (size + PAGE_SIZE - 1) >> PAGE_SHIFT); spin_unlock(&shmlock_user_lock); put_ucounts(ucounts); } |
| 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IP multicast routing support for mrouted 3.6/3.8 * * (c) 1995 Alan Cox, <alan@lxorguk.ukuu.org.uk> * Linux Consultancy and Custom Driver Development * * Fixes: * Michael Chastain : Incorrect size of copying. * Alan Cox : Added the cache manager code * Alan Cox : Fixed the clone/copy bug and device race. * Mike McLagan : Routing by source * Malcolm Beattie : Buffer handling fixes. * Alexey Kuznetsov : Double buffer free and other fixes. * SVR Anand : Fixed several multicast bugs and problems. * Alexey Kuznetsov : Status, optimisations and more. * Brad Parker : Better behaviour on mrouted upcall * overflow. * Carlos Picoto : PIMv1 Support * Pavlin Ivanov Radoslavov: PIMv2 Registers must checksum only PIM header * Relax this requirement to work with older peers. */ #include <linux/uaccess.h> #include <linux/types.h> #include <linux/cache.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/kernel.h> #include <linux/fcntl.h> #include <linux/stat.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/mroute.h> #include <linux/init.h> #include <linux/if_ether.h> #include <linux/slab.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <net/route.h> #include <net/icmp.h> #include <net/udp.h> #include <net/raw.h> #include <linux/notifier.h> #include <linux/if_arp.h> #include <linux/netfilter_ipv4.h> #include <linux/compat.h> #include <linux/export.h> #include <linux/rhashtable.h> #include <net/ip_tunnels.h> #include <net/checksum.h> #include <net/netlink.h> #include <net/fib_rules.h> #include <linux/netconf.h> #include <net/rtnh.h> #include <net/inet_dscp.h> #include <linux/nospec.h> struct ipmr_rule { struct fib_rule common; }; struct ipmr_result { struct mr_table *mrt; }; /* Big lock, protecting vif table, mrt cache and mroute socket state. * Note that the changes are semaphored via rtnl_lock. */ static DEFINE_SPINLOCK(mrt_lock); static struct net_device *vif_dev_read(const struct vif_device *vif) { return rcu_dereference(vif->dev); } /* Multicast router control variables */ /* Special spinlock for queue of unresolved entries */ static DEFINE_SPINLOCK(mfc_unres_lock); /* We return to original Alan's scheme. Hash table of resolved * entries is changed only in process context and protected * with weak lock mrt_lock. Queue of unresolved entries is protected * with strong spinlock mfc_unres_lock. * * In this case data path is free of exclusive locks at all. */ static struct kmem_cache *mrt_cachep __ro_after_init; static struct mr_table *ipmr_new_table(struct net *net, u32 id); static void ipmr_free_table(struct mr_table *mrt); static void ip_mr_forward(struct net *net, struct mr_table *mrt, struct net_device *dev, struct sk_buff *skb, struct mfc_cache *cache, int local); static int ipmr_cache_report(const struct mr_table *mrt, struct sk_buff *pkt, vifi_t vifi, int assert); static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, int cmd); static void igmpmsg_netlink_event(const struct mr_table *mrt, struct sk_buff *pkt); static void mroute_clean_tables(struct mr_table *mrt, int flags); static void ipmr_expire_process(struct timer_list *t); #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES #define ipmr_for_each_table(mrt, net) \ list_for_each_entry_rcu(mrt, &net->ipv4.mr_tables, list, \ lockdep_rtnl_is_held() || \ list_empty(&net->ipv4.mr_tables)) static bool ipmr_can_free_table(struct net *net) { return !check_net(net) || !net_initialized(net); } static struct mr_table *ipmr_mr_table_iter(struct net *net, struct mr_table *mrt) { struct mr_table *ret; if (!mrt) ret = list_entry_rcu(net->ipv4.mr_tables.next, struct mr_table, list); else ret = list_entry_rcu(mrt->list.next, struct mr_table, list); if (&ret->list == &net->ipv4.mr_tables) return NULL; return ret; } static struct mr_table *__ipmr_get_table(struct net *net, u32 id) { struct mr_table *mrt; ipmr_for_each_table(mrt, net) { if (mrt->id == id) return mrt; } return NULL; } static struct mr_table *ipmr_get_table(struct net *net, u32 id) { struct mr_table *mrt; rcu_read_lock(); mrt = __ipmr_get_table(net, id); rcu_read_unlock(); return mrt; } static int ipmr_fib_lookup(struct net *net, struct flowi4 *flp4, struct mr_table **mrt) { int err; struct ipmr_result res; struct fib_lookup_arg arg = { .result = &res, .flags = FIB_LOOKUP_NOREF, }; /* update flow if oif or iif point to device enslaved to l3mdev */ l3mdev_update_flow(net, flowi4_to_flowi(flp4)); err = fib_rules_lookup(net->ipv4.mr_rules_ops, flowi4_to_flowi(flp4), 0, &arg); if (err < 0) return err; *mrt = res.mrt; return 0; } static int ipmr_rule_action(struct fib_rule *rule, struct flowi *flp, int flags, struct fib_lookup_arg *arg) { struct ipmr_result *res = arg->result; struct mr_table *mrt; switch (rule->action) { case FR_ACT_TO_TBL: break; case FR_ACT_UNREACHABLE: return -ENETUNREACH; case FR_ACT_PROHIBIT: return -EACCES; case FR_ACT_BLACKHOLE: default: return -EINVAL; } arg->table = fib_rule_get_table(rule, arg); mrt = __ipmr_get_table(rule->fr_net, arg->table); if (!mrt) return -EAGAIN; res->mrt = mrt; return 0; } static int ipmr_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) { return 1; } static int ipmr_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, struct nlattr **tb, struct netlink_ext_ack *extack) { return 0; } static int ipmr_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, struct nlattr **tb) { return 1; } static int ipmr_rule_fill(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh) { frh->dst_len = 0; frh->src_len = 0; frh->tos = 0; return 0; } static const struct fib_rules_ops __net_initconst ipmr_rules_ops_template = { .family = RTNL_FAMILY_IPMR, .rule_size = sizeof(struct ipmr_rule), .addr_size = sizeof(u32), .action = ipmr_rule_action, .match = ipmr_rule_match, .configure = ipmr_rule_configure, .compare = ipmr_rule_compare, .fill = ipmr_rule_fill, .nlgroup = RTNLGRP_IPV4_RULE, .owner = THIS_MODULE, }; static int __net_init ipmr_rules_init(struct net *net) { struct fib_rules_ops *ops; struct mr_table *mrt; int err; ops = fib_rules_register(&ipmr_rules_ops_template, net); if (IS_ERR(ops)) return PTR_ERR(ops); INIT_LIST_HEAD(&net->ipv4.mr_tables); mrt = ipmr_new_table(net, RT_TABLE_DEFAULT); if (IS_ERR(mrt)) { err = PTR_ERR(mrt); goto err1; } err = fib_default_rule_add(ops, 0x7fff, RT_TABLE_DEFAULT); if (err < 0) goto err2; net->ipv4.mr_rules_ops = ops; return 0; err2: rtnl_lock(); ipmr_free_table(mrt); rtnl_unlock(); err1: fib_rules_unregister(ops); return err; } static void __net_exit ipmr_rules_exit(struct net *net) { struct mr_table *mrt, *next; ASSERT_RTNL(); list_for_each_entry_safe(mrt, next, &net->ipv4.mr_tables, list) { list_del(&mrt->list); ipmr_free_table(mrt); } fib_rules_unregister(net->ipv4.mr_rules_ops); } static int ipmr_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return fib_rules_dump(net, nb, RTNL_FAMILY_IPMR, extack); } static unsigned int ipmr_rules_seq_read(const struct net *net) { return fib_rules_seq_read(net, RTNL_FAMILY_IPMR); } bool ipmr_rule_default(const struct fib_rule *rule) { return fib_rule_matchall(rule) && rule->table == RT_TABLE_DEFAULT; } EXPORT_SYMBOL(ipmr_rule_default); #else #define ipmr_for_each_table(mrt, net) \ for (mrt = net->ipv4.mrt; mrt; mrt = NULL) static bool ipmr_can_free_table(struct net *net) { return !check_net(net); } static struct mr_table *ipmr_mr_table_iter(struct net *net, struct mr_table *mrt) { if (!mrt) return net->ipv4.mrt; return NULL; } static struct mr_table *ipmr_get_table(struct net *net, u32 id) { return net->ipv4.mrt; } #define __ipmr_get_table ipmr_get_table static int ipmr_fib_lookup(struct net *net, struct flowi4 *flp4, struct mr_table **mrt) { *mrt = net->ipv4.mrt; return 0; } static int __net_init ipmr_rules_init(struct net *net) { struct mr_table *mrt; mrt = ipmr_new_table(net, RT_TABLE_DEFAULT); if (IS_ERR(mrt)) return PTR_ERR(mrt); net->ipv4.mrt = mrt; return 0; } static void __net_exit ipmr_rules_exit(struct net *net) { ASSERT_RTNL(); ipmr_free_table(net->ipv4.mrt); net->ipv4.mrt = NULL; } static int ipmr_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return 0; } static unsigned int ipmr_rules_seq_read(const struct net *net) { return 0; } bool ipmr_rule_default(const struct fib_rule *rule) { return true; } EXPORT_SYMBOL(ipmr_rule_default); #endif static inline int ipmr_hash_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct mfc_cache_cmp_arg *cmparg = arg->key; const struct mfc_cache *c = ptr; return cmparg->mfc_mcastgrp != c->mfc_mcastgrp || cmparg->mfc_origin != c->mfc_origin; } static const struct rhashtable_params ipmr_rht_params = { .head_offset = offsetof(struct mr_mfc, mnode), .key_offset = offsetof(struct mfc_cache, cmparg), .key_len = sizeof(struct mfc_cache_cmp_arg), .nelem_hint = 3, .obj_cmpfn = ipmr_hash_cmp, .automatic_shrinking = true, }; static void ipmr_new_table_set(struct mr_table *mrt, struct net *net) { #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES list_add_tail_rcu(&mrt->list, &net->ipv4.mr_tables); #endif } static struct mfc_cache_cmp_arg ipmr_mr_table_ops_cmparg_any = { .mfc_mcastgrp = htonl(INADDR_ANY), .mfc_origin = htonl(INADDR_ANY), }; static struct mr_table_ops ipmr_mr_table_ops = { .rht_params = &ipmr_rht_params, .cmparg_any = &ipmr_mr_table_ops_cmparg_any, }; static struct mr_table *ipmr_new_table(struct net *net, u32 id) { struct mr_table *mrt; /* "pimreg%u" should not exceed 16 bytes (IFNAMSIZ) */ if (id != RT_TABLE_DEFAULT && id >= 1000000000) return ERR_PTR(-EINVAL); mrt = __ipmr_get_table(net, id); if (mrt) return mrt; return mr_table_alloc(net, id, &ipmr_mr_table_ops, ipmr_expire_process, ipmr_new_table_set); } static void ipmr_free_table(struct mr_table *mrt) { struct net *net = read_pnet(&mrt->net); WARN_ON_ONCE(!ipmr_can_free_table(net)); timer_shutdown_sync(&mrt->ipmr_expire_timer); mroute_clean_tables(mrt, MRT_FLUSH_VIFS | MRT_FLUSH_VIFS_STATIC | MRT_FLUSH_MFC | MRT_FLUSH_MFC_STATIC); rhltable_destroy(&mrt->mfc_hash); kfree(mrt); } /* Service routines creating virtual interfaces: DVMRP tunnels and PIMREG */ /* Initialize ipmr pimreg/tunnel in_device */ static bool ipmr_init_vif_indev(const struct net_device *dev) { struct in_device *in_dev; ASSERT_RTNL(); in_dev = __in_dev_get_rtnl(dev); if (!in_dev) return false; ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); IPV4_DEVCONF(in_dev->cnf, RP_FILTER) = 0; return true; } static struct net_device *ipmr_new_tunnel(struct net *net, struct vifctl *v) { struct net_device *tunnel_dev, *new_dev; struct ip_tunnel_parm_kern p = { }; int err; tunnel_dev = __dev_get_by_name(net, "tunl0"); if (!tunnel_dev) goto out; p.iph.daddr = v->vifc_rmt_addr.s_addr; p.iph.saddr = v->vifc_lcl_addr.s_addr; p.iph.version = 4; p.iph.ihl = 5; p.iph.protocol = IPPROTO_IPIP; sprintf(p.name, "dvmrp%d", v->vifc_vifi); if (!tunnel_dev->netdev_ops->ndo_tunnel_ctl) goto out; err = tunnel_dev->netdev_ops->ndo_tunnel_ctl(tunnel_dev, &p, SIOCADDTUNNEL); if (err) goto out; new_dev = __dev_get_by_name(net, p.name); if (!new_dev) goto out; new_dev->flags |= IFF_MULTICAST; if (!ipmr_init_vif_indev(new_dev)) goto out_unregister; if (dev_open(new_dev, NULL)) goto out_unregister; dev_hold(new_dev); err = dev_set_allmulti(new_dev, 1); if (err) { dev_close(new_dev); tunnel_dev->netdev_ops->ndo_tunnel_ctl(tunnel_dev, &p, SIOCDELTUNNEL); dev_put(new_dev); new_dev = ERR_PTR(err); } return new_dev; out_unregister: unregister_netdevice(new_dev); out: return ERR_PTR(-ENOBUFS); } #if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2) static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) { struct net *net = dev_net(dev); struct mr_table *mrt; struct flowi4 fl4 = { .flowi4_oif = dev->ifindex, .flowi4_iif = skb->skb_iif ? : LOOPBACK_IFINDEX, .flowi4_mark = skb->mark, }; int err; err = ipmr_fib_lookup(net, &fl4, &mrt); if (err < 0) { kfree_skb(skb); return err; } DEV_STATS_ADD(dev, tx_bytes, skb->len); DEV_STATS_INC(dev, tx_packets); rcu_read_lock(); /* Pairs with WRITE_ONCE() in vif_add() and vif_delete() */ ipmr_cache_report(mrt, skb, READ_ONCE(mrt->mroute_reg_vif_num), IGMPMSG_WHOLEPKT); rcu_read_unlock(); kfree_skb(skb); return NETDEV_TX_OK; } static int reg_vif_get_iflink(const struct net_device *dev) { return 0; } static const struct net_device_ops reg_vif_netdev_ops = { .ndo_start_xmit = reg_vif_xmit, .ndo_get_iflink = reg_vif_get_iflink, }; static void reg_vif_setup(struct net_device *dev) { dev->type = ARPHRD_PIMREG; dev->mtu = ETH_DATA_LEN - sizeof(struct iphdr) - 8; dev->flags = IFF_NOARP; dev->netdev_ops = ®_vif_netdev_ops; dev->needs_free_netdev = true; dev->netns_local = true; } static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) { struct net_device *dev; char name[IFNAMSIZ]; if (mrt->id == RT_TABLE_DEFAULT) sprintf(name, "pimreg"); else sprintf(name, "pimreg%u", mrt->id); dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, reg_vif_setup); if (!dev) return NULL; dev_net_set(dev, net); if (register_netdevice(dev)) { free_netdev(dev); return NULL; } if (!ipmr_init_vif_indev(dev)) goto failure; if (dev_open(dev, NULL)) goto failure; dev_hold(dev); return dev; failure: unregister_netdevice(dev); return NULL; } /* called with rcu_read_lock() */ static int __pim_rcv(struct mr_table *mrt, struct sk_buff *skb, unsigned int pimlen) { struct net_device *reg_dev = NULL; struct iphdr *encap; int vif_num; encap = (struct iphdr *)(skb_transport_header(skb) + pimlen); /* Check that: * a. packet is really sent to a multicast group * b. packet is not a NULL-REGISTER * c. packet is not truncated */ if (!ipv4_is_multicast(encap->daddr) || encap->tot_len == 0 || ntohs(encap->tot_len) + pimlen > skb->len) return 1; /* Pairs with WRITE_ONCE() in vif_add()/vid_delete() */ vif_num = READ_ONCE(mrt->mroute_reg_vif_num); if (vif_num >= 0) reg_dev = vif_dev_read(&mrt->vif_table[vif_num]); if (!reg_dev) return 1; skb->mac_header = skb->network_header; skb_pull(skb, (u8 *)encap - skb->data); skb_reset_network_header(skb); skb->protocol = htons(ETH_P_IP); skb->ip_summed = CHECKSUM_NONE; skb_tunnel_rx(skb, reg_dev, dev_net(reg_dev)); netif_rx(skb); return NET_RX_SUCCESS; } #else static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) { return NULL; } #endif static int call_ipmr_vif_entry_notifiers(struct net *net, enum fib_event_type event_type, struct vif_device *vif, struct net_device *vif_dev, vifi_t vif_index, u32 tb_id) { return mr_call_vif_notifiers(net, RTNL_FAMILY_IPMR, event_type, vif, vif_dev, vif_index, tb_id, &net->ipv4.ipmr_seq); } static int call_ipmr_mfc_entry_notifiers(struct net *net, enum fib_event_type event_type, struct mfc_cache *mfc, u32 tb_id) { return mr_call_mfc_notifiers(net, RTNL_FAMILY_IPMR, event_type, &mfc->_c, tb_id, &net->ipv4.ipmr_seq); } /** * vif_delete - Delete a VIF entry * @mrt: Table to delete from * @vifi: VIF identifier to delete * @notify: Set to 1, if the caller is a notifier_call * @head: if unregistering the VIF, place it on this queue */ static int vif_delete(struct mr_table *mrt, int vifi, int notify, struct list_head *head) { struct net *net = read_pnet(&mrt->net); struct vif_device *v; struct net_device *dev; struct in_device *in_dev; if (vifi < 0 || vifi >= mrt->maxvif) return -EADDRNOTAVAIL; v = &mrt->vif_table[vifi]; dev = rtnl_dereference(v->dev); if (!dev) return -EADDRNOTAVAIL; spin_lock(&mrt_lock); call_ipmr_vif_entry_notifiers(net, FIB_EVENT_VIF_DEL, v, dev, vifi, mrt->id); RCU_INIT_POINTER(v->dev, NULL); if (vifi == mrt->mroute_reg_vif_num) { /* Pairs with READ_ONCE() in ipmr_cache_report() and reg_vif_xmit() */ WRITE_ONCE(mrt->mroute_reg_vif_num, -1); } if (vifi + 1 == mrt->maxvif) { int tmp; for (tmp = vifi - 1; tmp >= 0; tmp--) { if (VIF_EXISTS(mrt, tmp)) break; } WRITE_ONCE(mrt->maxvif, tmp + 1); } spin_unlock(&mrt_lock); dev_set_allmulti(dev, -1); in_dev = __in_dev_get_rtnl(dev); if (in_dev) { IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)--; inet_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, dev->ifindex, &in_dev->cnf); ip_rt_multicast_event(in_dev); } if (v->flags & (VIFF_TUNNEL | VIFF_REGISTER) && !notify) unregister_netdevice_queue(dev, head); netdev_put(dev, &v->dev_tracker); return 0; } static void ipmr_cache_free_rcu(struct rcu_head *head) { struct mr_mfc *c = container_of(head, struct mr_mfc, rcu); kmem_cache_free(mrt_cachep, (struct mfc_cache *)c); } static void ipmr_cache_free(struct mfc_cache *c) { call_rcu(&c->_c.rcu, ipmr_cache_free_rcu); } /* Destroy an unresolved cache entry, killing queued skbs * and reporting error to netlink readers. */ static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c) { struct net *net = read_pnet(&mrt->net); struct sk_buff *skb; struct nlmsgerr *e; atomic_dec(&mrt->cache_resolve_queue_len); while ((skb = skb_dequeue(&c->_c.mfc_un.unres.unresolved))) { if (ip_hdr(skb)->version == 0) { struct nlmsghdr *nlh = skb_pull(skb, sizeof(struct iphdr)); nlh->nlmsg_type = NLMSG_ERROR; nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr)); skb_trim(skb, nlh->nlmsg_len); e = nlmsg_data(nlh); e->error = -ETIMEDOUT; memset(&e->msg, 0, sizeof(e->msg)); rtnl_unicast(skb, net, NETLINK_CB(skb).portid); } else { kfree_skb(skb); } } ipmr_cache_free(c); } /* Timer process for the unresolved queue. */ static void ipmr_expire_process(struct timer_list *t) { struct mr_table *mrt = from_timer(mrt, t, ipmr_expire_timer); struct mr_mfc *c, *next; unsigned long expires; unsigned long now; if (!spin_trylock(&mfc_unres_lock)) { mod_timer(&mrt->ipmr_expire_timer, jiffies+HZ/10); return; } if (list_empty(&mrt->mfc_unres_queue)) goto out; now = jiffies; expires = 10*HZ; list_for_each_entry_safe(c, next, &mrt->mfc_unres_queue, list) { if (time_after(c->mfc_un.unres.expires, now)) { unsigned long interval = c->mfc_un.unres.expires - now; if (interval < expires) expires = interval; continue; } list_del(&c->list); mroute_netlink_event(mrt, (struct mfc_cache *)c, RTM_DELROUTE); ipmr_destroy_unres(mrt, (struct mfc_cache *)c); } if (!list_empty(&mrt->mfc_unres_queue)) mod_timer(&mrt->ipmr_expire_timer, jiffies + expires); out: spin_unlock(&mfc_unres_lock); } /* Fill oifs list. It is called under locked mrt_lock. */ static void ipmr_update_thresholds(struct mr_table *mrt, struct mr_mfc *cache, unsigned char *ttls) { int vifi; cache->mfc_un.res.minvif = MAXVIFS; cache->mfc_un.res.maxvif = 0; memset(cache->mfc_un.res.ttls, 255, MAXVIFS); for (vifi = 0; vifi < mrt->maxvif; vifi++) { if (VIF_EXISTS(mrt, vifi) && ttls[vifi] && ttls[vifi] < 255) { cache->mfc_un.res.ttls[vifi] = ttls[vifi]; if (cache->mfc_un.res.minvif > vifi) cache->mfc_un.res.minvif = vifi; if (cache->mfc_un.res.maxvif <= vifi) cache->mfc_un.res.maxvif = vifi + 1; } } cache->mfc_un.res.lastuse = jiffies; } static int vif_add(struct net *net, struct mr_table *mrt, struct vifctl *vifc, int mrtsock) { struct netdev_phys_item_id ppid = { }; int vifi = vifc->vifc_vifi; struct vif_device *v = &mrt->vif_table[vifi]; struct net_device *dev; struct in_device *in_dev; int err; /* Is vif busy ? */ if (VIF_EXISTS(mrt, vifi)) return -EADDRINUSE; switch (vifc->vifc_flags) { case VIFF_REGISTER: if (!ipmr_pimsm_enabled()) return -EINVAL; /* Special Purpose VIF in PIM * All the packets will be sent to the daemon */ if (mrt->mroute_reg_vif_num >= 0) return -EADDRINUSE; dev = ipmr_reg_vif(net, mrt); if (!dev) return -ENOBUFS; err = dev_set_allmulti(dev, 1); if (err) { unregister_netdevice(dev); dev_put(dev); return err; } break; case VIFF_TUNNEL: dev = ipmr_new_tunnel(net, vifc); if (IS_ERR(dev)) return PTR_ERR(dev); break; case VIFF_USE_IFINDEX: case 0: if (vifc->vifc_flags == VIFF_USE_IFINDEX) { dev = dev_get_by_index(net, vifc->vifc_lcl_ifindex); if (dev && !__in_dev_get_rtnl(dev)) { dev_put(dev); return -EADDRNOTAVAIL; } } else { dev = ip_dev_find(net, vifc->vifc_lcl_addr.s_addr); } if (!dev) return -EADDRNOTAVAIL; err = dev_set_allmulti(dev, 1); if (err) { dev_put(dev); return err; } break; default: return -EINVAL; } in_dev = __in_dev_get_rtnl(dev); if (!in_dev) { dev_put(dev); return -EADDRNOTAVAIL; } IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)++; inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, dev->ifindex, &in_dev->cnf); ip_rt_multicast_event(in_dev); /* Fill in the VIF structures */ vif_device_init(v, dev, vifc->vifc_rate_limit, vifc->vifc_threshold, vifc->vifc_flags | (!mrtsock ? VIFF_STATIC : 0), (VIFF_TUNNEL | VIFF_REGISTER)); err = dev_get_port_parent_id(dev, &ppid, true); if (err == 0) { memcpy(v->dev_parent_id.id, ppid.id, ppid.id_len); v->dev_parent_id.id_len = ppid.id_len; } else { v->dev_parent_id.id_len = 0; } v->local = vifc->vifc_lcl_addr.s_addr; v->remote = vifc->vifc_rmt_addr.s_addr; /* And finish update writing critical data */ spin_lock(&mrt_lock); rcu_assign_pointer(v->dev, dev); netdev_tracker_alloc(dev, &v->dev_tracker, GFP_ATOMIC); if (v->flags & VIFF_REGISTER) { /* Pairs with READ_ONCE() in ipmr_cache_report() and reg_vif_xmit() */ WRITE_ONCE(mrt->mroute_reg_vif_num, vifi); } if (vifi+1 > mrt->maxvif) WRITE_ONCE(mrt->maxvif, vifi + 1); spin_unlock(&mrt_lock); call_ipmr_vif_entry_notifiers(net, FIB_EVENT_VIF_ADD, v, dev, vifi, mrt->id); return 0; } /* called with rcu_read_lock() */ static struct mfc_cache *ipmr_cache_find(struct mr_table *mrt, __be32 origin, __be32 mcastgrp) { struct mfc_cache_cmp_arg arg = { .mfc_mcastgrp = mcastgrp, .mfc_origin = origin }; return mr_mfc_find(mrt, &arg); } /* Look for a (*,G) entry */ static struct mfc_cache *ipmr_cache_find_any(struct mr_table *mrt, __be32 mcastgrp, int vifi) { struct mfc_cache_cmp_arg arg = { .mfc_mcastgrp = mcastgrp, .mfc_origin = htonl(INADDR_ANY) }; if (mcastgrp == htonl(INADDR_ANY)) return mr_mfc_find_any_parent(mrt, vifi); return mr_mfc_find_any(mrt, vifi, &arg); } /* Look for a (S,G,iif) entry if parent != -1 */ static struct mfc_cache *ipmr_cache_find_parent(struct mr_table *mrt, __be32 origin, __be32 mcastgrp, int parent) { struct mfc_cache_cmp_arg arg = { .mfc_mcastgrp = mcastgrp, .mfc_origin = origin, }; return mr_mfc_find_parent(mrt, &arg, parent); } /* Allocate a multicast cache entry */ static struct mfc_cache *ipmr_cache_alloc(void) { struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL); if (c) { c->_c.mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1; c->_c.mfc_un.res.minvif = MAXVIFS; c->_c.free = ipmr_cache_free_rcu; refcount_set(&c->_c.mfc_un.res.refcount, 1); } return c; } static struct mfc_cache *ipmr_cache_alloc_unres(void) { struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC); if (c) { skb_queue_head_init(&c->_c.mfc_un.unres.unresolved); c->_c.mfc_un.unres.expires = jiffies + 10 * HZ; } return c; } /* A cache entry has gone into a resolved state from queued */ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt, struct mfc_cache *uc, struct mfc_cache *c) { struct sk_buff *skb; struct nlmsgerr *e; /* Play the pending entries through our router */ while ((skb = __skb_dequeue(&uc->_c.mfc_un.unres.unresolved))) { if (ip_hdr(skb)->version == 0) { struct nlmsghdr *nlh = skb_pull(skb, sizeof(struct iphdr)); if (mr_fill_mroute(mrt, skb, &c->_c, nlmsg_data(nlh)) > 0) { nlh->nlmsg_len = skb_tail_pointer(skb) - (u8 *)nlh; } else { nlh->nlmsg_type = NLMSG_ERROR; nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr)); skb_trim(skb, nlh->nlmsg_len); e = nlmsg_data(nlh); e->error = -EMSGSIZE; memset(&e->msg, 0, sizeof(e->msg)); } rtnl_unicast(skb, net, NETLINK_CB(skb).portid); } else { rcu_read_lock(); ip_mr_forward(net, mrt, skb->dev, skb, c, 0); rcu_read_unlock(); } } } /* Bounce a cache query up to mrouted and netlink. * * Called under rcu_read_lock(). */ static int ipmr_cache_report(const struct mr_table *mrt, struct sk_buff *pkt, vifi_t vifi, int assert) { const int ihl = ip_hdrlen(pkt); struct sock *mroute_sk; struct igmphdr *igmp; struct igmpmsg *msg; struct sk_buff *skb; int ret; mroute_sk = rcu_dereference(mrt->mroute_sk); if (!mroute_sk) return -EINVAL; if (assert == IGMPMSG_WHOLEPKT || assert == IGMPMSG_WRVIFWHOLE) skb = skb_realloc_headroom(pkt, sizeof(struct iphdr)); else skb = alloc_skb(128, GFP_ATOMIC); if (!skb) return -ENOBUFS; if (assert == IGMPMSG_WHOLEPKT || assert == IGMPMSG_WRVIFWHOLE) { /* Ugly, but we have no choice with this interface. * Duplicate old header, fix ihl, length etc. * And all this only to mangle msg->im_msgtype and * to set msg->im_mbz to "mbz" :-) */ skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); skb_reset_transport_header(skb); msg = (struct igmpmsg *)skb_network_header(skb); memcpy(msg, skb_network_header(pkt), sizeof(struct iphdr)); msg->im_msgtype = assert; msg->im_mbz = 0; if (assert == IGMPMSG_WRVIFWHOLE) { msg->im_vif = vifi; msg->im_vif_hi = vifi >> 8; } else { /* Pairs with WRITE_ONCE() in vif_add() and vif_delete() */ int vif_num = READ_ONCE(mrt->mroute_reg_vif_num); msg->im_vif = vif_num; msg->im_vif_hi = vif_num >> 8; } ip_hdr(skb)->ihl = sizeof(struct iphdr) >> 2; ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(pkt)->tot_len) + sizeof(struct iphdr)); } else { /* Copy the IP header */ skb_set_network_header(skb, skb->len); skb_put(skb, ihl); skb_copy_to_linear_data(skb, pkt->data, ihl); /* Flag to the kernel this is a route add */ ip_hdr(skb)->protocol = 0; msg = (struct igmpmsg *)skb_network_header(skb); msg->im_vif = vifi; msg->im_vif_hi = vifi >> 8; ipv4_pktinfo_prepare(mroute_sk, pkt, false); memcpy(skb->cb, pkt->cb, sizeof(skb->cb)); /* Add our header */ igmp = skb_put(skb, sizeof(struct igmphdr)); igmp->type = assert; msg->im_msgtype = assert; igmp->code = 0; ip_hdr(skb)->tot_len = htons(skb->len); /* Fix the length */ skb->transport_header = skb->network_header; } igmpmsg_netlink_event(mrt, skb); /* Deliver to mrouted */ ret = sock_queue_rcv_skb(mroute_sk, skb); if (ret < 0) { net_warn_ratelimited("mroute: pending queue full, dropping entries\n"); kfree_skb(skb); } return ret; } /* Queue a packet for resolution. It gets locked cache entry! */ /* Called under rcu_read_lock() */ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb, struct net_device *dev) { const struct iphdr *iph = ip_hdr(skb); struct mfc_cache *c; bool found = false; int err; spin_lock_bh(&mfc_unres_lock); list_for_each_entry(c, &mrt->mfc_unres_queue, _c.list) { if (c->mfc_mcastgrp == iph->daddr && c->mfc_origin == iph->saddr) { found = true; break; } } if (!found) { /* Create a new entry if allowable */ c = ipmr_cache_alloc_unres(); if (!c) { spin_unlock_bh(&mfc_unres_lock); kfree_skb(skb); return -ENOBUFS; } /* Fill in the new cache entry */ c->_c.mfc_parent = -1; c->mfc_origin = iph->saddr; c->mfc_mcastgrp = iph->daddr; /* Reflect first query at mrouted. */ err = ipmr_cache_report(mrt, skb, vifi, IGMPMSG_NOCACHE); if (err < 0) { /* If the report failed throw the cache entry out - Brad Parker */ spin_unlock_bh(&mfc_unres_lock); ipmr_cache_free(c); kfree_skb(skb); return err; } atomic_inc(&mrt->cache_resolve_queue_len); list_add(&c->_c.list, &mrt->mfc_unres_queue); mroute_netlink_event(mrt, c, RTM_NEWROUTE); if (atomic_read(&mrt->cache_resolve_queue_len) == 1) mod_timer(&mrt->ipmr_expire_timer, c->_c.mfc_un.unres.expires); } /* See if we can append the packet */ if (c->_c.mfc_un.unres.unresolved.qlen > 3) { kfree_skb(skb); err = -ENOBUFS; } else { if (dev) { skb->dev = dev; skb->skb_iif = dev->ifindex; } skb_queue_tail(&c->_c.mfc_un.unres.unresolved, skb); err = 0; } spin_unlock_bh(&mfc_unres_lock); return err; } /* MFC cache manipulation by user space mroute daemon */ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent) { struct net *net = read_pnet(&mrt->net); struct mfc_cache *c; /* The entries are added/deleted only under RTNL */ rcu_read_lock(); c = ipmr_cache_find_parent(mrt, mfc->mfcc_origin.s_addr, mfc->mfcc_mcastgrp.s_addr, parent); rcu_read_unlock(); if (!c) return -ENOENT; rhltable_remove(&mrt->mfc_hash, &c->_c.mnode, ipmr_rht_params); list_del_rcu(&c->_c.list); call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c, mrt->id); mroute_netlink_event(mrt, c, RTM_DELROUTE); mr_cache_put(&c->_c); return 0; } static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, struct mfcctl *mfc, int mrtsock, int parent) { struct mfc_cache *uc, *c; struct mr_mfc *_uc; bool found; int ret; if (mfc->mfcc_parent >= MAXVIFS) return -ENFILE; /* The entries are added/deleted only under RTNL */ rcu_read_lock(); c = ipmr_cache_find_parent(mrt, mfc->mfcc_origin.s_addr, mfc->mfcc_mcastgrp.s_addr, parent); rcu_read_unlock(); if (c) { spin_lock(&mrt_lock); c->_c.mfc_parent = mfc->mfcc_parent; ipmr_update_thresholds(mrt, &c->_c, mfc->mfcc_ttls); if (!mrtsock) c->_c.mfc_flags |= MFC_STATIC; spin_unlock(&mrt_lock); call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, c, mrt->id); mroute_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } if (mfc->mfcc_mcastgrp.s_addr != htonl(INADDR_ANY) && !ipv4_is_multicast(mfc->mfcc_mcastgrp.s_addr)) return -EINVAL; c = ipmr_cache_alloc(); if (!c) return -ENOMEM; c->mfc_origin = mfc->mfcc_origin.s_addr; c->mfc_mcastgrp = mfc->mfcc_mcastgrp.s_addr; c->_c.mfc_parent = mfc->mfcc_parent; ipmr_update_thresholds(mrt, &c->_c, mfc->mfcc_ttls); if (!mrtsock) c->_c.mfc_flags |= MFC_STATIC; ret = rhltable_insert_key(&mrt->mfc_hash, &c->cmparg, &c->_c.mnode, ipmr_rht_params); if (ret) { pr_err("ipmr: rhtable insert error %d\n", ret); ipmr_cache_free(c); return ret; } list_add_tail_rcu(&c->_c.list, &mrt->mfc_cache_list); /* Check to see if we resolved a queued list. If so we * need to send on the frames and tidy up. */ found = false; spin_lock_bh(&mfc_unres_lock); list_for_each_entry(_uc, &mrt->mfc_unres_queue, list) { uc = (struct mfc_cache *)_uc; if (uc->mfc_origin == c->mfc_origin && uc->mfc_mcastgrp == c->mfc_mcastgrp) { list_del(&_uc->list); atomic_dec(&mrt->cache_resolve_queue_len); found = true; break; } } if (list_empty(&mrt->mfc_unres_queue)) del_timer(&mrt->ipmr_expire_timer); spin_unlock_bh(&mfc_unres_lock); if (found) { ipmr_cache_resolve(net, mrt, uc, c); ipmr_cache_free(uc); } call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_ADD, c, mrt->id); mroute_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } /* Close the multicast socket, and clear the vif tables etc */ static void mroute_clean_tables(struct mr_table *mrt, int flags) { struct net *net = read_pnet(&mrt->net); struct mr_mfc *c, *tmp; struct mfc_cache *cache; LIST_HEAD(list); int i; /* Shut down all active vif entries */ if (flags & (MRT_FLUSH_VIFS | MRT_FLUSH_VIFS_STATIC)) { for (i = 0; i < mrt->maxvif; i++) { if (((mrt->vif_table[i].flags & VIFF_STATIC) && !(flags & MRT_FLUSH_VIFS_STATIC)) || (!(mrt->vif_table[i].flags & VIFF_STATIC) && !(flags & MRT_FLUSH_VIFS))) continue; vif_delete(mrt, i, 0, &list); } unregister_netdevice_many(&list); } /* Wipe the cache */ if (flags & (MRT_FLUSH_MFC | MRT_FLUSH_MFC_STATIC)) { list_for_each_entry_safe(c, tmp, &mrt->mfc_cache_list, list) { if (((c->mfc_flags & MFC_STATIC) && !(flags & MRT_FLUSH_MFC_STATIC)) || (!(c->mfc_flags & MFC_STATIC) && !(flags & MRT_FLUSH_MFC))) continue; rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params); list_del_rcu(&c->list); cache = (struct mfc_cache *)c; call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, cache, mrt->id); mroute_netlink_event(mrt, cache, RTM_DELROUTE); mr_cache_put(c); } } if (flags & MRT_FLUSH_MFC) { if (atomic_read(&mrt->cache_resolve_queue_len) != 0) { spin_lock_bh(&mfc_unres_lock); list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) { list_del(&c->list); cache = (struct mfc_cache *)c; mroute_netlink_event(mrt, cache, RTM_DELROUTE); ipmr_destroy_unres(mrt, cache); } spin_unlock_bh(&mfc_unres_lock); } } } /* called from ip_ra_control(), before an RCU grace period, * we don't need to call synchronize_rcu() here */ static void mrtsock_destruct(struct sock *sk) { struct net *net = sock_net(sk); struct mr_table *mrt; rtnl_lock(); ipmr_for_each_table(mrt, net) { if (sk == rtnl_dereference(mrt->mroute_sk)) { IPV4_DEVCONF_ALL(net, MC_FORWARDING)--; inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv4.devconf_all); RCU_INIT_POINTER(mrt->mroute_sk, NULL); mroute_clean_tables(mrt, MRT_FLUSH_VIFS | MRT_FLUSH_MFC); } } rtnl_unlock(); } /* Socket options and virtual interface manipulation. The whole * virtual interface system is a complete heap, but unfortunately * that's how BSD mrouted happens to think. Maybe one day with a proper * MOSPF/PIM router set up we can clean this up. */ int ip_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval, unsigned int optlen) { struct net *net = sock_net(sk); int val, ret = 0, parent = 0; struct mr_table *mrt; struct vifctl vif; struct mfcctl mfc; bool do_wrvifwhole; u32 uval; /* There's one exception to the lock - MRT_DONE which needs to unlock */ rtnl_lock(); if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_IGMP) { ret = -EOPNOTSUPP; goto out_unlock; } mrt = __ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); if (!mrt) { ret = -ENOENT; goto out_unlock; } if (optname != MRT_INIT) { if (sk != rcu_access_pointer(mrt->mroute_sk) && !ns_capable(net->user_ns, CAP_NET_ADMIN)) { ret = -EACCES; goto out_unlock; } } switch (optname) { case MRT_INIT: if (optlen != sizeof(int)) { ret = -EINVAL; break; } if (rtnl_dereference(mrt->mroute_sk)) { ret = -EADDRINUSE; break; } ret = ip_ra_control(sk, 1, mrtsock_destruct); if (ret == 0) { rcu_assign_pointer(mrt->mroute_sk, sk); IPV4_DEVCONF_ALL(net, MC_FORWARDING)++; inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv4.devconf_all); } break; case MRT_DONE: if (sk != rcu_access_pointer(mrt->mroute_sk)) { ret = -EACCES; } else { /* We need to unlock here because mrtsock_destruct takes * care of rtnl itself and we can't change that due to * the IP_ROUTER_ALERT setsockopt which runs without it. */ rtnl_unlock(); ret = ip_ra_control(sk, 0, NULL); goto out; } break; case MRT_ADD_VIF: case MRT_DEL_VIF: if (optlen != sizeof(vif)) { ret = -EINVAL; break; } if (copy_from_sockptr(&vif, optval, sizeof(vif))) { ret = -EFAULT; break; } if (vif.vifc_vifi >= MAXVIFS) { ret = -ENFILE; break; } if (optname == MRT_ADD_VIF) { ret = vif_add(net, mrt, &vif, sk == rtnl_dereference(mrt->mroute_sk)); } else { ret = vif_delete(mrt, vif.vifc_vifi, 0, NULL); } break; /* Manipulate the forwarding caches. These live * in a sort of kernel/user symbiosis. */ case MRT_ADD_MFC: case MRT_DEL_MFC: parent = -1; fallthrough; case MRT_ADD_MFC_PROXY: case MRT_DEL_MFC_PROXY: if (optlen != sizeof(mfc)) { ret = -EINVAL; break; } if (copy_from_sockptr(&mfc, optval, sizeof(mfc))) { ret = -EFAULT; break; } if (parent == 0) parent = mfc.mfcc_parent; if (optname == MRT_DEL_MFC || optname == MRT_DEL_MFC_PROXY) ret = ipmr_mfc_delete(mrt, &mfc, parent); else ret = ipmr_mfc_add(net, mrt, &mfc, sk == rtnl_dereference(mrt->mroute_sk), parent); break; case MRT_FLUSH: if (optlen != sizeof(val)) { ret = -EINVAL; break; } if (copy_from_sockptr(&val, optval, sizeof(val))) { ret = -EFAULT; break; } mroute_clean_tables(mrt, val); break; /* Control PIM assert. */ case MRT_ASSERT: if (optlen != sizeof(val)) { ret = -EINVAL; break; } if (copy_from_sockptr(&val, optval, sizeof(val))) { ret = -EFAULT; break; } mrt->mroute_do_assert = val; break; case MRT_PIM: if (!ipmr_pimsm_enabled()) { ret = -ENOPROTOOPT; break; } if (optlen != sizeof(val)) { ret = -EINVAL; break; } if (copy_from_sockptr(&val, optval, sizeof(val))) { ret = -EFAULT; break; } do_wrvifwhole = (val == IGMPMSG_WRVIFWHOLE); val = !!val; if (val != mrt->mroute_do_pim) { mrt->mroute_do_pim = val; mrt->mroute_do_assert = val; mrt->mroute_do_wrvifwhole = do_wrvifwhole; } break; case MRT_TABLE: if (!IS_BUILTIN(CONFIG_IP_MROUTE_MULTIPLE_TABLES)) { ret = -ENOPROTOOPT; break; } if (optlen != sizeof(uval)) { ret = -EINVAL; break; } if (copy_from_sockptr(&uval, optval, sizeof(uval))) { ret = -EFAULT; break; } if (sk == rtnl_dereference(mrt->mroute_sk)) { ret = -EBUSY; } else { mrt = ipmr_new_table(net, uval); if (IS_ERR(mrt)) ret = PTR_ERR(mrt); else raw_sk(sk)->ipmr_table = uval; } break; /* Spurious command, or MRT_VERSION which you cannot set. */ default: ret = -ENOPROTOOPT; } out_unlock: rtnl_unlock(); out: return ret; } /* Execute if this ioctl is a special mroute ioctl */ int ipmr_sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) { switch (cmd) { /* These userspace buffers will be consumed by ipmr_ioctl() */ case SIOCGETVIFCNT: { struct sioc_vif_req buffer; return sock_ioctl_inout(sk, cmd, arg, &buffer, sizeof(buffer)); } case SIOCGETSGCNT: { struct sioc_sg_req buffer; return sock_ioctl_inout(sk, cmd, arg, &buffer, sizeof(buffer)); } } /* return code > 0 means that the ioctl was not executed */ return 1; } /* Getsock opt support for the multicast routing system. */ int ip_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval, sockptr_t optlen) { int olr; int val; struct net *net = sock_net(sk); struct mr_table *mrt; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_IGMP) return -EOPNOTSUPP; mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); if (!mrt) return -ENOENT; switch (optname) { case MRT_VERSION: val = 0x0305; break; case MRT_PIM: if (!ipmr_pimsm_enabled()) return -ENOPROTOOPT; val = mrt->mroute_do_pim; break; case MRT_ASSERT: val = mrt->mroute_do_assert; break; default: return -ENOPROTOOPT; } if (copy_from_sockptr(&olr, optlen, sizeof(int))) return -EFAULT; if (olr < 0) return -EINVAL; olr = min_t(unsigned int, olr, sizeof(int)); if (copy_to_sockptr(optlen, &olr, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &val, olr)) return -EFAULT; return 0; } /* The IP multicast ioctl support routines. */ int ipmr_ioctl(struct sock *sk, int cmd, void *arg) { struct vif_device *vif; struct mfc_cache *c; struct net *net = sock_net(sk); struct sioc_vif_req *vr; struct sioc_sg_req *sr; struct mr_table *mrt; mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); if (!mrt) return -ENOENT; switch (cmd) { case SIOCGETVIFCNT: vr = (struct sioc_vif_req *)arg; if (vr->vifi >= mrt->maxvif) return -EINVAL; vr->vifi = array_index_nospec(vr->vifi, mrt->maxvif); rcu_read_lock(); vif = &mrt->vif_table[vr->vifi]; if (VIF_EXISTS(mrt, vr->vifi)) { vr->icount = READ_ONCE(vif->pkt_in); vr->ocount = READ_ONCE(vif->pkt_out); vr->ibytes = READ_ONCE(vif->bytes_in); vr->obytes = READ_ONCE(vif->bytes_out); rcu_read_unlock(); return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; case SIOCGETSGCNT: sr = (struct sioc_sg_req *)arg; rcu_read_lock(); c = ipmr_cache_find(mrt, sr->src.s_addr, sr->grp.s_addr); if (c) { sr->pktcnt = c->_c.mfc_un.res.pkt; sr->bytecnt = c->_c.mfc_un.res.bytes; sr->wrong_if = c->_c.mfc_un.res.wrong_if; rcu_read_unlock(); return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; default: return -ENOIOCTLCMD; } } #ifdef CONFIG_COMPAT struct compat_sioc_sg_req { struct in_addr src; struct in_addr grp; compat_ulong_t pktcnt; compat_ulong_t bytecnt; compat_ulong_t wrong_if; }; struct compat_sioc_vif_req { vifi_t vifi; /* Which iface */ compat_ulong_t icount; compat_ulong_t ocount; compat_ulong_t ibytes; compat_ulong_t obytes; }; int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) { struct compat_sioc_sg_req sr; struct compat_sioc_vif_req vr; struct vif_device *vif; struct mfc_cache *c; struct net *net = sock_net(sk); struct mr_table *mrt; mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); if (!mrt) return -ENOENT; switch (cmd) { case SIOCGETVIFCNT: if (copy_from_user(&vr, arg, sizeof(vr))) return -EFAULT; if (vr.vifi >= mrt->maxvif) return -EINVAL; vr.vifi = array_index_nospec(vr.vifi, mrt->maxvif); rcu_read_lock(); vif = &mrt->vif_table[vr.vifi]; if (VIF_EXISTS(mrt, vr.vifi)) { vr.icount = READ_ONCE(vif->pkt_in); vr.ocount = READ_ONCE(vif->pkt_out); vr.ibytes = READ_ONCE(vif->bytes_in); vr.obytes = READ_ONCE(vif->bytes_out); rcu_read_unlock(); if (copy_to_user(arg, &vr, sizeof(vr))) return -EFAULT; return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; case SIOCGETSGCNT: if (copy_from_user(&sr, arg, sizeof(sr))) return -EFAULT; rcu_read_lock(); c = ipmr_cache_find(mrt, sr.src.s_addr, sr.grp.s_addr); if (c) { sr.pktcnt = c->_c.mfc_un.res.pkt; sr.bytecnt = c->_c.mfc_un.res.bytes; sr.wrong_if = c->_c.mfc_un.res.wrong_if; rcu_read_unlock(); if (copy_to_user(arg, &sr, sizeof(sr))) return -EFAULT; return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; default: return -ENOIOCTLCMD; } } #endif static int ipmr_device_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct mr_table *mrt; struct vif_device *v; int ct; if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; ipmr_for_each_table(mrt, net) { v = &mrt->vif_table[0]; for (ct = 0; ct < mrt->maxvif; ct++, v++) { if (rcu_access_pointer(v->dev) == dev) vif_delete(mrt, ct, 1, NULL); } } return NOTIFY_DONE; } static struct notifier_block ip_mr_notifier = { .notifier_call = ipmr_device_event, }; /* Encapsulate a packet by attaching a valid IPIP header to it. * This avoids tunnel drivers and other mess and gives us the speed so * important for multicast video. */ static void ip_encap(struct net *net, struct sk_buff *skb, __be32 saddr, __be32 daddr) { struct iphdr *iph; const struct iphdr *old_iph = ip_hdr(skb); skb_push(skb, sizeof(struct iphdr)); skb->transport_header = skb->network_header; skb_reset_network_header(skb); iph = ip_hdr(skb); iph->version = 4; iph->tos = old_iph->tos; iph->ttl = old_iph->ttl; iph->frag_off = 0; iph->daddr = daddr; iph->saddr = saddr; iph->protocol = IPPROTO_IPIP; iph->ihl = 5; iph->tot_len = htons(skb->len); ip_select_ident(net, skb, NULL); ip_send_check(iph); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); nf_reset_ct(skb); } static inline int ipmr_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { struct ip_options *opt = &(IPCB(skb)->opt); IP_INC_STATS(net, IPSTATS_MIB_OUTFORWDATAGRAMS); if (unlikely(opt->optlen)) ip_forward_options(skb); return dst_output(net, sk, skb); } #ifdef CONFIG_NET_SWITCHDEV static bool ipmr_forward_offloaded(struct sk_buff *skb, struct mr_table *mrt, int in_vifi, int out_vifi) { struct vif_device *out_vif = &mrt->vif_table[out_vifi]; struct vif_device *in_vif = &mrt->vif_table[in_vifi]; if (!skb->offload_l3_fwd_mark) return false; if (!out_vif->dev_parent_id.id_len || !in_vif->dev_parent_id.id_len) return false; return netdev_phys_item_id_same(&out_vif->dev_parent_id, &in_vif->dev_parent_id); } #else static bool ipmr_forward_offloaded(struct sk_buff *skb, struct mr_table *mrt, int in_vifi, int out_vifi) { return false; } #endif /* Processing handlers for ipmr_forward, under rcu_read_lock() */ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, int in_vifi, struct sk_buff *skb, int vifi) { const struct iphdr *iph = ip_hdr(skb); struct vif_device *vif = &mrt->vif_table[vifi]; struct net_device *vif_dev; struct net_device *dev; struct rtable *rt; struct flowi4 fl4; int encap = 0; vif_dev = vif_dev_read(vif); if (!vif_dev) goto out_free; if (vif->flags & VIFF_REGISTER) { WRITE_ONCE(vif->pkt_out, vif->pkt_out + 1); WRITE_ONCE(vif->bytes_out, vif->bytes_out + skb->len); DEV_STATS_ADD(vif_dev, tx_bytes, skb->len); DEV_STATS_INC(vif_dev, tx_packets); ipmr_cache_report(mrt, skb, vifi, IGMPMSG_WHOLEPKT); goto out_free; } if (ipmr_forward_offloaded(skb, mrt, in_vifi, vifi)) goto out_free; if (vif->flags & VIFF_TUNNEL) { rt = ip_route_output_ports(net, &fl4, NULL, vif->remote, vif->local, 0, 0, IPPROTO_IPIP, iph->tos & INET_DSCP_MASK, vif->link); if (IS_ERR(rt)) goto out_free; encap = sizeof(struct iphdr); } else { rt = ip_route_output_ports(net, &fl4, NULL, iph->daddr, 0, 0, 0, IPPROTO_IPIP, iph->tos & INET_DSCP_MASK, vif->link); if (IS_ERR(rt)) goto out_free; } dev = rt->dst.dev; if (skb->len+encap > dst_mtu(&rt->dst) && (ntohs(iph->frag_off) & IP_DF)) { /* Do not fragment multicasts. Alas, IPv4 does not * allow to send ICMP, so that packets will disappear * to blackhole. */ IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); ip_rt_put(rt); goto out_free; } encap += LL_RESERVED_SPACE(dev) + rt->dst.header_len; if (skb_cow(skb, encap)) { ip_rt_put(rt); goto out_free; } WRITE_ONCE(vif->pkt_out, vif->pkt_out + 1); WRITE_ONCE(vif->bytes_out, vif->bytes_out + skb->len); skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); ip_decrease_ttl(ip_hdr(skb)); /* FIXME: forward and output firewalls used to be called here. * What do we do with netfilter? -- RR */ if (vif->flags & VIFF_TUNNEL) { ip_encap(net, skb, vif->local, vif->remote); /* FIXME: extra output firewall step used to be here. --RR */ DEV_STATS_INC(vif_dev, tx_packets); DEV_STATS_ADD(vif_dev, tx_bytes, skb->len); } IPCB(skb)->flags |= IPSKB_FORWARDED; /* RFC1584 teaches, that DVMRP/PIM router must deliver packets locally * not only before forwarding, but after forwarding on all output * interfaces. It is clear, if mrouter runs a multicasting * program, it should receive packets not depending to what interface * program is joined. * If we will not make it, the program will have to join on all * interfaces. On the other hand, multihoming host (or router, but * not mrouter) cannot join to more than one interface - it will * result in receiving multiple packets. */ NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, net, NULL, skb, skb->dev, dev, ipmr_forward_finish); return; out_free: kfree_skb(skb); } /* Called with mrt_lock or rcu_read_lock() */ static int ipmr_find_vif(const struct mr_table *mrt, struct net_device *dev) { int ct; /* Pairs with WRITE_ONCE() in vif_delete()/vif_add() */ for (ct = READ_ONCE(mrt->maxvif) - 1; ct >= 0; ct--) { if (rcu_access_pointer(mrt->vif_table[ct].dev) == dev) break; } return ct; } /* "local" means that we should preserve one skb (for local delivery) */ /* Called uner rcu_read_lock() */ static void ip_mr_forward(struct net *net, struct mr_table *mrt, struct net_device *dev, struct sk_buff *skb, struct mfc_cache *c, int local) { int true_vifi = ipmr_find_vif(mrt, dev); int psend = -1; int vif, ct; vif = c->_c.mfc_parent; c->_c.mfc_un.res.pkt++; c->_c.mfc_un.res.bytes += skb->len; c->_c.mfc_un.res.lastuse = jiffies; if (c->mfc_origin == htonl(INADDR_ANY) && true_vifi >= 0) { struct mfc_cache *cache_proxy; /* For an (*,G) entry, we only check that the incoming * interface is part of the static tree. */ cache_proxy = mr_mfc_find_any_parent(mrt, vif); if (cache_proxy && cache_proxy->_c.mfc_un.res.ttls[true_vifi] < 255) goto forward; } /* Wrong interface: drop packet and (maybe) send PIM assert. */ if (rcu_access_pointer(mrt->vif_table[vif].dev) != dev) { if (rt_is_output_route(skb_rtable(skb))) { /* It is our own packet, looped back. * Very complicated situation... * * The best workaround until routing daemons will be * fixed is not to redistribute packet, if it was * send through wrong interface. It means, that * multicast applications WILL NOT work for * (S,G), which have default multicast route pointing * to wrong oif. In any case, it is not a good * idea to use multicasting applications on router. */ goto dont_forward; } c->_c.mfc_un.res.wrong_if++; if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, * so that we cannot check that packet arrived on an oif. * It is bad, but otherwise we would need to move pretty * large chunk of pimd to kernel. Ough... --ANK */ (mrt->mroute_do_pim || c->_c.mfc_un.res.ttls[true_vifi] < 255) && time_after(jiffies, c->_c.mfc_un.res.last_assert + MFC_ASSERT_THRESH)) { c->_c.mfc_un.res.last_assert = jiffies; ipmr_cache_report(mrt, skb, true_vifi, IGMPMSG_WRONGVIF); if (mrt->mroute_do_wrvifwhole) ipmr_cache_report(mrt, skb, true_vifi, IGMPMSG_WRVIFWHOLE); } goto dont_forward; } forward: WRITE_ONCE(mrt->vif_table[vif].pkt_in, mrt->vif_table[vif].pkt_in + 1); WRITE_ONCE(mrt->vif_table[vif].bytes_in, mrt->vif_table[vif].bytes_in + skb->len); /* Forward the frame */ if (c->mfc_origin == htonl(INADDR_ANY) && c->mfc_mcastgrp == htonl(INADDR_ANY)) { if (true_vifi >= 0 && true_vifi != c->_c.mfc_parent && ip_hdr(skb)->ttl > c->_c.mfc_un.res.ttls[c->_c.mfc_parent]) { /* It's an (*,*) entry and the packet is not coming from * the upstream: forward the packet to the upstream * only. */ psend = c->_c.mfc_parent; goto last_forward; } goto dont_forward; } for (ct = c->_c.mfc_un.res.maxvif - 1; ct >= c->_c.mfc_un.res.minvif; ct--) { /* For (*,G) entry, don't forward to the incoming interface */ if ((c->mfc_origin != htonl(INADDR_ANY) || ct != true_vifi) && ip_hdr(skb)->ttl > c->_c.mfc_un.res.ttls[ct]) { if (psend != -1) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) ipmr_queue_xmit(net, mrt, true_vifi, skb2, psend); } psend = ct; } } last_forward: if (psend != -1) { if (local) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) ipmr_queue_xmit(net, mrt, true_vifi, skb2, psend); } else { ipmr_queue_xmit(net, mrt, true_vifi, skb, psend); return; } } dont_forward: if (!local) kfree_skb(skb); } static struct mr_table *ipmr_rt_fib_lookup(struct net *net, struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct iphdr *iph = ip_hdr(skb); struct flowi4 fl4 = { .daddr = iph->daddr, .saddr = iph->saddr, .flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(iph)), .flowi4_oif = (rt_is_output_route(rt) ? skb->dev->ifindex : 0), .flowi4_iif = (rt_is_output_route(rt) ? LOOPBACK_IFINDEX : skb->dev->ifindex), .flowi4_mark = skb->mark, }; struct mr_table *mrt; int err; err = ipmr_fib_lookup(net, &fl4, &mrt); if (err) return ERR_PTR(err); return mrt; } /* Multicast packets for forwarding arrive here * Called with rcu_read_lock(); */ int ip_mr_input(struct sk_buff *skb) { struct mfc_cache *cache; struct net *net = dev_net(skb->dev); int local = skb_rtable(skb)->rt_flags & RTCF_LOCAL; struct mr_table *mrt; struct net_device *dev; /* skb->dev passed in is the loX master dev for vrfs. * As there are no vifs associated with loopback devices, * get the proper interface that does have a vif associated with it. */ dev = skb->dev; if (netif_is_l3_master(skb->dev)) { dev = dev_get_by_index_rcu(net, IPCB(skb)->iif); if (!dev) { kfree_skb(skb); return -ENODEV; } } /* Packet is looped back after forward, it should not be * forwarded second time, but still can be delivered locally. */ if (IPCB(skb)->flags & IPSKB_FORWARDED) goto dont_forward; mrt = ipmr_rt_fib_lookup(net, skb); if (IS_ERR(mrt)) { kfree_skb(skb); return PTR_ERR(mrt); } if (!local) { if (IPCB(skb)->opt.router_alert) { if (ip_call_ra_chain(skb)) return 0; } else if (ip_hdr(skb)->protocol == IPPROTO_IGMP) { /* IGMPv1 (and broken IGMPv2 implementations sort of * Cisco IOS <= 11.2(8)) do not put router alert * option to IGMP packets destined to routable * groups. It is very bad, because it means * that we can forward NO IGMP messages. */ struct sock *mroute_sk; mroute_sk = rcu_dereference(mrt->mroute_sk); if (mroute_sk) { nf_reset_ct(skb); raw_rcv(mroute_sk, skb); return 0; } } } /* already under rcu_read_lock() */ cache = ipmr_cache_find(mrt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr); if (!cache) { int vif = ipmr_find_vif(mrt, dev); if (vif >= 0) cache = ipmr_cache_find_any(mrt, ip_hdr(skb)->daddr, vif); } /* No usable cache entry */ if (!cache) { int vif; if (local) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); ip_local_deliver(skb); if (!skb2) return -ENOBUFS; skb = skb2; } vif = ipmr_find_vif(mrt, dev); if (vif >= 0) return ipmr_cache_unresolved(mrt, vif, skb, dev); kfree_skb(skb); return -ENODEV; } ip_mr_forward(net, mrt, dev, skb, cache, local); if (local) return ip_local_deliver(skb); return 0; dont_forward: if (local) return ip_local_deliver(skb); kfree_skb(skb); return 0; } #ifdef CONFIG_IP_PIMSM_V1 /* Handle IGMP messages of PIMv1 */ int pim_rcv_v1(struct sk_buff *skb) { struct igmphdr *pim; struct net *net = dev_net(skb->dev); struct mr_table *mrt; if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(struct iphdr))) goto drop; pim = igmp_hdr(skb); mrt = ipmr_rt_fib_lookup(net, skb); if (IS_ERR(mrt)) goto drop; if (!mrt->mroute_do_pim || pim->group != PIM_V1_VERSION || pim->code != PIM_V1_REGISTER) goto drop; if (__pim_rcv(mrt, skb, sizeof(*pim))) { drop: kfree_skb(skb); } return 0; } #endif #ifdef CONFIG_IP_PIMSM_V2 static int pim_rcv(struct sk_buff *skb) { struct pimreghdr *pim; struct net *net = dev_net(skb->dev); struct mr_table *mrt; if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(struct iphdr))) goto drop; pim = (struct pimreghdr *)skb_transport_header(skb); if (pim->type != ((PIM_VERSION << 4) | (PIM_TYPE_REGISTER)) || (pim->flags & PIM_NULL_REGISTER) || (ip_compute_csum((void *)pim, sizeof(*pim)) != 0 && csum_fold(skb_checksum(skb, 0, skb->len, 0)))) goto drop; mrt = ipmr_rt_fib_lookup(net, skb); if (IS_ERR(mrt)) goto drop; if (__pim_rcv(mrt, skb, sizeof(*pim))) { drop: kfree_skb(skb); } return 0; } #endif int ipmr_get_route(struct net *net, struct sk_buff *skb, __be32 saddr, __be32 daddr, struct rtmsg *rtm, u32 portid) { struct mfc_cache *cache; struct mr_table *mrt; int err; rcu_read_lock(); mrt = __ipmr_get_table(net, RT_TABLE_DEFAULT); if (!mrt) { rcu_read_unlock(); return -ENOENT; } cache = ipmr_cache_find(mrt, saddr, daddr); if (!cache && skb->dev) { int vif = ipmr_find_vif(mrt, skb->dev); if (vif >= 0) cache = ipmr_cache_find_any(mrt, daddr, vif); } if (!cache) { struct sk_buff *skb2; struct iphdr *iph; struct net_device *dev; int vif = -1; dev = skb->dev; if (dev) vif = ipmr_find_vif(mrt, dev); if (vif < 0) { rcu_read_unlock(); return -ENODEV; } skb2 = skb_realloc_headroom(skb, sizeof(struct iphdr)); if (!skb2) { rcu_read_unlock(); return -ENOMEM; } NETLINK_CB(skb2).portid = portid; skb_push(skb2, sizeof(struct iphdr)); skb_reset_network_header(skb2); iph = ip_hdr(skb2); iph->ihl = sizeof(struct iphdr) >> 2; iph->saddr = saddr; iph->daddr = daddr; iph->version = 0; err = ipmr_cache_unresolved(mrt, vif, skb2, dev); rcu_read_unlock(); return err; } err = mr_fill_mroute(mrt, skb, &cache->_c, rtm); rcu_read_unlock(); return err; } static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mfc_cache *c, int cmd, int flags) { struct nlmsghdr *nlh; struct rtmsg *rtm; int err; nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags); if (!nlh) return -EMSGSIZE; rtm = nlmsg_data(nlh); rtm->rtm_family = RTNL_FAMILY_IPMR; rtm->rtm_dst_len = 32; rtm->rtm_src_len = 32; rtm->rtm_tos = 0; rtm->rtm_table = mrt->id; if (nla_put_u32(skb, RTA_TABLE, mrt->id)) goto nla_put_failure; rtm->rtm_type = RTN_MULTICAST; rtm->rtm_scope = RT_SCOPE_UNIVERSE; if (c->_c.mfc_flags & MFC_STATIC) rtm->rtm_protocol = RTPROT_STATIC; else rtm->rtm_protocol = RTPROT_MROUTED; rtm->rtm_flags = 0; if (nla_put_in_addr(skb, RTA_SRC, c->mfc_origin) || nla_put_in_addr(skb, RTA_DST, c->mfc_mcastgrp)) goto nla_put_failure; err = mr_fill_mroute(mrt, skb, &c->_c, rtm); /* do not break the dump if cache is unresolved */ if (err < 0 && err != -ENOENT) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int _ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags) { return ipmr_fill_mroute(mrt, skb, portid, seq, (struct mfc_cache *)c, cmd, flags); } static size_t mroute_msgsize(bool unresolved, int maxvif) { size_t len = NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(4) /* RTA_TABLE */ + nla_total_size(4) /* RTA_SRC */ + nla_total_size(4) /* RTA_DST */ ; if (!unresolved) len = len + nla_total_size(4) /* RTA_IIF */ + nla_total_size(0) /* RTA_MULTIPATH */ + maxvif * NLA_ALIGN(sizeof(struct rtnexthop)) /* RTA_MFC_STATS */ + nla_total_size_64bit(sizeof(struct rta_mfc_stats)) ; return len; } static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, int cmd) { struct net *net = read_pnet(&mrt->net); struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(mroute_msgsize(mfc->_c.mfc_parent >= MAXVIFS, mrt->maxvif), GFP_ATOMIC); if (!skb) goto errout; err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0); if (err < 0) goto errout; rtnl_notify(skb, net, 0, RTNLGRP_IPV4_MROUTE, NULL, GFP_ATOMIC); return; errout: kfree_skb(skb); rtnl_set_sk_err(net, RTNLGRP_IPV4_MROUTE, err); } static size_t igmpmsg_netlink_msgsize(size_t payloadlen) { size_t len = NLMSG_ALIGN(sizeof(struct rtgenmsg)) + nla_total_size(1) /* IPMRA_CREPORT_MSGTYPE */ + nla_total_size(4) /* IPMRA_CREPORT_VIF_ID */ + nla_total_size(4) /* IPMRA_CREPORT_SRC_ADDR */ + nla_total_size(4) /* IPMRA_CREPORT_DST_ADDR */ + nla_total_size(4) /* IPMRA_CREPORT_TABLE */ /* IPMRA_CREPORT_PKT */ + nla_total_size(payloadlen) ; return len; } static void igmpmsg_netlink_event(const struct mr_table *mrt, struct sk_buff *pkt) { struct net *net = read_pnet(&mrt->net); struct nlmsghdr *nlh; struct rtgenmsg *rtgenm; struct igmpmsg *msg; struct sk_buff *skb; struct nlattr *nla; int payloadlen; payloadlen = pkt->len - sizeof(struct igmpmsg); msg = (struct igmpmsg *)skb_network_header(pkt); skb = nlmsg_new(igmpmsg_netlink_msgsize(payloadlen), GFP_ATOMIC); if (!skb) goto errout; nlh = nlmsg_put(skb, 0, 0, RTM_NEWCACHEREPORT, sizeof(struct rtgenmsg), 0); if (!nlh) goto errout; rtgenm = nlmsg_data(nlh); rtgenm->rtgen_family = RTNL_FAMILY_IPMR; if (nla_put_u8(skb, IPMRA_CREPORT_MSGTYPE, msg->im_msgtype) || nla_put_u32(skb, IPMRA_CREPORT_VIF_ID, msg->im_vif | (msg->im_vif_hi << 8)) || nla_put_in_addr(skb, IPMRA_CREPORT_SRC_ADDR, msg->im_src.s_addr) || nla_put_in_addr(skb, IPMRA_CREPORT_DST_ADDR, msg->im_dst.s_addr) || nla_put_u32(skb, IPMRA_CREPORT_TABLE, mrt->id)) goto nla_put_failure; nla = nla_reserve(skb, IPMRA_CREPORT_PKT, payloadlen); if (!nla || skb_copy_bits(pkt, sizeof(struct igmpmsg), nla_data(nla), payloadlen)) goto nla_put_failure; nlmsg_end(skb, nlh); rtnl_notify(skb, net, 0, RTNLGRP_IPV4_MROUTE_R, NULL, GFP_ATOMIC); return; nla_put_failure: nlmsg_cancel(skb, nlh); errout: kfree_skb(skb); rtnl_set_sk_err(net, RTNLGRP_IPV4_MROUTE_R, -ENOBUFS); } static int ipmr_rtm_valid_getroute_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct rtmsg *rtm; int i, err; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for multicast route get request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy, extack); rtm = nlmsg_data(nlh); if ((rtm->rtm_src_len && rtm->rtm_src_len != 32) || (rtm->rtm_dst_len && rtm->rtm_dst_len != 32) || rtm->rtm_tos || rtm->rtm_table || rtm->rtm_protocol || rtm->rtm_scope || rtm->rtm_type || rtm->rtm_flags) { NL_SET_ERR_MSG(extack, "ipv4: Invalid values in header for multicast route get request"); return -EINVAL; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy, extack); if (err) return err; if ((tb[RTA_SRC] && !rtm->rtm_src_len) || (tb[RTA_DST] && !rtm->rtm_dst_len)) { NL_SET_ERR_MSG(extack, "ipv4: rtm_src_len and rtm_dst_len must be 32 for IPv4"); return -EINVAL; } for (i = 0; i <= RTA_MAX; i++) { if (!tb[i]) continue; switch (i) { case RTA_SRC: case RTA_DST: case RTA_TABLE: break; default: NL_SET_ERR_MSG(extack, "ipv4: Unsupported attribute in multicast route get request"); return -EINVAL; } } return 0; } static int ipmr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[RTA_MAX + 1]; struct sk_buff *skb = NULL; struct mfc_cache *cache; struct mr_table *mrt; __be32 src, grp; u32 tableid; int err; err = ipmr_rtm_valid_getroute_req(in_skb, nlh, tb, extack); if (err < 0) goto errout; src = nla_get_in_addr_default(tb[RTA_SRC], 0); grp = nla_get_in_addr_default(tb[RTA_DST], 0); tableid = nla_get_u32_default(tb[RTA_TABLE], 0); mrt = __ipmr_get_table(net, tableid ? tableid : RT_TABLE_DEFAULT); if (!mrt) { err = -ENOENT; goto errout_free; } /* entries are added/deleted only under RTNL */ rcu_read_lock(); cache = ipmr_cache_find(mrt, src, grp); rcu_read_unlock(); if (!cache) { err = -ENOENT; goto errout_free; } skb = nlmsg_new(mroute_msgsize(false, mrt->maxvif), GFP_KERNEL); if (!skb) { err = -ENOBUFS; goto errout_free; } err = ipmr_fill_mroute(mrt, skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, cache, RTM_NEWROUTE, 0); if (err < 0) goto errout_free; err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: return err; errout_free: kfree_skb(skb); goto errout; } static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) { struct fib_dump_filter filter = { .rtnl_held = true, }; int err; if (cb->strict_check) { err = ip_valid_fib_dump_req(sock_net(skb->sk), cb->nlh, &filter, cb); if (err < 0) return err; } if (filter.table_id) { struct mr_table *mrt; mrt = __ipmr_get_table(sock_net(skb->sk), filter.table_id); if (!mrt) { if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IPMR) return skb->len; NL_SET_ERR_MSG(cb->extack, "ipv4: MR table does not exist"); return -ENOENT; } err = mr_table_dump(mrt, skb, cb, _ipmr_fill_mroute, &mfc_unres_lock, &filter); return skb->len ? : err; } return mr_rtm_dumproute(skb, cb, ipmr_mr_table_iter, _ipmr_fill_mroute, &mfc_unres_lock, &filter); } static const struct nla_policy rtm_ipmr_policy[RTA_MAX + 1] = { [RTA_SRC] = { .type = NLA_U32 }, [RTA_DST] = { .type = NLA_U32 }, [RTA_IIF] = { .type = NLA_U32 }, [RTA_TABLE] = { .type = NLA_U32 }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, }; static bool ipmr_rtm_validate_proto(unsigned char rtm_protocol) { switch (rtm_protocol) { case RTPROT_STATIC: case RTPROT_MROUTED: return true; } return false; } static int ipmr_nla_get_ttls(const struct nlattr *nla, struct mfcctl *mfcc) { struct rtnexthop *rtnh = nla_data(nla); int remaining = nla_len(nla), vifi = 0; while (rtnh_ok(rtnh, remaining)) { mfcc->mfcc_ttls[vifi] = rtnh->rtnh_hops; if (++vifi == MAXVIFS) break; rtnh = rtnh_next(rtnh, &remaining); } return remaining > 0 ? -EINVAL : vifi; } /* returns < 0 on error, 0 for ADD_MFC and 1 for ADD_MFC_PROXY */ static int rtm_to_ipmr_mfcc(struct net *net, struct nlmsghdr *nlh, struct mfcctl *mfcc, int *mrtsock, struct mr_table **mrtret, struct netlink_ext_ack *extack) { struct net_device *dev = NULL; u32 tblid = RT_TABLE_DEFAULT; struct mr_table *mrt; struct nlattr *attr; struct rtmsg *rtm; int ret, rem; ret = nlmsg_validate_deprecated(nlh, sizeof(*rtm), RTA_MAX, rtm_ipmr_policy, extack); if (ret < 0) goto out; rtm = nlmsg_data(nlh); ret = -EINVAL; if (rtm->rtm_family != RTNL_FAMILY_IPMR || rtm->rtm_dst_len != 32 || rtm->rtm_type != RTN_MULTICAST || rtm->rtm_scope != RT_SCOPE_UNIVERSE || !ipmr_rtm_validate_proto(rtm->rtm_protocol)) goto out; memset(mfcc, 0, sizeof(*mfcc)); mfcc->mfcc_parent = -1; ret = 0; nlmsg_for_each_attr(attr, nlh, sizeof(struct rtmsg), rem) { switch (nla_type(attr)) { case RTA_SRC: mfcc->mfcc_origin.s_addr = nla_get_be32(attr); break; case RTA_DST: mfcc->mfcc_mcastgrp.s_addr = nla_get_be32(attr); break; case RTA_IIF: dev = __dev_get_by_index(net, nla_get_u32(attr)); if (!dev) { ret = -ENODEV; goto out; } break; case RTA_MULTIPATH: if (ipmr_nla_get_ttls(attr, mfcc) < 0) { ret = -EINVAL; goto out; } break; case RTA_PREFSRC: ret = 1; break; case RTA_TABLE: tblid = nla_get_u32(attr); break; } } mrt = __ipmr_get_table(net, tblid); if (!mrt) { ret = -ENOENT; goto out; } *mrtret = mrt; *mrtsock = rtm->rtm_protocol == RTPROT_MROUTED ? 1 : 0; if (dev) mfcc->mfcc_parent = ipmr_find_vif(mrt, dev); out: return ret; } /* takes care of both newroute and delroute */ static int ipmr_rtm_route(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); int ret, mrtsock, parent; struct mr_table *tbl; struct mfcctl mfcc; mrtsock = 0; tbl = NULL; ret = rtm_to_ipmr_mfcc(net, nlh, &mfcc, &mrtsock, &tbl, extack); if (ret < 0) return ret; parent = ret ? mfcc.mfcc_parent : -1; if (nlh->nlmsg_type == RTM_NEWROUTE) return ipmr_mfc_add(net, tbl, &mfcc, mrtsock, parent); else return ipmr_mfc_delete(tbl, &mfcc, parent); } static bool ipmr_fill_table(struct mr_table *mrt, struct sk_buff *skb) { u32 queue_len = atomic_read(&mrt->cache_resolve_queue_len); if (nla_put_u32(skb, IPMRA_TABLE_ID, mrt->id) || nla_put_u32(skb, IPMRA_TABLE_CACHE_RES_QUEUE_LEN, queue_len) || nla_put_s32(skb, IPMRA_TABLE_MROUTE_REG_VIF_NUM, mrt->mroute_reg_vif_num) || nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_ASSERT, mrt->mroute_do_assert) || nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_PIM, mrt->mroute_do_pim) || nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_WRVIFWHOLE, mrt->mroute_do_wrvifwhole)) return false; return true; } static bool ipmr_fill_vif(struct mr_table *mrt, u32 vifid, struct sk_buff *skb) { struct net_device *vif_dev; struct nlattr *vif_nest; struct vif_device *vif; vif = &mrt->vif_table[vifid]; vif_dev = rtnl_dereference(vif->dev); /* if the VIF doesn't exist just continue */ if (!vif_dev) return true; vif_nest = nla_nest_start_noflag(skb, IPMRA_VIF); if (!vif_nest) return false; if (nla_put_u32(skb, IPMRA_VIFA_IFINDEX, vif_dev->ifindex) || nla_put_u32(skb, IPMRA_VIFA_VIF_ID, vifid) || nla_put_u16(skb, IPMRA_VIFA_FLAGS, vif->flags) || nla_put_u64_64bit(skb, IPMRA_VIFA_BYTES_IN, vif->bytes_in, IPMRA_VIFA_PAD) || nla_put_u64_64bit(skb, IPMRA_VIFA_BYTES_OUT, vif->bytes_out, IPMRA_VIFA_PAD) || nla_put_u64_64bit(skb, IPMRA_VIFA_PACKETS_IN, vif->pkt_in, IPMRA_VIFA_PAD) || nla_put_u64_64bit(skb, IPMRA_VIFA_PACKETS_OUT, vif->pkt_out, IPMRA_VIFA_PAD) || nla_put_be32(skb, IPMRA_VIFA_LOCAL_ADDR, vif->local) || nla_put_be32(skb, IPMRA_VIFA_REMOTE_ADDR, vif->remote)) { nla_nest_cancel(skb, vif_nest); return false; } nla_nest_end(skb, vif_nest); return true; } static int ipmr_valid_dumplink(const struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct ifinfomsg *ifm; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for ipmr link dump"); return -EINVAL; } if (nlmsg_attrlen(nlh, sizeof(*ifm))) { NL_SET_ERR_MSG(extack, "Invalid data after header in ipmr link dump"); return -EINVAL; } ifm = nlmsg_data(nlh); if (ifm->__ifi_pad || ifm->ifi_type || ifm->ifi_flags || ifm->ifi_change || ifm->ifi_index) { NL_SET_ERR_MSG(extack, "Invalid values in header for ipmr link dump request"); return -EINVAL; } return 0; } static int ipmr_rtm_dumplink(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct nlmsghdr *nlh = NULL; unsigned int t = 0, s_t; unsigned int e = 0, s_e; struct mr_table *mrt; if (cb->strict_check) { int err = ipmr_valid_dumplink(cb->nlh, cb->extack); if (err < 0) return err; } s_t = cb->args[0]; s_e = cb->args[1]; ipmr_for_each_table(mrt, net) { struct nlattr *vifs, *af; struct ifinfomsg *hdr; u32 i; if (t < s_t) goto skip_table; nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWLINK, sizeof(*hdr), NLM_F_MULTI); if (!nlh) break; hdr = nlmsg_data(nlh); memset(hdr, 0, sizeof(*hdr)); hdr->ifi_family = RTNL_FAMILY_IPMR; af = nla_nest_start_noflag(skb, IFLA_AF_SPEC); if (!af) { nlmsg_cancel(skb, nlh); goto out; } if (!ipmr_fill_table(mrt, skb)) { nlmsg_cancel(skb, nlh); goto out; } vifs = nla_nest_start_noflag(skb, IPMRA_TABLE_VIFS); if (!vifs) { nla_nest_end(skb, af); nlmsg_end(skb, nlh); goto out; } for (i = 0; i < mrt->maxvif; i++) { if (e < s_e) goto skip_entry; if (!ipmr_fill_vif(mrt, i, skb)) { nla_nest_end(skb, vifs); nla_nest_end(skb, af); nlmsg_end(skb, nlh); goto out; } skip_entry: e++; } s_e = 0; e = 0; nla_nest_end(skb, vifs); nla_nest_end(skb, af); nlmsg_end(skb, nlh); skip_table: t++; } out: cb->args[1] = e; cb->args[0] = t; return skb->len; } #ifdef CONFIG_PROC_FS /* The /proc interfaces to multicast routing : * /proc/net/ip_mr_cache & /proc/net/ip_mr_vif */ static void *ipmr_vif_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct mr_vif_iter *iter = seq->private; struct net *net = seq_file_net(seq); struct mr_table *mrt; rcu_read_lock(); mrt = __ipmr_get_table(net, RT_TABLE_DEFAULT); if (!mrt) { rcu_read_unlock(); return ERR_PTR(-ENOENT); } iter->mrt = mrt; return mr_vif_seq_start(seq, pos); } static void ipmr_vif_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static int ipmr_vif_seq_show(struct seq_file *seq, void *v) { struct mr_vif_iter *iter = seq->private; struct mr_table *mrt = iter->mrt; if (v == SEQ_START_TOKEN) { seq_puts(seq, "Interface BytesIn PktsIn BytesOut PktsOut Flags Local Remote\n"); } else { const struct vif_device *vif = v; const struct net_device *vif_dev; const char *name; vif_dev = vif_dev_read(vif); name = vif_dev ? vif_dev->name : "none"; seq_printf(seq, "%2td %-10s %8ld %7ld %8ld %7ld %05X %08X %08X\n", vif - mrt->vif_table, name, vif->bytes_in, vif->pkt_in, vif->bytes_out, vif->pkt_out, vif->flags, vif->local, vif->remote); } return 0; } static const struct seq_operations ipmr_vif_seq_ops = { .start = ipmr_vif_seq_start, .next = mr_vif_seq_next, .stop = ipmr_vif_seq_stop, .show = ipmr_vif_seq_show, }; static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) { struct net *net = seq_file_net(seq); struct mr_table *mrt; mrt = ipmr_get_table(net, RT_TABLE_DEFAULT); if (!mrt) return ERR_PTR(-ENOENT); return mr_mfc_seq_start(seq, pos, mrt, &mfc_unres_lock); } static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) { int n; if (v == SEQ_START_TOKEN) { seq_puts(seq, "Group Origin Iif Pkts Bytes Wrong Oifs\n"); } else { const struct mfc_cache *mfc = v; const struct mr_mfc_iter *it = seq->private; const struct mr_table *mrt = it->mrt; seq_printf(seq, "%08X %08X %-3hd", (__force u32) mfc->mfc_mcastgrp, (__force u32) mfc->mfc_origin, mfc->_c.mfc_parent); if (it->cache != &mrt->mfc_unres_queue) { seq_printf(seq, " %8lu %8lu %8lu", mfc->_c.mfc_un.res.pkt, mfc->_c.mfc_un.res.bytes, mfc->_c.mfc_un.res.wrong_if); for (n = mfc->_c.mfc_un.res.minvif; n < mfc->_c.mfc_un.res.maxvif; n++) { if (VIF_EXISTS(mrt, n) && mfc->_c.mfc_un.res.ttls[n] < 255) seq_printf(seq, " %2d:%-3d", n, mfc->_c.mfc_un.res.ttls[n]); } } else { /* unresolved mfc_caches don't contain * pkt, bytes and wrong_if values */ seq_printf(seq, " %8lu %8lu %8lu", 0ul, 0ul, 0ul); } seq_putc(seq, '\n'); } return 0; } static const struct seq_operations ipmr_mfc_seq_ops = { .start = ipmr_mfc_seq_start, .next = mr_mfc_seq_next, .stop = mr_mfc_seq_stop, .show = ipmr_mfc_seq_show, }; #endif #ifdef CONFIG_IP_PIMSM_V2 static const struct net_protocol pim_protocol = { .handler = pim_rcv, }; #endif static unsigned int ipmr_seq_read(const struct net *net) { return READ_ONCE(net->ipv4.ipmr_seq) + ipmr_rules_seq_read(net); } static int ipmr_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return mr_dump(net, nb, RTNL_FAMILY_IPMR, ipmr_rules_dump, ipmr_mr_table_iter, extack); } static const struct fib_notifier_ops ipmr_notifier_ops_template = { .family = RTNL_FAMILY_IPMR, .fib_seq_read = ipmr_seq_read, .fib_dump = ipmr_dump, .owner = THIS_MODULE, }; static int __net_init ipmr_notifier_init(struct net *net) { struct fib_notifier_ops *ops; net->ipv4.ipmr_seq = 0; ops = fib_notifier_ops_register(&ipmr_notifier_ops_template, net); if (IS_ERR(ops)) return PTR_ERR(ops); net->ipv4.ipmr_notifier_ops = ops; return 0; } static void __net_exit ipmr_notifier_exit(struct net *net) { fib_notifier_ops_unregister(net->ipv4.ipmr_notifier_ops); net->ipv4.ipmr_notifier_ops = NULL; } /* Setup for IP multicast routing */ static int __net_init ipmr_net_init(struct net *net) { int err; err = ipmr_notifier_init(net); if (err) goto ipmr_notifier_fail; err = ipmr_rules_init(net); if (err < 0) goto ipmr_rules_fail; #ifdef CONFIG_PROC_FS err = -ENOMEM; if (!proc_create_net("ip_mr_vif", 0, net->proc_net, &ipmr_vif_seq_ops, sizeof(struct mr_vif_iter))) goto proc_vif_fail; if (!proc_create_net("ip_mr_cache", 0, net->proc_net, &ipmr_mfc_seq_ops, sizeof(struct mr_mfc_iter))) goto proc_cache_fail; #endif return 0; #ifdef CONFIG_PROC_FS proc_cache_fail: remove_proc_entry("ip_mr_vif", net->proc_net); proc_vif_fail: rtnl_lock(); ipmr_rules_exit(net); rtnl_unlock(); #endif ipmr_rules_fail: ipmr_notifier_exit(net); ipmr_notifier_fail: return err; } static void __net_exit ipmr_net_exit(struct net *net) { #ifdef CONFIG_PROC_FS remove_proc_entry("ip_mr_cache", net->proc_net); remove_proc_entry("ip_mr_vif", net->proc_net); #endif ipmr_notifier_exit(net); } static void __net_exit ipmr_net_exit_batch(struct list_head *net_list) { struct net *net; rtnl_lock(); list_for_each_entry(net, net_list, exit_list) ipmr_rules_exit(net); rtnl_unlock(); } static struct pernet_operations ipmr_net_ops = { .init = ipmr_net_init, .exit = ipmr_net_exit, .exit_batch = ipmr_net_exit_batch, }; static const struct rtnl_msg_handler ipmr_rtnl_msg_handlers[] __initconst = { {.protocol = RTNL_FAMILY_IPMR, .msgtype = RTM_GETLINK, .dumpit = ipmr_rtm_dumplink}, {.protocol = RTNL_FAMILY_IPMR, .msgtype = RTM_NEWROUTE, .doit = ipmr_rtm_route}, {.protocol = RTNL_FAMILY_IPMR, .msgtype = RTM_DELROUTE, .doit = ipmr_rtm_route}, {.protocol = RTNL_FAMILY_IPMR, .msgtype = RTM_GETROUTE, .doit = ipmr_rtm_getroute, .dumpit = ipmr_rtm_dumproute}, }; int __init ip_mr_init(void) { int err; mrt_cachep = KMEM_CACHE(mfc_cache, SLAB_HWCACHE_ALIGN | SLAB_PANIC); err = register_pernet_subsys(&ipmr_net_ops); if (err) goto reg_pernet_fail; err = register_netdevice_notifier(&ip_mr_notifier); if (err) goto reg_notif_fail; #ifdef CONFIG_IP_PIMSM_V2 if (inet_add_protocol(&pim_protocol, IPPROTO_PIM) < 0) { pr_err("%s: can't add PIM protocol\n", __func__); err = -EAGAIN; goto add_proto_fail; } #endif rtnl_register_many(ipmr_rtnl_msg_handlers); return 0; #ifdef CONFIG_IP_PIMSM_V2 add_proto_fail: unregister_netdevice_notifier(&ip_mr_notifier); #endif reg_notif_fail: unregister_pernet_subsys(&ipmr_net_ops); reg_pernet_fail: kmem_cache_destroy(mrt_cachep); return err; } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions of the Internet Protocol. * * Version: @(#)in.h 1.0.1 04/21/93 * * Authors: Original taken from the GNU Project <netinet/in.h> file. * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _LINUX_IN_H #define _LINUX_IN_H #include <linux/errno.h> #include <uapi/linux/in.h> static inline int proto_ports_offset(int proto) { switch (proto) { case IPPROTO_TCP: case IPPROTO_UDP: case IPPROTO_DCCP: case IPPROTO_ESP: /* SPI */ case IPPROTO_SCTP: case IPPROTO_UDPLITE: return 0; case IPPROTO_AH: /* SPI */ return 4; default: return -EINVAL; } } static inline bool ipv4_is_loopback(__be32 addr) { return (addr & htonl(0xff000000)) == htonl(0x7f000000); } static inline bool ipv4_is_multicast(__be32 addr) { return (addr & htonl(0xf0000000)) == htonl(0xe0000000); } static inline bool ipv4_is_local_multicast(__be32 addr) { return (addr & htonl(0xffffff00)) == htonl(0xe0000000); } static inline bool ipv4_is_lbcast(__be32 addr) { /* limited broadcast */ return addr == htonl(INADDR_BROADCAST); } static inline bool ipv4_is_all_snoopers(__be32 addr) { return addr == htonl(INADDR_ALLSNOOPERS_GROUP); } static inline bool ipv4_is_zeronet(__be32 addr) { return (addr == 0); } /* Special-Use IPv4 Addresses (RFC3330) */ static inline bool ipv4_is_private_10(__be32 addr) { return (addr & htonl(0xff000000)) == htonl(0x0a000000); } static inline bool ipv4_is_private_172(__be32 addr) { return (addr & htonl(0xfff00000)) == htonl(0xac100000); } static inline bool ipv4_is_private_192(__be32 addr) { return (addr & htonl(0xffff0000)) == htonl(0xc0a80000); } static inline bool ipv4_is_linklocal_169(__be32 addr) { return (addr & htonl(0xffff0000)) == htonl(0xa9fe0000); } static inline bool ipv4_is_anycast_6to4(__be32 addr) { return (addr & htonl(0xffffff00)) == htonl(0xc0586300); } static inline bool ipv4_is_test_192(__be32 addr) { return (addr & htonl(0xffffff00)) == htonl(0xc0000200); } static inline bool ipv4_is_test_198(__be32 addr) { return (addr & htonl(0xfffe0000)) == htonl(0xc6120000); } #endif /* _LINUX_IN_H */ |
| 364 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_JUMP_LABEL_H #define _LINUX_JUMP_LABEL_H /* * Jump label support * * Copyright (C) 2009-2012 Jason Baron <jbaron@redhat.com> * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra * * DEPRECATED API: * * The use of 'struct static_key' directly, is now DEPRECATED. In addition * static_key_{true,false}() is also DEPRECATED. IE DO NOT use the following: * * struct static_key false = STATIC_KEY_INIT_FALSE; * struct static_key true = STATIC_KEY_INIT_TRUE; * static_key_true() * static_key_false() * * The updated API replacements are: * * DEFINE_STATIC_KEY_TRUE(key); * DEFINE_STATIC_KEY_FALSE(key); * DEFINE_STATIC_KEY_ARRAY_TRUE(keys, count); * DEFINE_STATIC_KEY_ARRAY_FALSE(keys, count); * static_branch_likely() * static_branch_unlikely() * * Jump labels provide an interface to generate dynamic branches using * self-modifying code. Assuming toolchain and architecture support, if we * define a "key" that is initially false via "DEFINE_STATIC_KEY_FALSE(key)", * an "if (static_branch_unlikely(&key))" statement is an unconditional branch * (which defaults to false - and the true block is placed out of line). * Similarly, we can define an initially true key via * "DEFINE_STATIC_KEY_TRUE(key)", and use it in the same * "if (static_branch_unlikely(&key))", in which case we will generate an * unconditional branch to the out-of-line true branch. Keys that are * initially true or false can be using in both static_branch_unlikely() * and static_branch_likely() statements. * * At runtime we can change the branch target by setting the key * to true via a call to static_branch_enable(), or false using * static_branch_disable(). If the direction of the branch is switched by * these calls then we run-time modify the branch target via a * no-op -> jump or jump -> no-op conversion. For example, for an * initially false key that is used in an "if (static_branch_unlikely(&key))" * statement, setting the key to true requires us to patch in a jump * to the out-of-line of true branch. * * In addition to static_branch_{enable,disable}, we can also reference count * the key or branch direction via static_branch_{inc,dec}. Thus, * static_branch_inc() can be thought of as a 'make more true' and * static_branch_dec() as a 'make more false'. * * Since this relies on modifying code, the branch modifying functions * must be considered absolute slow paths (machine wide synchronization etc.). * OTOH, since the affected branches are unconditional, their runtime overhead * will be absolutely minimal, esp. in the default (off) case where the total * effect is a single NOP of appropriate size. The on case will patch in a jump * to the out-of-line block. * * When the control is directly exposed to userspace, it is prudent to delay the * decrement to avoid high frequency code modifications which can (and do) * cause significant performance degradation. Struct static_key_deferred and * static_key_slow_dec_deferred() provide for this. * * Lacking toolchain and or architecture support, static keys fall back to a * simple conditional branch. * * Additional babbling in: Documentation/staging/static-keys.rst */ #ifndef __ASSEMBLY__ #include <linux/types.h> #include <linux/compiler.h> extern bool static_key_initialized; #define STATIC_KEY_CHECK_USE(key) WARN(!static_key_initialized, \ "%s(): static key '%pS' used before call to jump_label_init()", \ __func__, (key)) struct static_key { atomic_t enabled; #ifdef CONFIG_JUMP_LABEL /* * Note: * To make anonymous unions work with old compilers, the static * initialization of them requires brackets. This creates a dependency * on the order of the struct with the initializers. If any fields * are added, STATIC_KEY_INIT_TRUE and STATIC_KEY_INIT_FALSE may need * to be modified. * * bit 0 => 1 if key is initially true * 0 if initially false * bit 1 => 1 if points to struct static_key_mod * 0 if points to struct jump_entry */ union { unsigned long type; struct jump_entry *entries; struct static_key_mod *next; }; #endif /* CONFIG_JUMP_LABEL */ }; #endif /* __ASSEMBLY__ */ #ifdef CONFIG_JUMP_LABEL #include <asm/jump_label.h> #ifndef __ASSEMBLY__ #ifdef CONFIG_HAVE_ARCH_JUMP_LABEL_RELATIVE struct jump_entry { s32 code; s32 target; long key; // key may be far away from the core kernel under KASLR }; static inline unsigned long jump_entry_code(const struct jump_entry *entry) { return (unsigned long)&entry->code + entry->code; } static inline unsigned long jump_entry_target(const struct jump_entry *entry) { return (unsigned long)&entry->target + entry->target; } static inline struct static_key *jump_entry_key(const struct jump_entry *entry) { long offset = entry->key & ~3L; return (struct static_key *)((unsigned long)&entry->key + offset); } #else static inline unsigned long jump_entry_code(const struct jump_entry *entry) { return entry->code; } static inline unsigned long jump_entry_target(const struct jump_entry *entry) { return entry->target; } static inline struct static_key *jump_entry_key(const struct jump_entry *entry) { return (struct static_key *)((unsigned long)entry->key & ~3UL); } #endif static inline bool jump_entry_is_branch(const struct jump_entry *entry) { return (unsigned long)entry->key & 1UL; } static inline bool jump_entry_is_init(const struct jump_entry *entry) { return (unsigned long)entry->key & 2UL; } static inline void jump_entry_set_init(struct jump_entry *entry, bool set) { if (set) entry->key |= 2; else entry->key &= ~2; } static inline int jump_entry_size(struct jump_entry *entry) { #ifdef JUMP_LABEL_NOP_SIZE return JUMP_LABEL_NOP_SIZE; #else return arch_jump_entry_size(entry); #endif } #endif #endif #ifndef __ASSEMBLY__ enum jump_label_type { JUMP_LABEL_NOP = 0, JUMP_LABEL_JMP, }; struct module; #ifdef CONFIG_JUMP_LABEL #define JUMP_TYPE_FALSE 0UL #define JUMP_TYPE_TRUE 1UL #define JUMP_TYPE_LINKED 2UL #define JUMP_TYPE_MASK 3UL static __always_inline bool static_key_false(struct static_key *key) { return arch_static_branch(key, false); } static __always_inline bool static_key_true(struct static_key *key) { return !arch_static_branch(key, true); } extern struct jump_entry __start___jump_table[]; extern struct jump_entry __stop___jump_table[]; extern void jump_label_init(void); extern void jump_label_init_ro(void); extern void jump_label_lock(void); extern void jump_label_unlock(void); extern void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type); extern bool arch_jump_label_transform_queue(struct jump_entry *entry, enum jump_label_type type); extern void arch_jump_label_transform_apply(void); extern int jump_label_text_reserved(void *start, void *end); extern bool static_key_slow_inc(struct static_key *key); extern bool static_key_fast_inc_not_disabled(struct static_key *key); extern void static_key_slow_dec(struct static_key *key); extern bool static_key_slow_inc_cpuslocked(struct static_key *key); extern void static_key_slow_dec_cpuslocked(struct static_key *key); extern int static_key_count(struct static_key *key); extern void static_key_enable(struct static_key *key); extern void static_key_disable(struct static_key *key); extern void static_key_enable_cpuslocked(struct static_key *key); extern void static_key_disable_cpuslocked(struct static_key *key); extern enum jump_label_type jump_label_init_type(struct jump_entry *entry); /* * We should be using ATOMIC_INIT() for initializing .enabled, but * the inclusion of atomic.h is problematic for inclusion of jump_label.h * in 'low-level' headers. Thus, we are initializing .enabled with a * raw value, but have added a BUILD_BUG_ON() to catch any issues in * jump_label_init() see: kernel/jump_label.c. */ #define STATIC_KEY_INIT_TRUE \ { .enabled = { 1 }, \ { .type = JUMP_TYPE_TRUE } } #define STATIC_KEY_INIT_FALSE \ { .enabled = { 0 }, \ { .type = JUMP_TYPE_FALSE } } #else /* !CONFIG_JUMP_LABEL */ #include <linux/atomic.h> #include <linux/bug.h> static __always_inline int static_key_count(struct static_key *key) { return raw_atomic_read(&key->enabled); } static __always_inline void jump_label_init(void) { static_key_initialized = true; } static __always_inline void jump_label_init_ro(void) { } static __always_inline bool static_key_false(struct static_key *key) { if (unlikely_notrace(static_key_count(key) > 0)) return true; return false; } static __always_inline bool static_key_true(struct static_key *key) { if (likely_notrace(static_key_count(key) > 0)) return true; return false; } static inline bool static_key_fast_inc_not_disabled(struct static_key *key) { int v; STATIC_KEY_CHECK_USE(key); /* * Prevent key->enabled getting negative to follow the same semantics * as for CONFIG_JUMP_LABEL=y, see kernel/jump_label.c comment. */ v = atomic_read(&key->enabled); do { if (v < 0 || (v + 1) < 0) return false; } while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v + 1))); return true; } #define static_key_slow_inc(key) static_key_fast_inc_not_disabled(key) static inline void static_key_slow_dec(struct static_key *key) { STATIC_KEY_CHECK_USE(key); atomic_dec(&key->enabled); } #define static_key_slow_inc_cpuslocked(key) static_key_slow_inc(key) #define static_key_slow_dec_cpuslocked(key) static_key_slow_dec(key) static inline int jump_label_text_reserved(void *start, void *end) { return 0; } static inline void jump_label_lock(void) {} static inline void jump_label_unlock(void) {} static inline void static_key_enable(struct static_key *key) { STATIC_KEY_CHECK_USE(key); if (atomic_read(&key->enabled) != 0) { WARN_ON_ONCE(atomic_read(&key->enabled) != 1); return; } atomic_set(&key->enabled, 1); } static inline void static_key_disable(struct static_key *key) { STATIC_KEY_CHECK_USE(key); if (atomic_read(&key->enabled) != 1) { WARN_ON_ONCE(atomic_read(&key->enabled) != 0); return; } atomic_set(&key->enabled, 0); } #define static_key_enable_cpuslocked(k) static_key_enable((k)) #define static_key_disable_cpuslocked(k) static_key_disable((k)) #define STATIC_KEY_INIT_TRUE { .enabled = ATOMIC_INIT(1) } #define STATIC_KEY_INIT_FALSE { .enabled = ATOMIC_INIT(0) } #endif /* CONFIG_JUMP_LABEL */ #define STATIC_KEY_INIT STATIC_KEY_INIT_FALSE #define jump_label_enabled static_key_enabled /* -------------------------------------------------------------------------- */ /* * Two type wrappers around static_key, such that we can use compile time * type differentiation to emit the right code. * * All the below code is macros in order to play type games. */ struct static_key_true { struct static_key key; }; struct static_key_false { struct static_key key; }; #define STATIC_KEY_TRUE_INIT (struct static_key_true) { .key = STATIC_KEY_INIT_TRUE, } #define STATIC_KEY_FALSE_INIT (struct static_key_false){ .key = STATIC_KEY_INIT_FALSE, } #define DEFINE_STATIC_KEY_TRUE(name) \ struct static_key_true name = STATIC_KEY_TRUE_INIT #define DEFINE_STATIC_KEY_TRUE_RO(name) \ struct static_key_true name __ro_after_init = STATIC_KEY_TRUE_INIT #define DECLARE_STATIC_KEY_TRUE(name) \ extern struct static_key_true name #define DEFINE_STATIC_KEY_FALSE(name) \ struct static_key_false name = STATIC_KEY_FALSE_INIT #define DEFINE_STATIC_KEY_FALSE_RO(name) \ struct static_key_false name __ro_after_init = STATIC_KEY_FALSE_INIT #define DECLARE_STATIC_KEY_FALSE(name) \ extern struct static_key_false name #define DEFINE_STATIC_KEY_ARRAY_TRUE(name, count) \ struct static_key_true name[count] = { \ [0 ... (count) - 1] = STATIC_KEY_TRUE_INIT, \ } #define DEFINE_STATIC_KEY_ARRAY_FALSE(name, count) \ struct static_key_false name[count] = { \ [0 ... (count) - 1] = STATIC_KEY_FALSE_INIT, \ } #define _DEFINE_STATIC_KEY_1(name) DEFINE_STATIC_KEY_TRUE(name) #define _DEFINE_STATIC_KEY_0(name) DEFINE_STATIC_KEY_FALSE(name) #define DEFINE_STATIC_KEY_MAYBE(cfg, name) \ __PASTE(_DEFINE_STATIC_KEY_, IS_ENABLED(cfg))(name) #define _DEFINE_STATIC_KEY_RO_1(name) DEFINE_STATIC_KEY_TRUE_RO(name) #define _DEFINE_STATIC_KEY_RO_0(name) DEFINE_STATIC_KEY_FALSE_RO(name) #define DEFINE_STATIC_KEY_MAYBE_RO(cfg, name) \ __PASTE(_DEFINE_STATIC_KEY_RO_, IS_ENABLED(cfg))(name) #define _DECLARE_STATIC_KEY_1(name) DECLARE_STATIC_KEY_TRUE(name) #define _DECLARE_STATIC_KEY_0(name) DECLARE_STATIC_KEY_FALSE(name) #define DECLARE_STATIC_KEY_MAYBE(cfg, name) \ __PASTE(_DECLARE_STATIC_KEY_, IS_ENABLED(cfg))(name) extern bool ____wrong_branch_error(void); #define static_key_enabled(x) \ ({ \ if (!__builtin_types_compatible_p(typeof(*x), struct static_key) && \ !__builtin_types_compatible_p(typeof(*x), struct static_key_true) &&\ !__builtin_types_compatible_p(typeof(*x), struct static_key_false)) \ ____wrong_branch_error(); \ static_key_count((struct static_key *)x) > 0; \ }) #ifdef CONFIG_JUMP_LABEL /* * Combine the right initial value (type) with the right branch order * to generate the desired result. * * * type\branch| likely (1) | unlikely (0) * -----------+-----------------------+------------------ * | | * true (1) | ... | ... * | NOP | JMP L * | <br-stmts> | 1: ... * | L: ... | * | | * | | L: <br-stmts> * | | jmp 1b * | | * -----------+-----------------------+------------------ * | | * false (0) | ... | ... * | JMP L | NOP * | <br-stmts> | 1: ... * | L: ... | * | | * | | L: <br-stmts> * | | jmp 1b * | | * -----------+-----------------------+------------------ * * The initial value is encoded in the LSB of static_key::entries, * type: 0 = false, 1 = true. * * The branch type is encoded in the LSB of jump_entry::key, * branch: 0 = unlikely, 1 = likely. * * This gives the following logic table: * * enabled type branch instuction * -----------------------------+----------- * 0 0 0 | NOP * 0 0 1 | JMP * 0 1 0 | NOP * 0 1 1 | JMP * * 1 0 0 | JMP * 1 0 1 | NOP * 1 1 0 | JMP * 1 1 1 | NOP * * Which gives the following functions: * * dynamic: instruction = enabled ^ branch * static: instruction = type ^ branch * * See jump_label_type() / jump_label_init_type(). */ #define static_branch_likely(x) \ ({ \ bool branch; \ if (__builtin_types_compatible_p(typeof(*x), struct static_key_true)) \ branch = !arch_static_branch(&(x)->key, true); \ else if (__builtin_types_compatible_p(typeof(*x), struct static_key_false)) \ branch = !arch_static_branch_jump(&(x)->key, true); \ else \ branch = ____wrong_branch_error(); \ likely_notrace(branch); \ }) #define static_branch_unlikely(x) \ ({ \ bool branch; \ if (__builtin_types_compatible_p(typeof(*x), struct static_key_true)) \ branch = arch_static_branch_jump(&(x)->key, false); \ else if (__builtin_types_compatible_p(typeof(*x), struct static_key_false)) \ branch = arch_static_branch(&(x)->key, false); \ else \ branch = ____wrong_branch_error(); \ unlikely_notrace(branch); \ }) #else /* !CONFIG_JUMP_LABEL */ #define static_branch_likely(x) likely_notrace(static_key_enabled(&(x)->key)) #define static_branch_unlikely(x) unlikely_notrace(static_key_enabled(&(x)->key)) #endif /* CONFIG_JUMP_LABEL */ #define static_branch_maybe(config, x) \ (IS_ENABLED(config) ? static_branch_likely(x) \ : static_branch_unlikely(x)) /* * Advanced usage; refcount, branch is enabled when: count != 0 */ #define static_branch_inc(x) static_key_slow_inc(&(x)->key) #define static_branch_dec(x) static_key_slow_dec(&(x)->key) #define static_branch_inc_cpuslocked(x) static_key_slow_inc_cpuslocked(&(x)->key) #define static_branch_dec_cpuslocked(x) static_key_slow_dec_cpuslocked(&(x)->key) /* * Normal usage; boolean enable/disable. */ #define static_branch_enable(x) static_key_enable(&(x)->key) #define static_branch_disable(x) static_key_disable(&(x)->key) #define static_branch_enable_cpuslocked(x) static_key_enable_cpuslocked(&(x)->key) #define static_branch_disable_cpuslocked(x) static_key_disable_cpuslocked(&(x)->key) #endif /* __ASSEMBLY__ */ #endif /* _LINUX_JUMP_LABEL_H */ |
| 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 | /* * Copyright (c) 2015, Mellanox Technologies inc. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include "core_priv.h" #include <linux/in.h> #include <linux/in6.h> /* For in6_dev_get/in6_dev_put */ #include <net/addrconf.h> #include <net/bonding.h> #include <rdma/ib_cache.h> #include <rdma/ib_addr.h> static struct workqueue_struct *gid_cache_wq; enum gid_op_type { GID_DEL = 0, GID_ADD }; struct update_gid_event_work { struct work_struct work; union ib_gid gid; struct ib_gid_attr gid_attr; enum gid_op_type gid_op; }; #define ROCE_NETDEV_CALLBACK_SZ 3 struct netdev_event_work_cmd { roce_netdev_callback cb; roce_netdev_filter filter; struct net_device *ndev; struct net_device *filter_ndev; }; struct netdev_event_work { struct work_struct work; struct netdev_event_work_cmd cmds[ROCE_NETDEV_CALLBACK_SZ]; }; static const struct { bool (*is_supported)(const struct ib_device *device, u32 port_num); enum ib_gid_type gid_type; } PORT_CAP_TO_GID_TYPE[] = { {rdma_protocol_roce_eth_encap, IB_GID_TYPE_ROCE}, {rdma_protocol_roce_udp_encap, IB_GID_TYPE_ROCE_UDP_ENCAP}, }; #define CAP_TO_GID_TABLE_SIZE ARRAY_SIZE(PORT_CAP_TO_GID_TYPE) unsigned long roce_gid_type_mask_support(struct ib_device *ib_dev, u32 port) { int i; unsigned int ret_flags = 0; if (!rdma_protocol_roce(ib_dev, port)) return 1UL << IB_GID_TYPE_IB; for (i = 0; i < CAP_TO_GID_TABLE_SIZE; i++) if (PORT_CAP_TO_GID_TYPE[i].is_supported(ib_dev, port)) ret_flags |= 1UL << PORT_CAP_TO_GID_TYPE[i].gid_type; return ret_flags; } EXPORT_SYMBOL(roce_gid_type_mask_support); static void update_gid(enum gid_op_type gid_op, struct ib_device *ib_dev, u32 port, union ib_gid *gid, struct ib_gid_attr *gid_attr) { int i; unsigned long gid_type_mask = roce_gid_type_mask_support(ib_dev, port); for (i = 0; i < IB_GID_TYPE_SIZE; i++) { if ((1UL << i) & gid_type_mask) { gid_attr->gid_type = i; switch (gid_op) { case GID_ADD: ib_cache_gid_add(ib_dev, port, gid, gid_attr); break; case GID_DEL: ib_cache_gid_del(ib_dev, port, gid, gid_attr); break; } } } } enum bonding_slave_state { BONDING_SLAVE_STATE_ACTIVE = 1UL << 0, BONDING_SLAVE_STATE_INACTIVE = 1UL << 1, /* No primary slave or the device isn't a slave in bonding */ BONDING_SLAVE_STATE_NA = 1UL << 2, }; static enum bonding_slave_state is_eth_active_slave_of_bonding_rcu(struct net_device *dev, struct net_device *upper) { if (upper && netif_is_bond_master(upper)) { struct net_device *pdev = bond_option_active_slave_get_rcu(netdev_priv(upper)); if (pdev) return dev == pdev ? BONDING_SLAVE_STATE_ACTIVE : BONDING_SLAVE_STATE_INACTIVE; } return BONDING_SLAVE_STATE_NA; } #define REQUIRED_BOND_STATES (BONDING_SLAVE_STATE_ACTIVE | \ BONDING_SLAVE_STATE_NA) static bool is_eth_port_of_netdev_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *real_dev; bool res; if (!rdma_ndev) return false; rcu_read_lock(); real_dev = rdma_vlan_dev_real_dev(cookie); if (!real_dev) real_dev = cookie; res = ((rdma_is_upper_dev_rcu(rdma_ndev, cookie) && (is_eth_active_slave_of_bonding_rcu(rdma_ndev, real_dev) & REQUIRED_BOND_STATES)) || real_dev == rdma_ndev); rcu_read_unlock(); return res; } static bool is_eth_port_inactive_slave_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *master_dev; bool res; if (!rdma_ndev) return false; rcu_read_lock(); master_dev = netdev_master_upper_dev_get_rcu(rdma_ndev); res = is_eth_active_slave_of_bonding_rcu(rdma_ndev, master_dev) == BONDING_SLAVE_STATE_INACTIVE; rcu_read_unlock(); return res; } /** * is_ndev_for_default_gid_filter - Check if a given netdevice * can be considered for default GIDs or not. * @ib_dev: IB device to check * @port: Port to consider for adding default GID * @rdma_ndev: rdma netdevice pointer * @cookie: Netdevice to consider to form a default GID * * is_ndev_for_default_gid_filter() returns true if a given netdevice can be * considered for deriving default RoCE GID, returns false otherwise. */ static bool is_ndev_for_default_gid_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *cookie_ndev = cookie; bool res; if (!rdma_ndev) return false; rcu_read_lock(); /* * When rdma netdevice is used in bonding, bonding master netdevice * should be considered for default GIDs. Therefore, ignore slave rdma * netdevices when bonding is considered. * Additionally when event(cookie) netdevice is bond master device, * make sure that it the upper netdevice of rdma netdevice. */ res = ((cookie_ndev == rdma_ndev && !netif_is_bond_slave(rdma_ndev)) || (netif_is_bond_master(cookie_ndev) && rdma_is_upper_dev_rcu(rdma_ndev, cookie_ndev))); rcu_read_unlock(); return res; } static bool pass_all_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { return true; } static bool upper_device_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { bool res; if (!rdma_ndev) return false; if (rdma_ndev == cookie) return true; rcu_read_lock(); res = rdma_is_upper_dev_rcu(rdma_ndev, cookie); rcu_read_unlock(); return res; } /** * is_upper_ndev_bond_master_filter - Check if a given netdevice * is bond master device of netdevice of the RDMA device of port. * @ib_dev: IB device to check * @port: Port to consider for adding default GID * @rdma_ndev: Pointer to rdma netdevice * @cookie: Netdevice to consider to form a default GID * * is_upper_ndev_bond_master_filter() returns true if a cookie_netdev * is bond master device and rdma_ndev is its lower netdevice. It might * not have been established as slave device yet. */ static bool is_upper_ndev_bond_master_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *cookie_ndev = cookie; bool match = false; if (!rdma_ndev) return false; rcu_read_lock(); if (netif_is_bond_master(cookie_ndev) && rdma_is_upper_dev_rcu(rdma_ndev, cookie_ndev)) match = true; rcu_read_unlock(); return match; } static void update_gid_ip(enum gid_op_type gid_op, struct ib_device *ib_dev, u32 port, struct net_device *ndev, struct sockaddr *addr) { union ib_gid gid; struct ib_gid_attr gid_attr; rdma_ip2gid(addr, &gid); memset(&gid_attr, 0, sizeof(gid_attr)); gid_attr.ndev = ndev; update_gid(gid_op, ib_dev, port, &gid, &gid_attr); } static void bond_delete_netdev_default_gids(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, struct net_device *event_ndev) { struct net_device *real_dev = rdma_vlan_dev_real_dev(event_ndev); unsigned long gid_type_mask; if (!rdma_ndev) return; if (!real_dev) real_dev = event_ndev; rcu_read_lock(); if (((rdma_ndev != event_ndev && !rdma_is_upper_dev_rcu(rdma_ndev, event_ndev)) || is_eth_active_slave_of_bonding_rcu(rdma_ndev, real_dev) == BONDING_SLAVE_STATE_INACTIVE)) { rcu_read_unlock(); return; } rcu_read_unlock(); gid_type_mask = roce_gid_type_mask_support(ib_dev, port); ib_cache_gid_set_default_gid(ib_dev, port, rdma_ndev, gid_type_mask, IB_CACHE_GID_DEFAULT_MODE_DELETE); } static void enum_netdev_ipv4_ips(struct ib_device *ib_dev, u32 port, struct net_device *ndev) { const struct in_ifaddr *ifa; struct in_device *in_dev; struct sin_list { struct list_head list; struct sockaddr_in ip; }; struct sin_list *sin_iter; struct sin_list *sin_temp; LIST_HEAD(sin_list); if (ndev->reg_state >= NETREG_UNREGISTERING) return; rcu_read_lock(); in_dev = __in_dev_get_rcu(ndev); if (!in_dev) { rcu_read_unlock(); return; } in_dev_for_each_ifa_rcu(ifa, in_dev) { struct sin_list *entry = kzalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) continue; entry->ip.sin_family = AF_INET; entry->ip.sin_addr.s_addr = ifa->ifa_address; list_add_tail(&entry->list, &sin_list); } rcu_read_unlock(); list_for_each_entry_safe(sin_iter, sin_temp, &sin_list, list) { update_gid_ip(GID_ADD, ib_dev, port, ndev, (struct sockaddr *)&sin_iter->ip); list_del(&sin_iter->list); kfree(sin_iter); } } static void enum_netdev_ipv6_ips(struct ib_device *ib_dev, u32 port, struct net_device *ndev) { struct inet6_ifaddr *ifp; struct inet6_dev *in6_dev; struct sin6_list { struct list_head list; struct sockaddr_in6 sin6; }; struct sin6_list *sin6_iter; struct sin6_list *sin6_temp; struct ib_gid_attr gid_attr = {.ndev = ndev}; LIST_HEAD(sin6_list); if (ndev->reg_state >= NETREG_UNREGISTERING) return; in6_dev = in6_dev_get(ndev); if (!in6_dev) return; read_lock_bh(&in6_dev->lock); list_for_each_entry(ifp, &in6_dev->addr_list, if_list) { struct sin6_list *entry = kzalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) continue; entry->sin6.sin6_family = AF_INET6; entry->sin6.sin6_addr = ifp->addr; list_add_tail(&entry->list, &sin6_list); } read_unlock_bh(&in6_dev->lock); in6_dev_put(in6_dev); list_for_each_entry_safe(sin6_iter, sin6_temp, &sin6_list, list) { union ib_gid gid; rdma_ip2gid((struct sockaddr *)&sin6_iter->sin6, &gid); update_gid(GID_ADD, ib_dev, port, &gid, &gid_attr); list_del(&sin6_iter->list); kfree(sin6_iter); } } static void _add_netdev_ips(struct ib_device *ib_dev, u32 port, struct net_device *ndev) { enum_netdev_ipv4_ips(ib_dev, port, ndev); if (IS_ENABLED(CONFIG_IPV6)) enum_netdev_ipv6_ips(ib_dev, port, ndev); } static void add_netdev_ips(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { _add_netdev_ips(ib_dev, port, cookie); } static void del_netdev_ips(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { ib_cache_gid_del_all_netdev_gids(ib_dev, port, cookie); } /** * del_default_gids - Delete default GIDs of the event/cookie netdevice * @ib_dev: RDMA device pointer * @port: Port of the RDMA device whose GID table to consider * @rdma_ndev: Unused rdma netdevice * @cookie: Pointer to event netdevice * * del_default_gids() deletes the default GIDs of the event/cookie netdevice. */ static void del_default_gids(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *cookie_ndev = cookie; unsigned long gid_type_mask; gid_type_mask = roce_gid_type_mask_support(ib_dev, port); ib_cache_gid_set_default_gid(ib_dev, port, cookie_ndev, gid_type_mask, IB_CACHE_GID_DEFAULT_MODE_DELETE); } static void add_default_gids(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *event_ndev = cookie; unsigned long gid_type_mask; gid_type_mask = roce_gid_type_mask_support(ib_dev, port); ib_cache_gid_set_default_gid(ib_dev, port, event_ndev, gid_type_mask, IB_CACHE_GID_DEFAULT_MODE_SET); } static void enum_all_gids_of_dev_cb(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net *net; struct net_device *ndev; /* Lock the rtnl to make sure the netdevs does not move under * our feet */ rtnl_lock(); down_read(&net_rwsem); for_each_net(net) for_each_netdev(net, ndev) { /* * Filter and add default GIDs of the primary netdevice * when not in bonding mode, or add default GIDs * of bond master device, when in bonding mode. */ if (is_ndev_for_default_gid_filter(ib_dev, port, rdma_ndev, ndev)) add_default_gids(ib_dev, port, rdma_ndev, ndev); if (is_eth_port_of_netdev_filter(ib_dev, port, rdma_ndev, ndev)) _add_netdev_ips(ib_dev, port, ndev); } up_read(&net_rwsem); rtnl_unlock(); } /** * rdma_roce_rescan_device - Rescan all of the network devices in the system * and add their gids, as needed, to the relevant RoCE devices. * * @ib_dev: the rdma device */ void rdma_roce_rescan_device(struct ib_device *ib_dev) { ib_enum_roce_netdev(ib_dev, pass_all_filter, NULL, enum_all_gids_of_dev_cb, NULL); } EXPORT_SYMBOL(rdma_roce_rescan_device); /** * rdma_roce_rescan_port - Rescan all of the network devices in the system * and add their gids if relevant to the port of the RoCE device. * * @ib_dev: IB device * @port: Port number */ void rdma_roce_rescan_port(struct ib_device *ib_dev, u32 port) { struct net_device *ndev = NULL; if (rdma_protocol_roce(ib_dev, port)) { ndev = ib_device_get_netdev(ib_dev, port); if (!ndev) return; enum_all_gids_of_dev_cb(ib_dev, port, ndev, ndev); dev_put(ndev); } } EXPORT_SYMBOL(rdma_roce_rescan_port); static void callback_for_addr_gid_device_scan(struct ib_device *device, u32 port, struct net_device *rdma_ndev, void *cookie) { struct update_gid_event_work *parsed = cookie; return update_gid(parsed->gid_op, device, port, &parsed->gid, &parsed->gid_attr); } struct upper_list { struct list_head list; struct net_device *upper; }; static int netdev_upper_walk(struct net_device *upper, struct netdev_nested_priv *priv) { struct upper_list *entry = kmalloc(sizeof(*entry), GFP_ATOMIC); struct list_head *upper_list = (struct list_head *)priv->data; if (!entry) return 0; list_add_tail(&entry->list, upper_list); dev_hold(upper); entry->upper = upper; return 0; } static void handle_netdev_upper(struct ib_device *ib_dev, u32 port, void *cookie, void (*handle_netdev)(struct ib_device *ib_dev, u32 port, struct net_device *ndev)) { struct net_device *ndev = cookie; struct netdev_nested_priv priv; struct upper_list *upper_iter; struct upper_list *upper_temp; LIST_HEAD(upper_list); priv.data = &upper_list; rcu_read_lock(); netdev_walk_all_upper_dev_rcu(ndev, netdev_upper_walk, &priv); rcu_read_unlock(); handle_netdev(ib_dev, port, ndev); list_for_each_entry_safe(upper_iter, upper_temp, &upper_list, list) { handle_netdev(ib_dev, port, upper_iter->upper); dev_put(upper_iter->upper); list_del(&upper_iter->list); kfree(upper_iter); } } void roce_del_all_netdev_gids(struct ib_device *ib_dev, u32 port, struct net_device *ndev) { ib_cache_gid_del_all_netdev_gids(ib_dev, port, ndev); } EXPORT_SYMBOL(roce_del_all_netdev_gids); static void del_netdev_upper_ips(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { handle_netdev_upper(ib_dev, port, cookie, roce_del_all_netdev_gids); } static void add_netdev_upper_ips(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { handle_netdev_upper(ib_dev, port, cookie, _add_netdev_ips); } static void del_netdev_default_ips_join(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *master_ndev; rcu_read_lock(); master_ndev = netdev_master_upper_dev_get_rcu(rdma_ndev); dev_hold(master_ndev); rcu_read_unlock(); if (master_ndev) { bond_delete_netdev_default_gids(ib_dev, port, rdma_ndev, master_ndev); dev_put(master_ndev); } } /* The following functions operate on all IB devices. netdevice_event and * addr_event execute ib_enum_all_roce_netdevs through a work. * ib_enum_all_roce_netdevs iterates through all IB devices. */ static void netdevice_event_work_handler(struct work_struct *_work) { struct netdev_event_work *work = container_of(_work, struct netdev_event_work, work); unsigned int i; for (i = 0; i < ARRAY_SIZE(work->cmds) && work->cmds[i].cb; i++) { ib_enum_all_roce_netdevs(work->cmds[i].filter, work->cmds[i].filter_ndev, work->cmds[i].cb, work->cmds[i].ndev); dev_put(work->cmds[i].ndev); dev_put(work->cmds[i].filter_ndev); } kfree(work); } static int netdevice_queue_work(struct netdev_event_work_cmd *cmds, struct net_device *ndev) { unsigned int i; struct netdev_event_work *ndev_work = kmalloc(sizeof(*ndev_work), GFP_KERNEL); if (!ndev_work) return NOTIFY_DONE; memcpy(ndev_work->cmds, cmds, sizeof(ndev_work->cmds)); for (i = 0; i < ARRAY_SIZE(ndev_work->cmds) && ndev_work->cmds[i].cb; i++) { if (!ndev_work->cmds[i].ndev) ndev_work->cmds[i].ndev = ndev; if (!ndev_work->cmds[i].filter_ndev) ndev_work->cmds[i].filter_ndev = ndev; dev_hold(ndev_work->cmds[i].ndev); dev_hold(ndev_work->cmds[i].filter_ndev); } INIT_WORK(&ndev_work->work, netdevice_event_work_handler); queue_work(gid_cache_wq, &ndev_work->work); return NOTIFY_DONE; } static const struct netdev_event_work_cmd add_cmd = { .cb = add_netdev_ips, .filter = is_eth_port_of_netdev_filter }; static const struct netdev_event_work_cmd add_cmd_upper_ips = { .cb = add_netdev_upper_ips, .filter = is_eth_port_of_netdev_filter }; static void ndev_event_unlink(struct netdev_notifier_changeupper_info *changeupper_info, struct netdev_event_work_cmd *cmds) { static const struct netdev_event_work_cmd upper_ips_del_cmd = { .cb = del_netdev_upper_ips, .filter = upper_device_filter }; cmds[0] = upper_ips_del_cmd; cmds[0].ndev = changeupper_info->upper_dev; cmds[1] = add_cmd; } static const struct netdev_event_work_cmd bonding_default_add_cmd = { .cb = add_default_gids, .filter = is_upper_ndev_bond_master_filter }; static void ndev_event_link(struct net_device *event_ndev, struct netdev_notifier_changeupper_info *changeupper_info, struct netdev_event_work_cmd *cmds) { static const struct netdev_event_work_cmd bonding_default_del_cmd = { .cb = del_default_gids, .filter = is_upper_ndev_bond_master_filter }; /* * When a lower netdev is linked to its upper bonding * netdev, delete lower slave netdev's default GIDs. */ cmds[0] = bonding_default_del_cmd; cmds[0].ndev = event_ndev; cmds[0].filter_ndev = changeupper_info->upper_dev; /* Now add bonding upper device default GIDs */ cmds[1] = bonding_default_add_cmd; cmds[1].ndev = changeupper_info->upper_dev; cmds[1].filter_ndev = changeupper_info->upper_dev; /* Now add bonding upper device IP based GIDs */ cmds[2] = add_cmd_upper_ips; cmds[2].ndev = changeupper_info->upper_dev; cmds[2].filter_ndev = changeupper_info->upper_dev; } static void netdevice_event_changeupper(struct net_device *event_ndev, struct netdev_notifier_changeupper_info *changeupper_info, struct netdev_event_work_cmd *cmds) { if (changeupper_info->linking) ndev_event_link(event_ndev, changeupper_info, cmds); else ndev_event_unlink(changeupper_info, cmds); } static const struct netdev_event_work_cmd add_default_gid_cmd = { .cb = add_default_gids, .filter = is_ndev_for_default_gid_filter, }; static int netdevice_event(struct notifier_block *this, unsigned long event, void *ptr) { static const struct netdev_event_work_cmd del_cmd = { .cb = del_netdev_ips, .filter = pass_all_filter}; static const struct netdev_event_work_cmd bonding_default_del_cmd_join = { .cb = del_netdev_default_ips_join, .filter = is_eth_port_inactive_slave_filter }; static const struct netdev_event_work_cmd netdev_del_cmd = { .cb = del_netdev_ips, .filter = is_eth_port_of_netdev_filter }; static const struct netdev_event_work_cmd bonding_event_ips_del_cmd = { .cb = del_netdev_upper_ips, .filter = upper_device_filter}; struct net_device *ndev = netdev_notifier_info_to_dev(ptr); struct netdev_event_work_cmd cmds[ROCE_NETDEV_CALLBACK_SZ] = { {NULL} }; if (ndev->type != ARPHRD_ETHER) return NOTIFY_DONE; switch (event) { case NETDEV_REGISTER: case NETDEV_UP: cmds[0] = bonding_default_del_cmd_join; cmds[1] = add_default_gid_cmd; cmds[2] = add_cmd; break; case NETDEV_UNREGISTER: if (ndev->reg_state < NETREG_UNREGISTERED) cmds[0] = del_cmd; else return NOTIFY_DONE; break; case NETDEV_CHANGEADDR: cmds[0] = netdev_del_cmd; if (ndev->reg_state == NETREG_REGISTERED) { cmds[1] = add_default_gid_cmd; cmds[2] = add_cmd; } break; case NETDEV_CHANGEUPPER: netdevice_event_changeupper(ndev, container_of(ptr, struct netdev_notifier_changeupper_info, info), cmds); break; case NETDEV_BONDING_FAILOVER: cmds[0] = bonding_event_ips_del_cmd; /* Add default GIDs of the bond device */ cmds[1] = bonding_default_add_cmd; /* Add IP based GIDs of the bond device */ cmds[2] = add_cmd_upper_ips; break; default: return NOTIFY_DONE; } return netdevice_queue_work(cmds, ndev); } static void update_gid_event_work_handler(struct work_struct *_work) { struct update_gid_event_work *work = container_of(_work, struct update_gid_event_work, work); ib_enum_all_roce_netdevs(is_eth_port_of_netdev_filter, work->gid_attr.ndev, callback_for_addr_gid_device_scan, work); dev_put(work->gid_attr.ndev); kfree(work); } static int addr_event(struct notifier_block *this, unsigned long event, struct sockaddr *sa, struct net_device *ndev) { struct update_gid_event_work *work; enum gid_op_type gid_op; if (ndev->type != ARPHRD_ETHER) return NOTIFY_DONE; switch (event) { case NETDEV_UP: gid_op = GID_ADD; break; case NETDEV_DOWN: gid_op = GID_DEL; break; default: return NOTIFY_DONE; } work = kmalloc(sizeof(*work), GFP_ATOMIC); if (!work) return NOTIFY_DONE; INIT_WORK(&work->work, update_gid_event_work_handler); rdma_ip2gid(sa, &work->gid); work->gid_op = gid_op; memset(&work->gid_attr, 0, sizeof(work->gid_attr)); dev_hold(ndev); work->gid_attr.ndev = ndev; queue_work(gid_cache_wq, &work->work); return NOTIFY_DONE; } static int inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr) { struct sockaddr_in in; struct net_device *ndev; struct in_ifaddr *ifa = ptr; in.sin_family = AF_INET; in.sin_addr.s_addr = ifa->ifa_address; ndev = ifa->ifa_dev->dev; return addr_event(this, event, (struct sockaddr *)&in, ndev); } static int inet6addr_event(struct notifier_block *this, unsigned long event, void *ptr) { struct sockaddr_in6 in6; struct net_device *ndev; struct inet6_ifaddr *ifa6 = ptr; in6.sin6_family = AF_INET6; in6.sin6_addr = ifa6->addr; ndev = ifa6->idev->dev; return addr_event(this, event, (struct sockaddr *)&in6, ndev); } static struct notifier_block nb_netdevice = { .notifier_call = netdevice_event }; static struct notifier_block nb_inetaddr = { .notifier_call = inetaddr_event }; static struct notifier_block nb_inet6addr = { .notifier_call = inet6addr_event }; int __init roce_gid_mgmt_init(void) { gid_cache_wq = alloc_ordered_workqueue("gid-cache-wq", 0); if (!gid_cache_wq) return -ENOMEM; register_inetaddr_notifier(&nb_inetaddr); if (IS_ENABLED(CONFIG_IPV6)) register_inet6addr_notifier(&nb_inet6addr); /* We relay on the netdevice notifier to enumerate all * existing devices in the system. Register to this notifier * last to make sure we will not miss any IP add/del * callbacks. */ register_netdevice_notifier(&nb_netdevice); return 0; } void __exit roce_gid_mgmt_cleanup(void) { if (IS_ENABLED(CONFIG_IPV6)) unregister_inet6addr_notifier(&nb_inet6addr); unregister_inetaddr_notifier(&nb_inetaddr); unregister_netdevice_notifier(&nb_netdevice); /* Ensure all gid deletion tasks complete before we go down, * to avoid any reference to free'd memory. By the time * ib-core is removed, all physical devices have been removed, * so no issue with remaining hardware contexts. */ destroy_workqueue(gid_cache_wq); } |
| 6 6 67 67 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 | /* * Compatibility functions which bloat the callers too much to make inline. * All of the callers of these functions should be converted to use folios * eventually. */ #include <linux/migrate.h> #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/swap.h> #include "internal.h" void unlock_page(struct page *page) { return folio_unlock(page_folio(page)); } EXPORT_SYMBOL(unlock_page); void end_page_writeback(struct page *page) { return folio_end_writeback(page_folio(page)); } EXPORT_SYMBOL(end_page_writeback); void wait_on_page_writeback(struct page *page) { return folio_wait_writeback(page_folio(page)); } EXPORT_SYMBOL_GPL(wait_on_page_writeback); void wait_for_stable_page(struct page *page) { return folio_wait_stable(page_folio(page)); } EXPORT_SYMBOL_GPL(wait_for_stable_page); void mark_page_accessed(struct page *page) { folio_mark_accessed(page_folio(page)); } EXPORT_SYMBOL(mark_page_accessed); void set_page_writeback(struct page *page) { folio_start_writeback(page_folio(page)); } EXPORT_SYMBOL(set_page_writeback); bool set_page_dirty(struct page *page) { return folio_mark_dirty(page_folio(page)); } EXPORT_SYMBOL(set_page_dirty); int set_page_dirty_lock(struct page *page) { return folio_mark_dirty_lock(page_folio(page)); } EXPORT_SYMBOL(set_page_dirty_lock); bool clear_page_dirty_for_io(struct page *page) { return folio_clear_dirty_for_io(page_folio(page)); } EXPORT_SYMBOL(clear_page_dirty_for_io); bool redirty_page_for_writepage(struct writeback_control *wbc, struct page *page) { return folio_redirty_for_writepage(wbc, page_folio(page)); } EXPORT_SYMBOL(redirty_page_for_writepage); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp) { return filemap_add_folio(mapping, page_folio(page), index, gfp); } EXPORT_SYMBOL(add_to_page_cache_lru); noinline struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, fgf_t fgp_flags, gfp_t gfp) { struct folio *folio; folio = __filemap_get_folio(mapping, index, fgp_flags, gfp); if (IS_ERR(folio)) return NULL; return folio_file_page(folio, index); } EXPORT_SYMBOL(pagecache_get_page); struct page *grab_cache_page_write_begin(struct address_space *mapping, pgoff_t index) { return pagecache_get_page(mapping, index, FGP_WRITEBEGIN, mapping_gfp_mask(mapping)); } EXPORT_SYMBOL(grab_cache_page_write_begin); |
| 1118 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_PREEMPT_H #define __LINUX_PREEMPT_H /* * include/linux/preempt.h - macros for accessing and manipulating * preempt_count (used for kernel preemption, interrupt count, etc.) */ #include <linux/linkage.h> #include <linux/cleanup.h> #include <linux/types.h> /* * We put the hardirq and softirq counter into the preemption * counter. The bitmask has the following meaning: * * - bits 0-7 are the preemption count (max preemption depth: 256) * - bits 8-15 are the softirq count (max # of softirqs: 256) * * The hardirq count could in theory be the same as the number of * interrupts in the system, but we run all interrupt handlers with * interrupts disabled, so we cannot have nesting interrupts. Though * there are a few palaeontologic drivers which reenable interrupts in * the handler, so we need more than one bit here. * * PREEMPT_MASK: 0x000000ff * SOFTIRQ_MASK: 0x0000ff00 * HARDIRQ_MASK: 0x000f0000 * NMI_MASK: 0x00f00000 * PREEMPT_NEED_RESCHED: 0x80000000 */ #define PREEMPT_BITS 8 #define SOFTIRQ_BITS 8 #define HARDIRQ_BITS 4 #define NMI_BITS 4 #define PREEMPT_SHIFT 0 #define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS) #define HARDIRQ_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS) #define NMI_SHIFT (HARDIRQ_SHIFT + HARDIRQ_BITS) #define __IRQ_MASK(x) ((1UL << (x))-1) #define PREEMPT_MASK (__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT) #define SOFTIRQ_MASK (__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT) #define HARDIRQ_MASK (__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT) #define NMI_MASK (__IRQ_MASK(NMI_BITS) << NMI_SHIFT) #define PREEMPT_OFFSET (1UL << PREEMPT_SHIFT) #define SOFTIRQ_OFFSET (1UL << SOFTIRQ_SHIFT) #define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) #define NMI_OFFSET (1UL << NMI_SHIFT) #define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) #define PREEMPT_DISABLED (PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED) /* * Disable preemption until the scheduler is running -- use an unconditional * value so that it also works on !PREEMPT_COUNT kernels. * * Reset by start_kernel()->sched_init()->init_idle()->init_idle_preempt_count(). */ #define INIT_PREEMPT_COUNT PREEMPT_OFFSET /* * Initial preempt_count value; reflects the preempt_count schedule invariant * which states that during context switches: * * preempt_count() == 2*PREEMPT_DISABLE_OFFSET * * Note: PREEMPT_DISABLE_OFFSET is 0 for !PREEMPT_COUNT kernels. * Note: See finish_task_switch(). */ #define FORK_PREEMPT_COUNT (2*PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED) /* preempt_count() and related functions, depends on PREEMPT_NEED_RESCHED */ #include <asm/preempt.h> /** * interrupt_context_level - return interrupt context level * * Returns the current interrupt context level. * 0 - normal context * 1 - softirq context * 2 - hardirq context * 3 - NMI context */ static __always_inline unsigned char interrupt_context_level(void) { unsigned long pc = preempt_count(); unsigned char level = 0; level += !!(pc & (NMI_MASK)); level += !!(pc & (NMI_MASK | HARDIRQ_MASK)); level += !!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)); return level; } /* * These macro definitions avoid redundant invocations of preempt_count() * because such invocations would result in redundant loads given that * preempt_count() is commonly implemented with READ_ONCE(). */ #define nmi_count() (preempt_count() & NMI_MASK) #define hardirq_count() (preempt_count() & HARDIRQ_MASK) #ifdef CONFIG_PREEMPT_RT # define softirq_count() (current->softirq_disable_cnt & SOFTIRQ_MASK) # define irq_count() ((preempt_count() & (NMI_MASK | HARDIRQ_MASK)) | softirq_count()) #else # define softirq_count() (preempt_count() & SOFTIRQ_MASK) # define irq_count() (preempt_count() & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_MASK)) #endif /* * Macros to retrieve the current execution context: * * in_nmi() - We're in NMI context * in_hardirq() - We're in hard IRQ context * in_serving_softirq() - We're in softirq context * in_task() - We're in task context */ #define in_nmi() (nmi_count()) #define in_hardirq() (hardirq_count()) #define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) #ifdef CONFIG_PREEMPT_RT # define in_task() (!((preempt_count() & (NMI_MASK | HARDIRQ_MASK)) | in_serving_softirq())) #else # define in_task() (!(preempt_count() & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET))) #endif /* * The following macros are deprecated and should not be used in new code: * in_irq() - Obsolete version of in_hardirq() * in_softirq() - We have BH disabled, or are processing softirqs * in_interrupt() - We're in NMI,IRQ,SoftIRQ context or have BH disabled */ #define in_irq() (hardirq_count()) #define in_softirq() (softirq_count()) #define in_interrupt() (irq_count()) /* * The preempt_count offset after preempt_disable(); */ #if defined(CONFIG_PREEMPT_COUNT) # define PREEMPT_DISABLE_OFFSET PREEMPT_OFFSET #else # define PREEMPT_DISABLE_OFFSET 0 #endif /* * The preempt_count offset after spin_lock() */ #if !defined(CONFIG_PREEMPT_RT) #define PREEMPT_LOCK_OFFSET PREEMPT_DISABLE_OFFSET #else /* Locks on RT do not disable preemption */ #define PREEMPT_LOCK_OFFSET 0 #endif /* * The preempt_count offset needed for things like: * * spin_lock_bh() * * Which need to disable both preemption (CONFIG_PREEMPT_COUNT) and * softirqs, such that unlock sequences of: * * spin_unlock(); * local_bh_enable(); * * Work as expected. */ #define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_LOCK_OFFSET) /* * Are we running in atomic context? WARNING: this macro cannot * always detect atomic context; in particular, it cannot know about * held spinlocks in non-preemptible kernels. Thus it should not be * used in the general case to determine whether sleeping is possible. * Do not use in_atomic() in driver code. */ #define in_atomic() (preempt_count() != 0) /* * Check whether we were atomic before we did preempt_disable(): * (used by the scheduler) */ #define in_atomic_preempt_off() (preempt_count() != PREEMPT_DISABLE_OFFSET) #if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_TRACE_PREEMPT_TOGGLE) extern void preempt_count_add(int val); extern void preempt_count_sub(int val); #define preempt_count_dec_and_test() \ ({ preempt_count_sub(1); should_resched(0); }) #else #define preempt_count_add(val) __preempt_count_add(val) #define preempt_count_sub(val) __preempt_count_sub(val) #define preempt_count_dec_and_test() __preempt_count_dec_and_test() #endif #define __preempt_count_inc() __preempt_count_add(1) #define __preempt_count_dec() __preempt_count_sub(1) #define preempt_count_inc() preempt_count_add(1) #define preempt_count_dec() preempt_count_sub(1) #ifdef CONFIG_PREEMPT_COUNT #define preempt_disable() \ do { \ preempt_count_inc(); \ barrier(); \ } while (0) #define sched_preempt_enable_no_resched() \ do { \ barrier(); \ preempt_count_dec(); \ } while (0) #define preempt_enable_no_resched() sched_preempt_enable_no_resched() #define preemptible() (preempt_count() == 0 && !irqs_disabled()) #ifdef CONFIG_PREEMPTION #define preempt_enable() \ do { \ barrier(); \ if (unlikely(preempt_count_dec_and_test())) \ __preempt_schedule(); \ } while (0) #define preempt_enable_notrace() \ do { \ barrier(); \ if (unlikely(__preempt_count_dec_and_test())) \ __preempt_schedule_notrace(); \ } while (0) #define preempt_check_resched() \ do { \ if (should_resched(0)) \ __preempt_schedule(); \ } while (0) #else /* !CONFIG_PREEMPTION */ #define preempt_enable() \ do { \ barrier(); \ preempt_count_dec(); \ } while (0) #define preempt_enable_notrace() \ do { \ barrier(); \ __preempt_count_dec(); \ } while (0) #define preempt_check_resched() do { } while (0) #endif /* CONFIG_PREEMPTION */ #define preempt_disable_notrace() \ do { \ __preempt_count_inc(); \ barrier(); \ } while (0) #define preempt_enable_no_resched_notrace() \ do { \ barrier(); \ __preempt_count_dec(); \ } while (0) #else /* !CONFIG_PREEMPT_COUNT */ /* * Even if we don't have any preemption, we need preempt disable/enable * to be barriers, so that we don't have things like get_user/put_user * that can cause faults and scheduling migrate into our preempt-protected * region. */ #define preempt_disable() barrier() #define sched_preempt_enable_no_resched() barrier() #define preempt_enable_no_resched() barrier() #define preempt_enable() barrier() #define preempt_check_resched() do { } while (0) #define preempt_disable_notrace() barrier() #define preempt_enable_no_resched_notrace() barrier() #define preempt_enable_notrace() barrier() #define preemptible() 0 #endif /* CONFIG_PREEMPT_COUNT */ #ifdef MODULE /* * Modules have no business playing preemption tricks. */ #undef sched_preempt_enable_no_resched #undef preempt_enable_no_resched #undef preempt_enable_no_resched_notrace #undef preempt_check_resched #endif #define preempt_set_need_resched() \ do { \ set_preempt_need_resched(); \ } while (0) #define preempt_fold_need_resched() \ do { \ if (tif_need_resched()) \ set_preempt_need_resched(); \ } while (0) #ifdef CONFIG_PREEMPT_NOTIFIERS struct preempt_notifier; /** * preempt_ops - notifiers called when a task is preempted and rescheduled * @sched_in: we're about to be rescheduled: * notifier: struct preempt_notifier for the task being scheduled * cpu: cpu we're scheduled on * @sched_out: we've just been preempted * notifier: struct preempt_notifier for the task being preempted * next: the task that's kicking us out * * Please note that sched_in and out are called under different * contexts. sched_out is called with rq lock held and irq disabled * while sched_in is called without rq lock and irq enabled. This * difference is intentional and depended upon by its users. */ struct preempt_ops { void (*sched_in)(struct preempt_notifier *notifier, int cpu); void (*sched_out)(struct preempt_notifier *notifier, struct task_struct *next); }; /** * preempt_notifier - key for installing preemption notifiers * @link: internal use * @ops: defines the notifier functions to be called * * Usually used in conjunction with container_of(). */ struct preempt_notifier { struct hlist_node link; struct preempt_ops *ops; }; void preempt_notifier_inc(void); void preempt_notifier_dec(void); void preempt_notifier_register(struct preempt_notifier *notifier); void preempt_notifier_unregister(struct preempt_notifier *notifier); static inline void preempt_notifier_init(struct preempt_notifier *notifier, struct preempt_ops *ops) { /* INIT_HLIST_NODE() open coded, to avoid dependency on list.h */ notifier->link.next = NULL; notifier->link.pprev = NULL; notifier->ops = ops; } #endif #ifdef CONFIG_SMP /* * Migrate-Disable and why it is undesired. * * When a preempted task becomes elegible to run under the ideal model (IOW it * becomes one of the M highest priority tasks), it might still have to wait * for the preemptee's migrate_disable() section to complete. Thereby suffering * a reduction in bandwidth in the exact duration of the migrate_disable() * section. * * Per this argument, the change from preempt_disable() to migrate_disable() * gets us: * * - a higher priority tasks gains reduced wake-up latency; with preempt_disable() * it would have had to wait for the lower priority task. * * - a lower priority tasks; which under preempt_disable() could've instantly * migrated away when another CPU becomes available, is now constrained * by the ability to push the higher priority task away, which might itself be * in a migrate_disable() section, reducing it's available bandwidth. * * IOW it trades latency / moves the interference term, but it stays in the * system, and as long as it remains unbounded, the system is not fully * deterministic. * * * The reason we have it anyway. * * PREEMPT_RT breaks a number of assumptions traditionally held. By forcing a * number of primitives into becoming preemptible, they would also allow * migration. This turns out to break a bunch of per-cpu usage. To this end, * all these primitives employ migirate_disable() to restore this implicit * assumption. * * This is a 'temporary' work-around at best. The correct solution is getting * rid of the above assumptions and reworking the code to employ explicit * per-cpu locking or short preempt-disable regions. * * The end goal must be to get rid of migrate_disable(), alternatively we need * a schedulability theory that does not depend on abritrary migration. * * * Notes on the implementation. * * The implementation is particularly tricky since existing code patterns * dictate neither migrate_disable() nor migrate_enable() is allowed to block. * This means that it cannot use cpus_read_lock() to serialize against hotplug, * nor can it easily migrate itself into a pending affinity mask change on * migrate_enable(). * * * Note: even non-work-conserving schedulers like semi-partitioned depends on * migration, so migrate_disable() is not only a problem for * work-conserving schedulers. * */ extern void migrate_disable(void); extern void migrate_enable(void); #else static inline void migrate_disable(void) { } static inline void migrate_enable(void) { } #endif /* CONFIG_SMP */ /** * preempt_disable_nested - Disable preemption inside a normally preempt disabled section * * Use for code which requires preemption protection inside a critical * section which has preemption disabled implicitly on non-PREEMPT_RT * enabled kernels, by e.g.: * - holding a spinlock/rwlock * - soft interrupt context * - regular interrupt handlers * * On PREEMPT_RT enabled kernels spinlock/rwlock held sections, soft * interrupt context and regular interrupt handlers are preemptible and * only prevent migration. preempt_disable_nested() ensures that preemption * is disabled for cases which require CPU local serialization even on * PREEMPT_RT. For non-PREEMPT_RT kernels this is a NOP. * * The use cases are code sequences which are not serialized by a * particular lock instance, e.g.: * - seqcount write side critical sections where the seqcount is not * associated to a particular lock and therefore the automatic * protection mechanism does not work. This prevents a live lock * against a preempting high priority reader. * - RMW per CPU variable updates like vmstat. */ /* Macro to avoid header recursion hell vs. lockdep */ #define preempt_disable_nested() \ do { \ if (IS_ENABLED(CONFIG_PREEMPT_RT)) \ preempt_disable(); \ else \ lockdep_assert_preemption_disabled(); \ } while (0) /** * preempt_enable_nested - Undo the effect of preempt_disable_nested() */ static __always_inline void preempt_enable_nested(void) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) preempt_enable(); } DEFINE_LOCK_GUARD_0(preempt, preempt_disable(), preempt_enable()) DEFINE_LOCK_GUARD_0(preempt_notrace, preempt_disable_notrace(), preempt_enable_notrace()) DEFINE_LOCK_GUARD_0(migrate, migrate_disable(), migrate_enable()) #ifdef CONFIG_PREEMPT_DYNAMIC extern bool preempt_model_none(void); extern bool preempt_model_voluntary(void); extern bool preempt_model_full(void); extern bool preempt_model_lazy(void); #else static inline bool preempt_model_none(void) { return IS_ENABLED(CONFIG_PREEMPT_NONE); } static inline bool preempt_model_voluntary(void) { return IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY); } static inline bool preempt_model_full(void) { return IS_ENABLED(CONFIG_PREEMPT); } static inline bool preempt_model_lazy(void) { return IS_ENABLED(CONFIG_PREEMPT_LAZY); } #endif static inline bool preempt_model_rt(void) { return IS_ENABLED(CONFIG_PREEMPT_RT); } /* * Does the preemption model allow non-cooperative preemption? * * For !CONFIG_PREEMPT_DYNAMIC kernels this is an exact match with * CONFIG_PREEMPTION; for CONFIG_PREEMPT_DYNAMIC this doesn't work as the * kernel is *built* with CONFIG_PREEMPTION=y but may run with e.g. the * PREEMPT_NONE model. */ static inline bool preempt_model_preemptible(void) { return preempt_model_full() || preempt_model_lazy() || preempt_model_rt(); } #endif /* __LINUX_PREEMPT_H */ |
| 109 559 196 196 197 197 185 184 553 552 38 38 535 536 535 229 228 170 170 170 499 500 262 263 263 312 312 75 74 102 102 50 50 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 | // SPDX-License-Identifier: GPL-2.0-only /* * Simple NUMA memory policy for the Linux kernel. * * Copyright 2003,2004 Andi Kleen, SuSE Labs. * (C) Copyright 2005 Christoph Lameter, Silicon Graphics, Inc. * * NUMA policy allows the user to give hints in which node(s) memory should * be allocated. * * Support six policies per VMA and per process: * * The VMA policy has priority over the process policy for a page fault. * * interleave Allocate memory interleaved over a set of nodes, * with normal fallback if it fails. * For VMA based allocations this interleaves based on the * offset into the backing object or offset into the mapping * for anonymous memory. For process policy an process counter * is used. * * weighted interleave * Allocate memory interleaved over a set of nodes based on * a set of weights (per-node), with normal fallback if it * fails. Otherwise operates the same as interleave. * Example: nodeset(0,1) & weights (2,1) - 2 pages allocated * on node 0 for every 1 page allocated on node 1. * * bind Only allocate memory on a specific set of nodes, * no fallback. * FIXME: memory is allocated starting with the first node * to the last. It would be better if bind would truly restrict * the allocation to memory nodes instead * * preferred Try a specific node first before normal fallback. * As a special case NUMA_NO_NODE here means do the allocation * on the local CPU. This is normally identical to default, * but useful to set in a VMA when you have a non default * process policy. * * preferred many Try a set of nodes first before normal fallback. This is * similar to preferred without the special case. * * default Allocate on the local node first, or when on a VMA * use the process policy. This is what Linux always did * in a NUMA aware kernel and still does by, ahem, default. * * The process policy is applied for most non interrupt memory allocations * in that process' context. Interrupts ignore the policies and always * try to allocate on the local CPU. The VMA policy is only applied for memory * allocations for a VMA in the VM. * * Currently there are a few corner cases in swapping where the policy * is not applied, but the majority should be handled. When process policy * is used it is not remembered over swap outs/swap ins. * * Only the highest zone in the zone hierarchy gets policied. Allocations * requesting a lower zone just use default policy. This implies that * on systems with highmem kernel lowmem allocation don't get policied. * Same with GFP_DMA allocations. * * For shmem/tmpfs shared memory the policy is shared between * all users and remembered even when nobody has memory mapped. */ /* Notebook: fix mmap readahead to honour policy and enable policy for any page cache object statistics for bigpages global policy for page cache? currently it uses process policy. Requires first item above. handle mremap for shared memory (currently ignored for the policy) grows down? make bind policy root only? It can trigger oom much faster and the kernel is not always grateful with that. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mempolicy.h> #include <linux/pagewalk.h> #include <linux/highmem.h> #include <linux/hugetlb.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/task.h> #include <linux/nodemask.h> #include <linux/cpuset.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/export.h> #include <linux/nsproxy.h> #include <linux/interrupt.h> #include <linux/init.h> #include <linux/compat.h> #include <linux/ptrace.h> #include <linux/swap.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/migrate.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/ctype.h> #include <linux/mm_inline.h> #include <linux/mmu_notifier.h> #include <linux/printk.h> #include <linux/swapops.h> #include <asm/tlbflush.h> #include <asm/tlb.h> #include <linux/uaccess.h> #include "internal.h" /* Internal flags */ #define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0) /* Skip checks for continuous vmas */ #define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1) /* Invert check for nodemask */ #define MPOL_MF_WRLOCK (MPOL_MF_INTERNAL << 2) /* Write-lock walked vmas */ static struct kmem_cache *policy_cache; static struct kmem_cache *sn_cache; /* Highest zone. An specific allocation for a zone below that is not policied. */ enum zone_type policy_zone = 0; /* * run-time system-wide default policy => local allocation */ static struct mempolicy default_policy = { .refcnt = ATOMIC_INIT(1), /* never free it */ .mode = MPOL_LOCAL, }; static struct mempolicy preferred_node_policy[MAX_NUMNODES]; /* * iw_table is the sysfs-set interleave weight table, a value of 0 denotes * system-default value should be used. A NULL iw_table also denotes that * system-default values should be used. Until the system-default table * is implemented, the system-default is always 1. * * iw_table is RCU protected */ static u8 __rcu *iw_table; static DEFINE_MUTEX(iw_table_lock); static u8 get_il_weight(int node) { u8 *table; u8 weight; rcu_read_lock(); table = rcu_dereference(iw_table); /* if no iw_table, use system default */ weight = table ? table[node] : 1; /* if value in iw_table is 0, use system default */ weight = weight ? weight : 1; rcu_read_unlock(); return weight; } /** * numa_nearest_node - Find nearest node by state * @node: Node id to start the search * @state: State to filter the search * * Lookup the closest node by distance if @nid is not in state. * * Return: this @node if it is in state, otherwise the closest node by distance */ int numa_nearest_node(int node, unsigned int state) { int min_dist = INT_MAX, dist, n, min_node; if (state >= NR_NODE_STATES) return -EINVAL; if (node == NUMA_NO_NODE || node_state(node, state)) return node; min_node = node; for_each_node_state(n, state) { dist = node_distance(node, n); if (dist < min_dist) { min_dist = dist; min_node = n; } } return min_node; } EXPORT_SYMBOL_GPL(numa_nearest_node); struct mempolicy *get_task_policy(struct task_struct *p) { struct mempolicy *pol = p->mempolicy; int node; if (pol) return pol; node = numa_node_id(); if (node != NUMA_NO_NODE) { pol = &preferred_node_policy[node]; /* preferred_node_policy is not initialised early in boot */ if (pol->mode) return pol; } return &default_policy; } static const struct mempolicy_operations { int (*create)(struct mempolicy *pol, const nodemask_t *nodes); void (*rebind)(struct mempolicy *pol, const nodemask_t *nodes); } mpol_ops[MPOL_MAX]; static inline int mpol_store_user_nodemask(const struct mempolicy *pol) { return pol->flags & MPOL_MODE_FLAGS; } static void mpol_relative_nodemask(nodemask_t *ret, const nodemask_t *orig, const nodemask_t *rel) { nodemask_t tmp; nodes_fold(tmp, *orig, nodes_weight(*rel)); nodes_onto(*ret, tmp, *rel); } static int mpol_new_nodemask(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; pol->nodes = *nodes; return 0; } static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; nodes_clear(pol->nodes); node_set(first_node(*nodes), pol->nodes); return 0; } /* * mpol_set_nodemask is called after mpol_new() to set up the nodemask, if * any, for the new policy. mpol_new() has already validated the nodes * parameter with respect to the policy mode and flags. * * Must be called holding task's alloc_lock to protect task's mems_allowed * and mempolicy. May also be called holding the mmap_lock for write. */ static int mpol_set_nodemask(struct mempolicy *pol, const nodemask_t *nodes, struct nodemask_scratch *nsc) { int ret; /* * Default (pol==NULL) resp. local memory policies are not a * subject of any remapping. They also do not need any special * constructor. */ if (!pol || pol->mode == MPOL_LOCAL) return 0; /* Check N_MEMORY */ nodes_and(nsc->mask1, cpuset_current_mems_allowed, node_states[N_MEMORY]); VM_BUG_ON(!nodes); if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1); else nodes_and(nsc->mask2, *nodes, nsc->mask1); if (mpol_store_user_nodemask(pol)) pol->w.user_nodemask = *nodes; else pol->w.cpuset_mems_allowed = cpuset_current_mems_allowed; ret = mpol_ops[pol->mode].create(pol, &nsc->mask2); return ret; } /* * This function just creates a new policy, does some check and simple * initialization. You must invoke mpol_set_nodemask() to set nodes. */ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *policy; if (mode == MPOL_DEFAULT) { if (nodes && !nodes_empty(*nodes)) return ERR_PTR(-EINVAL); return NULL; } VM_BUG_ON(!nodes); /* * MPOL_PREFERRED cannot be used with MPOL_F_STATIC_NODES or * MPOL_F_RELATIVE_NODES if the nodemask is empty (local allocation). * All other modes require a valid pointer to a non-empty nodemask. */ if (mode == MPOL_PREFERRED) { if (nodes_empty(*nodes)) { if (((flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES))) return ERR_PTR(-EINVAL); mode = MPOL_LOCAL; } } else if (mode == MPOL_LOCAL) { if (!nodes_empty(*nodes) || (flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES)) return ERR_PTR(-EINVAL); } else if (nodes_empty(*nodes)) return ERR_PTR(-EINVAL); policy = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!policy) return ERR_PTR(-ENOMEM); atomic_set(&policy->refcnt, 1); policy->mode = mode; policy->flags = flags; policy->home_node = NUMA_NO_NODE; return policy; } /* Slow path of a mpol destructor. */ void __mpol_put(struct mempolicy *pol) { if (!atomic_dec_and_test(&pol->refcnt)) return; kmem_cache_free(policy_cache, pol); } static void mpol_rebind_default(struct mempolicy *pol, const nodemask_t *nodes) { } static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes) { nodemask_t tmp; if (pol->flags & MPOL_F_STATIC_NODES) nodes_and(tmp, pol->w.user_nodemask, *nodes); else if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); else { nodes_remap(tmp, pol->nodes, pol->w.cpuset_mems_allowed, *nodes); pol->w.cpuset_mems_allowed = *nodes; } if (nodes_empty(tmp)) tmp = *nodes; pol->nodes = tmp; } static void mpol_rebind_preferred(struct mempolicy *pol, const nodemask_t *nodes) { pol->w.cpuset_mems_allowed = *nodes; } /* * mpol_rebind_policy - Migrate a policy to a different set of nodes * * Per-vma policies are protected by mmap_lock. Allocations using per-task * policies are protected by task->mems_allowed_seq to prevent a premature * OOM/allocation failure due to parallel nodemask modification. */ static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask) { if (!pol || pol->mode == MPOL_LOCAL) return; if (!mpol_store_user_nodemask(pol) && nodes_equal(pol->w.cpuset_mems_allowed, *newmask)) return; mpol_ops[pol->mode].rebind(pol, newmask); } /* * Wrapper for mpol_rebind_policy() that just requires task * pointer, and updates task mempolicy. * * Called with task's alloc_lock held. */ void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) { mpol_rebind_policy(tsk->mempolicy, new); } /* * Rebind each vma in mm to new nodemask. * * Call holding a reference to mm. Takes mm->mmap_lock during call. */ void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, 0); mmap_write_lock(mm); for_each_vma(vmi, vma) { vma_start_write(vma); mpol_rebind_policy(vma->vm_policy, new); } mmap_write_unlock(mm); } static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { [MPOL_DEFAULT] = { .rebind = mpol_rebind_default, }, [MPOL_INTERLEAVE] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, [MPOL_PREFERRED] = { .create = mpol_new_preferred, .rebind = mpol_rebind_preferred, }, [MPOL_BIND] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, [MPOL_LOCAL] = { .rebind = mpol_rebind_default, }, [MPOL_PREFERRED_MANY] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_preferred, }, [MPOL_WEIGHTED_INTERLEAVE] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, }; static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags); static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *pol, pgoff_t ilx, int *nid); static bool strictly_unmovable(unsigned long flags) { /* * STRICT without MOVE flags lets do_mbind() fail immediately with -EIO * if any misplaced page is found. */ return (flags & (MPOL_MF_STRICT | MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) == MPOL_MF_STRICT; } struct migration_mpol { /* for alloc_migration_target_by_mpol() */ struct mempolicy *pol; pgoff_t ilx; }; struct queue_pages { struct list_head *pagelist; unsigned long flags; nodemask_t *nmask; unsigned long start; unsigned long end; struct vm_area_struct *first; struct folio *large; /* note last large folio encountered */ long nr_failed; /* could not be isolated at this time */ }; /* * Check if the folio's nid is in qp->nmask. * * If MPOL_MF_INVERT is set in qp->flags, check if the nid is * in the invert of qp->nmask. */ static inline bool queue_folio_required(struct folio *folio, struct queue_pages *qp) { int nid = folio_nid(folio); unsigned long flags = qp->flags; return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT); } static void queue_folios_pmd(pmd_t *pmd, struct mm_walk *walk) { struct folio *folio; struct queue_pages *qp = walk->private; if (unlikely(is_pmd_migration_entry(*pmd))) { qp->nr_failed++; return; } folio = pmd_folio(*pmd); if (is_huge_zero_folio(folio)) { walk->action = ACTION_CONTINUE; return; } if (!queue_folio_required(folio, qp)) return; if (!(qp->flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(walk->vma) || !migrate_folio_add(folio, qp->pagelist, qp->flags)) qp->nr_failed++; } /* * Scan through folios, checking if they satisfy the required conditions, * moving them from LRU to local pagelist for migration if they do (or not). * * queue_folios_pte_range() has two possible return values: * 0 - continue walking to scan for more, even if an existing folio on the * wrong node could not be isolated and queued for migration. * -EIO - only MPOL_MF_STRICT was specified, without MPOL_MF_MOVE or ..._ALL, * and an existing folio was on a node that does not follow the policy. */ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; struct folio *folio; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; pte_t *pte, *mapped_pte; pte_t ptent; spinlock_t *ptl; ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { queue_folios_pmd(pmd, walk); spin_unlock(ptl); goto out; } mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); if (!pte) { walk->action = ACTION_AGAIN; return 0; } for (; addr != end; pte++, addr += PAGE_SIZE) { ptent = ptep_get(pte); if (pte_none(ptent)) continue; if (!pte_present(ptent)) { if (is_migration_entry(pte_to_swp_entry(ptent))) qp->nr_failed++; continue; } folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; /* * vm_normal_folio() filters out zero pages, but there might * still be reserved folios to skip, perhaps in a VDSO. */ if (folio_test_reserved(folio)) continue; if (!queue_folio_required(folio, qp)) continue; if (folio_test_large(folio)) { /* * A large folio can only be isolated from LRU once, * but may be mapped by many PTEs (and Copy-On-Write may * intersperse PTEs of other, order 0, folios). This is * a common case, so don't mistake it for failure (but * there can be other cases of multi-mapped pages which * this quick check does not help to filter out - and a * search of the pagelist might grow to be prohibitive). * * migrate_pages(&pagelist) returns nr_failed folios, so * check "large" now so that queue_pages_range() returns * a comparable nr_failed folios. This does imply that * if folio could not be isolated for some racy reason * at its first PTE, later PTEs will not give it another * chance of isolation; but keeps the accounting simple. */ if (folio == qp->large) continue; qp->large = folio; } if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(vma) || !migrate_folio_add(folio, qp->pagelist, flags)) { qp->nr_failed++; if (strictly_unmovable(flags)) break; } } pte_unmap_unlock(mapped_pte, ptl); cond_resched(); out: if (qp->nr_failed && strictly_unmovable(flags)) return -EIO; return 0; } static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { #ifdef CONFIG_HUGETLB_PAGE struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; struct folio *folio; spinlock_t *ptl; pte_t entry; ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte); entry = huge_ptep_get(walk->mm, addr, pte); if (!pte_present(entry)) { if (unlikely(is_hugetlb_entry_migration(entry))) qp->nr_failed++; goto unlock; } folio = pfn_folio(pte_pfn(entry)); if (!queue_folio_required(folio, qp)) goto unlock; if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(walk->vma)) { qp->nr_failed++; goto unlock; } /* * Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio. * Choosing not to migrate a shared folio is not counted as a failure. * * See folio_likely_mapped_shared() on possible imprecision when we * cannot easily detect if a folio is shared. */ if ((flags & MPOL_MF_MOVE_ALL) || (!folio_likely_mapped_shared(folio) && !hugetlb_pmd_shared(pte))) if (!isolate_hugetlb(folio, qp->pagelist)) qp->nr_failed++; unlock: spin_unlock(ptl); if (qp->nr_failed && strictly_unmovable(flags)) return -EIO; #endif return 0; } #ifdef CONFIG_NUMA_BALANCING /* * This is used to mark a range of virtual addresses to be inaccessible. * These are later cleared by a NUMA hinting fault. Depending on these * faults, pages may be migrated for better NUMA placement. * * This is assuming that NUMA faults are handled using PROT_NONE. If * an architecture makes a different choice, it will need further * changes to the core. */ unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long addr, unsigned long end) { struct mmu_gather tlb; long nr_updated; tlb_gather_mmu(&tlb, vma->vm_mm); nr_updated = change_protection(&tlb, vma, addr, end, MM_CP_PROT_NUMA); if (nr_updated > 0) { count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated); count_memcg_events_mm(vma->vm_mm, NUMA_PTE_UPDATES, nr_updated); } tlb_finish_mmu(&tlb); return nr_updated; } #endif /* CONFIG_NUMA_BALANCING */ static int queue_pages_test_walk(unsigned long start, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *next, *vma = walk->vma; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; /* range check first */ VM_BUG_ON_VMA(!range_in_vma(vma, start, end), vma); if (!qp->first) { qp->first = vma; if (!(flags & MPOL_MF_DISCONTIG_OK) && (qp->start < vma->vm_start)) /* hole at head side of range */ return -EFAULT; } next = find_vma(vma->vm_mm, vma->vm_end); if (!(flags & MPOL_MF_DISCONTIG_OK) && ((vma->vm_end < qp->end) && (!next || vma->vm_end < next->vm_start))) /* hole at middle or tail of range */ return -EFAULT; /* * Need check MPOL_MF_STRICT to return -EIO if possible * regardless of vma_migratable */ if (!vma_migratable(vma) && !(flags & MPOL_MF_STRICT)) return 1; /* * Check page nodes, and queue pages to move, in the current vma. * But if no moving, and no strict checking, the scan can be skipped. */ if (flags & (MPOL_MF_STRICT | MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) return 0; return 1; } static const struct mm_walk_ops queue_pages_walk_ops = { .hugetlb_entry = queue_folios_hugetlb, .pmd_entry = queue_folios_pte_range, .test_walk = queue_pages_test_walk, .walk_lock = PGWALK_RDLOCK, }; static const struct mm_walk_ops queue_pages_lock_vma_walk_ops = { .hugetlb_entry = queue_folios_hugetlb, .pmd_entry = queue_folios_pte_range, .test_walk = queue_pages_test_walk, .walk_lock = PGWALK_WRLOCK, }; /* * Walk through page tables and collect pages to be migrated. * * If pages found in a given range are not on the required set of @nodes, * and migration is allowed, they are isolated and queued to @pagelist. * * queue_pages_range() may return: * 0 - all pages already on the right node, or successfully queued for moving * (or neither strict checking nor moving requested: only range checking). * >0 - this number of misplaced folios could not be queued for moving * (a hugetlbfs page or a transparent huge page being counted as 1). * -EIO - a misplaced page found, when MPOL_MF_STRICT specified without MOVEs. * -EFAULT - a hole in the memory range, when MPOL_MF_DISCONTIG_OK unspecified. */ static long queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, nodemask_t *nodes, unsigned long flags, struct list_head *pagelist) { int err; struct queue_pages qp = { .pagelist = pagelist, .flags = flags, .nmask = nodes, .start = start, .end = end, .first = NULL, }; const struct mm_walk_ops *ops = (flags & MPOL_MF_WRLOCK) ? &queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops; err = walk_page_range(mm, start, end, ops, &qp); if (!qp.first) /* whole range in hole */ err = -EFAULT; return err ? : qp.nr_failed; } /* * Apply policy to a single VMA * This must be called with the mmap_lock held for writing. */ static int vma_replace_policy(struct vm_area_struct *vma, struct mempolicy *pol) { int err; struct mempolicy *old; struct mempolicy *new; vma_assert_write_locked(vma); new = mpol_dup(pol); if (IS_ERR(new)) return PTR_ERR(new); if (vma->vm_ops && vma->vm_ops->set_policy) { err = vma->vm_ops->set_policy(vma, new); if (err) goto err_out; } old = vma->vm_policy; vma->vm_policy = new; /* protected by mmap_lock */ mpol_put(old); return 0; err_out: mpol_put(new); return err; } /* Split or merge the VMA (if required) and apply the new policy */ static int mbind_range(struct vma_iterator *vmi, struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, struct mempolicy *new_pol) { unsigned long vmstart, vmend; vmend = min(end, vma->vm_end); if (start > vma->vm_start) { *prev = vma; vmstart = start; } else { vmstart = vma->vm_start; } if (mpol_equal(vma->vm_policy, new_pol)) { *prev = vma; return 0; } vma = vma_modify_policy(vmi, *prev, vma, vmstart, vmend, new_pol); if (IS_ERR(vma)) return PTR_ERR(vma); *prev = vma; return vma_replace_policy(vma, new_pol); } /* Set the process memory policy */ static long do_set_mempolicy(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *new, *old; NODEMASK_SCRATCH(scratch); int ret; if (!scratch) return -ENOMEM; new = mpol_new(mode, flags, nodes); if (IS_ERR(new)) { ret = PTR_ERR(new); goto out; } task_lock(current); ret = mpol_set_nodemask(new, nodes, scratch); if (ret) { task_unlock(current); mpol_put(new); goto out; } old = current->mempolicy; current->mempolicy = new; if (new && (new->mode == MPOL_INTERLEAVE || new->mode == MPOL_WEIGHTED_INTERLEAVE)) { current->il_prev = MAX_NUMNODES-1; current->il_weight = 0; } task_unlock(current); mpol_put(old); ret = 0; out: NODEMASK_SCRATCH_FREE(scratch); return ret; } /* * Return nodemask for policy for get_mempolicy() query * * Called with task's alloc_lock held */ static void get_policy_nodemask(struct mempolicy *pol, nodemask_t *nodes) { nodes_clear(*nodes); if (pol == &default_policy) return; switch (pol->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_WEIGHTED_INTERLEAVE: *nodes = pol->nodes; break; case MPOL_LOCAL: /* return empty node mask for local allocation */ break; default: BUG(); } } static int lookup_node(struct mm_struct *mm, unsigned long addr) { struct page *p = NULL; int ret; ret = get_user_pages_fast(addr & PAGE_MASK, 1, 0, &p); if (ret > 0) { ret = page_to_nid(p); put_page(p); } return ret; } /* Retrieve NUMA policy */ static long do_get_mempolicy(int *policy, nodemask_t *nmask, unsigned long addr, unsigned long flags) { int err; struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; struct mempolicy *pol = current->mempolicy, *pol_refcount = NULL; if (flags & ~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR|MPOL_F_MEMS_ALLOWED)) return -EINVAL; if (flags & MPOL_F_MEMS_ALLOWED) { if (flags & (MPOL_F_NODE|MPOL_F_ADDR)) return -EINVAL; *policy = 0; /* just so it's initialized */ task_lock(current); *nmask = cpuset_current_mems_allowed; task_unlock(current); return 0; } if (flags & MPOL_F_ADDR) { pgoff_t ilx; /* ignored here */ /* * Do NOT fall back to task policy if the * vma/shared policy at addr is NULL. We * want to return MPOL_DEFAULT in this case. */ mmap_read_lock(mm); vma = vma_lookup(mm, addr); if (!vma) { mmap_read_unlock(mm); return -EFAULT; } pol = __get_vma_policy(vma, addr, &ilx); } else if (addr) return -EINVAL; if (!pol) pol = &default_policy; /* indicates default behavior */ if (flags & MPOL_F_NODE) { if (flags & MPOL_F_ADDR) { /* * Take a refcount on the mpol, because we are about to * drop the mmap_lock, after which only "pol" remains * valid, "vma" is stale. */ pol_refcount = pol; vma = NULL; mpol_get(pol); mmap_read_unlock(mm); err = lookup_node(mm, addr); if (err < 0) goto out; *policy = err; } else if (pol == current->mempolicy && pol->mode == MPOL_INTERLEAVE) { *policy = next_node_in(current->il_prev, pol->nodes); } else if (pol == current->mempolicy && pol->mode == MPOL_WEIGHTED_INTERLEAVE) { if (current->il_weight) *policy = current->il_prev; else *policy = next_node_in(current->il_prev, pol->nodes); } else { err = -EINVAL; goto out; } } else { *policy = pol == &default_policy ? MPOL_DEFAULT : pol->mode; /* * Internal mempolicy flags must be masked off before exposing * the policy to userspace. */ *policy |= (pol->flags & MPOL_MODE_FLAGS); } err = 0; if (nmask) { if (mpol_store_user_nodemask(pol)) { *nmask = pol->w.user_nodemask; } else { task_lock(current); get_policy_nodemask(pol, nmask); task_unlock(current); } } out: mpol_cond_put(pol); if (vma) mmap_read_unlock(mm); if (pol_refcount) mpol_put(pol_refcount); return err; } #ifdef CONFIG_MIGRATION static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags) { /* * Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio. * Choosing not to migrate a shared folio is not counted as a failure. * * See folio_likely_mapped_shared() on possible imprecision when we * cannot easily detect if a folio is shared. */ if ((flags & MPOL_MF_MOVE_ALL) || !folio_likely_mapped_shared(folio)) { if (folio_isolate_lru(folio)) { list_add_tail(&folio->lru, foliolist); node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); } else { /* * Non-movable folio may reach here. And, there may be * temporary off LRU folios or non-LRU movable folios. * Treat them as unmovable folios since they can't be * isolated, so they can't be moved at the moment. */ return false; } } return true; } /* * Migrate pages from one node to a target node. * Returns error or the number of pages not migrated. */ static long migrate_to_node(struct mm_struct *mm, int source, int dest, int flags) { nodemask_t nmask; struct vm_area_struct *vma; LIST_HEAD(pagelist); long nr_failed; long err = 0; struct migration_target_control mtc = { .nid = dest, .gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, .reason = MR_SYSCALL, }; nodes_clear(nmask); node_set(source, nmask); VM_BUG_ON(!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))); mmap_read_lock(mm); vma = find_vma(mm, 0); if (unlikely(!vma)) { mmap_read_unlock(mm); return 0; } /* * This does not migrate the range, but isolates all pages that * need migration. Between passing in the full user address * space range and MPOL_MF_DISCONTIG_OK, this call cannot fail, * but passes back the count of pages which could not be isolated. */ nr_failed = queue_pages_range(mm, vma->vm_start, mm->task_size, &nmask, flags | MPOL_MF_DISCONTIG_OK, &pagelist); mmap_read_unlock(mm); if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL, NULL); if (err) putback_movable_pages(&pagelist); } if (err >= 0) err += nr_failed; return err; } /* * Move pages between the two nodesets so as to preserve the physical * layout as much as possible. * * Returns the number of page that could not be moved. */ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { long nr_failed = 0; long err = 0; nodemask_t tmp; lru_cache_disable(); /* * Find a 'source' bit set in 'tmp' whose corresponding 'dest' * bit in 'to' is not also set in 'tmp'. Clear the found 'source' * bit in 'tmp', and return that <source, dest> pair for migration. * The pair of nodemasks 'to' and 'from' define the map. * * If no pair of bits is found that way, fallback to picking some * pair of 'source' and 'dest' bits that are not the same. If the * 'source' and 'dest' bits are the same, this represents a node * that will be migrating to itself, so no pages need move. * * If no bits are left in 'tmp', or if all remaining bits left * in 'tmp' correspond to the same bit in 'to', return false * (nothing left to migrate). * * This lets us pick a pair of nodes to migrate between, such that * if possible the dest node is not already occupied by some other * source node, minimizing the risk of overloading the memory on a * node that would happen if we migrated incoming memory to a node * before migrating outgoing memory source that same node. * * A single scan of tmp is sufficient. As we go, we remember the * most recent <s, d> pair that moved (s != d). If we find a pair * that not only moved, but what's better, moved to an empty slot * (d is not set in tmp), then we break out then, with that pair. * Otherwise when we finish scanning from_tmp, we at least have the * most recent <s, d> pair that moved. If we get all the way through * the scan of tmp without finding any node that moved, much less * moved to an empty node, then there is nothing left worth migrating. */ tmp = *from; while (!nodes_empty(tmp)) { int s, d; int source = NUMA_NO_NODE; int dest = 0; for_each_node_mask(s, tmp) { /* * do_migrate_pages() tries to maintain the relative * node relationship of the pages established between * threads and memory areas. * * However if the number of source nodes is not equal to * the number of destination nodes we can not preserve * this node relative relationship. In that case, skip * copying memory from a node that is in the destination * mask. * * Example: [2,3,4] -> [3,4,5] moves everything. * [0-7] - > [3,4,5] moves only 0,1,2,6,7. */ if ((nodes_weight(*from) != nodes_weight(*to)) && (node_isset(s, *to))) continue; d = node_remap(s, *from, *to); if (s == d) continue; source = s; /* Node moved. Memorize */ dest = d; /* dest not in remaining from nodes? */ if (!node_isset(dest, tmp)) break; } if (source == NUMA_NO_NODE) break; node_clear(source, tmp); err = migrate_to_node(mm, source, dest, flags); if (err > 0) nr_failed += err; if (err < 0) break; } lru_cache_enable(); if (err < 0) return err; return (nr_failed < INT_MAX) ? nr_failed : INT_MAX; } /* * Allocate a new folio for page migration, according to NUMA mempolicy. */ static struct folio *alloc_migration_target_by_mpol(struct folio *src, unsigned long private) { struct migration_mpol *mmpol = (struct migration_mpol *)private; struct mempolicy *pol = mmpol->pol; pgoff_t ilx = mmpol->ilx; unsigned int order; int nid = numa_node_id(); gfp_t gfp; order = folio_order(src); ilx += src->index >> order; if (folio_test_hugetlb(src)) { nodemask_t *nodemask; struct hstate *h; h = folio_hstate(src); gfp = htlb_alloc_mask(h); nodemask = policy_nodemask(gfp, pol, ilx, &nid); return alloc_hugetlb_folio_nodemask(h, nid, nodemask, gfp, htlb_allow_alloc_fallback(MR_MEMPOLICY_MBIND)); } if (folio_test_large(src)) gfp = GFP_TRANSHUGE; else gfp = GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL | __GFP_COMP; return folio_alloc_mpol(gfp, order, pol, ilx, nid); } #else static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags) { return false; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { return -ENOSYS; } static struct folio *alloc_migration_target_by_mpol(struct folio *src, unsigned long private) { return NULL; } #endif static long do_mbind(unsigned long start, unsigned long len, unsigned short mode, unsigned short mode_flags, nodemask_t *nmask, unsigned long flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct vma_iterator vmi; struct migration_mpol mmpol; struct mempolicy *new; unsigned long end; long err; long nr_failed; LIST_HEAD(pagelist); if (flags & ~(unsigned long)MPOL_MF_VALID) return -EINVAL; if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE)) return -EPERM; if (start & ~PAGE_MASK) return -EINVAL; if (mode == MPOL_DEFAULT) flags &= ~MPOL_MF_STRICT; len = PAGE_ALIGN(len); end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; new = mpol_new(mode, mode_flags, nmask); if (IS_ERR(new)) return PTR_ERR(new); /* * If we are using the default policy then operation * on discontinuous address spaces is okay after all */ if (!new) flags |= MPOL_MF_DISCONTIG_OK; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) lru_cache_disable(); { NODEMASK_SCRATCH(scratch); if (scratch) { mmap_write_lock(mm); err = mpol_set_nodemask(new, nmask, scratch); if (err) mmap_write_unlock(mm); } else err = -ENOMEM; NODEMASK_SCRATCH_FREE(scratch); } if (err) goto mpol_out; /* * Lock the VMAs before scanning for pages to migrate, * to ensure we don't miss a concurrently inserted page. */ nr_failed = queue_pages_range(mm, start, end, nmask, flags | MPOL_MF_INVERT | MPOL_MF_WRLOCK, &pagelist); if (nr_failed < 0) { err = nr_failed; nr_failed = 0; } else { vma_iter_init(&vmi, mm, start); prev = vma_prev(&vmi); for_each_vma_range(vmi, vma, end) { err = mbind_range(&vmi, vma, &prev, start, end, new); if (err) break; } } if (!err && !list_empty(&pagelist)) { /* Convert MPOL_DEFAULT's NULL to task or default policy */ if (!new) { new = get_task_policy(current); mpol_get(new); } mmpol.pol = new; mmpol.ilx = 0; /* * In the interleaved case, attempt to allocate on exactly the * targeted nodes, for the first VMA to be migrated; for later * VMAs, the nodes will still be interleaved from the targeted * nodemask, but one by one may be selected differently. */ if (new->mode == MPOL_INTERLEAVE || new->mode == MPOL_WEIGHTED_INTERLEAVE) { struct folio *folio; unsigned int order; unsigned long addr = -EFAULT; list_for_each_entry(folio, &pagelist, lru) { if (!folio_test_ksm(folio)) break; } if (!list_entry_is_head(folio, &pagelist, lru)) { vma_iter_init(&vmi, mm, start); for_each_vma_range(vmi, vma, end) { addr = page_address_in_vma(folio, folio_page(folio, 0), vma); if (addr != -EFAULT) break; } } if (addr != -EFAULT) { order = folio_order(folio); /* We already know the pol, but not the ilx */ mpol_cond_put(get_vma_policy(vma, addr, order, &mmpol.ilx)); /* Set base from which to increment by index */ mmpol.ilx -= folio->index >> order; } } } mmap_write_unlock(mm); if (!err && !list_empty(&pagelist)) { nr_failed |= migrate_pages(&pagelist, alloc_migration_target_by_mpol, NULL, (unsigned long)&mmpol, MIGRATE_SYNC, MR_MEMPOLICY_MBIND, NULL); } if (nr_failed && (flags & MPOL_MF_STRICT)) err = -EIO; if (!list_empty(&pagelist)) putback_movable_pages(&pagelist); mpol_out: mpol_put(new); if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) lru_cache_enable(); return err; } /* * User space interface with variable sized bitmaps for nodelists. */ static int get_bitmap(unsigned long *mask, const unsigned long __user *nmask, unsigned long maxnode) { unsigned long nlongs = BITS_TO_LONGS(maxnode); int ret; if (in_compat_syscall()) ret = compat_get_bitmap(mask, (const compat_ulong_t __user *)nmask, maxnode); else ret = copy_from_user(mask, nmask, nlongs * sizeof(unsigned long)); if (ret) return -EFAULT; if (maxnode % BITS_PER_LONG) mask[nlongs - 1] &= (1UL << (maxnode % BITS_PER_LONG)) - 1; return 0; } /* Copy a node mask from user space. */ static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask, unsigned long maxnode) { --maxnode; nodes_clear(*nodes); if (maxnode == 0 || !nmask) return 0; if (maxnode > PAGE_SIZE*BITS_PER_BYTE) return -EINVAL; /* * When the user specified more nodes than supported just check * if the non supported part is all zero, one word at a time, * starting at the end. */ while (maxnode > MAX_NUMNODES) { unsigned long bits = min_t(unsigned long, maxnode, BITS_PER_LONG); unsigned long t; if (get_bitmap(&t, &nmask[(maxnode - 1) / BITS_PER_LONG], bits)) return -EFAULT; if (maxnode - bits >= MAX_NUMNODES) { maxnode -= bits; } else { maxnode = MAX_NUMNODES; t &= ~((1UL << (MAX_NUMNODES % BITS_PER_LONG)) - 1); } if (t) return -EINVAL; } return get_bitmap(nodes_addr(*nodes), nmask, maxnode); } /* Copy a kernel node mask to user space */ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, nodemask_t *nodes) { unsigned long copy = ALIGN(maxnode-1, 64) / 8; unsigned int nbytes = BITS_TO_LONGS(nr_node_ids) * sizeof(long); bool compat = in_compat_syscall(); if (compat) nbytes = BITS_TO_COMPAT_LONGS(nr_node_ids) * sizeof(compat_long_t); if (copy > nbytes) { if (copy > PAGE_SIZE) return -EINVAL; if (clear_user((char __user *)mask + nbytes, copy - nbytes)) return -EFAULT; copy = nbytes; maxnode = nr_node_ids; } if (compat) return compat_put_bitmap((compat_ulong_t __user *)mask, nodes_addr(*nodes), maxnode); return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0; } /* Basic parameter sanity check used by both mbind() and set_mempolicy() */ static inline int sanitize_mpol_flags(int *mode, unsigned short *flags) { *flags = *mode & MPOL_MODE_FLAGS; *mode &= ~MPOL_MODE_FLAGS; if ((unsigned int)(*mode) >= MPOL_MAX) return -EINVAL; if ((*flags & MPOL_F_STATIC_NODES) && (*flags & MPOL_F_RELATIVE_NODES)) return -EINVAL; if (*flags & MPOL_F_NUMA_BALANCING) { if (*mode == MPOL_BIND || *mode == MPOL_PREFERRED_MANY) *flags |= (MPOL_F_MOF | MPOL_F_MORON); else return -EINVAL; } return 0; } static long kernel_mbind(unsigned long start, unsigned long len, unsigned long mode, const unsigned long __user *nmask, unsigned long maxnode, unsigned int flags) { unsigned short mode_flags; nodemask_t nodes; int lmode = mode; int err; start = untagged_addr(start); err = sanitize_mpol_flags(&lmode, &mode_flags); if (err) return err; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; return do_mbind(start, len, lmode, mode_flags, &nodes, flags); } SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, len, unsigned long, home_node, unsigned long, flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct mempolicy *new, *old; unsigned long end; int err = -ENOENT; VMA_ITERATOR(vmi, mm, start); start = untagged_addr(start); if (start & ~PAGE_MASK) return -EINVAL; /* * flags is used for future extension if any. */ if (flags != 0) return -EINVAL; /* * Check home_node is online to avoid accessing uninitialized * NODE_DATA. */ if (home_node >= MAX_NUMNODES || !node_online(home_node)) return -EINVAL; len = PAGE_ALIGN(len); end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; mmap_write_lock(mm); prev = vma_prev(&vmi); for_each_vma_range(vmi, vma, end) { /* * If any vma in the range got policy other than MPOL_BIND * or MPOL_PREFERRED_MANY we return error. We don't reset * the home node for vmas we already updated before. */ old = vma_policy(vma); if (!old) { prev = vma; continue; } if (old->mode != MPOL_BIND && old->mode != MPOL_PREFERRED_MANY) { err = -EOPNOTSUPP; break; } new = mpol_dup(old); if (IS_ERR(new)) { err = PTR_ERR(new); break; } vma_start_write(vma); new->home_node = home_node; err = mbind_range(&vmi, vma, &prev, start, end, new); mpol_put(new); if (err) break; } mmap_write_unlock(mm); return err; } SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, unsigned long, mode, const unsigned long __user *, nmask, unsigned long, maxnode, unsigned int, flags) { return kernel_mbind(start, len, mode, nmask, maxnode, flags); } /* Set the process memory policy */ static long kernel_set_mempolicy(int mode, const unsigned long __user *nmask, unsigned long maxnode) { unsigned short mode_flags; nodemask_t nodes; int lmode = mode; int err; err = sanitize_mpol_flags(&lmode, &mode_flags); if (err) return err; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; return do_set_mempolicy(lmode, mode_flags, &nodes); } SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask, unsigned long, maxnode) { return kernel_set_mempolicy(mode, nmask, maxnode); } static int kernel_migrate_pages(pid_t pid, unsigned long maxnode, const unsigned long __user *old_nodes, const unsigned long __user *new_nodes) { struct mm_struct *mm = NULL; struct task_struct *task; nodemask_t task_nodes; int err; nodemask_t *old; nodemask_t *new; NODEMASK_SCRATCH(scratch); if (!scratch) return -ENOMEM; old = &scratch->mask1; new = &scratch->mask2; err = get_nodes(old, old_nodes, maxnode); if (err) goto out; err = get_nodes(new, new_nodes, maxnode); if (err) goto out; /* Find the mm_struct */ rcu_read_lock(); task = pid ? find_task_by_vpid(pid) : current; if (!task) { rcu_read_unlock(); err = -ESRCH; goto out; } get_task_struct(task); err = -EINVAL; /* * Check if this process has the right to modify the specified process. * Use the regular "ptrace_may_access()" checks. */ if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) { rcu_read_unlock(); err = -EPERM; goto out_put; } rcu_read_unlock(); task_nodes = cpuset_mems_allowed(task); /* Is the user allowed to access the target nodes? */ if (!nodes_subset(*new, task_nodes) && !capable(CAP_SYS_NICE)) { err = -EPERM; goto out_put; } task_nodes = cpuset_mems_allowed(current); nodes_and(*new, *new, task_nodes); if (nodes_empty(*new)) goto out_put; err = security_task_movememory(task); if (err) goto out_put; mm = get_task_mm(task); put_task_struct(task); if (!mm) { err = -EINVAL; goto out; } err = do_migrate_pages(mm, old, new, capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE); mmput(mm); out: NODEMASK_SCRATCH_FREE(scratch); return err; out_put: put_task_struct(task); goto out; } SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, const unsigned long __user *, old_nodes, const unsigned long __user *, new_nodes) { return kernel_migrate_pages(pid, maxnode, old_nodes, new_nodes); } /* Retrieve NUMA policy */ static int kernel_get_mempolicy(int __user *policy, unsigned long __user *nmask, unsigned long maxnode, unsigned long addr, unsigned long flags) { int err; int pval; nodemask_t nodes; if (nmask != NULL && maxnode < nr_node_ids) return -EINVAL; addr = untagged_addr(addr); err = do_get_mempolicy(&pval, &nodes, addr, flags); if (err) return err; if (policy && put_user(pval, policy)) return -EFAULT; if (nmask) err = copy_nodes_to_user(nmask, maxnode, &nodes); return err; } SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, unsigned long __user *, nmask, unsigned long, maxnode, unsigned long, addr, unsigned long, flags) { return kernel_get_mempolicy(policy, nmask, maxnode, addr, flags); } bool vma_migratable(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_IO | VM_PFNMAP)) return false; /* * DAX device mappings require predictable access latency, so avoid * incurring periodic faults. */ if (vma_is_dax(vma)) return false; if (is_vm_hugetlb_page(vma) && !hugepage_migration_supported(hstate_vma(vma))) return false; /* * Migration allocates pages in the highest zone. If we cannot * do so then migration (at least from node to node) is not * possible. */ if (vma->vm_file && gfp_zone(mapping_gfp_mask(vma->vm_file->f_mapping)) < policy_zone) return false; return true; } struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx) { *ilx = 0; return (vma->vm_ops && vma->vm_ops->get_policy) ? vma->vm_ops->get_policy(vma, addr, ilx) : vma->vm_policy; } /* * get_vma_policy(@vma, @addr, @order, @ilx) * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup * @order: 0, or appropriate huge_page_order for interleaving * @ilx: interleave index (output), for use only when MPOL_INTERLEAVE or * MPOL_WEIGHTED_INTERLEAVE * * Returns effective policy for a VMA at specified address. * Falls back to current->mempolicy or system default policy, as necessary. * Shared policies [those marked as MPOL_F_SHARED] require an extra reference * count--added by the get_policy() vm_op, as appropriate--to protect against * freeing by another task. It is the caller's responsibility to free the * extra reference for shared policies. */ struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr, int order, pgoff_t *ilx) { struct mempolicy *pol; pol = __get_vma_policy(vma, addr, ilx); if (!pol) pol = get_task_policy(current); if (pol->mode == MPOL_INTERLEAVE || pol->mode == MPOL_WEIGHTED_INTERLEAVE) { *ilx += vma->vm_pgoff >> order; *ilx += (addr - vma->vm_start) >> (PAGE_SHIFT + order); } return pol; } bool vma_policy_mof(struct vm_area_struct *vma) { struct mempolicy *pol; if (vma->vm_ops && vma->vm_ops->get_policy) { bool ret = false; pgoff_t ilx; /* ignored here */ pol = vma->vm_ops->get_policy(vma, vma->vm_start, &ilx); if (pol && (pol->flags & MPOL_F_MOF)) ret = true; mpol_cond_put(pol); return ret; } pol = vma->vm_policy; if (!pol) pol = get_task_policy(current); return pol->flags & MPOL_F_MOF; } bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone) { enum zone_type dynamic_policy_zone = policy_zone; BUG_ON(dynamic_policy_zone == ZONE_MOVABLE); /* * if policy->nodes has movable memory only, * we apply policy when gfp_zone(gfp) = ZONE_MOVABLE only. * * policy->nodes is intersect with node_states[N_MEMORY]. * so if the following test fails, it implies * policy->nodes has movable memory only. */ if (!nodes_intersects(policy->nodes, node_states[N_HIGH_MEMORY])) dynamic_policy_zone = ZONE_MOVABLE; return zone >= dynamic_policy_zone; } static unsigned int weighted_interleave_nodes(struct mempolicy *policy) { unsigned int node; unsigned int cpuset_mems_cookie; retry: /* to prevent miscount use tsk->mems_allowed_seq to detect rebind */ cpuset_mems_cookie = read_mems_allowed_begin(); node = current->il_prev; if (!current->il_weight || !node_isset(node, policy->nodes)) { node = next_node_in(node, policy->nodes); if (read_mems_allowed_retry(cpuset_mems_cookie)) goto retry; if (node == MAX_NUMNODES) return node; current->il_prev = node; current->il_weight = get_il_weight(node); } current->il_weight--; return node; } /* Do dynamic interleaving for a process */ static unsigned int interleave_nodes(struct mempolicy *policy) { unsigned int nid; unsigned int cpuset_mems_cookie; /* to prevent miscount, use tsk->mems_allowed_seq to detect rebind */ do { cpuset_mems_cookie = read_mems_allowed_begin(); nid = next_node_in(current->il_prev, policy->nodes); } while (read_mems_allowed_retry(cpuset_mems_cookie)); if (nid < MAX_NUMNODES) current->il_prev = nid; return nid; } /* * Depending on the memory policy provide a node from which to allocate the * next slab entry. */ unsigned int mempolicy_slab_node(void) { struct mempolicy *policy; int node = numa_mem_id(); if (!in_task()) return node; policy = current->mempolicy; if (!policy) return node; switch (policy->mode) { case MPOL_PREFERRED: return first_node(policy->nodes); case MPOL_INTERLEAVE: return interleave_nodes(policy); case MPOL_WEIGHTED_INTERLEAVE: return weighted_interleave_nodes(policy); case MPOL_BIND: case MPOL_PREFERRED_MANY: { struct zoneref *z; /* * Follow bind policy behavior and start allocation at the * first node. */ struct zonelist *zonelist; enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL); zonelist = &NODE_DATA(node)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, highest_zoneidx, &policy->nodes); return zonelist_zone(z) ? zonelist_node_idx(z) : node; } case MPOL_LOCAL: return node; default: BUG(); } } static unsigned int read_once_policy_nodemask(struct mempolicy *pol, nodemask_t *mask) { /* * barrier stabilizes the nodemask locally so that it can be iterated * over safely without concern for changes. Allocators validate node * selection does not violate mems_allowed, so this is safe. */ barrier(); memcpy(mask, &pol->nodes, sizeof(nodemask_t)); barrier(); return nodes_weight(*mask); } static unsigned int weighted_interleave_nid(struct mempolicy *pol, pgoff_t ilx) { nodemask_t nodemask; unsigned int target, nr_nodes; u8 *table; unsigned int weight_total = 0; u8 weight; int nid; nr_nodes = read_once_policy_nodemask(pol, &nodemask); if (!nr_nodes) return numa_node_id(); rcu_read_lock(); table = rcu_dereference(iw_table); /* calculate the total weight */ for_each_node_mask(nid, nodemask) { /* detect system default usage */ weight = table ? table[nid] : 1; weight = weight ? weight : 1; weight_total += weight; } /* Calculate the node offset based on totals */ target = ilx % weight_total; nid = first_node(nodemask); while (target) { /* detect system default usage */ weight = table ? table[nid] : 1; weight = weight ? weight : 1; if (target < weight) break; target -= weight; nid = next_node_in(nid, nodemask); } rcu_read_unlock(); return nid; } /* * Do static interleaving for interleave index @ilx. Returns the ilx'th * node in pol->nodes (starting from ilx=0), wrapping around if ilx * exceeds the number of present nodes. */ static unsigned int interleave_nid(struct mempolicy *pol, pgoff_t ilx) { nodemask_t nodemask; unsigned int target, nnodes; int i; int nid; nnodes = read_once_policy_nodemask(pol, &nodemask); if (!nnodes) return numa_node_id(); target = ilx % nnodes; nid = first_node(nodemask); for (i = 0; i < target; i++) nid = next_node(nid, nodemask); return nid; } /* * Return a nodemask representing a mempolicy for filtering nodes for * page allocation, together with preferred node id (or the input node id). */ static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *pol, pgoff_t ilx, int *nid) { nodemask_t *nodemask = NULL; switch (pol->mode) { case MPOL_PREFERRED: /* Override input node id */ *nid = first_node(pol->nodes); break; case MPOL_PREFERRED_MANY: nodemask = &pol->nodes; if (pol->home_node != NUMA_NO_NODE) *nid = pol->home_node; break; case MPOL_BIND: /* Restrict to nodemask (but not on lower zones) */ if (apply_policy_zone(pol, gfp_zone(gfp)) && cpuset_nodemask_valid_mems_allowed(&pol->nodes)) nodemask = &pol->nodes; if (pol->home_node != NUMA_NO_NODE) *nid = pol->home_node; /* * __GFP_THISNODE shouldn't even be used with the bind policy * because we might easily break the expectation to stay on the * requested node and not break the policy. */ WARN_ON_ONCE(gfp & __GFP_THISNODE); break; case MPOL_INTERLEAVE: /* Override input node id */ *nid = (ilx == NO_INTERLEAVE_INDEX) ? interleave_nodes(pol) : interleave_nid(pol, ilx); break; case MPOL_WEIGHTED_INTERLEAVE: *nid = (ilx == NO_INTERLEAVE_INDEX) ? weighted_interleave_nodes(pol) : weighted_interleave_nid(pol, ilx); break; } return nodemask; } #ifdef CONFIG_HUGETLBFS /* * huge_node(@vma, @addr, @gfp_flags, @mpol) * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup and interleave policy * @gfp_flags: for requested zone * @mpol: pointer to mempolicy pointer for reference counted mempolicy * @nodemask: pointer to nodemask pointer for 'bind' and 'prefer-many' policy * * Returns a nid suitable for a huge page allocation and a pointer * to the struct mempolicy for conditional unref after allocation. * If the effective policy is 'bind' or 'prefer-many', returns a pointer * to the mempolicy's @nodemask for filtering the zonelist. */ int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask) { pgoff_t ilx; int nid; nid = numa_node_id(); *mpol = get_vma_policy(vma, addr, hstate_vma(vma)->order, &ilx); *nodemask = policy_nodemask(gfp_flags, *mpol, ilx, &nid); return nid; } /* * init_nodemask_of_mempolicy * * If the current task's mempolicy is "default" [NULL], return 'false' * to indicate default policy. Otherwise, extract the policy nodemask * for 'bind' or 'interleave' policy into the argument nodemask, or * initialize the argument nodemask to contain the single node for * 'preferred' or 'local' policy and return 'true' to indicate presence * of non-default mempolicy. * * We don't bother with reference counting the mempolicy [mpol_get/put] * because the current task is examining it's own mempolicy and a task's * mempolicy is only ever changed by the task itself. * * N.B., it is the caller's responsibility to free a returned nodemask. */ bool init_nodemask_of_mempolicy(nodemask_t *mask) { struct mempolicy *mempolicy; if (!(mask && current->mempolicy)) return false; task_lock(current); mempolicy = current->mempolicy; switch (mempolicy->mode) { case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: *mask = mempolicy->nodes; break; case MPOL_LOCAL: init_nodemask_of_node(mask, numa_node_id()); break; default: BUG(); } task_unlock(current); return true; } #endif /* * mempolicy_in_oom_domain * * If tsk's mempolicy is "bind", check for intersection between mask and * the policy nodemask. Otherwise, return true for all other policies * including "interleave", as a tsk with "interleave" policy may have * memory allocated from all nodes in system. * * Takes task_lock(tsk) to prevent freeing of its mempolicy. */ bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask) { struct mempolicy *mempolicy; bool ret = true; if (!mask) return ret; task_lock(tsk); mempolicy = tsk->mempolicy; if (mempolicy && mempolicy->mode == MPOL_BIND) ret = nodes_intersects(mempolicy->nodes, *mask); task_unlock(tsk); return ret; } static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order, int nid, nodemask_t *nodemask) { struct page *page; gfp_t preferred_gfp; /* * This is a two pass approach. The first pass will only try the * preferred nodes but skip the direct reclaim and allow the * allocation to fail, while the second pass will try all the * nodes in system. */ preferred_gfp = gfp | __GFP_NOWARN; preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); page = __alloc_pages_noprof(preferred_gfp, order, nid, nodemask); if (!page) page = __alloc_pages_noprof(gfp, order, nid, NULL); return page; } /** * alloc_pages_mpol - Allocate pages according to NUMA mempolicy. * @gfp: GFP flags. * @order: Order of the page allocation. * @pol: Pointer to the NUMA mempolicy. * @ilx: Index for interleave mempolicy (also distinguishes alloc_pages()). * @nid: Preferred node (usually numa_node_id() but @mpol may override it). * * Return: The page on success or NULL if allocation fails. */ struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *pol, pgoff_t ilx, int nid) { nodemask_t *nodemask; struct page *page; nodemask = policy_nodemask(gfp, pol, ilx, &nid); if (pol->mode == MPOL_PREFERRED_MANY) return alloc_pages_preferred_many(gfp, order, nid, nodemask); if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && /* filter "hugepage" allocation, unless from alloc_pages() */ order == HPAGE_PMD_ORDER && ilx != NO_INTERLEAVE_INDEX) { /* * For hugepage allocation and non-interleave policy which * allows the current node (or other explicitly preferred * node) we only try to allocate from the current/preferred * node and don't fall back to other nodes, as the cost of * remote accesses would likely offset THP benefits. * * If the policy is interleave or does not allow the current * node in its nodemask, we allocate the standard way. */ if (pol->mode != MPOL_INTERLEAVE && pol->mode != MPOL_WEIGHTED_INTERLEAVE && (!nodemask || node_isset(nid, *nodemask))) { /* * First, try to allocate THP only on local node, but * don't reclaim unnecessarily, just compact. */ page = __alloc_pages_node_noprof(nid, gfp | __GFP_THISNODE | __GFP_NORETRY, order); if (page || !(gfp & __GFP_DIRECT_RECLAIM)) return page; /* * If hugepage allocations are configured to always * synchronous compact or the vma has been madvised * to prefer hugepage backing, retry allowing remote * memory with both reclaim and compact as well. */ } } page = __alloc_pages_noprof(gfp, order, nid, nodemask); if (unlikely(pol->mode == MPOL_INTERLEAVE) && page) { /* skip NUMA_INTERLEAVE_HIT update if numa stats is disabled */ if (static_branch_likely(&vm_numa_stat_key) && page_to_nid(page) == nid) { preempt_disable(); __count_numa_event(page_zone(page), NUMA_INTERLEAVE_HIT); preempt_enable(); } } return page; } struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *pol, pgoff_t ilx, int nid) { return page_rmappable_folio(alloc_pages_mpol_noprof(gfp | __GFP_COMP, order, pol, ilx, nid)); } /** * vma_alloc_folio - Allocate a folio for a VMA. * @gfp: GFP flags. * @order: Order of the folio. * @vma: Pointer to VMA. * @addr: Virtual address of the allocation. Must be inside @vma. * * Allocate a folio for a specific address in @vma, using the appropriate * NUMA policy. The caller must hold the mmap_lock of the mm_struct of the * VMA to prevent it from going away. Should be used for all allocations * for folios that will be mapped into user space, excepting hugetlbfs, and * excepting where direct use of alloc_pages_mpol() is more appropriate. * * Return: The folio on success or NULL if allocation fails. */ struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol; pgoff_t ilx; struct folio *folio; if (vma->vm_flags & VM_DROPPABLE) gfp |= __GFP_NOWARN; pol = get_vma_policy(vma, addr, order, &ilx); folio = folio_alloc_mpol_noprof(gfp, order, pol, ilx, numa_node_id()); mpol_cond_put(pol); return folio; } EXPORT_SYMBOL(vma_alloc_folio_noprof); /** * alloc_pages - Allocate pages. * @gfp: GFP flags. * @order: Power of two of number of pages to allocate. * * Allocate 1 << @order contiguous pages. The physical address of the * first page is naturally aligned (eg an order-3 allocation will be aligned * to a multiple of 8 * PAGE_SIZE bytes). The NUMA policy of the current * process is honoured when in process context. * * Context: Can be called from any context, providing the appropriate GFP * flags are used. * Return: The page on success or NULL if allocation fails. */ struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order) { struct mempolicy *pol = &default_policy; /* * No reference counting needed for current->mempolicy * nor system default_policy */ if (!in_interrupt() && !(gfp & __GFP_THISNODE)) pol = get_task_policy(current); return alloc_pages_mpol_noprof(gfp, order, pol, NO_INTERLEAVE_INDEX, numa_node_id()); } EXPORT_SYMBOL(alloc_pages_noprof); struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) { return page_rmappable_folio(alloc_pages_noprof(gfp | __GFP_COMP, order)); } EXPORT_SYMBOL(folio_alloc_noprof); static unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { int nodes; unsigned long nr_pages_per_node; int delta; int i; unsigned long nr_allocated; unsigned long total_allocated = 0; nodes = nodes_weight(pol->nodes); nr_pages_per_node = nr_pages / nodes; delta = nr_pages - nodes * nr_pages_per_node; for (i = 0; i < nodes; i++) { if (delta) { nr_allocated = alloc_pages_bulk_noprof(gfp, interleave_nodes(pol), NULL, nr_pages_per_node + 1, NULL, page_array); delta--; } else { nr_allocated = alloc_pages_bulk_noprof(gfp, interleave_nodes(pol), NULL, nr_pages_per_node, NULL, page_array); } page_array += nr_allocated; total_allocated += nr_allocated; } return total_allocated; } static unsigned long alloc_pages_bulk_array_weighted_interleave(gfp_t gfp, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { struct task_struct *me = current; unsigned int cpuset_mems_cookie; unsigned long total_allocated = 0; unsigned long nr_allocated = 0; unsigned long rounds; unsigned long node_pages, delta; u8 *table, *weights, weight; unsigned int weight_total = 0; unsigned long rem_pages = nr_pages; nodemask_t nodes; int nnodes, node; int resume_node = MAX_NUMNODES - 1; u8 resume_weight = 0; int prev_node; int i; if (!nr_pages) return 0; /* read the nodes onto the stack, retry if done during rebind */ do { cpuset_mems_cookie = read_mems_allowed_begin(); nnodes = read_once_policy_nodemask(pol, &nodes); } while (read_mems_allowed_retry(cpuset_mems_cookie)); /* if the nodemask has become invalid, we cannot do anything */ if (!nnodes) return 0; /* Continue allocating from most recent node and adjust the nr_pages */ node = me->il_prev; weight = me->il_weight; if (weight && node_isset(node, nodes)) { node_pages = min(rem_pages, weight); nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages, NULL, page_array); page_array += nr_allocated; total_allocated += nr_allocated; /* if that's all the pages, no need to interleave */ if (rem_pages <= weight) { me->il_weight -= rem_pages; return total_allocated; } /* Otherwise we adjust remaining pages, continue from there */ rem_pages -= weight; } /* clear active weight in case of an allocation failure */ me->il_weight = 0; prev_node = node; /* create a local copy of node weights to operate on outside rcu */ weights = kzalloc(nr_node_ids, GFP_KERNEL); if (!weights) return total_allocated; rcu_read_lock(); table = rcu_dereference(iw_table); if (table) memcpy(weights, table, nr_node_ids); rcu_read_unlock(); /* calculate total, detect system default usage */ for_each_node_mask(node, nodes) { if (!weights[node]) weights[node] = 1; weight_total += weights[node]; } /* * Calculate rounds/partial rounds to minimize __alloc_pages_bulk calls. * Track which node weighted interleave should resume from. * * if (rounds > 0) and (delta == 0), resume_node will always be * the node following prev_node and its weight. */ rounds = rem_pages / weight_total; delta = rem_pages % weight_total; resume_node = next_node_in(prev_node, nodes); resume_weight = weights[resume_node]; for (i = 0; i < nnodes; i++) { node = next_node_in(prev_node, nodes); weight = weights[node]; node_pages = weight * rounds; /* If a delta exists, add this node's portion of the delta */ if (delta > weight) { node_pages += weight; delta -= weight; } else if (delta) { /* when delta is depleted, resume from that node */ node_pages += delta; resume_node = node; resume_weight = weight - delta; delta = 0; } /* node_pages can be 0 if an allocation fails and rounds == 0 */ if (!node_pages) break; nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages, NULL, page_array); page_array += nr_allocated; total_allocated += nr_allocated; if (total_allocated == nr_pages) break; prev_node = node; } me->il_prev = resume_node; me->il_weight = resume_weight; kfree(weights); return total_allocated; } static unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { gfp_t preferred_gfp; unsigned long nr_allocated = 0; preferred_gfp = gfp | __GFP_NOWARN; preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); nr_allocated = alloc_pages_bulk_noprof(preferred_gfp, nid, &pol->nodes, nr_pages, NULL, page_array); if (nr_allocated < nr_pages) nr_allocated += alloc_pages_bulk_noprof(gfp, numa_node_id(), NULL, nr_pages - nr_allocated, NULL, page_array + nr_allocated); return nr_allocated; } /* alloc pages bulk and mempolicy should be considered at the * same time in some situation such as vmalloc. * * It can accelerate memory allocation especially interleaving * allocate memory. */ unsigned long alloc_pages_bulk_array_mempolicy_noprof(gfp_t gfp, unsigned long nr_pages, struct page **page_array) { struct mempolicy *pol = &default_policy; nodemask_t *nodemask; int nid; if (!in_interrupt() && !(gfp & __GFP_THISNODE)) pol = get_task_policy(current); if (pol->mode == MPOL_INTERLEAVE) return alloc_pages_bulk_array_interleave(gfp, pol, nr_pages, page_array); if (pol->mode == MPOL_WEIGHTED_INTERLEAVE) return alloc_pages_bulk_array_weighted_interleave( gfp, pol, nr_pages, page_array); if (pol->mode == MPOL_PREFERRED_MANY) return alloc_pages_bulk_array_preferred_many(gfp, numa_node_id(), pol, nr_pages, page_array); nid = numa_node_id(); nodemask = policy_nodemask(gfp, pol, NO_INTERLEAVE_INDEX, &nid); return alloc_pages_bulk_noprof(gfp, nid, nodemask, nr_pages, NULL, page_array); } int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { struct mempolicy *pol = mpol_dup(src->vm_policy); if (IS_ERR(pol)) return PTR_ERR(pol); dst->vm_policy = pol; return 0; } /* * If mpol_dup() sees current->cpuset == cpuset_being_rebound, then it * rebinds the mempolicy its copying by calling mpol_rebind_policy() * with the mems_allowed returned by cpuset_mems_allowed(). This * keeps mempolicies cpuset relative after its cpuset moves. See * further kernel/cpuset.c update_nodemask(). * * current's mempolicy may be rebinded by the other task(the task that changes * cpuset's mems), so we needn't do rebind work for current task. */ /* Slow path of a mempolicy duplicate */ struct mempolicy *__mpol_dup(struct mempolicy *old) { struct mempolicy *new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!new) return ERR_PTR(-ENOMEM); /* task's mempolicy is protected by alloc_lock */ if (old == current->mempolicy) { task_lock(current); *new = *old; task_unlock(current); } else *new = *old; if (current_cpuset_is_being_rebound()) { nodemask_t mems = cpuset_mems_allowed(current); mpol_rebind_policy(new, &mems); } atomic_set(&new->refcnt, 1); return new; } /* Slow path of a mempolicy comparison */ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) { if (!a || !b) return false; if (a->mode != b->mode) return false; if (a->flags != b->flags) return false; if (a->home_node != b->home_node) return false; if (mpol_store_user_nodemask(a)) if (!nodes_equal(a->w.user_nodemask, b->w.user_nodemask)) return false; switch (a->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_WEIGHTED_INTERLEAVE: return !!nodes_equal(a->nodes, b->nodes); case MPOL_LOCAL: return true; default: BUG(); return false; } } /* * Shared memory backing store policy support. * * Remember policies even when nobody has shared memory mapped. * The policies are kept in Red-Black tree linked from the inode. * They are protected by the sp->lock rwlock, which should be held * for any accesses to the tree. */ /* * lookup first element intersecting start-end. Caller holds sp->lock for * reading or for writing */ static struct sp_node *sp_lookup(struct shared_policy *sp, pgoff_t start, pgoff_t end) { struct rb_node *n = sp->root.rb_node; while (n) { struct sp_node *p = rb_entry(n, struct sp_node, nd); if (start >= p->end) n = n->rb_right; else if (end <= p->start) n = n->rb_left; else break; } if (!n) return NULL; for (;;) { struct sp_node *w = NULL; struct rb_node *prev = rb_prev(n); if (!prev) break; w = rb_entry(prev, struct sp_node, nd); if (w->end <= start) break; n = prev; } return rb_entry(n, struct sp_node, nd); } /* * Insert a new shared policy into the list. Caller holds sp->lock for * writing. */ static void sp_insert(struct shared_policy *sp, struct sp_node *new) { struct rb_node **p = &sp->root.rb_node; struct rb_node *parent = NULL; struct sp_node *nd; while (*p) { parent = *p; nd = rb_entry(parent, struct sp_node, nd); if (new->start < nd->start) p = &(*p)->rb_left; else if (new->end > nd->end) p = &(*p)->rb_right; else BUG(); } rb_link_node(&new->nd, parent, p); rb_insert_color(&new->nd, &sp->root); } /* Find shared policy intersecting idx */ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx) { struct mempolicy *pol = NULL; struct sp_node *sn; if (!sp->root.rb_node) return NULL; read_lock(&sp->lock); sn = sp_lookup(sp, idx, idx+1); if (sn) { mpol_get(sn->policy); pol = sn->policy; } read_unlock(&sp->lock); return pol; } static void sp_free(struct sp_node *n) { mpol_put(n->policy); kmem_cache_free(sn_cache, n); } /** * mpol_misplaced - check whether current folio node is valid in policy * * @folio: folio to be checked * @vmf: structure describing the fault * @addr: virtual address in @vma for shared policy lookup and interleave policy * * Lookup current policy node id for vma,addr and "compare to" folio's * node id. Policy determination "mimics" alloc_page_vma(). * Called from fault path where we know the vma and faulting address. * * Return: NUMA_NO_NODE if the page is in a node that is valid for this * policy, or a suitable node ID to allocate a replacement folio from. */ int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, unsigned long addr) { struct mempolicy *pol; pgoff_t ilx; struct zoneref *z; int curnid = folio_nid(folio); struct vm_area_struct *vma = vmf->vma; int thiscpu = raw_smp_processor_id(); int thisnid = numa_node_id(); int polnid = NUMA_NO_NODE; int ret = NUMA_NO_NODE; /* * Make sure ptl is held so that we don't preempt and we * have a stable smp processor id */ lockdep_assert_held(vmf->ptl); pol = get_vma_policy(vma, addr, folio_order(folio), &ilx); if (!(pol->flags & MPOL_F_MOF)) goto out; switch (pol->mode) { case MPOL_INTERLEAVE: polnid = interleave_nid(pol, ilx); break; case MPOL_WEIGHTED_INTERLEAVE: polnid = weighted_interleave_nid(pol, ilx); break; case MPOL_PREFERRED: if (node_isset(curnid, pol->nodes)) goto out; polnid = first_node(pol->nodes); break; case MPOL_LOCAL: polnid = numa_node_id(); break; case MPOL_BIND: case MPOL_PREFERRED_MANY: /* * Even though MPOL_PREFERRED_MANY can allocate pages outside * policy nodemask we don't allow numa migration to nodes * outside policy nodemask for now. This is done so that if we * want demotion to slow memory to happen, before allocating * from some DRAM node say 'x', we will end up using a * MPOL_PREFERRED_MANY mask excluding node 'x'. In such scenario * we should not promote to node 'x' from slow memory node. */ if (pol->flags & MPOL_F_MORON) { /* * Optimize placement among multiple nodes * via NUMA balancing */ if (node_isset(thisnid, pol->nodes)) break; goto out; } /* * use current page if in policy nodemask, * else select nearest allowed node, if any. * If no allowed nodes, use current [!misplaced]. */ if (node_isset(curnid, pol->nodes)) goto out; z = first_zones_zonelist( node_zonelist(thisnid, GFP_HIGHUSER), gfp_zone(GFP_HIGHUSER), &pol->nodes); polnid = zonelist_node_idx(z); break; default: BUG(); } /* Migrate the folio towards the node whose CPU is referencing it */ if (pol->flags & MPOL_F_MORON) { polnid = thisnid; if (!should_numa_migrate_memory(current, folio, curnid, thiscpu)) goto out; } if (curnid != polnid) ret = polnid; out: mpol_cond_put(pol); return ret; } /* * Drop the (possibly final) reference to task->mempolicy. It needs to be * dropped after task->mempolicy is set to NULL so that any allocation done as * part of its kmem_cache_free(), such as by KASAN, doesn't reference a freed * policy. */ void mpol_put_task_policy(struct task_struct *task) { struct mempolicy *pol; task_lock(task); pol = task->mempolicy; task->mempolicy = NULL; task_unlock(task); mpol_put(pol); } static void sp_delete(struct shared_policy *sp, struct sp_node *n) { rb_erase(&n->nd, &sp->root); sp_free(n); } static void sp_node_init(struct sp_node *node, unsigned long start, unsigned long end, struct mempolicy *pol) { node->start = start; node->end = end; node->policy = pol; } static struct sp_node *sp_alloc(unsigned long start, unsigned long end, struct mempolicy *pol) { struct sp_node *n; struct mempolicy *newpol; n = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n) return NULL; newpol = mpol_dup(pol); if (IS_ERR(newpol)) { kmem_cache_free(sn_cache, n); return NULL; } newpol->flags |= MPOL_F_SHARED; sp_node_init(n, start, end, newpol); return n; } /* Replace a policy range. */ static int shared_policy_replace(struct shared_policy *sp, pgoff_t start, pgoff_t end, struct sp_node *new) { struct sp_node *n; struct sp_node *n_new = NULL; struct mempolicy *mpol_new = NULL; int ret = 0; restart: write_lock(&sp->lock); n = sp_lookup(sp, start, end); /* Take care of old policies in the same range. */ while (n && n->start < end) { struct rb_node *next = rb_next(&n->nd); if (n->start >= start) { if (n->end <= end) sp_delete(sp, n); else n->start = end; } else { /* Old policy spanning whole new range. */ if (n->end > end) { if (!n_new) goto alloc_new; *mpol_new = *n->policy; atomic_set(&mpol_new->refcnt, 1); sp_node_init(n_new, end, n->end, mpol_new); n->end = start; sp_insert(sp, n_new); n_new = NULL; mpol_new = NULL; break; } else n->end = start; } if (!next) break; n = rb_entry(next, struct sp_node, nd); } if (new) sp_insert(sp, new); write_unlock(&sp->lock); ret = 0; err_out: if (mpol_new) mpol_put(mpol_new); if (n_new) kmem_cache_free(sn_cache, n_new); return ret; alloc_new: write_unlock(&sp->lock); ret = -ENOMEM; n_new = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n_new) goto err_out; mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!mpol_new) goto err_out; atomic_set(&mpol_new->refcnt, 1); goto restart; } /** * mpol_shared_policy_init - initialize shared policy for inode * @sp: pointer to inode shared policy * @mpol: struct mempolicy to install * * Install non-NULL @mpol in inode's shared policy rb-tree. * On entry, the current task has a reference on a non-NULL @mpol. * This must be released on exit. * This is called at get_inode() calls and we can use GFP_KERNEL. */ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) { int ret; sp->root = RB_ROOT; /* empty tree == default mempolicy */ rwlock_init(&sp->lock); if (mpol) { struct sp_node *sn; struct mempolicy *npol; NODEMASK_SCRATCH(scratch); if (!scratch) goto put_mpol; /* contextualize the tmpfs mount point mempolicy to this file */ npol = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask); if (IS_ERR(npol)) goto free_scratch; /* no valid nodemask intersection */ task_lock(current); ret = mpol_set_nodemask(npol, &mpol->w.user_nodemask, scratch); task_unlock(current); if (ret) goto put_npol; /* alloc node covering entire file; adds ref to file's npol */ sn = sp_alloc(0, MAX_LFS_FILESIZE >> PAGE_SHIFT, npol); if (sn) sp_insert(sp, sn); put_npol: mpol_put(npol); /* drop initial ref on file's npol */ free_scratch: NODEMASK_SCRATCH_FREE(scratch); put_mpol: mpol_put(mpol); /* drop our incoming ref on sb mpol */ } } int mpol_set_shared_policy(struct shared_policy *sp, struct vm_area_struct *vma, struct mempolicy *pol) { int err; struct sp_node *new = NULL; unsigned long sz = vma_pages(vma); if (pol) { new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, pol); if (!new) return -ENOMEM; } err = shared_policy_replace(sp, vma->vm_pgoff, vma->vm_pgoff + sz, new); if (err && new) sp_free(new); return err; } /* Free a backing policy store on inode delete. */ void mpol_free_shared_policy(struct shared_policy *sp) { struct sp_node *n; struct rb_node *next; if (!sp->root.rb_node) return; write_lock(&sp->lock); next = rb_first(&sp->root); while (next) { n = rb_entry(next, struct sp_node, nd); next = rb_next(&n->nd); sp_delete(sp, n); } write_unlock(&sp->lock); } #ifdef CONFIG_NUMA_BALANCING static int __initdata numabalancing_override; static void __init check_numabalancing_enable(void) { bool numabalancing_default = false; if (IS_ENABLED(CONFIG_NUMA_BALANCING_DEFAULT_ENABLED)) numabalancing_default = true; /* Parsed by setup_numabalancing. override == 1 enables, -1 disables */ if (numabalancing_override) set_numabalancing_state(numabalancing_override == 1); if (num_online_nodes() > 1 && !numabalancing_override) { pr_info("%s automatic NUMA balancing. Configure with numa_balancing= or the kernel.numa_balancing sysctl\n", numabalancing_default ? "Enabling" : "Disabling"); set_numabalancing_state(numabalancing_default); } } static int __init setup_numabalancing(char *str) { int ret = 0; if (!str) goto out; if (!strcmp(str, "enable")) { numabalancing_override = 1; ret = 1; } else if (!strcmp(str, "disable")) { numabalancing_override = -1; ret = 1; } out: if (!ret) pr_warn("Unable to parse numa_balancing=\n"); return ret; } __setup("numa_balancing=", setup_numabalancing); #else static inline void __init check_numabalancing_enable(void) { } #endif /* CONFIG_NUMA_BALANCING */ void __init numa_policy_init(void) { nodemask_t interleave_nodes; unsigned long largest = 0; int nid, prefer = 0; policy_cache = kmem_cache_create("numa_policy", sizeof(struct mempolicy), 0, SLAB_PANIC, NULL); sn_cache = kmem_cache_create("shared_policy_node", sizeof(struct sp_node), 0, SLAB_PANIC, NULL); for_each_node(nid) { preferred_node_policy[nid] = (struct mempolicy) { .refcnt = ATOMIC_INIT(1), .mode = MPOL_PREFERRED, .flags = MPOL_F_MOF | MPOL_F_MORON, .nodes = nodemask_of_node(nid), }; } /* * Set interleaving policy for system init. Interleaving is only * enabled across suitably sized nodes (default is >= 16MB), or * fall back to the largest node if they're all smaller. */ nodes_clear(interleave_nodes); for_each_node_state(nid, N_MEMORY) { unsigned long total_pages = node_present_pages(nid); /* Preserve the largest node */ if (largest < total_pages) { largest = total_pages; prefer = nid; } /* Interleave this node? */ if ((total_pages << PAGE_SHIFT) >= (16 << 20)) node_set(nid, interleave_nodes); } /* All too small, use the largest */ if (unlikely(nodes_empty(interleave_nodes))) node_set(prefer, interleave_nodes); if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes)) pr_err("%s: interleaving failed\n", __func__); check_numabalancing_enable(); } /* Reset policy of current process to default */ void numa_default_policy(void) { do_set_mempolicy(MPOL_DEFAULT, 0, NULL); } /* * Parse and format mempolicy from/to strings */ static const char * const policy_modes[] = { [MPOL_DEFAULT] = "default", [MPOL_PREFERRED] = "prefer", [MPOL_BIND] = "bind", [MPOL_INTERLEAVE] = "interleave", [MPOL_WEIGHTED_INTERLEAVE] = "weighted interleave", [MPOL_LOCAL] = "local", [MPOL_PREFERRED_MANY] = "prefer (many)", }; #ifdef CONFIG_TMPFS /** * mpol_parse_str - parse string to mempolicy, for tmpfs mpol mount option. * @str: string containing mempolicy to parse * @mpol: pointer to struct mempolicy pointer, returned on success. * * Format of input: * <mode>[=<flags>][:<nodelist>] * * Return: %0 on success, else %1 */ int mpol_parse_str(char *str, struct mempolicy **mpol) { struct mempolicy *new = NULL; unsigned short mode_flags; nodemask_t nodes; char *nodelist = strchr(str, ':'); char *flags = strchr(str, '='); int err = 1, mode; if (flags) *flags++ = '\0'; /* terminate mode string */ if (nodelist) { /* NUL-terminate mode or flags string */ *nodelist++ = '\0'; if (nodelist_parse(nodelist, nodes)) goto out; if (!nodes_subset(nodes, node_states[N_MEMORY])) goto out; } else nodes_clear(nodes); mode = match_string(policy_modes, MPOL_MAX, str); if (mode < 0) goto out; switch (mode) { case MPOL_PREFERRED: /* * Insist on a nodelist of one node only, although later * we use first_node(nodes) to grab a single node, so here * nodelist (or nodes) cannot be empty. */ if (nodelist) { char *rest = nodelist; while (isdigit(*rest)) rest++; if (*rest) goto out; if (nodes_empty(nodes)) goto out; } break; case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: /* * Default to online nodes with memory if no nodelist */ if (!nodelist) nodes = node_states[N_MEMORY]; break; case MPOL_LOCAL: /* * Don't allow a nodelist; mpol_new() checks flags */ if (nodelist) goto out; break; case MPOL_DEFAULT: /* * Insist on a empty nodelist */ if (!nodelist) err = 0; goto out; case MPOL_PREFERRED_MANY: case MPOL_BIND: /* * Insist on a nodelist */ if (!nodelist) goto out; } mode_flags = 0; if (flags) { /* * Currently, we only support two mutually exclusive * mode flags. */ if (!strcmp(flags, "static")) mode_flags |= MPOL_F_STATIC_NODES; else if (!strcmp(flags, "relative")) mode_flags |= MPOL_F_RELATIVE_NODES; else goto out; } new = mpol_new(mode, mode_flags, &nodes); if (IS_ERR(new)) goto out; /* * Save nodes for mpol_to_str() to show the tmpfs mount options * for /proc/mounts, /proc/pid/mounts and /proc/pid/mountinfo. */ if (mode != MPOL_PREFERRED) { new->nodes = nodes; } else if (nodelist) { nodes_clear(new->nodes); node_set(first_node(nodes), new->nodes); } else { new->mode = MPOL_LOCAL; } /* * Save nodes for contextualization: this will be used to "clone" * the mempolicy in a specific context [cpuset] at a later time. */ new->w.user_nodemask = nodes; err = 0; out: /* Restore string for error message */ if (nodelist) *--nodelist = ':'; if (flags) *--flags = '='; if (!err) *mpol = new; return err; } #endif /* CONFIG_TMPFS */ /** * mpol_to_str - format a mempolicy structure for printing * @buffer: to contain formatted mempolicy string * @maxlen: length of @buffer * @pol: pointer to mempolicy to be formatted * * Convert @pol into a string. If @buffer is too short, truncate the string. * Recommend a @maxlen of at least 51 for the longest mode, "weighted * interleave", plus the longest flag flags, "relative|balancing", and to * display at least a few node ids. */ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) { char *p = buffer; nodemask_t nodes = NODE_MASK_NONE; unsigned short mode = MPOL_DEFAULT; unsigned short flags = 0; if (pol && pol != &default_policy && !(pol >= &preferred_node_policy[0] && pol <= &preferred_node_policy[ARRAY_SIZE(preferred_node_policy) - 1])) { mode = pol->mode; flags = pol->flags; } switch (mode) { case MPOL_DEFAULT: case MPOL_LOCAL: break; case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: nodes = pol->nodes; break; default: WARN_ON_ONCE(1); snprintf(p, maxlen, "unknown"); return; } p += snprintf(p, maxlen, "%s", policy_modes[mode]); if (flags & MPOL_MODE_FLAGS) { p += snprintf(p, buffer + maxlen - p, "="); /* * Static and relative are mutually exclusive. */ if (flags & MPOL_F_STATIC_NODES) p += snprintf(p, buffer + maxlen - p, "static"); else if (flags & MPOL_F_RELATIVE_NODES) p += snprintf(p, buffer + maxlen - p, "relative"); if (flags & MPOL_F_NUMA_BALANCING) { if (!is_power_of_2(flags & MPOL_MODE_FLAGS)) p += snprintf(p, buffer + maxlen - p, "|"); p += snprintf(p, buffer + maxlen - p, "balancing"); } } if (!nodes_empty(nodes)) p += scnprintf(p, buffer + maxlen - p, ":%*pbl", nodemask_pr_args(&nodes)); } #ifdef CONFIG_SYSFS struct iw_node_attr { struct kobj_attribute kobj_attr; int nid; }; static ssize_t node_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct iw_node_attr *node_attr; u8 weight; node_attr = container_of(attr, struct iw_node_attr, kobj_attr); weight = get_il_weight(node_attr->nid); return sysfs_emit(buf, "%d\n", weight); } static ssize_t node_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct iw_node_attr *node_attr; u8 *new; u8 *old; u8 weight = 0; node_attr = container_of(attr, struct iw_node_attr, kobj_attr); if (count == 0 || sysfs_streq(buf, "")) weight = 0; else if (kstrtou8(buf, 0, &weight)) return -EINVAL; new = kzalloc(nr_node_ids, GFP_KERNEL); if (!new) return -ENOMEM; mutex_lock(&iw_table_lock); old = rcu_dereference_protected(iw_table, lockdep_is_held(&iw_table_lock)); if (old) memcpy(new, old, nr_node_ids); new[node_attr->nid] = weight; rcu_assign_pointer(iw_table, new); mutex_unlock(&iw_table_lock); synchronize_rcu(); kfree(old); return count; } static struct iw_node_attr **node_attrs; static void sysfs_wi_node_release(struct iw_node_attr *node_attr, struct kobject *parent) { if (!node_attr) return; sysfs_remove_file(parent, &node_attr->kobj_attr.attr); kfree(node_attr->kobj_attr.attr.name); kfree(node_attr); } static void sysfs_wi_release(struct kobject *wi_kobj) { int i; for (i = 0; i < nr_node_ids; i++) sysfs_wi_node_release(node_attrs[i], wi_kobj); kobject_put(wi_kobj); } static const struct kobj_type wi_ktype = { .sysfs_ops = &kobj_sysfs_ops, .release = sysfs_wi_release, }; static int add_weight_node(int nid, struct kobject *wi_kobj) { struct iw_node_attr *node_attr; char *name; node_attr = kzalloc(sizeof(*node_attr), GFP_KERNEL); if (!node_attr) return -ENOMEM; name = kasprintf(GFP_KERNEL, "node%d", nid); if (!name) { kfree(node_attr); return -ENOMEM; } sysfs_attr_init(&node_attr->kobj_attr.attr); node_attr->kobj_attr.attr.name = name; node_attr->kobj_attr.attr.mode = 0644; node_attr->kobj_attr.show = node_show; node_attr->kobj_attr.store = node_store; node_attr->nid = nid; if (sysfs_create_file(wi_kobj, &node_attr->kobj_attr.attr)) { kfree(node_attr->kobj_attr.attr.name); kfree(node_attr); pr_err("failed to add attribute to weighted_interleave\n"); return -ENOMEM; } node_attrs[nid] = node_attr; return 0; } static int add_weighted_interleave_group(struct kobject *root_kobj) { struct kobject *wi_kobj; int nid, err; wi_kobj = kzalloc(sizeof(struct kobject), GFP_KERNEL); if (!wi_kobj) return -ENOMEM; err = kobject_init_and_add(wi_kobj, &wi_ktype, root_kobj, "weighted_interleave"); if (err) { kfree(wi_kobj); return err; } for_each_node_state(nid, N_POSSIBLE) { err = add_weight_node(nid, wi_kobj); if (err) { pr_err("failed to add sysfs [node%d]\n", nid); break; } } if (err) kobject_put(wi_kobj); return 0; } static void mempolicy_kobj_release(struct kobject *kobj) { u8 *old; mutex_lock(&iw_table_lock); old = rcu_dereference_protected(iw_table, lockdep_is_held(&iw_table_lock)); rcu_assign_pointer(iw_table, NULL); mutex_unlock(&iw_table_lock); synchronize_rcu(); kfree(old); kfree(node_attrs); kfree(kobj); } static const struct kobj_type mempolicy_ktype = { .release = mempolicy_kobj_release }; static int __init mempolicy_sysfs_init(void) { int err; static struct kobject *mempolicy_kobj; mempolicy_kobj = kzalloc(sizeof(*mempolicy_kobj), GFP_KERNEL); if (!mempolicy_kobj) { err = -ENOMEM; goto err_out; } node_attrs = kcalloc(nr_node_ids, sizeof(struct iw_node_attr *), GFP_KERNEL); if (!node_attrs) { err = -ENOMEM; goto mempol_out; } err = kobject_init_and_add(mempolicy_kobj, &mempolicy_ktype, mm_kobj, "mempolicy"); if (err) goto node_out; err = add_weighted_interleave_group(mempolicy_kobj); if (err) { pr_err("mempolicy sysfs structure failed to initialize\n"); kobject_put(mempolicy_kobj); return err; } return err; node_out: kfree(node_attrs); mempol_out: kfree(mempolicy_kobj); err_out: pr_err("failed to add mempolicy kobject to the system\n"); return err; } late_initcall(mempolicy_sysfs_init); #endif /* CONFIG_SYSFS */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2016 ARM Ltd. */ #ifndef __ASM_CHECKSUM_H #define __ASM_CHECKSUM_H #include <linux/in6.h> #define _HAVE_ARCH_IPV6_CSUM __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, __u32 len, __u8 proto, __wsum sum); static inline __sum16 csum_fold(__wsum csum) { u32 sum = (__force u32)csum; sum += (sum >> 16) | (sum << 16); return ~(__force __sum16)(sum >> 16); } #define csum_fold csum_fold static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) { __uint128_t tmp; u64 sum; int n = ihl; /* we want it signed */ tmp = *(const __uint128_t *)iph; iph += 16; n -= 4; tmp += ((tmp >> 64) | (tmp << 64)); sum = tmp >> 64; do { sum += *(const u32 *)iph; iph += 4; } while (--n > 0); sum += ((sum >> 32) | (sum << 32)); return csum_fold((__force __wsum)(sum >> 32)); } #define ip_fast_csum ip_fast_csum extern unsigned int do_csum(const unsigned char *buff, int len); #define do_csum do_csum #include <asm-generic/checksum.h> #endif /* __ASM_CHECKSUM_H */ |
| 261 431 483 5 5 452 451 431 447 452 449 451 450 451 450 453 451 450 451 451 450 450 447 448 24 429 8 20 20 8 8 8 8 8 8 764 766 5 5 5 262 264 263 264 264 264 261 263 263 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/uaccess.h> #include <linux/fs_struct.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/prefetch.h> #include "mount.h" #include "internal.h" struct prepend_buffer { char *buf; int len; }; #define DECLARE_BUFFER(__name, __buf, __len) \ struct prepend_buffer __name = {.buf = __buf + __len, .len = __len} static char *extract_string(struct prepend_buffer *p) { if (likely(p->len >= 0)) return p->buf; return ERR_PTR(-ENAMETOOLONG); } static bool prepend_char(struct prepend_buffer *p, unsigned char c) { if (likely(p->len > 0)) { p->len--; *--p->buf = c; return true; } p->len = -1; return false; } /* * The source of the prepend data can be an optimistic load * of a dentry name and length. And because we don't hold any * locks, the length and the pointer to the name may not be * in sync if a concurrent rename happens, and the kernel * copy might fault as a result. * * The end result will correct itself when we check the * rename sequence count, but we need to be able to handle * the fault gracefully. */ static bool prepend_copy(void *dst, const void *src, int len) { if (unlikely(copy_from_kernel_nofault(dst, src, len))) { memset(dst, 'x', len); return false; } return true; } static bool prepend(struct prepend_buffer *p, const char *str, int namelen) { // Already overflowed? if (p->len < 0) return false; // Will overflow? if (p->len < namelen) { // Fill as much as possible from the end of the name str += namelen - p->len; p->buf -= p->len; prepend_copy(p->buf, str, p->len); p->len = -1; return false; } // Fits fully p->len -= namelen; p->buf -= namelen; return prepend_copy(p->buf, str, namelen); } /** * prepend_name - prepend a pathname in front of current buffer pointer * @p: prepend buffer which contains buffer pointer and allocated length * @name: name string and length qstr structure * * With RCU path tracing, it may race with d_move(). Use READ_ONCE() to * make sure that either the old or the new name pointer and length are * fetched. However, there may be mismatch between length and pointer. * But since the length cannot be trusted, we need to copy the name very * carefully when doing the prepend_copy(). It also prepends "/" at * the beginning of the name. The sequence number check at the caller will * retry it again when a d_move() does happen. So any garbage in the buffer * due to mismatched pointer and length will be discarded. * * Load acquire is needed to make sure that we see the new name data even * if we might get the length wrong. */ static bool prepend_name(struct prepend_buffer *p, const struct qstr *name) { const char *dname = smp_load_acquire(&name->name); /* ^^^ */ u32 dlen = READ_ONCE(name->len); return prepend(p, dname, dlen) && prepend_char(p, '/'); } static int __prepend_path(const struct dentry *dentry, const struct mount *mnt, const struct path *root, struct prepend_buffer *p) { while (dentry != root->dentry || &mnt->mnt != root->mnt) { const struct dentry *parent = READ_ONCE(dentry->d_parent); if (dentry == mnt->mnt.mnt_root) { struct mount *m = READ_ONCE(mnt->mnt_parent); struct mnt_namespace *mnt_ns; if (likely(mnt != m)) { dentry = READ_ONCE(mnt->mnt_mountpoint); mnt = m; continue; } /* Global root */ mnt_ns = READ_ONCE(mnt->mnt_ns); /* open-coded is_mounted() to use local mnt_ns */ if (!IS_ERR_OR_NULL(mnt_ns) && !is_anon_ns(mnt_ns)) return 1; // absolute root else return 2; // detached or not attached yet } if (unlikely(dentry == parent)) /* Escaped? */ return 3; prefetch(parent); if (!prepend_name(p, &dentry->d_name)) break; dentry = parent; } return 0; } /** * prepend_path - Prepend path string to a buffer * @path: the dentry/vfsmount to report * @root: root vfsmnt/dentry * @p: prepend buffer which contains buffer pointer and allocated length * * The function will first try to write out the pathname without taking any * lock other than the RCU read lock to make sure that dentries won't go away. * It only checks the sequence number of the global rename_lock as any change * in the dentry's d_seq will be preceded by changes in the rename_lock * sequence number. If the sequence number had been changed, it will restart * the whole pathname back-tracing sequence again by taking the rename_lock. * In this case, there is no need to take the RCU read lock as the recursive * parent pointer references will keep the dentry chain alive as long as no * rename operation is performed. */ static int prepend_path(const struct path *path, const struct path *root, struct prepend_buffer *p) { unsigned seq, m_seq = 0; struct prepend_buffer b; int error; rcu_read_lock(); restart_mnt: read_seqbegin_or_lock(&mount_lock, &m_seq); seq = 0; rcu_read_lock(); restart: b = *p; read_seqbegin_or_lock(&rename_lock, &seq); error = __prepend_path(path->dentry, real_mount(path->mnt), root, &b); if (!(seq & 1)) rcu_read_unlock(); if (need_seqretry(&rename_lock, seq)) { seq = 1; goto restart; } done_seqretry(&rename_lock, seq); if (!(m_seq & 1)) rcu_read_unlock(); if (need_seqretry(&mount_lock, m_seq)) { m_seq = 1; goto restart_mnt; } done_seqretry(&mount_lock, m_seq); if (unlikely(error == 3)) b = *p; if (b.len == p->len) prepend_char(&b, '/'); *p = b; return error; } /** * __d_path - return the path of a dentry * @path: the dentry/vfsmount to report * @root: root vfsmnt/dentry * @buf: buffer to return value in * @buflen: buffer length * * Convert a dentry into an ASCII path name. * * Returns a pointer into the buffer or an error code if the * path was too long. * * "buflen" should be positive. * * If the path is not reachable from the supplied root, return %NULL. */ char *__d_path(const struct path *path, const struct path *root, char *buf, int buflen) { DECLARE_BUFFER(b, buf, buflen); prepend_char(&b, 0); if (unlikely(prepend_path(path, root, &b) > 0)) return NULL; return extract_string(&b); } char *d_absolute_path(const struct path *path, char *buf, int buflen) { struct path root = {}; DECLARE_BUFFER(b, buf, buflen); prepend_char(&b, 0); if (unlikely(prepend_path(path, &root, &b) > 1)) return ERR_PTR(-EINVAL); return extract_string(&b); } static void get_fs_root_rcu(struct fs_struct *fs, struct path *root) { unsigned seq; do { seq = read_seqcount_begin(&fs->seq); *root = fs->root; } while (read_seqcount_retry(&fs->seq, seq)); } /** * d_path - return the path of a dentry * @path: path to report * @buf: buffer to return value in * @buflen: buffer length * * Convert a dentry into an ASCII path name. If the entry has been deleted * the string " (deleted)" is appended. Note that this is ambiguous. * * Returns a pointer into the buffer or an error code if the path was * too long. Note: Callers should use the returned pointer, not the passed * in buffer, to use the name! The implementation often starts at an offset * into the buffer, and may leave 0 bytes at the start. * * "buflen" should be positive. */ char *d_path(const struct path *path, char *buf, int buflen) { DECLARE_BUFFER(b, buf, buflen); struct path root; /* * We have various synthetic filesystems that never get mounted. On * these filesystems dentries are never used for lookup purposes, and * thus don't need to be hashed. They also don't need a name until a * user wants to identify the object in /proc/pid/fd/. The little hack * below allows us to generate a name for these objects on demand: * * Some pseudo inodes are mountable. When they are mounted * path->dentry == path->mnt->mnt_root. In that case don't call d_dname * and instead have d_path return the mounted path. */ if (path->dentry->d_op && path->dentry->d_op->d_dname && (!IS_ROOT(path->dentry) || path->dentry != path->mnt->mnt_root)) return path->dentry->d_op->d_dname(path->dentry, buf, buflen); rcu_read_lock(); get_fs_root_rcu(current->fs, &root); if (unlikely(d_unlinked(path->dentry))) prepend(&b, " (deleted)", 11); else prepend_char(&b, 0); prepend_path(path, &root, &b); rcu_read_unlock(); return extract_string(&b); } EXPORT_SYMBOL(d_path); /* * Helper function for dentry_operations.d_dname() members */ char *dynamic_dname(char *buffer, int buflen, const char *fmt, ...) { va_list args; char temp[64]; int sz; va_start(args, fmt); sz = vsnprintf(temp, sizeof(temp), fmt, args) + 1; va_end(args); if (sz > sizeof(temp) || sz > buflen) return ERR_PTR(-ENAMETOOLONG); buffer += buflen - sz; return memcpy(buffer, temp, sz); } char *simple_dname(struct dentry *dentry, char *buffer, int buflen) { DECLARE_BUFFER(b, buffer, buflen); /* these dentries are never renamed, so d_lock is not needed */ prepend(&b, " (deleted)", 11); prepend(&b, dentry->d_name.name, dentry->d_name.len); prepend_char(&b, '/'); return extract_string(&b); } /* * Write full pathname from the root of the filesystem into the buffer. */ static char *__dentry_path(const struct dentry *d, struct prepend_buffer *p) { const struct dentry *dentry; struct prepend_buffer b; int seq = 0; rcu_read_lock(); restart: dentry = d; b = *p; read_seqbegin_or_lock(&rename_lock, &seq); while (!IS_ROOT(dentry)) { const struct dentry *parent = dentry->d_parent; prefetch(parent); if (!prepend_name(&b, &dentry->d_name)) break; dentry = parent; } if (!(seq & 1)) rcu_read_unlock(); if (need_seqretry(&rename_lock, seq)) { seq = 1; goto restart; } done_seqretry(&rename_lock, seq); if (b.len == p->len) prepend_char(&b, '/'); return extract_string(&b); } char *dentry_path_raw(const struct dentry *dentry, char *buf, int buflen) { DECLARE_BUFFER(b, buf, buflen); prepend_char(&b, 0); return __dentry_path(dentry, &b); } EXPORT_SYMBOL(dentry_path_raw); char *dentry_path(const struct dentry *dentry, char *buf, int buflen) { DECLARE_BUFFER(b, buf, buflen); if (unlikely(d_unlinked(dentry))) prepend(&b, "//deleted", 10); else prepend_char(&b, 0); return __dentry_path(dentry, &b); } static void get_fs_root_and_pwd_rcu(struct fs_struct *fs, struct path *root, struct path *pwd) { unsigned seq; do { seq = read_seqcount_begin(&fs->seq); *root = fs->root; *pwd = fs->pwd; } while (read_seqcount_retry(&fs->seq, seq)); } /* * NOTE! The user-level library version returns a * character pointer. The kernel system call just * returns the length of the buffer filled (which * includes the ending '\0' character), or a negative * error value. So libc would do something like * * char *getcwd(char * buf, size_t size) * { * int retval; * * retval = sys_getcwd(buf, size); * if (retval >= 0) * return buf; * errno = -retval; * return NULL; * } */ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size) { int error; struct path pwd, root; char *page = __getname(); if (!page) return -ENOMEM; rcu_read_lock(); get_fs_root_and_pwd_rcu(current->fs, &root, &pwd); if (unlikely(d_unlinked(pwd.dentry))) { rcu_read_unlock(); error = -ENOENT; } else { unsigned len; DECLARE_BUFFER(b, page, PATH_MAX); prepend_char(&b, 0); if (unlikely(prepend_path(&pwd, &root, &b) > 0)) prepend(&b, "(unreachable)", 13); rcu_read_unlock(); len = PATH_MAX - b.len; if (unlikely(len > PATH_MAX)) error = -ENAMETOOLONG; else if (unlikely(len > size)) error = -ERANGE; else if (copy_to_user(buf, b.buf, len)) error = -EFAULT; else error = len; } __putname(page); return error; } |
| 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 272 275 1 1 140 139 140 10 140 46 46 46 69 107 51 51 51 51 51 51 51 51 35 35 35 51 69 69 69 69 68 169 170 202 200 171 171 169 163 200 202 58 171 169 171 171 162 169 171 200 13 9 13 13 13 13 13 1 13 13 1 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/filemap.c * * Copyright (C) 1994-1999 Linus Torvalds */ /* * This file handles the generic file mmap semantics used by * most "normal" filesystems (but you don't /have/ to use this: * the NFS filesystem used to do this differently, for example) */ #include <linux/export.h> #include <linux/compiler.h> #include <linux/dax.h> #include <linux/fs.h> #include <linux/sched/signal.h> #include <linux/uaccess.h> #include <linux/capability.h> #include <linux/kernel_stat.h> #include <linux/gfp.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/syscalls.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/uio.h> #include <linux/error-injection.h> #include <linux/hash.h> #include <linux/writeback.h> #include <linux/backing-dev.h> #include <linux/pagevec.h> #include <linux/security.h> #include <linux/cpuset.h> #include <linux/hugetlb.h> #include <linux/memcontrol.h> #include <linux/shmem_fs.h> #include <linux/rmap.h> #include <linux/delayacct.h> #include <linux/psi.h> #include <linux/ramfs.h> #include <linux/page_idle.h> #include <linux/migrate.h> #include <linux/pipe_fs_i.h> #include <linux/splice.h> #include <linux/rcupdate_wait.h> #include <linux/sched/mm.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/filemap.h> /* * FIXME: remove all knowledge of the buffer layer from the core VM */ #include <linux/buffer_head.h> /* for try_to_free_buffers */ #include <asm/mman.h> #include "swap.h" /* * Shared mappings implemented 30.11.1994. It's not fully working yet, * though. * * Shared mappings now work. 15.8.1995 Bruno. * * finished 'unifying' the page and buffer cache and SMP-threaded the * page-cache, 21.05.1999, Ingo Molnar <mingo@redhat.com> * * SMP-threaded pagemap-LRU 1999, Andrea Arcangeli <andrea@suse.de> */ /* * Lock ordering: * * ->i_mmap_rwsem (truncate_pagecache) * ->private_lock (__free_pte->block_dirty_folio) * ->swap_lock (exclusive_swap_page, others) * ->i_pages lock * * ->i_rwsem * ->invalidate_lock (acquired by fs in truncate path) * ->i_mmap_rwsem (truncate->unmap_mapping_range) * * ->mmap_lock * ->i_mmap_rwsem * ->page_table_lock or pte_lock (various, mainly in memory.c) * ->i_pages lock (arch-dependent flush_dcache_mmap_lock) * * ->mmap_lock * ->invalidate_lock (filemap_fault) * ->lock_page (filemap_fault, access_process_vm) * * ->i_rwsem (generic_perform_write) * ->mmap_lock (fault_in_readable->do_page_fault) * * bdi->wb.list_lock * sb_lock (fs/fs-writeback.c) * ->i_pages lock (__sync_single_inode) * * ->i_mmap_rwsem * ->anon_vma.lock (vma_merge) * * ->anon_vma.lock * ->page_table_lock or pte_lock (anon_vma_prepare and various) * * ->page_table_lock or pte_lock * ->swap_lock (try_to_unmap_one) * ->private_lock (try_to_unmap_one) * ->i_pages lock (try_to_unmap_one) * ->lruvec->lru_lock (follow_page_mask->mark_page_accessed) * ->lruvec->lru_lock (check_pte_range->folio_isolate_lru) * ->private_lock (folio_remove_rmap_pte->set_page_dirty) * ->i_pages lock (folio_remove_rmap_pte->set_page_dirty) * bdi.wb->list_lock (folio_remove_rmap_pte->set_page_dirty) * ->inode->i_lock (folio_remove_rmap_pte->set_page_dirty) * bdi.wb->list_lock (zap_pte_range->set_page_dirty) * ->inode->i_lock (zap_pte_range->set_page_dirty) * ->private_lock (zap_pte_range->block_dirty_folio) */ static void mapping_set_update(struct xa_state *xas, struct address_space *mapping) { if (dax_mapping(mapping) || shmem_mapping(mapping)) return; xas_set_update(xas, workingset_update_node); xas_set_lru(xas, &shadow_nodes); } static void page_cache_delete(struct address_space *mapping, struct folio *folio, void *shadow) { XA_STATE(xas, &mapping->i_pages, folio->index); long nr = 1; mapping_set_update(&xas, mapping); xas_set_order(&xas, folio->index, folio_order(folio)); nr = folio_nr_pages(folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); xas_store(&xas, shadow); xas_init_marks(&xas); folio->mapping = NULL; /* Leave page->index set: truncation lookup relies upon it */ mapping->nrpages -= nr; } static void filemap_unaccount_folio(struct address_space *mapping, struct folio *folio) { long nr; VM_BUG_ON_FOLIO(folio_mapped(folio), folio); if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(folio_mapped(folio))) { pr_alert("BUG: Bad page cache in process %s pfn:%05lx\n", current->comm, folio_pfn(folio)); dump_page(&folio->page, "still mapped when deleted"); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); if (mapping_exiting(mapping) && !folio_test_large(folio)) { int mapcount = folio_mapcount(folio); if (folio_ref_count(folio) >= mapcount + 2) { /* * All vmas have already been torn down, so it's * a good bet that actually the page is unmapped * and we'd rather not leak it: if we're wrong, * another bad page check should catch it later. */ atomic_set(&folio->_mapcount, -1); folio_ref_sub(folio, mapcount); } } } /* hugetlb folios do not participate in page cache accounting. */ if (folio_test_hugetlb(folio)) return; nr = folio_nr_pages(folio); __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, -nr); if (folio_test_swapbacked(folio)) { __lruvec_stat_mod_folio(folio, NR_SHMEM, -nr); if (folio_test_pmd_mappable(folio)) __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, -nr); } else if (folio_test_pmd_mappable(folio)) { __lruvec_stat_mod_folio(folio, NR_FILE_THPS, -nr); filemap_nr_thps_dec(mapping); } /* * At this point folio must be either written or cleaned by * truncate. Dirty folio here signals a bug and loss of * unwritten data - on ordinary filesystems. * * But it's harmless on in-memory filesystems like tmpfs; and can * occur when a driver which did get_user_pages() sets page dirty * before putting it, while the inode is being finally evicted. * * Below fixes dirty accounting after removing the folio entirely * but leaves the dirty flag set: it has no effect for truncated * folio and anyway will be cleared before returning folio to * buddy allocator. */ if (WARN_ON_ONCE(folio_test_dirty(folio) && mapping_can_writeback(mapping))) folio_account_cleaned(folio, inode_to_wb(mapping->host)); } /* * Delete a page from the page cache and free it. Caller has to make * sure the page is locked and that nobody else uses it - or that usage * is safe. The caller must hold the i_pages lock. */ void __filemap_remove_folio(struct folio *folio, void *shadow) { struct address_space *mapping = folio->mapping; trace_mm_filemap_delete_from_page_cache(folio); filemap_unaccount_folio(mapping, folio); page_cache_delete(mapping, folio, shadow); } void filemap_free_folio(struct address_space *mapping, struct folio *folio) { void (*free_folio)(struct folio *); int refs = 1; free_folio = mapping->a_ops->free_folio; if (free_folio) free_folio(folio); if (folio_test_large(folio)) refs = folio_nr_pages(folio); folio_put_refs(folio, refs); } /** * filemap_remove_folio - Remove folio from page cache. * @folio: The folio. * * This must be called only on folios that are locked and have been * verified to be in the page cache. It will never put the folio into * the free list because the caller has a reference on the page. */ void filemap_remove_folio(struct folio *folio) { struct address_space *mapping = folio->mapping; BUG_ON(!folio_test_locked(folio)); spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); __filemap_remove_folio(folio, NULL); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); filemap_free_folio(mapping, folio); } /* * page_cache_delete_batch - delete several folios from page cache * @mapping: the mapping to which folios belong * @fbatch: batch of folios to delete * * The function walks over mapping->i_pages and removes folios passed in * @fbatch from the mapping. The function expects @fbatch to be sorted * by page index and is optimised for it to be dense. * It tolerates holes in @fbatch (mapping entries at those indices are not * modified). * * The function expects the i_pages lock to be held. */ static void page_cache_delete_batch(struct address_space *mapping, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, fbatch->folios[0]->index); long total_pages = 0; int i = 0; struct folio *folio; mapping_set_update(&xas, mapping); xas_for_each(&xas, folio, ULONG_MAX) { if (i >= folio_batch_count(fbatch)) break; /* A swap/dax/shadow entry got inserted? Skip it. */ if (xa_is_value(folio)) continue; /* * A page got inserted in our range? Skip it. We have our * pages locked so they are protected from being removed. * If we see a page whose index is higher than ours, it * means our page has been removed, which shouldn't be * possible because we're holding the PageLock. */ if (folio != fbatch->folios[i]) { VM_BUG_ON_FOLIO(folio->index > fbatch->folios[i]->index, folio); continue; } WARN_ON_ONCE(!folio_test_locked(folio)); folio->mapping = NULL; /* Leave folio->index set: truncation lookup relies on it */ i++; xas_store(&xas, NULL); total_pages += folio_nr_pages(folio); } mapping->nrpages -= total_pages; } void delete_from_page_cache_batch(struct address_space *mapping, struct folio_batch *fbatch) { int i; if (!folio_batch_count(fbatch)) return; spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); for (i = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; trace_mm_filemap_delete_from_page_cache(folio); filemap_unaccount_folio(mapping, folio); } page_cache_delete_batch(mapping, fbatch); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); for (i = 0; i < folio_batch_count(fbatch); i++) filemap_free_folio(mapping, fbatch->folios[i]); } int filemap_check_errors(struct address_space *mapping) { int ret = 0; /* Check for outstanding write errors */ if (test_bit(AS_ENOSPC, &mapping->flags) && test_and_clear_bit(AS_ENOSPC, &mapping->flags)) ret = -ENOSPC; if (test_bit(AS_EIO, &mapping->flags) && test_and_clear_bit(AS_EIO, &mapping->flags)) ret = -EIO; return ret; } EXPORT_SYMBOL(filemap_check_errors); static int filemap_check_and_keep_errors(struct address_space *mapping) { /* Check for outstanding write errors */ if (test_bit(AS_EIO, &mapping->flags)) return -EIO; if (test_bit(AS_ENOSPC, &mapping->flags)) return -ENOSPC; return 0; } /** * filemap_fdatawrite_wbc - start writeback on mapping dirty pages in range * @mapping: address space structure to write * @wbc: the writeback_control controlling the writeout * * Call writepages on the mapping using the provided wbc to control the * writeout. * * Return: %0 on success, negative error code otherwise. */ int filemap_fdatawrite_wbc(struct address_space *mapping, struct writeback_control *wbc) { int ret; if (!mapping_can_writeback(mapping) || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) return 0; wbc_attach_fdatawrite_inode(wbc, mapping->host); ret = do_writepages(mapping, wbc); wbc_detach_inode(wbc); return ret; } EXPORT_SYMBOL(filemap_fdatawrite_wbc); /** * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range * @mapping: address space structure to write * @start: offset in bytes where the range starts * @end: offset in bytes where the range ends (inclusive) * @sync_mode: enable synchronous operation * * Start writeback against all of a mapping's dirty pages that lie * within the byte offsets <start, end> inclusive. * * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as * opposed to a regular memory cleansing writeback. The difference between * these two operations is that if a dirty page/buffer is encountered, it must * be waited upon, and not just skipped over. * * Return: %0 on success, negative error code otherwise. */ int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end, int sync_mode) { struct writeback_control wbc = { .sync_mode = sync_mode, .nr_to_write = LONG_MAX, .range_start = start, .range_end = end, }; return filemap_fdatawrite_wbc(mapping, &wbc); } static inline int __filemap_fdatawrite(struct address_space *mapping, int sync_mode) { return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode); } int filemap_fdatawrite(struct address_space *mapping) { return __filemap_fdatawrite(mapping, WB_SYNC_ALL); } EXPORT_SYMBOL(filemap_fdatawrite); int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end) { return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL); } EXPORT_SYMBOL(filemap_fdatawrite_range); /** * filemap_flush - mostly a non-blocking flush * @mapping: target address_space * * This is a mostly non-blocking flush. Not suitable for data-integrity * purposes - I/O may not be started against all dirty pages. * * Return: %0 on success, negative error code otherwise. */ int filemap_flush(struct address_space *mapping) { return __filemap_fdatawrite(mapping, WB_SYNC_NONE); } EXPORT_SYMBOL(filemap_flush); /** * filemap_range_has_page - check if a page exists in range. * @mapping: address space within which to check * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Find at least one page in the range supplied, usually used to check if * direct writing in this range will trigger a writeback. * * Return: %true if at least one page exists in the specified range, * %false otherwise. */ bool filemap_range_has_page(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { struct folio *folio; XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); pgoff_t max = end_byte >> PAGE_SHIFT; if (end_byte < start_byte) return false; rcu_read_lock(); for (;;) { folio = xas_find(&xas, max); if (xas_retry(&xas, folio)) continue; /* Shadow entries don't count */ if (xa_is_value(folio)) continue; /* * We don't need to try to pin this page; we're about to * release the RCU lock anyway. It is enough to know that * there was a page here recently. */ break; } rcu_read_unlock(); return folio != NULL; } EXPORT_SYMBOL(filemap_range_has_page); static void __filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { pgoff_t index = start_byte >> PAGE_SHIFT; pgoff_t end = end_byte >> PAGE_SHIFT; struct folio_batch fbatch; unsigned nr_folios; folio_batch_init(&fbatch); while (index <= end) { unsigned i; nr_folios = filemap_get_folios_tag(mapping, &index, end, PAGECACHE_TAG_WRITEBACK, &fbatch); if (!nr_folios) break; for (i = 0; i < nr_folios; i++) { struct folio *folio = fbatch.folios[i]; folio_wait_writeback(folio); } folio_batch_release(&fbatch); cond_resched(); } } /** * filemap_fdatawait_range - wait for writeback to complete * @mapping: address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the given address space * in the given range and wait for all of them. Check error status of * the address space and return it. * * Since the error status of the address space is cleared by this function, * callers are responsible for checking the return value and handling and/or * reporting the error. * * Return: error status of the address space. */ int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { __filemap_fdatawait_range(mapping, start_byte, end_byte); return filemap_check_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_range); /** * filemap_fdatawait_range_keep_errors - wait for writeback to complete * @mapping: address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the given address space in the * given range and wait for all of them. Unlike filemap_fdatawait_range(), * this function does not clear error status of the address space. * * Use this function if callers don't handle errors themselves. Expected * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), * fsfreeze(8) */ int filemap_fdatawait_range_keep_errors(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { __filemap_fdatawait_range(mapping, start_byte, end_byte); return filemap_check_and_keep_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_range_keep_errors); /** * file_fdatawait_range - wait for writeback to complete * @file: file pointing to address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the address space that file * refers to, in the given range and wait for all of them. Check error * status of the address space vs. the file->f_wb_err cursor and return it. * * Since the error status of the file is advanced by this function, * callers are responsible for checking the return value and handling and/or * reporting the error. * * Return: error status of the address space vs. the file->f_wb_err cursor. */ int file_fdatawait_range(struct file *file, loff_t start_byte, loff_t end_byte) { struct address_space *mapping = file->f_mapping; __filemap_fdatawait_range(mapping, start_byte, end_byte); return file_check_and_advance_wb_err(file); } EXPORT_SYMBOL(file_fdatawait_range); /** * filemap_fdatawait_keep_errors - wait for writeback without clearing errors * @mapping: address space structure to wait for * * Walk the list of under-writeback pages of the given address space * and wait for all of them. Unlike filemap_fdatawait(), this function * does not clear error status of the address space. * * Use this function if callers don't handle errors themselves. Expected * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), * fsfreeze(8) * * Return: error status of the address space. */ int filemap_fdatawait_keep_errors(struct address_space *mapping) { __filemap_fdatawait_range(mapping, 0, LLONG_MAX); return filemap_check_and_keep_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_keep_errors); /* Returns true if writeback might be needed or already in progress. */ static bool mapping_needs_writeback(struct address_space *mapping) { return mapping->nrpages; } bool filemap_range_has_writeback(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); pgoff_t max = end_byte >> PAGE_SHIFT; struct folio *folio; if (end_byte < start_byte) return false; rcu_read_lock(); xas_for_each(&xas, folio, max) { if (xas_retry(&xas, folio)) continue; if (xa_is_value(folio)) continue; if (folio_test_dirty(folio) || folio_test_locked(folio) || folio_test_writeback(folio)) break; } rcu_read_unlock(); return folio != NULL; } EXPORT_SYMBOL_GPL(filemap_range_has_writeback); /** * filemap_write_and_wait_range - write out & wait on a file range * @mapping: the address_space for the pages * @lstart: offset in bytes where the range starts * @lend: offset in bytes where the range ends (inclusive) * * Write out and wait upon file offsets lstart->lend, inclusive. * * Note that @lend is inclusive (describes the last byte to be written) so * that this function can be used to write to the very end-of-file (end = -1). * * Return: error status of the address space. */ int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend) { int err = 0, err2; if (lend < lstart) return 0; if (mapping_needs_writeback(mapping)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); /* * Even if the above returned error, the pages may be * written partially (e.g. -ENOSPC), so we wait for it. * But the -EIO is special case, it may indicate the worst * thing (e.g. bug) happened, so we avoid waiting for it. */ if (err != -EIO) __filemap_fdatawait_range(mapping, lstart, lend); } err2 = filemap_check_errors(mapping); if (!err) err = err2; return err; } EXPORT_SYMBOL(filemap_write_and_wait_range); void __filemap_set_wb_err(struct address_space *mapping, int err) { errseq_t eseq = errseq_set(&mapping->wb_err, err); trace_filemap_set_wb_err(mapping, eseq); } EXPORT_SYMBOL(__filemap_set_wb_err); /** * file_check_and_advance_wb_err - report wb error (if any) that was previously * and advance wb_err to current one * @file: struct file on which the error is being reported * * When userland calls fsync (or something like nfsd does the equivalent), we * want to report any writeback errors that occurred since the last fsync (or * since the file was opened if there haven't been any). * * Grab the wb_err from the mapping. If it matches what we have in the file, * then just quickly return 0. The file is all caught up. * * If it doesn't match, then take the mapping value, set the "seen" flag in * it and try to swap it into place. If it works, or another task beat us * to it with the new value, then update the f_wb_err and return the error * portion. The error at this point must be reported via proper channels * (a'la fsync, or NFS COMMIT operation, etc.). * * While we handle mapping->wb_err with atomic operations, the f_wb_err * value is protected by the f_lock since we must ensure that it reflects * the latest value swapped in for this file descriptor. * * Return: %0 on success, negative error code otherwise. */ int file_check_and_advance_wb_err(struct file *file) { int err = 0; errseq_t old = READ_ONCE(file->f_wb_err); struct address_space *mapping = file->f_mapping; /* Locklessly handle the common case where nothing has changed */ if (errseq_check(&mapping->wb_err, old)) { /* Something changed, must use slow path */ spin_lock(&file->f_lock); old = file->f_wb_err; err = errseq_check_and_advance(&mapping->wb_err, &file->f_wb_err); trace_file_check_and_advance_wb_err(file, old); spin_unlock(&file->f_lock); } /* * We're mostly using this function as a drop in replacement for * filemap_check_errors. Clear AS_EIO/AS_ENOSPC to emulate the effect * that the legacy code would have had on these flags. */ clear_bit(AS_EIO, &mapping->flags); clear_bit(AS_ENOSPC, &mapping->flags); return err; } EXPORT_SYMBOL(file_check_and_advance_wb_err); /** * file_write_and_wait_range - write out & wait on a file range * @file: file pointing to address_space with pages * @lstart: offset in bytes where the range starts * @lend: offset in bytes where the range ends (inclusive) * * Write out and wait upon file offsets lstart->lend, inclusive. * * Note that @lend is inclusive (describes the last byte to be written) so * that this function can be used to write to the very end-of-file (end = -1). * * After writing out and waiting on the data, we check and advance the * f_wb_err cursor to the latest value, and return any errors detected there. * * Return: %0 on success, negative error code otherwise. */ int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend) { int err = 0, err2; struct address_space *mapping = file->f_mapping; if (lend < lstart) return 0; if (mapping_needs_writeback(mapping)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); /* See comment of filemap_write_and_wait() */ if (err != -EIO) __filemap_fdatawait_range(mapping, lstart, lend); } err2 = file_check_and_advance_wb_err(file); if (!err) err = err2; return err; } EXPORT_SYMBOL(file_write_and_wait_range); /** * replace_page_cache_folio - replace a pagecache folio with a new one * @old: folio to be replaced * @new: folio to replace with * * This function replaces a folio in the pagecache with a new one. On * success it acquires the pagecache reference for the new folio and * drops it for the old folio. Both the old and new folios must be * locked. This function does not add the new folio to the LRU, the * caller must do that. * * The remove + add is atomic. This function cannot fail. */ void replace_page_cache_folio(struct folio *old, struct folio *new) { struct address_space *mapping = old->mapping; void (*free_folio)(struct folio *) = mapping->a_ops->free_folio; pgoff_t offset = old->index; XA_STATE(xas, &mapping->i_pages, offset); VM_BUG_ON_FOLIO(!folio_test_locked(old), old); VM_BUG_ON_FOLIO(!folio_test_locked(new), new); VM_BUG_ON_FOLIO(new->mapping, new); folio_get(new); new->mapping = mapping; new->index = offset; mem_cgroup_replace_folio(old, new); xas_lock_irq(&xas); xas_store(&xas, new); old->mapping = NULL; /* hugetlb pages do not participate in page cache accounting. */ if (!folio_test_hugetlb(old)) __lruvec_stat_sub_folio(old, NR_FILE_PAGES); if (!folio_test_hugetlb(new)) __lruvec_stat_add_folio(new, NR_FILE_PAGES); if (folio_test_swapbacked(old)) __lruvec_stat_sub_folio(old, NR_SHMEM); if (folio_test_swapbacked(new)) __lruvec_stat_add_folio(new, NR_SHMEM); xas_unlock_irq(&xas); if (free_folio) free_folio(old); folio_put(old); } EXPORT_SYMBOL_GPL(replace_page_cache_folio); noinline int __filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp) { XA_STATE(xas, &mapping->i_pages, index); void *alloced_shadow = NULL; int alloced_order = 0; bool huge; long nr; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio); VM_BUG_ON_FOLIO(folio_order(folio) < mapping_min_folio_order(mapping), folio); mapping_set_update(&xas, mapping); VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio); xas_set_order(&xas, index, folio_order(folio)); huge = folio_test_hugetlb(folio); nr = folio_nr_pages(folio); gfp &= GFP_RECLAIM_MASK; folio_ref_add(folio, nr); folio->mapping = mapping; folio->index = xas.xa_index; for (;;) { int order = -1, split_order = 0; void *entry, *old = NULL; xas_lock_irq(&xas); xas_for_each_conflict(&xas, entry) { old = entry; if (!xa_is_value(entry)) { xas_set_err(&xas, -EEXIST); goto unlock; } /* * If a larger entry exists, * it will be the first and only entry iterated. */ if (order == -1) order = xas_get_order(&xas); } /* entry may have changed before we re-acquire the lock */ if (alloced_order && (old != alloced_shadow || order != alloced_order)) { xas_destroy(&xas); alloced_order = 0; } if (old) { if (order > 0 && order > folio_order(folio)) { /* How to handle large swap entries? */ BUG_ON(shmem_mapping(mapping)); if (!alloced_order) { split_order = order; goto unlock; } xas_split(&xas, old, order); xas_reset(&xas); } if (shadowp) *shadowp = old; } xas_store(&xas, folio); if (xas_error(&xas)) goto unlock; mapping->nrpages += nr; /* hugetlb pages do not participate in page cache accounting */ if (!huge) { __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr); if (folio_test_pmd_mappable(folio)) __lruvec_stat_mod_folio(folio, NR_FILE_THPS, nr); } unlock: xas_unlock_irq(&xas); /* split needed, alloc here and retry. */ if (split_order) { xas_split_alloc(&xas, old, split_order, gfp); if (xas_error(&xas)) goto error; alloced_shadow = old; alloced_order = split_order; xas_reset(&xas); continue; } if (!xas_nomem(&xas, gfp)) break; } if (xas_error(&xas)) goto error; trace_mm_filemap_add_to_page_cache(folio); return 0; error: folio->mapping = NULL; /* Leave page->index set: truncation relies upon it */ folio_put_refs(folio, nr); return xas_error(&xas); } ALLOW_ERROR_INJECTION(__filemap_add_folio, ERRNO); int filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp) { void *shadow = NULL; int ret; ret = mem_cgroup_charge(folio, NULL, gfp); if (ret) return ret; __folio_set_locked(folio); ret = __filemap_add_folio(mapping, folio, index, gfp, &shadow); if (unlikely(ret)) { mem_cgroup_uncharge(folio); __folio_clear_locked(folio); } else { /* * The folio might have been evicted from cache only * recently, in which case it should be activated like * any other repeatedly accessed folio. * The exception is folios getting rewritten; evicting other * data from the working set, only to cache data that will * get overwritten with something else, is a waste of memory. */ WARN_ON_ONCE(folio_test_active(folio)); if (!(gfp & __GFP_WRITE) && shadow) workingset_refault(folio, shadow); folio_add_lru(folio); } return ret; } EXPORT_SYMBOL_GPL(filemap_add_folio); #ifdef CONFIG_NUMA struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order) { int n; struct folio *folio; if (cpuset_do_page_mem_spread()) { unsigned int cpuset_mems_cookie; do { cpuset_mems_cookie = read_mems_allowed_begin(); n = cpuset_mem_spread_node(); folio = __folio_alloc_node_noprof(gfp, order, n); } while (!folio && read_mems_allowed_retry(cpuset_mems_cookie)); return folio; } return folio_alloc_noprof(gfp, order); } EXPORT_SYMBOL(filemap_alloc_folio_noprof); #endif /* * filemap_invalidate_lock_two - lock invalidate_lock for two mappings * * Lock exclusively invalidate_lock of any passed mapping that is not NULL. * * @mapping1: the first mapping to lock * @mapping2: the second mapping to lock */ void filemap_invalidate_lock_two(struct address_space *mapping1, struct address_space *mapping2) { if (mapping1 > mapping2) swap(mapping1, mapping2); if (mapping1) down_write(&mapping1->invalidate_lock); if (mapping2 && mapping1 != mapping2) down_write_nested(&mapping2->invalidate_lock, 1); } EXPORT_SYMBOL(filemap_invalidate_lock_two); /* * filemap_invalidate_unlock_two - unlock invalidate_lock for two mappings * * Unlock exclusive invalidate_lock of any passed mapping that is not NULL. * * @mapping1: the first mapping to unlock * @mapping2: the second mapping to unlock */ void filemap_invalidate_unlock_two(struct address_space *mapping1, struct address_space *mapping2) { if (mapping1) up_write(&mapping1->invalidate_lock); if (mapping2 && mapping1 != mapping2) up_write(&mapping2->invalidate_lock); } EXPORT_SYMBOL(filemap_invalidate_unlock_two); /* * In order to wait for pages to become available there must be * waitqueues associated with pages. By using a hash table of * waitqueues where the bucket discipline is to maintain all * waiters on the same queue and wake all when any of the pages * become available, and for the woken contexts to check to be * sure the appropriate page became available, this saves space * at a cost of "thundering herd" phenomena during rare hash * collisions. */ #define PAGE_WAIT_TABLE_BITS 8 #define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS) static wait_queue_head_t folio_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned; static wait_queue_head_t *folio_waitqueue(struct folio *folio) { return &folio_wait_table[hash_ptr(folio, PAGE_WAIT_TABLE_BITS)]; } void __init pagecache_init(void) { int i; for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++) init_waitqueue_head(&folio_wait_table[i]); page_writeback_init(); } /* * The page wait code treats the "wait->flags" somewhat unusually, because * we have multiple different kinds of waits, not just the usual "exclusive" * one. * * We have: * * (a) no special bits set: * * We're just waiting for the bit to be released, and when a waker * calls the wakeup function, we set WQ_FLAG_WOKEN and wake it up, * and remove it from the wait queue. * * Simple and straightforward. * * (b) WQ_FLAG_EXCLUSIVE: * * The waiter is waiting to get the lock, and only one waiter should * be woken up to avoid any thundering herd behavior. We'll set the * WQ_FLAG_WOKEN bit, wake it up, and remove it from the wait queue. * * This is the traditional exclusive wait. * * (c) WQ_FLAG_EXCLUSIVE | WQ_FLAG_CUSTOM: * * The waiter is waiting to get the bit, and additionally wants the * lock to be transferred to it for fair lock behavior. If the lock * cannot be taken, we stop walking the wait queue without waking * the waiter. * * This is the "fair lock handoff" case, and in addition to setting * WQ_FLAG_WOKEN, we set WQ_FLAG_DONE to let the waiter easily see * that it now has the lock. */ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg) { unsigned int flags; struct wait_page_key *key = arg; struct wait_page_queue *wait_page = container_of(wait, struct wait_page_queue, wait); if (!wake_page_match(wait_page, key)) return 0; /* * If it's a lock handoff wait, we get the bit for it, and * stop walking (and do not wake it up) if we can't. */ flags = wait->flags; if (flags & WQ_FLAG_EXCLUSIVE) { if (test_bit(key->bit_nr, &key->folio->flags)) return -1; if (flags & WQ_FLAG_CUSTOM) { if (test_and_set_bit(key->bit_nr, &key->folio->flags)) return -1; flags |= WQ_FLAG_DONE; } } /* * We are holding the wait-queue lock, but the waiter that * is waiting for this will be checking the flags without * any locking. * * So update the flags atomically, and wake up the waiter * afterwards to avoid any races. This store-release pairs * with the load-acquire in folio_wait_bit_common(). */ smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN); wake_up_state(wait->private, mode); /* * Ok, we have successfully done what we're waiting for, * and we can unconditionally remove the wait entry. * * Note that this pairs with the "finish_wait()" in the * waiter, and has to be the absolute last thing we do. * After this list_del_init(&wait->entry) the wait entry * might be de-allocated and the process might even have * exited. */ list_del_init_careful(&wait->entry); return (flags & WQ_FLAG_EXCLUSIVE) != 0; } static void folio_wake_bit(struct folio *folio, int bit_nr) { wait_queue_head_t *q = folio_waitqueue(folio); struct wait_page_key key; unsigned long flags; key.folio = folio; key.bit_nr = bit_nr; key.page_match = 0; spin_lock_irqsave(&q->lock, flags); __wake_up_locked_key(q, TASK_NORMAL, &key); /* * It's possible to miss clearing waiters here, when we woke our page * waiters, but the hashed waitqueue has waiters for other pages on it. * That's okay, it's a rare case. The next waker will clear it. * * Note that, depending on the page pool (buddy, hugetlb, ZONE_DEVICE, * other), the flag may be cleared in the course of freeing the page; * but that is not required for correctness. */ if (!waitqueue_active(q) || !key.page_match) folio_clear_waiters(folio); spin_unlock_irqrestore(&q->lock, flags); } /* * A choice of three behaviors for folio_wait_bit_common(): */ enum behavior { EXCLUSIVE, /* Hold ref to page and take the bit when woken, like * __folio_lock() waiting on then setting PG_locked. */ SHARED, /* Hold ref to page and check the bit when woken, like * folio_wait_writeback() waiting on PG_writeback. */ DROP, /* Drop ref to page before wait, no check when woken, * like folio_put_wait_locked() on PG_locked. */ }; /* * Attempt to check (or get) the folio flag, and mark us done * if successful. */ static inline bool folio_trylock_flag(struct folio *folio, int bit_nr, struct wait_queue_entry *wait) { if (wait->flags & WQ_FLAG_EXCLUSIVE) { if (test_and_set_bit(bit_nr, &folio->flags)) return false; } else if (test_bit(bit_nr, &folio->flags)) return false; wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE; return true; } /* How many times do we accept lock stealing from under a waiter? */ int sysctl_page_lock_unfairness = 5; static inline int folio_wait_bit_common(struct folio *folio, int bit_nr, int state, enum behavior behavior) { wait_queue_head_t *q = folio_waitqueue(folio); int unfairness = sysctl_page_lock_unfairness; struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; bool thrashing = false; unsigned long pflags; bool in_thrashing; if (bit_nr == PG_locked && !folio_test_uptodate(folio) && folio_test_workingset(folio)) { delayacct_thrashing_start(&in_thrashing); psi_memstall_enter(&pflags); thrashing = true; } init_wait(wait); wait->func = wake_page_function; wait_page.folio = folio; wait_page.bit_nr = bit_nr; repeat: wait->flags = 0; if (behavior == EXCLUSIVE) { wait->flags = WQ_FLAG_EXCLUSIVE; if (--unfairness < 0) wait->flags |= WQ_FLAG_CUSTOM; } /* * Do one last check whether we can get the * page bit synchronously. * * Do the folio_set_waiters() marking before that * to let any waker we _just_ missed know they * need to wake us up (otherwise they'll never * even go to the slow case that looks at the * page queue), and add ourselves to the wait * queue if we need to sleep. * * This part needs to be done under the queue * lock to avoid races. */ spin_lock_irq(&q->lock); folio_set_waiters(folio); if (!folio_trylock_flag(folio, bit_nr, wait)) __add_wait_queue_entry_tail(q, wait); spin_unlock_irq(&q->lock); /* * From now on, all the logic will be based on * the WQ_FLAG_WOKEN and WQ_FLAG_DONE flag, to * see whether the page bit testing has already * been done by the wake function. * * We can drop our reference to the folio. */ if (behavior == DROP) folio_put(folio); /* * Note that until the "finish_wait()", or until * we see the WQ_FLAG_WOKEN flag, we need to * be very careful with the 'wait->flags', because * we may race with a waker that sets them. */ for (;;) { unsigned int flags; set_current_state(state); /* Loop until we've been woken or interrupted */ flags = smp_load_acquire(&wait->flags); if (!(flags & WQ_FLAG_WOKEN)) { if (signal_pending_state(state, current)) break; io_schedule(); continue; } /* If we were non-exclusive, we're done */ if (behavior != EXCLUSIVE) break; /* If the waker got the lock for us, we're done */ if (flags & WQ_FLAG_DONE) break; /* * Otherwise, if we're getting the lock, we need to * try to get it ourselves. * * And if that fails, we'll have to retry this all. */ if (unlikely(test_and_set_bit(bit_nr, folio_flags(folio, 0)))) goto repeat; wait->flags |= WQ_FLAG_DONE; break; } /* * If a signal happened, this 'finish_wait()' may remove the last * waiter from the wait-queues, but the folio waiters bit will remain * set. That's ok. The next wakeup will take care of it, and trying * to do it here would be difficult and prone to races. */ finish_wait(q, wait); if (thrashing) { delayacct_thrashing_end(&in_thrashing); psi_memstall_leave(&pflags); } /* * NOTE! The wait->flags weren't stable until we've done the * 'finish_wait()', and we could have exited the loop above due * to a signal, and had a wakeup event happen after the signal * test but before the 'finish_wait()'. * * So only after the finish_wait() can we reliably determine * if we got woken up or not, so we can now figure out the final * return value based on that state without races. * * Also note that WQ_FLAG_WOKEN is sufficient for a non-exclusive * waiter, but an exclusive one requires WQ_FLAG_DONE. */ if (behavior == EXCLUSIVE) return wait->flags & WQ_FLAG_DONE ? 0 : -EINTR; return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR; } #ifdef CONFIG_MIGRATION /** * migration_entry_wait_on_locked - Wait for a migration entry to be removed * @entry: migration swap entry. * @ptl: already locked ptl. This function will drop the lock. * * Wait for a migration entry referencing the given page to be removed. This is * equivalent to put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE) except * this can be called without taking a reference on the page. Instead this * should be called while holding the ptl for the migration entry referencing * the page. * * Returns after unlocking the ptl. * * This follows the same logic as folio_wait_bit_common() so see the comments * there. */ void migration_entry_wait_on_locked(swp_entry_t entry, spinlock_t *ptl) __releases(ptl) { struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; bool thrashing = false; unsigned long pflags; bool in_thrashing; wait_queue_head_t *q; struct folio *folio = pfn_swap_entry_folio(entry); q = folio_waitqueue(folio); if (!folio_test_uptodate(folio) && folio_test_workingset(folio)) { delayacct_thrashing_start(&in_thrashing); psi_memstall_enter(&pflags); thrashing = true; } init_wait(wait); wait->func = wake_page_function; wait_page.folio = folio; wait_page.bit_nr = PG_locked; wait->flags = 0; spin_lock_irq(&q->lock); folio_set_waiters(folio); if (!folio_trylock_flag(folio, PG_locked, wait)) __add_wait_queue_entry_tail(q, wait); spin_unlock_irq(&q->lock); /* * If a migration entry exists for the page the migration path must hold * a valid reference to the page, and it must take the ptl to remove the * migration entry. So the page is valid until the ptl is dropped. */ spin_unlock(ptl); for (;;) { unsigned int flags; set_current_state(TASK_UNINTERRUPTIBLE); /* Loop until we've been woken or interrupted */ flags = smp_load_acquire(&wait->flags); if (!(flags & WQ_FLAG_WOKEN)) { if (signal_pending_state(TASK_UNINTERRUPTIBLE, current)) break; io_schedule(); continue; } break; } finish_wait(q, wait); if (thrashing) { delayacct_thrashing_end(&in_thrashing); psi_memstall_leave(&pflags); } } #endif void folio_wait_bit(struct folio *folio, int bit_nr) { folio_wait_bit_common(folio, bit_nr, TASK_UNINTERRUPTIBLE, SHARED); } EXPORT_SYMBOL(folio_wait_bit); int folio_wait_bit_killable(struct folio *folio, int bit_nr) { return folio_wait_bit_common(folio, bit_nr, TASK_KILLABLE, SHARED); } EXPORT_SYMBOL(folio_wait_bit_killable); /** * folio_put_wait_locked - Drop a reference and wait for it to be unlocked * @folio: The folio to wait for. * @state: The sleep state (TASK_KILLABLE, TASK_UNINTERRUPTIBLE, etc). * * The caller should hold a reference on @folio. They expect the page to * become unlocked relatively soon, but do not wish to hold up migration * (for example) by holding the reference while waiting for the folio to * come unlocked. After this function returns, the caller should not * dereference @folio. * * Return: 0 if the folio was unlocked or -EINTR if interrupted by a signal. */ static int folio_put_wait_locked(struct folio *folio, int state) { return folio_wait_bit_common(folio, PG_locked, state, DROP); } /** * folio_add_wait_queue - Add an arbitrary waiter to a folio's wait queue * @folio: Folio defining the wait queue of interest * @waiter: Waiter to add to the queue * * Add an arbitrary @waiter to the wait queue for the nominated @folio. */ void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter) { wait_queue_head_t *q = folio_waitqueue(folio); unsigned long flags; spin_lock_irqsave(&q->lock, flags); __add_wait_queue_entry_tail(q, waiter); folio_set_waiters(folio); spin_unlock_irqrestore(&q->lock, flags); } EXPORT_SYMBOL_GPL(folio_add_wait_queue); /** * folio_unlock - Unlock a locked folio. * @folio: The folio. * * Unlocks the folio and wakes up any thread sleeping on the page lock. * * Context: May be called from interrupt or process context. May not be * called from NMI context. */ void folio_unlock(struct folio *folio) { /* Bit 7 allows x86 to check the byte's sign bit */ BUILD_BUG_ON(PG_waiters != 7); BUILD_BUG_ON(PG_locked > 7); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (folio_xor_flags_has_waiters(folio, 1 << PG_locked)) folio_wake_bit(folio, PG_locked); } EXPORT_SYMBOL(folio_unlock); /** * folio_end_read - End read on a folio. * @folio: The folio. * @success: True if all reads completed successfully. * * When all reads against a folio have completed, filesystems should * call this function to let the pagecache know that no more reads * are outstanding. This will unlock the folio and wake up any thread * sleeping on the lock. The folio will also be marked uptodate if all * reads succeeded. * * Context: May be called from interrupt or process context. May not be * called from NMI context. */ void folio_end_read(struct folio *folio, bool success) { unsigned long mask = 1 << PG_locked; /* Must be in bottom byte for x86 to work */ BUILD_BUG_ON(PG_uptodate > 7); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_uptodate(folio), folio); if (likely(success)) mask |= 1 << PG_uptodate; if (folio_xor_flags_has_waiters(folio, mask)) folio_wake_bit(folio, PG_locked); } EXPORT_SYMBOL(folio_end_read); /** * folio_end_private_2 - Clear PG_private_2 and wake any waiters. * @folio: The folio. * * Clear the PG_private_2 bit on a folio and wake up any sleepers waiting for * it. The folio reference held for PG_private_2 being set is released. * * This is, for example, used when a netfs folio is being written to a local * disk cache, thereby allowing writes to the cache for the same folio to be * serialised. */ void folio_end_private_2(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_private_2(folio), folio); clear_bit_unlock(PG_private_2, folio_flags(folio, 0)); folio_wake_bit(folio, PG_private_2); folio_put(folio); } EXPORT_SYMBOL(folio_end_private_2); /** * folio_wait_private_2 - Wait for PG_private_2 to be cleared on a folio. * @folio: The folio to wait on. * * Wait for PG_private_2 to be cleared on a folio. */ void folio_wait_private_2(struct folio *folio) { while (folio_test_private_2(folio)) folio_wait_bit(folio, PG_private_2); } EXPORT_SYMBOL(folio_wait_private_2); /** * folio_wait_private_2_killable - Wait for PG_private_2 to be cleared on a folio. * @folio: The folio to wait on. * * Wait for PG_private_2 to be cleared on a folio or until a fatal signal is * received by the calling task. * * Return: * - 0 if successful. * - -EINTR if a fatal signal was encountered. */ int folio_wait_private_2_killable(struct folio *folio) { int ret = 0; while (folio_test_private_2(folio)) { ret = folio_wait_bit_killable(folio, PG_private_2); if (ret < 0) break; } return ret; } EXPORT_SYMBOL(folio_wait_private_2_killable); /** * folio_end_writeback - End writeback against a folio. * @folio: The folio. * * The folio must actually be under writeback. * * Context: May be called from process or interrupt context. */ void folio_end_writeback(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_writeback(folio), folio); /* * folio_test_clear_reclaim() could be used here but it is an * atomic operation and overkill in this particular case. Failing * to shuffle a folio marked for immediate reclaim is too mild * a gain to justify taking an atomic operation penalty at the * end of every folio writeback. */ if (folio_test_reclaim(folio)) { folio_clear_reclaim(folio); folio_rotate_reclaimable(folio); } /* * Writeback does not hold a folio reference of its own, relying * on truncation to wait for the clearing of PG_writeback. * But here we must make sure that the folio is not freed and * reused before the folio_wake_bit(). */ folio_get(folio); if (__folio_end_writeback(folio)) folio_wake_bit(folio, PG_writeback); acct_reclaim_writeback(folio); folio_put(folio); } EXPORT_SYMBOL(folio_end_writeback); /** * __folio_lock - Get a lock on the folio, assuming we need to sleep to get it. * @folio: The folio to lock */ void __folio_lock(struct folio *folio) { folio_wait_bit_common(folio, PG_locked, TASK_UNINTERRUPTIBLE, EXCLUSIVE); } EXPORT_SYMBOL(__folio_lock); int __folio_lock_killable(struct folio *folio) { return folio_wait_bit_common(folio, PG_locked, TASK_KILLABLE, EXCLUSIVE); } EXPORT_SYMBOL_GPL(__folio_lock_killable); static int __folio_lock_async(struct folio *folio, struct wait_page_queue *wait) { struct wait_queue_head *q = folio_waitqueue(folio); int ret; wait->folio = folio; wait->bit_nr = PG_locked; spin_lock_irq(&q->lock); __add_wait_queue_entry_tail(q, &wait->wait); folio_set_waiters(folio); ret = !folio_trylock(folio); /* * If we were successful now, we know we're still on the * waitqueue as we're still under the lock. This means it's * safe to remove and return success, we know the callback * isn't going to trigger. */ if (!ret) __remove_wait_queue(q, &wait->wait); else ret = -EIOCBQUEUED; spin_unlock_irq(&q->lock); return ret; } /* * Return values: * 0 - folio is locked. * non-zero - folio is not locked. * mmap_lock or per-VMA lock has been released (mmap_read_unlock() or * vma_end_read()), unless flags had both FAULT_FLAG_ALLOW_RETRY and * FAULT_FLAG_RETRY_NOWAIT set, in which case the lock is still held. * * If neither ALLOW_RETRY nor KILLABLE are set, will always return 0 * with the folio locked and the mmap_lock/per-VMA lock is left unperturbed. */ vm_fault_t __folio_lock_or_retry(struct folio *folio, struct vm_fault *vmf) { unsigned int flags = vmf->flags; if (fault_flag_allow_retry_first(flags)) { /* * CAUTION! In this case, mmap_lock/per-VMA lock is not * released even though returning VM_FAULT_RETRY. */ if (flags & FAULT_FLAG_RETRY_NOWAIT) return VM_FAULT_RETRY; release_fault_lock(vmf); if (flags & FAULT_FLAG_KILLABLE) folio_wait_locked_killable(folio); else folio_wait_locked(folio); return VM_FAULT_RETRY; } if (flags & FAULT_FLAG_KILLABLE) { bool ret; ret = __folio_lock_killable(folio); if (ret) { release_fault_lock(vmf); return VM_FAULT_RETRY; } } else { __folio_lock(folio); } return 0; } /** * page_cache_next_miss() - Find the next gap in the page cache. * @mapping: Mapping. * @index: Index. * @max_scan: Maximum range to search. * * Search the range [index, min(index + max_scan - 1, ULONG_MAX)] for the * gap with the lowest index. * * This function may be called under the rcu_read_lock. However, this will * not atomically search a snapshot of the cache at a single point in time. * For example, if a gap is created at index 5, then subsequently a gap is * created at index 10, page_cache_next_miss covering both indices may * return 10 if called under the rcu_read_lock. * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'return - index >= max_scan' will be true). * In the rare case of index wrap-around, 0 will be returned. */ pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { XA_STATE(xas, &mapping->i_pages, index); while (max_scan--) { void *entry = xas_next(&xas); if (!entry || xa_is_value(entry)) return xas.xa_index; if (xas.xa_index == 0) return 0; } return index + max_scan; } EXPORT_SYMBOL(page_cache_next_miss); /** * page_cache_prev_miss() - Find the previous gap in the page cache. * @mapping: Mapping. * @index: Index. * @max_scan: Maximum range to search. * * Search the range [max(index - max_scan + 1, 0), index] for the * gap with the highest index. * * This function may be called under the rcu_read_lock. However, this will * not atomically search a snapshot of the cache at a single point in time. * For example, if a gap is created at index 10, then subsequently a gap is * created at index 5, page_cache_prev_miss() covering both indices may * return 5 if called under the rcu_read_lock. * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'index - return >= max_scan' will be true). * In the rare case of wrap-around, ULONG_MAX will be returned. */ pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { XA_STATE(xas, &mapping->i_pages, index); while (max_scan--) { void *entry = xas_prev(&xas); if (!entry || xa_is_value(entry)) break; if (xas.xa_index == ULONG_MAX) break; } return xas.xa_index; } EXPORT_SYMBOL(page_cache_prev_miss); /* * Lockless page cache protocol: * On the lookup side: * 1. Load the folio from i_pages * 2. Increment the refcount if it's not zero * 3. If the folio is not found by xas_reload(), put the refcount and retry * * On the removal side: * A. Freeze the page (by zeroing the refcount if nobody else has a reference) * B. Remove the page from i_pages * C. Return the page to the page allocator * * This means that any page may have its reference count temporarily * increased by a speculative page cache (or GUP-fast) lookup as it can * be allocated by another user before the RCU grace period expires. * Because the refcount temporarily acquired here may end up being the * last refcount on the page, any page allocation must be freeable by * folio_put(). */ /* * filemap_get_entry - Get a page cache entry. * @mapping: the address_space to search * @index: The page cache index. * * Looks up the page cache entry at @mapping & @index. If it is a folio, * it is returned with an increased refcount. If it is a shadow entry * of a previously evicted folio, or a swap entry from shmem/tmpfs, * it is returned without further action. * * Return: The folio, swap or shadow entry, %NULL if nothing is found. */ void *filemap_get_entry(struct address_space *mapping, pgoff_t index) { XA_STATE(xas, &mapping->i_pages, index); struct folio *folio; rcu_read_lock(); repeat: xas_reset(&xas); folio = xas_load(&xas); if (xas_retry(&xas, folio)) goto repeat; /* * A shadow entry of a recently evicted page, or a swap entry from * shmem/tmpfs. Return it without attempting to raise page count. */ if (!folio || xa_is_value(folio)) goto out; if (!folio_try_get(folio)) goto repeat; if (unlikely(folio != xas_reload(&xas))) { folio_put(folio); goto repeat; } out: rcu_read_unlock(); return folio; } /** * __filemap_get_folio - Find and get a reference to a folio. * @mapping: The address_space to search. * @index: The page index. * @fgp_flags: %FGP flags modify how the folio is returned. * @gfp: Memory allocation flags to use if %FGP_CREAT is specified. * * Looks up the page cache entry at @mapping & @index. * * If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even * if the %GFP flags specified for %FGP_CREAT are atomic. * * If this function returns a folio, it is returned with an increased refcount. * * Return: The found folio or an ERR_PTR() otherwise. */ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, fgf_t fgp_flags, gfp_t gfp) { struct folio *folio; repeat: folio = filemap_get_entry(mapping, index); if (xa_is_value(folio)) folio = NULL; if (!folio) goto no_page; if (fgp_flags & FGP_LOCK) { if (fgp_flags & FGP_NOWAIT) { if (!folio_trylock(folio)) { folio_put(folio); return ERR_PTR(-EAGAIN); } } else { folio_lock(folio); } /* Has the page been truncated? */ if (unlikely(folio->mapping != mapping)) { folio_unlock(folio); folio_put(folio); goto repeat; } VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); } if (fgp_flags & FGP_ACCESSED) folio_mark_accessed(folio); else if (fgp_flags & FGP_WRITE) { /* Clear idle flag for buffer write */ if (folio_test_idle(folio)) folio_clear_idle(folio); } if (fgp_flags & FGP_STABLE) folio_wait_stable(folio); no_page: if (!folio && (fgp_flags & FGP_CREAT)) { unsigned int min_order = mapping_min_folio_order(mapping); unsigned int order = max(min_order, FGF_GET_ORDER(fgp_flags)); int err; index = mapping_align_index(mapping, index); if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping)) gfp |= __GFP_WRITE; if (fgp_flags & FGP_NOFS) gfp &= ~__GFP_FS; if (fgp_flags & FGP_NOWAIT) { gfp &= ~GFP_KERNEL; gfp |= GFP_NOWAIT | __GFP_NOWARN; } if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP)))) fgp_flags |= FGP_LOCK; if (order > mapping_max_folio_order(mapping)) order = mapping_max_folio_order(mapping); /* If we're not aligned, allocate a smaller folio */ if (index & ((1UL << order) - 1)) order = __ffs(index); do { gfp_t alloc_gfp = gfp; err = -ENOMEM; if (order > min_order) alloc_gfp |= __GFP_NORETRY | __GFP_NOWARN; folio = filemap_alloc_folio(alloc_gfp, order); if (!folio) continue; /* Init accessed so avoid atomic mark_page_accessed later */ if (fgp_flags & FGP_ACCESSED) __folio_set_referenced(folio); err = filemap_add_folio(mapping, folio, index, gfp); if (!err) break; folio_put(folio); folio = NULL; } while (order-- > min_order); if (err == -EEXIST) goto repeat; if (err) return ERR_PTR(err); /* * filemap_add_folio locks the page, and for mmap * we expect an unlocked page. */ if (folio && (fgp_flags & FGP_FOR_MMAP)) folio_unlock(folio); } if (!folio) return ERR_PTR(-ENOENT); return folio; } EXPORT_SYMBOL(__filemap_get_folio); static inline struct folio *find_get_entry(struct xa_state *xas, pgoff_t max, xa_mark_t mark) { struct folio *folio; retry: if (mark == XA_PRESENT) folio = xas_find(xas, max); else folio = xas_find_marked(xas, max, mark); if (xas_retry(xas, folio)) goto retry; /* * A shadow entry of a recently evicted page, a swap * entry from shmem/tmpfs or a DAX entry. Return it * without attempting to raise page count. */ if (!folio || xa_is_value(folio)) return folio; if (!folio_try_get(folio)) goto reset; if (unlikely(folio != xas_reload(xas))) { folio_put(folio); goto reset; } return folio; reset: xas_reset(xas); goto retry; } /** * find_get_entries - gang pagecache lookup * @mapping: The address_space to search * @start: The starting page cache index * @end: The final page index (inclusive). * @fbatch: Where the resulting entries are placed. * @indices: The cache indices corresponding to the entries in @entries * * find_get_entries() will search for and return a batch of entries in * the mapping. The entries are placed in @fbatch. find_get_entries() * takes a reference on any actual folios it returns. * * The entries have ascending indexes. The indices may not be consecutive * due to not-present entries or large folios. * * Any shadow entries of evicted folios, or swap entries from * shmem/tmpfs, are included in the returned array. * * Return: The number of entries which were found. */ unsigned find_get_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, *start); struct folio *folio; rcu_read_lock(); while ((folio = find_get_entry(&xas, end, XA_PRESENT)) != NULL) { indices[fbatch->nr] = xas.xa_index; if (!folio_batch_add(fbatch, folio)) break; } if (folio_batch_count(fbatch)) { unsigned long nr; int idx = folio_batch_count(fbatch) - 1; folio = fbatch->folios[idx]; if (!xa_is_value(folio)) nr = folio_nr_pages(folio); else nr = 1 << xa_get_order(&mapping->i_pages, indices[idx]); *start = round_down(indices[idx] + nr, nr); } rcu_read_unlock(); return folio_batch_count(fbatch); } /** * find_lock_entries - Find a batch of pagecache entries. * @mapping: The address_space to search. * @start: The starting page cache index. * @end: The final page index (inclusive). * @fbatch: Where the resulting entries are placed. * @indices: The cache indices of the entries in @fbatch. * * find_lock_entries() will return a batch of entries from @mapping. * Swap, shadow and DAX entries are included. Folios are returned * locked and with an incremented refcount. Folios which are locked * by somebody else or under writeback are skipped. Folios which are * partially outside the range are not returned. * * The entries have ascending indexes. The indices may not be consecutive * due to not-present entries, large folios, folios which could not be * locked or folios under writeback. * * Return: The number of entries which were found. */ unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, *start); struct folio *folio; rcu_read_lock(); while ((folio = find_get_entry(&xas, end, XA_PRESENT))) { unsigned long base; unsigned long nr; if (!xa_is_value(folio)) { nr = folio_nr_pages(folio); base = folio->index; /* Omit large folio which begins before the start */ if (base < *start) goto put; /* Omit large folio which extends beyond the end */ if (base + nr - 1 > end) goto put; if (!folio_trylock(folio)) goto put; if (folio->mapping != mapping || folio_test_writeback(folio)) goto unlock; VM_BUG_ON_FOLIO(!folio_contains(folio, xas.xa_index), folio); } else { nr = 1 << xas_get_order(&xas); base = xas.xa_index & ~(nr - 1); /* Omit order>0 value which begins before the start */ if (base < *start) continue; /* Omit order>0 value which extends beyond the end */ if (base + nr - 1 > end) break; } /* Update start now so that last update is correct on return */ *start = base + nr; indices[fbatch->nr] = xas.xa_index; if (!folio_batch_add(fbatch, folio)) break; continue; unlock: folio_unlock(folio); put: folio_put(folio); } rcu_read_unlock(); return folio_batch_count(fbatch); } /** * filemap_get_folios - Get a batch of folios * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) * @fbatch: The batch to fill. * * Search for and return a batch of folios in the mapping starting at * index @start and up to index @end (inclusive). The folios are returned * in @fbatch with an elevated reference count. * * Return: The number of folios which were found. * We also update @start to index the next folio for the traversal. */ unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch) { return filemap_get_folios_tag(mapping, start, end, XA_PRESENT, fbatch); } EXPORT_SYMBOL(filemap_get_folios); /** * filemap_get_folios_contig - Get a batch of contiguous folios * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) * @fbatch: The batch to fill * * filemap_get_folios_contig() works exactly like filemap_get_folios(), * except the returned folios are guaranteed to be contiguous. This may * not return all contiguous folios if the batch gets filled up. * * Return: The number of folios found. * Also update @start to be positioned for traversal of the next folio. */ unsigned filemap_get_folios_contig(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, *start); unsigned long nr; struct folio *folio; rcu_read_lock(); for (folio = xas_load(&xas); folio && xas.xa_index <= end; folio = xas_next(&xas)) { if (xas_retry(&xas, folio)) continue; /* * If the entry has been swapped out, we can stop looking. * No current caller is looking for DAX entries. */ if (xa_is_value(folio)) goto update_start; /* If we landed in the middle of a THP, continue at its end. */ if (xa_is_sibling(folio)) goto update_start; if (!folio_try_get(folio)) goto retry; if (unlikely(folio != xas_reload(&xas))) goto put_folio; if (!folio_batch_add(fbatch, folio)) { nr = folio_nr_pages(folio); *start = folio->index + nr; goto out; } continue; put_folio: folio_put(folio); retry: xas_reset(&xas); } update_start: nr = folio_batch_count(fbatch); if (nr) { folio = fbatch->folios[nr - 1]; *start = folio_next_index(folio); } out: rcu_read_unlock(); return folio_batch_count(fbatch); } EXPORT_SYMBOL(filemap_get_folios_contig); /** * filemap_get_folios_tag - Get a batch of folios matching @tag * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) * @tag: The tag index * @fbatch: The batch to fill * * The first folio may start before @start; if it does, it will contain * @start. The final folio may extend beyond @end; if it does, it will * contain @end. The folios have ascending indices. There may be gaps * between the folios if there are indices which have no folio in the * page cache. If folios are added to or removed from the page cache * while this is running, they may or may not be found by this call. * Only returns folios that are tagged with @tag. * * Return: The number of folios found. * Also update @start to index the next folio for traversal. */ unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start, pgoff_t end, xa_mark_t tag, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, *start); struct folio *folio; rcu_read_lock(); while ((folio = find_get_entry(&xas, end, tag)) != NULL) { /* * Shadow entries should never be tagged, but this iteration * is lockless so there is a window for page reclaim to evict * a page we saw tagged. Skip over it. */ if (xa_is_value(folio)) continue; if (!folio_batch_add(fbatch, folio)) { unsigned long nr = folio_nr_pages(folio); *start = folio->index + nr; goto out; } } /* * We come here when there is no page beyond @end. We take care to not * overflow the index @start as it confuses some of the callers. This * breaks the iteration when there is a page at index -1 but that is * already broke anyway. */ if (end == (pgoff_t)-1) *start = (pgoff_t)-1; else *start = end + 1; out: rcu_read_unlock(); return folio_batch_count(fbatch); } EXPORT_SYMBOL(filemap_get_folios_tag); /* * CD/DVDs are error prone. When a medium error occurs, the driver may fail * a _large_ part of the i/o request. Imagine the worst scenario: * * ---R__________________________________________B__________ * ^ reading here ^ bad block(assume 4k) * * read(R) => miss => readahead(R...B) => media error => frustrating retries * => failing the whole request => read(R) => read(R+1) => * readahead(R+1...B+1) => bang => read(R+2) => read(R+3) => * readahead(R+3...B+2) => bang => read(R+3) => read(R+4) => * readahead(R+4...B+3) => bang => read(R+4) => read(R+5) => ...... * * It is going insane. Fix it by quickly scaling down the readahead size. */ static void shrink_readahead_size_eio(struct file_ra_state *ra) { ra->ra_pages /= 4; } /* * filemap_get_read_batch - Get a batch of folios for read * * Get a batch of folios which represent a contiguous range of bytes in * the file. No exceptional entries will be returned. If @index is in * the middle of a folio, the entire folio will be returned. The last * folio in the batch may have the readahead flag set or the uptodate flag * clear so that the caller can take the appropriate action. */ static void filemap_get_read_batch(struct address_space *mapping, pgoff_t index, pgoff_t max, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, index); struct folio *folio; rcu_read_lock(); for (folio = xas_load(&xas); folio; folio = xas_next(&xas)) { if (xas_retry(&xas, folio)) continue; if (xas.xa_index > max || xa_is_value(folio)) break; if (xa_is_sibling(folio)) break; if (!folio_try_get(folio)) goto retry; if (unlikely(folio != xas_reload(&xas))) goto put_folio; if (!folio_batch_add(fbatch, folio)) break; if (!folio_test_uptodate(folio)) break; if (folio_test_readahead(folio)) break; xas_advance(&xas, folio_next_index(folio) - 1); continue; put_folio: folio_put(folio); retry: xas_reset(&xas); } rcu_read_unlock(); } static int filemap_read_folio(struct file *file, filler_t filler, struct folio *folio) { bool workingset = folio_test_workingset(folio); unsigned long pflags; int error; /* Start the actual read. The read will unlock the page. */ if (unlikely(workingset)) psi_memstall_enter(&pflags); error = filler(file, folio); if (unlikely(workingset)) psi_memstall_leave(&pflags); if (error) return error; error = folio_wait_locked_killable(folio); if (error) return error; if (folio_test_uptodate(folio)) return 0; if (file) shrink_readahead_size_eio(&file->f_ra); return -EIO; } static bool filemap_range_uptodate(struct address_space *mapping, loff_t pos, size_t count, struct folio *folio, bool need_uptodate) { if (folio_test_uptodate(folio)) return true; /* pipes can't handle partially uptodate pages */ if (need_uptodate) return false; if (!mapping->a_ops->is_partially_uptodate) return false; if (mapping->host->i_blkbits >= folio_shift(folio)) return false; if (folio_pos(folio) > pos) { count -= folio_pos(folio) - pos; pos = 0; } else { pos -= folio_pos(folio); } return mapping->a_ops->is_partially_uptodate(folio, pos, count); } static int filemap_update_page(struct kiocb *iocb, struct address_space *mapping, size_t count, struct folio *folio, bool need_uptodate) { int error; if (iocb->ki_flags & IOCB_NOWAIT) { if (!filemap_invalidate_trylock_shared(mapping)) return -EAGAIN; } else { filemap_invalidate_lock_shared(mapping); } if (!folio_trylock(folio)) { error = -EAGAIN; if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO)) goto unlock_mapping; if (!(iocb->ki_flags & IOCB_WAITQ)) { filemap_invalidate_unlock_shared(mapping); /* * This is where we usually end up waiting for a * previously submitted readahead to finish. */ folio_put_wait_locked(folio, TASK_KILLABLE); return AOP_TRUNCATED_PAGE; } error = __folio_lock_async(folio, iocb->ki_waitq); if (error) goto unlock_mapping; } error = AOP_TRUNCATED_PAGE; if (!folio->mapping) goto unlock; error = 0; if (filemap_range_uptodate(mapping, iocb->ki_pos, count, folio, need_uptodate)) goto unlock; error = -EAGAIN; if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT | IOCB_WAITQ)) goto unlock; error = filemap_read_folio(iocb->ki_filp, mapping->a_ops->read_folio, folio); goto unlock_mapping; unlock: folio_unlock(folio); unlock_mapping: filemap_invalidate_unlock_shared(mapping); if (error == AOP_TRUNCATED_PAGE) folio_put(folio); return error; } static int filemap_create_folio(struct file *file, struct address_space *mapping, loff_t pos, struct folio_batch *fbatch) { struct folio *folio; int error; unsigned int min_order = mapping_min_folio_order(mapping); pgoff_t index; folio = filemap_alloc_folio(mapping_gfp_mask(mapping), min_order); if (!folio) return -ENOMEM; /* * Protect against truncate / hole punch. Grabbing invalidate_lock * here assures we cannot instantiate and bring uptodate new * pagecache folios after evicting page cache during truncate * and before actually freeing blocks. Note that we could * release invalidate_lock after inserting the folio into * the page cache as the locked folio would then be enough to * synchronize with hole punching. But there are code paths * such as filemap_update_page() filling in partially uptodate * pages or ->readahead() that need to hold invalidate_lock * while mapping blocks for IO so let's hold the lock here as * well to keep locking rules simple. */ filemap_invalidate_lock_shared(mapping); index = (pos >> (PAGE_SHIFT + min_order)) << min_order; error = filemap_add_folio(mapping, folio, index, mapping_gfp_constraint(mapping, GFP_KERNEL)); if (error == -EEXIST) error = AOP_TRUNCATED_PAGE; if (error) goto error; error = filemap_read_folio(file, mapping->a_ops->read_folio, folio); if (error) goto error; filemap_invalidate_unlock_shared(mapping); folio_batch_add(fbatch, folio); return 0; error: filemap_invalidate_unlock_shared(mapping); folio_put(folio); return error; } static int filemap_readahead(struct kiocb *iocb, struct file *file, struct address_space *mapping, struct folio *folio, pgoff_t last_index) { DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, folio->index); if (iocb->ki_flags & IOCB_NOIO) return -EAGAIN; page_cache_async_ra(&ractl, folio, last_index - folio->index); return 0; } static int filemap_get_pages(struct kiocb *iocb, size_t count, struct folio_batch *fbatch, bool need_uptodate) { struct file *filp = iocb->ki_filp; struct address_space *mapping = filp->f_mapping; struct file_ra_state *ra = &filp->f_ra; pgoff_t index = iocb->ki_pos >> PAGE_SHIFT; pgoff_t last_index; struct folio *folio; unsigned int flags; int err = 0; /* "last_index" is the index of the page beyond the end of the read */ last_index = DIV_ROUND_UP(iocb->ki_pos + count, PAGE_SIZE); retry: if (fatal_signal_pending(current)) return -EINTR; filemap_get_read_batch(mapping, index, last_index - 1, fbatch); if (!folio_batch_count(fbatch)) { if (iocb->ki_flags & IOCB_NOIO) return -EAGAIN; if (iocb->ki_flags & IOCB_NOWAIT) flags = memalloc_noio_save(); page_cache_sync_readahead(mapping, ra, filp, index, last_index - index); if (iocb->ki_flags & IOCB_NOWAIT) memalloc_noio_restore(flags); filemap_get_read_batch(mapping, index, last_index - 1, fbatch); } if (!folio_batch_count(fbatch)) { if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ)) return -EAGAIN; err = filemap_create_folio(filp, mapping, iocb->ki_pos, fbatch); if (err == AOP_TRUNCATED_PAGE) goto retry; return err; } folio = fbatch->folios[folio_batch_count(fbatch) - 1]; if (folio_test_readahead(folio)) { err = filemap_readahead(iocb, filp, mapping, folio, last_index); if (err) goto err; } if (!folio_test_uptodate(folio)) { if ((iocb->ki_flags & IOCB_WAITQ) && folio_batch_count(fbatch) > 1) iocb->ki_flags |= IOCB_NOWAIT; err = filemap_update_page(iocb, mapping, count, folio, need_uptodate); if (err) goto err; } trace_mm_filemap_get_pages(mapping, index, last_index - 1); return 0; err: if (err < 0) folio_put(folio); if (likely(--fbatch->nr)) return 0; if (err == AOP_TRUNCATED_PAGE) goto retry; return err; } static inline bool pos_same_folio(loff_t pos1, loff_t pos2, struct folio *folio) { unsigned int shift = folio_shift(folio); return (pos1 >> shift == pos2 >> shift); } /** * filemap_read - Read data from the page cache. * @iocb: The iocb to read. * @iter: Destination for the data. * @already_read: Number of bytes already read by the caller. * * Copies data from the page cache. If the data is not currently present, * uses the readahead and read_folio address_space operations to fetch it. * * Return: Total number of bytes copied, including those already read by * the caller. If an error happens before any bytes are copied, returns * a negative error number. */ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, ssize_t already_read) { struct file *filp = iocb->ki_filp; struct file_ra_state *ra = &filp->f_ra; struct address_space *mapping = filp->f_mapping; struct inode *inode = mapping->host; struct folio_batch fbatch; int i, error = 0; bool writably_mapped; loff_t isize, end_offset; loff_t last_pos = ra->prev_pos; if (unlikely(iocb->ki_pos < 0)) return -EINVAL; if (unlikely(iocb->ki_pos >= inode->i_sb->s_maxbytes)) return 0; if (unlikely(!iov_iter_count(iter))) return 0; iov_iter_truncate(iter, inode->i_sb->s_maxbytes - iocb->ki_pos); folio_batch_init(&fbatch); do { cond_resched(); /* * If we've already successfully copied some data, then we * can no longer safely return -EIOCBQUEUED. Hence mark * an async read NOWAIT at that point. */ if ((iocb->ki_flags & IOCB_WAITQ) && already_read) iocb->ki_flags |= IOCB_NOWAIT; if (unlikely(iocb->ki_pos >= i_size_read(inode))) break; error = filemap_get_pages(iocb, iter->count, &fbatch, false); if (error < 0) break; /* * i_size must be checked after we know the pages are Uptodate. * * Checking i_size after the check allows us to calculate * the correct value for "nr", which means the zero-filled * part of the page is not copied back to userspace (unless * another truncate extends the file - this is desired though). */ isize = i_size_read(inode); if (unlikely(iocb->ki_pos >= isize)) goto put_folios; end_offset = min_t(loff_t, isize, iocb->ki_pos + iter->count); /* * Once we start copying data, we don't want to be touching any * cachelines that might be contended: */ writably_mapped = mapping_writably_mapped(mapping); /* * When a read accesses the same folio several times, only * mark it as accessed the first time. */ if (!pos_same_folio(iocb->ki_pos, last_pos - 1, fbatch.folios[0])) folio_mark_accessed(fbatch.folios[0]); for (i = 0; i < folio_batch_count(&fbatch); i++) { struct folio *folio = fbatch.folios[i]; size_t fsize = folio_size(folio); size_t offset = iocb->ki_pos & (fsize - 1); size_t bytes = min_t(loff_t, end_offset - iocb->ki_pos, fsize - offset); size_t copied; if (end_offset < folio_pos(folio)) break; if (i > 0) folio_mark_accessed(folio); /* * If users can be writing to this folio using arbitrary * virtual addresses, take care of potential aliasing * before reading the folio on the kernel side. */ if (writably_mapped) flush_dcache_folio(folio); copied = copy_folio_to_iter(folio, offset, bytes, iter); already_read += copied; iocb->ki_pos += copied; last_pos = iocb->ki_pos; if (copied < bytes) { error = -EFAULT; break; } } put_folios: for (i = 0; i < folio_batch_count(&fbatch); i++) folio_put(fbatch.folios[i]); folio_batch_init(&fbatch); } while (iov_iter_count(iter) && iocb->ki_pos < isize && !error); file_accessed(filp); ra->prev_pos = last_pos; return already_read ? already_read : error; } EXPORT_SYMBOL_GPL(filemap_read); int kiocb_write_and_wait(struct kiocb *iocb, size_t count) { struct address_space *mapping = iocb->ki_filp->f_mapping; loff_t pos = iocb->ki_pos; loff_t end = pos + count - 1; if (iocb->ki_flags & IOCB_NOWAIT) { if (filemap_range_needs_writeback(mapping, pos, end)) return -EAGAIN; return 0; } return filemap_write_and_wait_range(mapping, pos, end); } EXPORT_SYMBOL_GPL(kiocb_write_and_wait); int filemap_invalidate_pages(struct address_space *mapping, loff_t pos, loff_t end, bool nowait) { int ret; if (nowait) { /* we could block if there are any pages in the range */ if (filemap_range_has_page(mapping, pos, end)) return -EAGAIN; } else { ret = filemap_write_and_wait_range(mapping, pos, end); if (ret) return ret; } /* * After a write we want buffered reads to be sure to go to disk to get * the new data. We invalidate clean cached page from the region we're * about to write. We do this *before* the write so that we can return * without clobbering -EIOCBQUEUED from ->direct_IO(). */ return invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end >> PAGE_SHIFT); } int kiocb_invalidate_pages(struct kiocb *iocb, size_t count) { struct address_space *mapping = iocb->ki_filp->f_mapping; return filemap_invalidate_pages(mapping, iocb->ki_pos, iocb->ki_pos + count - 1, iocb->ki_flags & IOCB_NOWAIT); } EXPORT_SYMBOL_GPL(kiocb_invalidate_pages); /** * generic_file_read_iter - generic filesystem read routine * @iocb: kernel I/O control block * @iter: destination for the data read * * This is the "read_iter()" routine for all filesystems * that can use the page cache directly. * * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall * be returned when no data can be read without waiting for I/O requests * to complete; it doesn't prevent readahead. * * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O * requests shall be made for the read or for readahead. When no data * can be read, -EAGAIN shall be returned. When readahead would be * triggered, a partial, possibly empty read shall be returned. * * Return: * * number of bytes copied, even for partial reads * * negative error code (or 0 if IOCB_NOIO) if nothing was read */ ssize_t generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { size_t count = iov_iter_count(iter); ssize_t retval = 0; if (!count) return 0; /* skip atime */ if (iocb->ki_flags & IOCB_DIRECT) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; retval = kiocb_write_and_wait(iocb, count); if (retval < 0) return retval; file_accessed(file); retval = mapping->a_ops->direct_IO(iocb, iter); if (retval >= 0) { iocb->ki_pos += retval; count -= retval; } if (retval != -EIOCBQUEUED) iov_iter_revert(iter, count - iov_iter_count(iter)); /* * Btrfs can have a short DIO read if we encounter * compressed extents, so if there was an error, or if * we've already read everything we wanted to, or if * there was a short read because we hit EOF, go ahead * and return. Otherwise fallthrough to buffered io for * the rest of the read. Buffered reads will not work for * DAX files, so don't bother trying. */ if (retval < 0 || !count || IS_DAX(inode)) return retval; if (iocb->ki_pos >= i_size_read(inode)) return retval; } return filemap_read(iocb, iter, retval); } EXPORT_SYMBOL(generic_file_read_iter); /* * Splice subpages from a folio into a pipe. */ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, struct folio *folio, loff_t fpos, size_t size) { struct page *page; size_t spliced = 0, offset = offset_in_folio(folio, fpos); page = folio_page(folio, offset / PAGE_SIZE); size = min(size, folio_size(folio) - offset); offset %= PAGE_SIZE; while (spliced < size && !pipe_full(pipe->head, pipe->tail, pipe->max_usage)) { struct pipe_buffer *buf = pipe_head_buf(pipe); size_t part = min_t(size_t, PAGE_SIZE - offset, size - spliced); *buf = (struct pipe_buffer) { .ops = &page_cache_pipe_buf_ops, .page = page, .offset = offset, .len = part, }; folio_get(folio); pipe->head++; page++; spliced += part; offset = 0; } return spliced; } /** * filemap_splice_read - Splice data from a file's pagecache into a pipe * @in: The file to read from * @ppos: Pointer to the file position to read from * @pipe: The pipe to splice into * @len: The amount to splice * @flags: The SPLICE_F_* flags * * This function gets folios from a file's pagecache and splices them into the * pipe. Readahead will be called as necessary to fill more folios. This may * be used for blockdevs also. * * Return: On success, the number of bytes read will be returned and *@ppos * will be updated if appropriate; 0 will be returned if there is no more data * to be read; -EAGAIN will be returned if the pipe had no space, and some * other negative error code will be returned on error. A short read may occur * if the pipe has insufficient space, we reach the end of the data or we hit a * hole. */ ssize_t filemap_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct folio_batch fbatch; struct kiocb iocb; size_t total_spliced = 0, used, npages; loff_t isize, end_offset; bool writably_mapped; int i, error = 0; if (unlikely(*ppos >= in->f_mapping->host->i_sb->s_maxbytes)) return 0; init_sync_kiocb(&iocb, in); iocb.ki_pos = *ppos; /* Work out how much data we can actually add into the pipe */ used = pipe_occupancy(pipe->head, pipe->tail); npages = max_t(ssize_t, pipe->max_usage - used, 0); len = min_t(size_t, len, npages * PAGE_SIZE); folio_batch_init(&fbatch); do { cond_resched(); if (*ppos >= i_size_read(in->f_mapping->host)) break; iocb.ki_pos = *ppos; error = filemap_get_pages(&iocb, len, &fbatch, true); if (error < 0) break; /* * i_size must be checked after we know the pages are Uptodate. * * Checking i_size after the check allows us to calculate * the correct value for "nr", which means the zero-filled * part of the page is not copied back to userspace (unless * another truncate extends the file - this is desired though). */ isize = i_size_read(in->f_mapping->host); if (unlikely(*ppos >= isize)) break; end_offset = min_t(loff_t, isize, *ppos + len); /* * Once we start copying data, we don't want to be touching any * cachelines that might be contended: */ writably_mapped = mapping_writably_mapped(in->f_mapping); for (i = 0; i < folio_batch_count(&fbatch); i++) { struct folio *folio = fbatch.folios[i]; size_t n; if (folio_pos(folio) >= end_offset) goto out; folio_mark_accessed(folio); /* * If users can be writing to this folio using arbitrary * virtual addresses, take care of potential aliasing * before reading the folio on the kernel side. */ if (writably_mapped) flush_dcache_folio(folio); n = min_t(loff_t, len, isize - *ppos); n = splice_folio_into_pipe(pipe, folio, *ppos, n); if (!n) goto out; len -= n; total_spliced += n; *ppos += n; in->f_ra.prev_pos = *ppos; if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) goto out; } folio_batch_release(&fbatch); } while (len); out: folio_batch_release(&fbatch); file_accessed(in); return total_spliced ? total_spliced : error; } EXPORT_SYMBOL(filemap_splice_read); static inline loff_t folio_seek_hole_data(struct xa_state *xas, struct address_space *mapping, struct folio *folio, loff_t start, loff_t end, bool seek_data) { const struct address_space_operations *ops = mapping->a_ops; size_t offset, bsz = i_blocksize(mapping->host); if (xa_is_value(folio) || folio_test_uptodate(folio)) return seek_data ? start : end; if (!ops->is_partially_uptodate) return seek_data ? end : start; xas_pause(xas); rcu_read_unlock(); folio_lock(folio); if (unlikely(folio->mapping != mapping)) goto unlock; offset = offset_in_folio(folio, start) & ~(bsz - 1); do { if (ops->is_partially_uptodate(folio, offset, bsz) == seek_data) break; start = (start + bsz) & ~(bsz - 1); offset += bsz; } while (offset < folio_size(folio)); unlock: folio_unlock(folio); rcu_read_lock(); return start; } static inline size_t seek_folio_size(struct xa_state *xas, struct folio *folio) { if (xa_is_value(folio)) return PAGE_SIZE << xas_get_order(xas); return folio_size(folio); } /** * mapping_seek_hole_data - Seek for SEEK_DATA / SEEK_HOLE in the page cache. * @mapping: Address space to search. * @start: First byte to consider. * @end: Limit of search (exclusive). * @whence: Either SEEK_HOLE or SEEK_DATA. * * If the page cache knows which blocks contain holes and which blocks * contain data, your filesystem can use this function to implement * SEEK_HOLE and SEEK_DATA. This is useful for filesystems which are * entirely memory-based such as tmpfs, and filesystems which support * unwritten extents. * * Return: The requested offset on success, or -ENXIO if @whence specifies * SEEK_DATA and there is no data after @start. There is an implicit hole * after @end - 1, so SEEK_HOLE returns @end if all the bytes between @start * and @end contain data. */ loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start, loff_t end, int whence) { XA_STATE(xas, &mapping->i_pages, start >> PAGE_SHIFT); pgoff_t max = (end - 1) >> PAGE_SHIFT; bool seek_data = (whence == SEEK_DATA); struct folio *folio; if (end <= start) return -ENXIO; rcu_read_lock(); while ((folio = find_get_entry(&xas, max, XA_PRESENT))) { loff_t pos = (u64)xas.xa_index << PAGE_SHIFT; size_t seek_size; if (start < pos) { if (!seek_data) goto unlock; start = pos; } seek_size = seek_folio_size(&xas, folio); pos = round_up((u64)pos + 1, seek_size); start = folio_seek_hole_data(&xas, mapping, folio, start, pos, seek_data); if (start < pos) goto unlock; if (start >= end) break; if (seek_size > PAGE_SIZE) xas_set(&xas, pos >> PAGE_SHIFT); if (!xa_is_value(folio)) folio_put(folio); } if (seek_data) start = -ENXIO; unlock: rcu_read_unlock(); if (folio && !xa_is_value(folio)) folio_put(folio); if (start > end) return end; return start; } #ifdef CONFIG_MMU #define MMAP_LOTSAMISS (100) /* * lock_folio_maybe_drop_mmap - lock the page, possibly dropping the mmap_lock * @vmf - the vm_fault for this fault. * @folio - the folio to lock. * @fpin - the pointer to the file we may pin (or is already pinned). * * This works similar to lock_folio_or_retry in that it can drop the * mmap_lock. It differs in that it actually returns the folio locked * if it returns 1 and 0 if it couldn't lock the folio. If we did have * to drop the mmap_lock then fpin will point to the pinned file and * needs to be fput()'ed at a later point. */ static int lock_folio_maybe_drop_mmap(struct vm_fault *vmf, struct folio *folio, struct file **fpin) { if (folio_trylock(folio)) return 1; /* * NOTE! This will make us return with VM_FAULT_RETRY, but with * the fault lock still held. That's how FAULT_FLAG_RETRY_NOWAIT * is supposed to work. We have way too many special cases.. */ if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) return 0; *fpin = maybe_unlock_mmap_for_io(vmf, *fpin); if (vmf->flags & FAULT_FLAG_KILLABLE) { if (__folio_lock_killable(folio)) { /* * We didn't have the right flags to drop the * fault lock, but all fault_handlers only check * for fatal signals if we return VM_FAULT_RETRY, * so we need to drop the fault lock here and * return 0 if we don't have a fpin. */ if (*fpin == NULL) release_fault_lock(vmf); return 0; } } else __folio_lock(folio); return 1; } /* * Synchronous readahead happens when we don't even find a page in the page * cache at all. We don't want to perform IO under the mmap sem, so if we have * to drop the mmap sem we return the file that was pinned in order for us to do * that. If we didn't pin a file then we return NULL. The file that is * returned needs to be fput()'ed when we're done with it. */ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct file_ra_state *ra = &file->f_ra; struct address_space *mapping = file->f_mapping; DEFINE_READAHEAD(ractl, file, ra, mapping, vmf->pgoff); struct file *fpin = NULL; unsigned long vm_flags = vmf->vma->vm_flags; unsigned int mmap_miss; #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* Use the readahead code, even if readahead is disabled */ if ((vm_flags & VM_HUGEPAGE) && HPAGE_PMD_ORDER <= MAX_PAGECACHE_ORDER) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); ractl._index &= ~((unsigned long)HPAGE_PMD_NR - 1); ra->size = HPAGE_PMD_NR; /* * Fetch two PMD folios, so we get the chance to actually * readahead, unless we've been told not to. */ if (!(vm_flags & VM_RAND_READ)) ra->size *= 2; ra->async_size = HPAGE_PMD_NR; page_cache_ra_order(&ractl, ra, HPAGE_PMD_ORDER); return fpin; } #endif /* If we don't want any read-ahead, don't bother */ if (vm_flags & VM_RAND_READ) return fpin; if (!ra->ra_pages) return fpin; if (vm_flags & VM_SEQ_READ) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_sync_ra(&ractl, ra->ra_pages); return fpin; } /* Avoid banging the cache line if not needed */ mmap_miss = READ_ONCE(ra->mmap_miss); if (mmap_miss < MMAP_LOTSAMISS * 10) WRITE_ONCE(ra->mmap_miss, ++mmap_miss); /* * Do we miss much more than hit in this file? If so, * stop bothering with read-ahead. It will only hurt. */ if (mmap_miss > MMAP_LOTSAMISS) return fpin; /* * mmap read-around */ fpin = maybe_unlock_mmap_for_io(vmf, fpin); ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2); ra->size = ra->ra_pages; ra->async_size = ra->ra_pages / 4; ractl._index = ra->start; page_cache_ra_order(&ractl, ra, 0); return fpin; } /* * Asynchronous readahead happens when we find the page and PG_readahead, * so we want to possibly extend the readahead further. We return the file that * was pinned if we have to drop the mmap_lock in order to do IO. */ static struct file *do_async_mmap_readahead(struct vm_fault *vmf, struct folio *folio) { struct file *file = vmf->vma->vm_file; struct file_ra_state *ra = &file->f_ra; DEFINE_READAHEAD(ractl, file, ra, file->f_mapping, vmf->pgoff); struct file *fpin = NULL; unsigned int mmap_miss; /* If we don't want any read-ahead, don't bother */ if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages) return fpin; mmap_miss = READ_ONCE(ra->mmap_miss); if (mmap_miss) WRITE_ONCE(ra->mmap_miss, --mmap_miss); if (folio_test_readahead(folio)) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_async_ra(&ractl, folio, ra->ra_pages); } return fpin; } static vm_fault_t filemap_fault_recheck_pte_none(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = 0; pte_t *ptep; /* * We might have COW'ed a pagecache folio and might now have an mlocked * anon folio mapped. The original pagecache folio is not mlocked and * might have been evicted. During a read+clear/modify/write update of * the PTE, such as done in do_numa_page()/change_pte_range(), we * temporarily clear the PTE under PT lock and might detect it here as * "none" when not holding the PT lock. * * Not rechecking the PTE under PT lock could result in an unexpected * major fault in an mlock'ed region. Recheck only for this special * scenario while holding the PT lock, to not degrade non-mlocked * scenarios. Recheck the PTE without PT lock firstly, thereby reducing * the number of times we hold PT lock. */ if (!(vma->vm_flags & VM_LOCKED)) return 0; if (!(vmf->flags & FAULT_FLAG_ORIG_PTE_VALID)) return 0; ptep = pte_offset_map_ro_nolock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!ptep)) return VM_FAULT_NOPAGE; if (unlikely(!pte_none(ptep_get_lockless(ptep)))) { ret = VM_FAULT_NOPAGE; } else { spin_lock(vmf->ptl); if (unlikely(!pte_none(ptep_get(ptep)))) ret = VM_FAULT_NOPAGE; spin_unlock(vmf->ptl); } pte_unmap(ptep); return ret; } /** * filemap_fault - read in file data for page fault handling * @vmf: struct vm_fault containing details of the fault * * filemap_fault() is invoked via the vma operations vector for a * mapped memory region to read in file data during a page fault. * * The goto's are kind of ugly, but this streamlines the normal case of having * it in the page cache, and handles the special cases reasonably without * having a lot of duplicated code. * * vma->vm_mm->mmap_lock must be held on entry. * * If our return value has VM_FAULT_RETRY set, it's because the mmap_lock * may be dropped before doing I/O or by lock_folio_maybe_drop_mmap(). * * If our return value does not have VM_FAULT_RETRY set, the mmap_lock * has not been released. * * We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set. * * Return: bitwise-OR of %VM_FAULT_ codes. */ vm_fault_t filemap_fault(struct vm_fault *vmf) { int error; struct file *file = vmf->vma->vm_file; struct file *fpin = NULL; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; pgoff_t max_idx, index = vmf->pgoff; struct folio *folio; vm_fault_t ret = 0; bool mapping_locked = false; max_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(index >= max_idx)) return VM_FAULT_SIGBUS; trace_mm_filemap_fault(mapping, index); /* * Do we have something in the page cache already? */ folio = filemap_get_folio(mapping, index); if (likely(!IS_ERR(folio))) { /* * We found the page, so try async readahead before waiting for * the lock. */ if (!(vmf->flags & FAULT_FLAG_TRIED)) fpin = do_async_mmap_readahead(vmf, folio); if (unlikely(!folio_test_uptodate(folio))) { filemap_invalidate_lock_shared(mapping); mapping_locked = true; } } else { ret = filemap_fault_recheck_pte_none(vmf); if (unlikely(ret)) return ret; /* No page in the page cache at all */ count_vm_event(PGMAJFAULT); count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT); ret = VM_FAULT_MAJOR; fpin = do_sync_mmap_readahead(vmf); retry_find: /* * See comment in filemap_create_folio() why we need * invalidate_lock */ if (!mapping_locked) { filemap_invalidate_lock_shared(mapping); mapping_locked = true; } folio = __filemap_get_folio(mapping, index, FGP_CREAT|FGP_FOR_MMAP, vmf->gfp_mask); if (IS_ERR(folio)) { if (fpin) goto out_retry; filemap_invalidate_unlock_shared(mapping); return VM_FAULT_OOM; } } if (!lock_folio_maybe_drop_mmap(vmf, folio, &fpin)) goto out_retry; /* Did it get truncated? */ if (unlikely(folio->mapping != mapping)) { folio_unlock(folio); folio_put(folio); goto retry_find; } VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); /* * We have a locked folio in the page cache, now we need to check * that it's up-to-date. If not, it is going to be due to an error, * or because readahead was otherwise unable to retrieve it. */ if (unlikely(!folio_test_uptodate(folio))) { /* * If the invalidate lock is not held, the folio was in cache * and uptodate and now it is not. Strange but possible since we * didn't hold the page lock all the time. Let's drop * everything, get the invalidate lock and try again. */ if (!mapping_locked) { folio_unlock(folio); folio_put(folio); goto retry_find; } /* * OK, the folio is really not uptodate. This can be because the * VMA has the VM_RAND_READ flag set, or because an error * arose. Let's read it in directly. */ goto page_not_uptodate; } /* * We've made it this far and we had to drop our mmap_lock, now is the * time to return to the upper layer and have it re-find the vma and * redo the fault. */ if (fpin) { folio_unlock(folio); goto out_retry; } if (mapping_locked) filemap_invalidate_unlock_shared(mapping); /* * Found the page and have a reference on it. * We must recheck i_size under page lock. */ max_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(index >= max_idx)) { folio_unlock(folio); folio_put(folio); return VM_FAULT_SIGBUS; } vmf->page = folio_file_page(folio, index); return ret | VM_FAULT_LOCKED; page_not_uptodate: /* * Umm, take care of errors if the page isn't up-to-date. * Try to re-read it _once_. We do this synchronously, * because there really aren't any performance issues here * and we need to check for errors. */ fpin = maybe_unlock_mmap_for_io(vmf, fpin); error = filemap_read_folio(file, mapping->a_ops->read_folio, folio); if (fpin) goto out_retry; folio_put(folio); if (!error || error == AOP_TRUNCATED_PAGE) goto retry_find; filemap_invalidate_unlock_shared(mapping); return VM_FAULT_SIGBUS; out_retry: /* * We dropped the mmap_lock, we need to return to the fault handler to * re-find the vma and come back and find our hopefully still populated * page. */ if (!IS_ERR(folio)) folio_put(folio); if (mapping_locked) filemap_invalidate_unlock_shared(mapping); if (fpin) fput(fpin); return ret | VM_FAULT_RETRY; } EXPORT_SYMBOL(filemap_fault); static bool filemap_map_pmd(struct vm_fault *vmf, struct folio *folio, pgoff_t start) { struct mm_struct *mm = vmf->vma->vm_mm; /* Huge page is mapped? No need to proceed. */ if (pmd_trans_huge(*vmf->pmd)) { folio_unlock(folio); folio_put(folio); return true; } if (pmd_none(*vmf->pmd) && folio_test_pmd_mappable(folio)) { struct page *page = folio_file_page(folio, start); vm_fault_t ret = do_set_pmd(vmf, page); if (!ret) { /* The page is mapped successfully, reference consumed. */ folio_unlock(folio); return true; } } if (pmd_none(*vmf->pmd) && vmf->prealloc_pte) pmd_install(mm, vmf->pmd, &vmf->prealloc_pte); return false; } static struct folio *next_uptodate_folio(struct xa_state *xas, struct address_space *mapping, pgoff_t end_pgoff) { struct folio *folio = xas_next_entry(xas, end_pgoff); unsigned long max_idx; do { if (!folio) return NULL; if (xas_retry(xas, folio)) continue; if (xa_is_value(folio)) continue; if (!folio_try_get(folio)) continue; if (folio_test_locked(folio)) goto skip; /* Has the page moved or been split? */ if (unlikely(folio != xas_reload(xas))) goto skip; if (!folio_test_uptodate(folio) || folio_test_readahead(folio)) goto skip; if (!folio_trylock(folio)) goto skip; if (folio->mapping != mapping) goto unlock; if (!folio_test_uptodate(folio)) goto unlock; max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); if (xas->xa_index >= max_idx) goto unlock; return folio; unlock: folio_unlock(folio); skip: folio_put(folio); } while ((folio = xas_next_entry(xas, end_pgoff)) != NULL); return NULL; } /* * Map page range [start_page, start_page + nr_pages) of folio. * start_page is gotten from start by folio_page(folio, start) */ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf, struct folio *folio, unsigned long start, unsigned long addr, unsigned int nr_pages, unsigned long *rss, unsigned int *mmap_miss) { vm_fault_t ret = 0; struct page *page = folio_page(folio, start); unsigned int count = 0; pte_t *old_ptep = vmf->pte; do { if (PageHWPoison(page + count)) goto skip; /* * If there are too many folios that are recently evicted * in a file, they will probably continue to be evicted. * In such situation, read-ahead is only a waste of IO. * Don't decrease mmap_miss in this scenario to make sure * we can stop read-ahead. */ if (!folio_test_workingset(folio)) (*mmap_miss)++; /* * NOTE: If there're PTE markers, we'll leave them to be * handled in the specific fault path, and it'll prohibit the * fault-around logic. */ if (!pte_none(ptep_get(&vmf->pte[count]))) goto skip; count++; continue; skip: if (count) { set_pte_range(vmf, folio, page, count, addr); *rss += count; folio_ref_add(folio, count); if (in_range(vmf->address, addr, count * PAGE_SIZE)) ret = VM_FAULT_NOPAGE; } count++; page += count; vmf->pte += count; addr += count * PAGE_SIZE; count = 0; } while (--nr_pages > 0); if (count) { set_pte_range(vmf, folio, page, count, addr); *rss += count; folio_ref_add(folio, count); if (in_range(vmf->address, addr, count * PAGE_SIZE)) ret = VM_FAULT_NOPAGE; } vmf->pte = old_ptep; return ret; } static vm_fault_t filemap_map_order0_folio(struct vm_fault *vmf, struct folio *folio, unsigned long addr, unsigned long *rss, unsigned int *mmap_miss) { vm_fault_t ret = 0; struct page *page = &folio->page; if (PageHWPoison(page)) return ret; /* See comment of filemap_map_folio_range() */ if (!folio_test_workingset(folio)) (*mmap_miss)++; /* * NOTE: If there're PTE markers, we'll leave them to be * handled in the specific fault path, and it'll prohibit * the fault-around logic. */ if (!pte_none(ptep_get(vmf->pte))) return ret; if (vmf->address == addr) ret = VM_FAULT_NOPAGE; set_pte_range(vmf, folio, page, 1, addr); (*rss)++; folio_ref_inc(folio); return ret; } vm_fault_t filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff) { struct vm_area_struct *vma = vmf->vma; struct file *file = vma->vm_file; struct address_space *mapping = file->f_mapping; pgoff_t file_end, last_pgoff = start_pgoff; unsigned long addr; XA_STATE(xas, &mapping->i_pages, start_pgoff); struct folio *folio; vm_fault_t ret = 0; unsigned long rss = 0; unsigned int nr_pages = 0, mmap_miss = 0, mmap_miss_saved, folio_type; rcu_read_lock(); folio = next_uptodate_folio(&xas, mapping, end_pgoff); if (!folio) goto out; if (filemap_map_pmd(vmf, folio, start_pgoff)) { ret = VM_FAULT_NOPAGE; goto out; } addr = vma->vm_start + ((start_pgoff - vma->vm_pgoff) << PAGE_SHIFT); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl); if (!vmf->pte) { folio_unlock(folio); folio_put(folio); goto out; } file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE) - 1; if (end_pgoff > file_end) end_pgoff = file_end; folio_type = mm_counter_file(folio); do { unsigned long end; addr += (xas.xa_index - last_pgoff) << PAGE_SHIFT; vmf->pte += xas.xa_index - last_pgoff; last_pgoff = xas.xa_index; end = folio_next_index(folio) - 1; nr_pages = min(end, end_pgoff) - xas.xa_index + 1; if (!folio_test_large(folio)) ret |= filemap_map_order0_folio(vmf, folio, addr, &rss, &mmap_miss); else ret |= filemap_map_folio_range(vmf, folio, xas.xa_index - folio->index, addr, nr_pages, &rss, &mmap_miss); folio_unlock(folio); folio_put(folio); } while ((folio = next_uptodate_folio(&xas, mapping, end_pgoff)) != NULL); add_mm_counter(vma->vm_mm, folio_type, rss); pte_unmap_unlock(vmf->pte, vmf->ptl); trace_mm_filemap_map_pages(mapping, start_pgoff, end_pgoff); out: rcu_read_unlock(); mmap_miss_saved = READ_ONCE(file->f_ra.mmap_miss); if (mmap_miss >= mmap_miss_saved) WRITE_ONCE(file->f_ra.mmap_miss, 0); else WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss_saved - mmap_miss); return ret; } EXPORT_SYMBOL(filemap_map_pages); vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { struct address_space *mapping = vmf->vma->vm_file->f_mapping; struct folio *folio = page_folio(vmf->page); vm_fault_t ret = VM_FAULT_LOCKED; sb_start_pagefault(mapping->host->i_sb); file_update_time(vmf->vma->vm_file); folio_lock(folio); if (folio->mapping != mapping) { folio_unlock(folio); ret = VM_FAULT_NOPAGE; goto out; } /* * We mark the folio dirty already here so that when freeze is in * progress, we are guaranteed that writeback during freezing will * see the dirty folio and writeprotect it again. */ folio_mark_dirty(folio); folio_wait_stable(folio); out: sb_end_pagefault(mapping->host->i_sb); return ret; } const struct vm_operations_struct generic_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = filemap_page_mkwrite, }; /* This is used for a general mmap of a disk file */ int generic_file_mmap(struct file *file, struct vm_area_struct *vma) { struct address_space *mapping = file->f_mapping; if (!mapping->a_ops->read_folio) return -ENOEXEC; file_accessed(file); vma->vm_ops = &generic_file_vm_ops; return 0; } /* * This is for filesystems which do not implement ->writepage. */ int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma) { if (vma_is_shared_maywrite(vma)) return -EINVAL; return generic_file_mmap(file, vma); } #else vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { return VM_FAULT_SIGBUS; } int generic_file_mmap(struct file *file, struct vm_area_struct *vma) { return -ENOSYS; } int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma) { return -ENOSYS; } #endif /* CONFIG_MMU */ EXPORT_SYMBOL(filemap_page_mkwrite); EXPORT_SYMBOL(generic_file_mmap); EXPORT_SYMBOL(generic_file_readonly_mmap); static struct folio *do_read_cache_folio(struct address_space *mapping, pgoff_t index, filler_t filler, struct file *file, gfp_t gfp) { struct folio *folio; int err; if (!filler) filler = mapping->a_ops->read_folio; repeat: folio = filemap_get_folio(mapping, index); if (IS_ERR(folio)) { folio = filemap_alloc_folio(gfp, mapping_min_folio_order(mapping)); if (!folio) return ERR_PTR(-ENOMEM); index = mapping_align_index(mapping, index); err = filemap_add_folio(mapping, folio, index, gfp); if (unlikely(err)) { folio_put(folio); if (err == -EEXIST) goto repeat; /* Presumably ENOMEM for xarray node */ return ERR_PTR(err); } goto filler; } if (folio_test_uptodate(folio)) goto out; if (!folio_trylock(folio)) { folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE); goto repeat; } /* Folio was truncated from mapping */ if (!folio->mapping) { folio_unlock(folio); folio_put(folio); goto repeat; } /* Someone else locked and filled the page in a very small window */ if (folio_test_uptodate(folio)) { folio_unlock(folio); goto out; } filler: err = filemap_read_folio(file, filler, folio); if (err) { folio_put(folio); if (err == AOP_TRUNCATED_PAGE) goto repeat; return ERR_PTR(err); } out: folio_mark_accessed(folio); return folio; } /** * read_cache_folio - Read into page cache, fill it if needed. * @mapping: The address_space to read from. * @index: The index to read. * @filler: Function to perform the read, or NULL to use aops->read_folio(). * @file: Passed to filler function, may be NULL if not required. * * Read one page into the page cache. If it succeeds, the folio returned * will contain @index, but it may not be the first page of the folio. * * If the filler function returns an error, it will be returned to the * caller. * * Context: May sleep. Expects mapping->invalidate_lock to be held. * Return: An uptodate folio on success, ERR_PTR() on failure. */ struct folio *read_cache_folio(struct address_space *mapping, pgoff_t index, filler_t filler, struct file *file) { return do_read_cache_folio(mapping, index, filler, file, mapping_gfp_mask(mapping)); } EXPORT_SYMBOL(read_cache_folio); /** * mapping_read_folio_gfp - Read into page cache, using specified allocation flags. * @mapping: The address_space for the folio. * @index: The index that the allocated folio will contain. * @gfp: The page allocator flags to use if allocating. * * This is the same as "read_cache_folio(mapping, index, NULL, NULL)", but with * any new memory allocations done using the specified allocation flags. * * The most likely error from this function is EIO, but ENOMEM is * possible and so is EINTR. If ->read_folio returns another error, * that will be returned to the caller. * * The function expects mapping->invalidate_lock to be already held. * * Return: Uptodate folio on success, ERR_PTR() on failure. */ struct folio *mapping_read_folio_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp) { return do_read_cache_folio(mapping, index, NULL, NULL, gfp); } EXPORT_SYMBOL(mapping_read_folio_gfp); static struct page *do_read_cache_page(struct address_space *mapping, pgoff_t index, filler_t *filler, struct file *file, gfp_t gfp) { struct folio *folio; folio = do_read_cache_folio(mapping, index, filler, file, gfp); if (IS_ERR(folio)) return &folio->page; return folio_file_page(folio, index); } struct page *read_cache_page(struct address_space *mapping, pgoff_t index, filler_t *filler, struct file *file) { return do_read_cache_page(mapping, index, filler, file, mapping_gfp_mask(mapping)); } EXPORT_SYMBOL(read_cache_page); /** * read_cache_page_gfp - read into page cache, using specified page allocation flags. * @mapping: the page's address_space * @index: the page index * @gfp: the page allocator flags to use if allocating * * This is the same as "read_mapping_page(mapping, index, NULL)", but with * any new page allocations done using the specified allocation flags. * * If the page does not get brought uptodate, return -EIO. * * The function expects mapping->invalidate_lock to be already held. * * Return: up to date page on success, ERR_PTR() on failure. */ struct page *read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp) { return do_read_cache_page(mapping, index, NULL, NULL, gfp); } EXPORT_SYMBOL(read_cache_page_gfp); /* * Warn about a page cache invalidation failure during a direct I/O write. */ static void dio_warn_stale_pagecache(struct file *filp) { static DEFINE_RATELIMIT_STATE(_rs, 86400 * HZ, DEFAULT_RATELIMIT_BURST); char pathname[128]; char *path; errseq_set(&filp->f_mapping->wb_err, -EIO); if (__ratelimit(&_rs)) { path = file_path(filp, pathname, sizeof(pathname)); if (IS_ERR(path)) path = "(unknown)"; pr_crit("Page cache invalidation failure on direct I/O. Possible data corruption due to collision with buffered I/O!\n"); pr_crit("File: %s PID: %d Comm: %.20s\n", path, current->pid, current->comm); } } void kiocb_invalidate_post_direct_write(struct kiocb *iocb, size_t count) { struct address_space *mapping = iocb->ki_filp->f_mapping; if (mapping->nrpages && invalidate_inode_pages2_range(mapping, iocb->ki_pos >> PAGE_SHIFT, (iocb->ki_pos + count - 1) >> PAGE_SHIFT)) dio_warn_stale_pagecache(iocb->ki_filp); } ssize_t generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) { struct address_space *mapping = iocb->ki_filp->f_mapping; size_t write_len = iov_iter_count(from); ssize_t written; /* * If a page can not be invalidated, return 0 to fall back * to buffered write. */ written = kiocb_invalidate_pages(iocb, write_len); if (written) { if (written == -EBUSY) return 0; return written; } written = mapping->a_ops->direct_IO(iocb, from); /* * Finally, try again to invalidate clean pages which might have been * cached by non-direct readahead, or faulted in by get_user_pages() * if the source of the write was an mmap'ed region of the file * we're writing. Either one is a pretty crazy thing to do, * so we don't support it 100%. If this invalidation * fails, tough, the write still worked... * * Most of the time we do not need this since dio_complete() will do * the invalidation for us. However there are some file systems that * do not end up with dio_complete() being called, so let's not break * them by removing it completely. * * Noticeable example is a blkdev_direct_IO(). * * Skip invalidation for async writes or if mapping has no pages. */ if (written > 0) { struct inode *inode = mapping->host; loff_t pos = iocb->ki_pos; kiocb_invalidate_post_direct_write(iocb, written); pos += written; write_len -= written; if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) { i_size_write(inode, pos); mark_inode_dirty(inode); } iocb->ki_pos = pos; } if (written != -EIOCBQUEUED) iov_iter_revert(from, write_len - iov_iter_count(from)); return written; } EXPORT_SYMBOL(generic_file_direct_write); ssize_t generic_perform_write(struct kiocb *iocb, struct iov_iter *i) { struct file *file = iocb->ki_filp; loff_t pos = iocb->ki_pos; struct address_space *mapping = file->f_mapping; const struct address_space_operations *a_ops = mapping->a_ops; size_t chunk = mapping_max_folio_size(mapping); long status = 0; ssize_t written = 0; do { struct folio *folio; size_t offset; /* Offset into folio */ size_t bytes; /* Bytes to write to folio */ size_t copied; /* Bytes copied from user */ void *fsdata = NULL; bytes = iov_iter_count(i); retry: offset = pos & (chunk - 1); bytes = min(chunk - offset, bytes); balance_dirty_pages_ratelimited(mapping); /* * Bring in the user page that we will copy from _first_. * Otherwise there's a nasty deadlock on copying from the * same page as we're writing to, without it being marked * up-to-date. */ if (unlikely(fault_in_iov_iter_readable(i, bytes) == bytes)) { status = -EFAULT; break; } if (fatal_signal_pending(current)) { status = -EINTR; break; } status = a_ops->write_begin(file, mapping, pos, bytes, &folio, &fsdata); if (unlikely(status < 0)) break; offset = offset_in_folio(folio, pos); if (bytes > folio_size(folio) - offset) bytes = folio_size(folio) - offset; if (mapping_writably_mapped(mapping)) flush_dcache_folio(folio); copied = copy_folio_from_iter_atomic(folio, offset, bytes, i); flush_dcache_folio(folio); status = a_ops->write_end(file, mapping, pos, bytes, copied, folio, fsdata); if (unlikely(status != copied)) { iov_iter_revert(i, copied - max(status, 0L)); if (unlikely(status < 0)) break; } cond_resched(); if (unlikely(status == 0)) { /* * A short copy made ->write_end() reject the * thing entirely. Might be memory poisoning * halfway through, might be a race with munmap, * might be severe memory pressure. */ if (chunk > PAGE_SIZE) chunk /= 2; if (copied) { bytes = copied; goto retry; } } else { pos += status; written += status; } } while (iov_iter_count(i)); if (!written) return status; iocb->ki_pos += written; return written; } EXPORT_SYMBOL(generic_perform_write); /** * __generic_file_write_iter - write data to a file * @iocb: IO state structure (file, offset, etc.) * @from: iov_iter with data to write * * This function does all the work needed for actually writing data to a * file. It does all basic checks, removes SUID from the file, updates * modification times and calls proper subroutines depending on whether we * do direct IO or a standard buffered write. * * It expects i_rwsem to be grabbed unless we work on a block device or similar * object which does not need locking at all. * * This function does *not* take care of syncing data in case of O_SYNC write. * A caller has to handle it. This is mainly due to the fact that we want to * avoid syncing under i_rwsem. * * Return: * * number of bytes written, even for truncated writes * * negative error code if no data has been written at all */ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t ret; ret = file_remove_privs(file); if (ret) return ret; ret = file_update_time(file); if (ret) return ret; if (iocb->ki_flags & IOCB_DIRECT) { ret = generic_file_direct_write(iocb, from); /* * If the write stopped short of completing, fall back to * buffered writes. Some filesystems do this for writes to * holes, for example. For DAX files, a buffered write will * not succeed (even if it did, DAX does not handle dirty * page-cache pages correctly). */ if (ret < 0 || !iov_iter_count(from) || IS_DAX(inode)) return ret; return direct_write_fallback(iocb, from, ret, generic_perform_write(iocb, from)); } return generic_perform_write(iocb, from); } EXPORT_SYMBOL(__generic_file_write_iter); /** * generic_file_write_iter - write data to a file * @iocb: IO state structure * @from: iov_iter with data to write * * This is a wrapper around __generic_file_write_iter() to be used by most * filesystems. It takes care of syncing the file in case of O_SYNC file * and acquires i_rwsem as needed. * Return: * * negative error code if no data has been written at all of * vfs_fsync_range() failed for a synchronous write * * number of bytes written, even for truncated writes */ ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; ssize_t ret; inode_lock(inode); ret = generic_write_checks(iocb, from); if (ret > 0) ret = __generic_file_write_iter(iocb, from); inode_unlock(inode); if (ret > 0) ret = generic_write_sync(iocb, ret); return ret; } EXPORT_SYMBOL(generic_file_write_iter); /** * filemap_release_folio() - Release fs-specific metadata on a folio. * @folio: The folio which the kernel is trying to free. * @gfp: Memory allocation flags (and I/O mode). * * The address_space is trying to release any data attached to a folio * (presumably at folio->private). * * This will also be called if the private_2 flag is set on a page, * indicating that the folio has other metadata associated with it. * * The @gfp argument specifies whether I/O may be performed to release * this page (__GFP_IO), and whether the call may block * (__GFP_RECLAIM & __GFP_FS). * * Return: %true if the release was successful, otherwise %false. */ bool filemap_release_folio(struct folio *folio, gfp_t gfp) { struct address_space * const mapping = folio->mapping; BUG_ON(!folio_test_locked(folio)); if (!folio_needs_release(folio)) return true; if (folio_test_writeback(folio)) return false; if (mapping && mapping->a_ops->release_folio) return mapping->a_ops->release_folio(folio, gfp); return try_to_free_buffers(folio); } EXPORT_SYMBOL(filemap_release_folio); /** * filemap_invalidate_inode - Invalidate/forcibly write back a range of an inode's pagecache * @inode: The inode to flush * @flush: Set to write back rather than simply invalidate. * @start: First byte to in range. * @end: Last byte in range (inclusive), or LLONG_MAX for everything from start * onwards. * * Invalidate all the folios on an inode that contribute to the specified * range, possibly writing them back first. Whilst the operation is * undertaken, the invalidate lock is held to prevent new folios from being * installed. */ int filemap_invalidate_inode(struct inode *inode, bool flush, loff_t start, loff_t end) { struct address_space *mapping = inode->i_mapping; pgoff_t first = start >> PAGE_SHIFT; pgoff_t last = end >> PAGE_SHIFT; pgoff_t nr = end == LLONG_MAX ? ULONG_MAX : last - first + 1; if (!mapping || !mapping->nrpages || end < start) goto out; /* Prevent new folios from being added to the inode. */ filemap_invalidate_lock(mapping); if (!mapping->nrpages) goto unlock; unmap_mapping_pages(mapping, first, nr, false); /* Write back the data if we're asked to. */ if (flush) { struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = LONG_MAX, .range_start = start, .range_end = end, }; filemap_fdatawrite_wbc(mapping, &wbc); } /* Wait for writeback to complete on all folios and discard. */ invalidate_inode_pages2_range(mapping, start / PAGE_SIZE, end / PAGE_SIZE); unlock: filemap_invalidate_unlock(mapping); out: return filemap_check_errors(mapping); } EXPORT_SYMBOL_GPL(filemap_invalidate_inode); #ifdef CONFIG_CACHESTAT_SYSCALL /** * filemap_cachestat() - compute the page cache statistics of a mapping * @mapping: The mapping to compute the statistics for. * @first_index: The starting page cache index. * @last_index: The final page index (inclusive). * @cs: the cachestat struct to write the result to. * * This will query the page cache statistics of a mapping in the * page range of [first_index, last_index] (inclusive). The statistics * queried include: number of dirty pages, number of pages marked for * writeback, and the number of (recently) evicted pages. */ static void filemap_cachestat(struct address_space *mapping, pgoff_t first_index, pgoff_t last_index, struct cachestat *cs) { XA_STATE(xas, &mapping->i_pages, first_index); struct folio *folio; /* Flush stats (and potentially sleep) outside the RCU read section. */ mem_cgroup_flush_stats_ratelimited(NULL); rcu_read_lock(); xas_for_each(&xas, folio, last_index) { int order; unsigned long nr_pages; pgoff_t folio_first_index, folio_last_index; /* * Don't deref the folio. It is not pinned, and might * get freed (and reused) underneath us. * * We *could* pin it, but that would be expensive for * what should be a fast and lightweight syscall. * * Instead, derive all information of interest from * the rcu-protected xarray. */ if (xas_retry(&xas, folio)) continue; order = xas_get_order(&xas); nr_pages = 1 << order; folio_first_index = round_down(xas.xa_index, 1 << order); folio_last_index = folio_first_index + nr_pages - 1; /* Folios might straddle the range boundaries, only count covered pages */ if (folio_first_index < first_index) nr_pages -= first_index - folio_first_index; if (folio_last_index > last_index) nr_pages -= folio_last_index - last_index; if (xa_is_value(folio)) { /* page is evicted */ void *shadow = (void *)folio; bool workingset; /* not used */ cs->nr_evicted += nr_pages; #ifdef CONFIG_SWAP /* implies CONFIG_MMU */ if (shmem_mapping(mapping)) { /* shmem file - in swap cache */ swp_entry_t swp = radix_to_swp_entry(folio); /* swapin error results in poisoned entry */ if (non_swap_entry(swp)) goto resched; /* * Getting a swap entry from the shmem * inode means we beat * shmem_unuse(). rcu_read_lock() * ensures swapoff waits for us before * freeing the swapper space. However, * we can race with swapping and * invalidation, so there might not be * a shadow in the swapcache (yet). */ shadow = get_shadow_from_swap_cache(swp); if (!shadow) goto resched; } #endif if (workingset_test_recent(shadow, true, &workingset, false)) cs->nr_recently_evicted += nr_pages; goto resched; } /* page is in cache */ cs->nr_cache += nr_pages; if (xas_get_mark(&xas, PAGECACHE_TAG_DIRTY)) cs->nr_dirty += nr_pages; if (xas_get_mark(&xas, PAGECACHE_TAG_WRITEBACK)) cs->nr_writeback += nr_pages; resched: if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } } rcu_read_unlock(); } /* * The cachestat(2) system call. * * cachestat() returns the page cache statistics of a file in the * bytes range specified by `off` and `len`: number of cached pages, * number of dirty pages, number of pages marked for writeback, * number of evicted pages, and number of recently evicted pages. * * An evicted page is a page that is previously in the page cache * but has been evicted since. A page is recently evicted if its last * eviction was recent enough that its reentry to the cache would * indicate that it is actively being used by the system, and that * there is memory pressure on the system. * * `off` and `len` must be non-negative integers. If `len` > 0, * the queried range is [`off`, `off` + `len`]. If `len` == 0, * we will query in the range from `off` to the end of the file. * * The `flags` argument is unused for now, but is included for future * extensibility. User should pass 0 (i.e no flag specified). * * Currently, hugetlbfs is not supported. * * Because the status of a page can change after cachestat() checks it * but before it returns to the application, the returned values may * contain stale information. * * return values: * zero - success * -EFAULT - cstat or cstat_range points to an illegal address * -EINVAL - invalid flags * -EBADF - invalid file descriptor * -EOPNOTSUPP - file descriptor is of a hugetlbfs file */ SYSCALL_DEFINE4(cachestat, unsigned int, fd, struct cachestat_range __user *, cstat_range, struct cachestat __user *, cstat, unsigned int, flags) { CLASS(fd, f)(fd); struct address_space *mapping; struct cachestat_range csr; struct cachestat cs; pgoff_t first_index, last_index; if (fd_empty(f)) return -EBADF; if (copy_from_user(&csr, cstat_range, sizeof(struct cachestat_range))) return -EFAULT; /* hugetlbfs is not supported */ if (is_file_hugepages(fd_file(f))) return -EOPNOTSUPP; if (flags != 0) return -EINVAL; first_index = csr.off >> PAGE_SHIFT; last_index = csr.len == 0 ? ULONG_MAX : (csr.off + csr.len - 1) >> PAGE_SHIFT; memset(&cs, 0, sizeof(struct cachestat)); mapping = fd_file(f)->f_mapping; filemap_cachestat(mapping, first_index, last_index, &cs); if (copy_to_user(cstat, &cs, sizeof(struct cachestat))) return -EFAULT; return 0; } #endif /* CONFIG_CACHESTAT_SYSCALL */ |
| 71 41 249 80 80 10 71 1 80 80 1 80 242 198 242 312 312 217 216 216 113 217 312 348 348 241 40 221 195 242 348 347 40 40 40 40 1 151 151 159 159 159 60 100 252 249 168 168 258 281 168 168 168 168 168 1 167 168 168 168 249 252 252 250 250 252 97 97 97 97 97 97 41 41 40 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 | /* * 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_rwsem (while writing or truncating, not reading or faulting) * mm->mmap_lock * mapping->invalidate_lock (in filemap_fault) * folio_lock * hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share, see hugetlbfs below) * vma_start_write * mapping->i_mmap_rwsem * 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 block_dirty_folio) * i_pages lock (widely used) * lruvec->lru_lock (in folio_lruvec_lock_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_mmap_rwsem (memory_failure, collect_procs_anon) * ->tasklist_lock * pte map lock * * hugetlbfs PageHuge() take locks in this order: * hugetlb_fault_mutex (hugetlbfs specific page fault mutex) * vma_lock (hugetlb specific lock for pmd_sharing) * mapping->i_mmap_rwsem (also used for hugetlb pmd sharing) * folio_lock */ #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 <linux/mm_inline.h> #include <linux/oom.h> #include <asm/tlbflush.h> #define CREATE_TRACE_POINTS #include <trace/events/tlb.h> #include <trace/events/migrate.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->num_children = 0; anon_vma->num_active_vmas = 0; 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 folio_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 folio_lock_anon_vma_read(). This orders: * * folio_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 folio_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. */ 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; mmap_assert_locked(mm); 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; anon_vma->num_children++; /* self-parent link for new root */ 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); anon_vma->num_active_vmas++; 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_expand(), vma_merge(), __split_vma(), * copy_vma() and anon_vma_fork(). The first four 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 it has no vma and only one * anon_vma child. * * 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->num_children < 2 && anon_vma->num_active_vmas == 0) dst->anon_vma = anon_vma; } if (dst->anon_vma) dst->anon_vma->num_active_vmas++; unlock_anon_vma_root(root); return 0; enomem_failure: /* * dst->anon_vma is dropped here otherwise its num_active_vmas 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; anon_vma->num_active_vmas++; 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->num_children++; 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->num_children--; continue; } list_del(&avc->same_vma); anon_vma_chain_free(avc); } if (vma->anon_vma) { vma->anon_vma->num_active_vmas--; /* * 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->num_children); VM_WARN_ON(anon_vma->num_active_vmas); 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 folio_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 * folio_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. * * NOTE: the caller should normally hold folio lock when calling this. If * not, the caller needs to double check the anon_vma didn't change after * taking the anon_vma lock for either read or write (UFFDIO_MOVE can modify it * concurrently without folio lock protection). See folio_lock_anon_vma_read() * which has already covered that, and comment above remap_pages(). */ struct anon_vma *folio_get_anon_vma(const struct folio *folio) { struct anon_vma *anon_vma = NULL; unsigned long anon_mapping; rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(folio->mapping); if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) goto out; if (!folio_mapped(folio)) 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 folio 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 (!folio_mapped(folio)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; } out: rcu_read_unlock(); return anon_vma; } /* * Similar to folio_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 folio_get_anon_vma() and then block on the mutex * on !rwc->try_lock case. */ struct anon_vma *folio_lock_anon_vma_read(const struct folio *folio, struct rmap_walk_control *rwc) { struct anon_vma *anon_vma = NULL; struct anon_vma *root_anon_vma; unsigned long anon_mapping; retry: rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(folio->mapping); if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) goto out; if (!folio_mapped(folio)) 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)) { /* * folio_move_anon_rmap() might have changed the anon_vma as we * might not hold the folio lock here. */ if (unlikely((unsigned long)READ_ONCE(folio->mapping) != anon_mapping)) { up_read(&root_anon_vma->rwsem); rcu_read_unlock(); goto retry; } /* * If the folio 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 (!folio_mapped(folio)) { up_read(&root_anon_vma->rwsem); anon_vma = NULL; } goto out; } if (rwc && rwc->try_lock) { anon_vma = NULL; rwc->contended = true; goto out; } /* trylock failed, we got to sleep */ if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; goto out; } if (!folio_mapped(folio)) { 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); /* * folio_move_anon_rmap() might have changed the anon_vma as we might * not hold the folio lock here. */ if (unlikely((unsigned long)READ_ONCE(folio->mapping) != anon_mapping)) { anon_vma_unlock_read(anon_vma); put_anon_vma(anon_vma); anon_vma = NULL; goto retry; } 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; } #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 = ¤t->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 = ¤t->tlb_ubc; if (tlb_ubc->writable) try_to_unmap_flush(); } /* * Bits 0-14 of mm->tlb_flush_batched record pending generations. * Bits 16-30 of mm->tlb_flush_batched bit record flushed generations. */ #define TLB_FLUSH_BATCH_FLUSHED_SHIFT 16 #define TLB_FLUSH_BATCH_PENDING_MASK \ ((1 << (TLB_FLUSH_BATCH_FLUSHED_SHIFT - 1)) - 1) #define TLB_FLUSH_BATCH_PENDING_LARGE \ (TLB_FLUSH_BATCH_PENDING_MASK / 2) static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval, unsigned long uaddr) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; int batch; bool writable = pte_dirty(pteval); if (!pte_accessible(mm, pteval)) return; arch_tlbbatch_add_pending(&tlb_ubc->arch, mm, uaddr); tlb_ubc->flush_required = true; /* * Ensure compiler does not re-order the setting of tlb_flush_batched * before the PTE is cleared. */ barrier(); batch = atomic_read(&mm->tlb_flush_batched); retry: if ((batch & TLB_FLUSH_BATCH_PENDING_MASK) > TLB_FLUSH_BATCH_PENDING_LARGE) { /* * Prevent `pending' from catching up with `flushed' because of * overflow. Reset `pending' and `flushed' to be 1 and 0 if * `pending' becomes large. */ if (!atomic_try_cmpxchg(&mm->tlb_flush_batched, &batch, 1)) goto retry; } else { atomic_inc(&mm->tlb_flush_batched); } /* * 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) { if (!(flags & TTU_BATCH_FLUSH)) return false; return arch_tlbbatch_should_defer(mm); } /* * 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) { int batch = atomic_read(&mm->tlb_flush_batched); int pending = batch & TLB_FLUSH_BATCH_PENDING_MASK; int flushed = batch >> TLB_FLUSH_BATCH_FLUSHED_SHIFT; if (pending != flushed) { arch_flush_tlb_batched_pending(mm); /* * If the new TLB flushing is pending during flushing, leave * mm->tlb_flush_batched as is, to avoid losing flushing. */ atomic_cmpxchg(&mm->tlb_flush_batched, batch, pending | (pending << TLB_FLUSH_BATCH_FLUSHED_SHIFT)); } } #else static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval, unsigned long uaddr) { } static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { return false; } #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ /** * page_address_in_vma - The virtual address of a page in this VMA. * @folio: The folio containing the page. * @page: The page within the folio. * @vma: The VMA we need to know the address in. * * Calculates the user virtual address of this page in the specified VMA. * It is the caller's responsibililty to check the page is actually * within the VMA. There may not currently be a PTE pointing at this * page, but if a page fault occurs at this address, this is the page * which will be accessed. * * Context: Caller should hold a reference to the folio. Caller should * hold a lock (eg the i_mmap_lock or the mmap_lock) which keeps the * VMA from being altered. * * Return: The virtual address corresponding to this page in the VMA. */ unsigned long page_address_in_vma(const struct folio *folio, const struct page *page, const struct vm_area_struct *vma) { if (folio_test_anon(folio)) { struct anon_vma *page__anon_vma = folio_anon_vma(folio); /* * 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 (!vma->vm_file) { return -EFAULT; } else if (vma->vm_file->f_mapping != folio->mapping) { return -EFAULT; } /* KSM folios don't reach here because of the !page__anon_vma check */ return vma_address(vma, page_pgoff(folio, page), 1); } /* * Returns the actual pmd_t* where we expect 'address' to be mapped from, or * NULL if it doesn't exist. No guarantees / checks on what the pmd_t* * represents. */ 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; 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); out: return pmd; } struct folio_referenced_arg { int mapcount; int referenced; unsigned long vm_flags; struct mem_cgroup *memcg; }; /* * arg: folio_referenced_arg will be passed */ static bool folio_referenced_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct folio_referenced_arg *pra = arg; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); int referenced = 0; unsigned long start = address, ptes = 0; while (page_vma_mapped_walk(&pvmw)) { address = pvmw.address; if (vma->vm_flags & VM_LOCKED) { if (!folio_test_large(folio) || !pvmw.pte) { /* Restore the mlock which got missed */ mlock_vma_folio(folio, vma); page_vma_mapped_walk_done(&pvmw); pra->vm_flags |= VM_LOCKED; return false; /* To break the loop */ } /* * For large folio fully mapped to VMA, will * be handled after the pvmw loop. * * For large folio cross VMA boundaries, it's * expected to be picked by page reclaim. But * should skip reference of pages which are in * the range of VM_LOCKED vma. As page reclaim * should just count the reference of pages out * the range of VM_LOCKED vma. */ ptes++; pra->mapcount--; continue; } /* * Skip the non-shared swapbacked folio mapped solely by * the exiting or OOM-reaped process. This avoids redundant * swap-out followed by an immediate unmap. */ if ((!atomic_read(&vma->vm_mm->mm_users) || check_stable_address_space(vma->vm_mm)) && folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_likely_mapped_shared(folio)) { pra->referenced = -1; page_vma_mapped_walk_done(&pvmw); return false; } if (lru_gen_enabled() && pvmw.pte) { if (lru_gen_look_around(&pvmw)) referenced++; } else if (pvmw.pte) { if (ptep_clear_flush_young_notify(vma, address, pvmw.pte)) referenced++; } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { if (pmdp_clear_flush_young_notify(vma, address, pvmw.pmd)) referenced++; } else { /* unexpected pmd-mapped folio? */ WARN_ON_ONCE(1); } pra->mapcount--; } if ((vma->vm_flags & VM_LOCKED) && folio_test_large(folio) && folio_within_vma(folio, vma)) { unsigned long s_align, e_align; s_align = ALIGN_DOWN(start, PMD_SIZE); e_align = ALIGN_DOWN(start + folio_size(folio) - 1, PMD_SIZE); /* folio doesn't cross page table boundary and fully mapped */ if ((s_align == e_align) && (ptes == folio_nr_pages(folio))) { /* Restore the mlock which got missed */ mlock_vma_folio(folio, vma); pra->vm_flags |= VM_LOCKED; return false; /* To break the loop */ } } if (referenced) folio_clear_idle(folio); if (folio_test_clear_young(folio)) referenced++; if (referenced) { pra->referenced++; pra->vm_flags |= vma->vm_flags & ~VM_LOCKED; } if (!pra->mapcount) return false; /* To break the loop */ return true; } static bool invalid_folio_referenced_vma(struct vm_area_struct *vma, void *arg) { struct folio_referenced_arg *pra = arg; struct mem_cgroup *memcg = pra->memcg; /* * Ignore references from this mapping if it has no recency. If the * folio has been used in another mapping, we will catch it; if this * other mapping is already gone, the unmap path will have set the * referenced flag or activated the folio in zap_pte_range(). */ if (!vma_has_recency(vma)) return true; /* * If we are reclaiming on behalf of a cgroup, skip counting on behalf * of references from different cgroups. */ if (memcg && !mm_match_cgroup(vma->vm_mm, memcg)) return true; return false; } /** * folio_referenced() - Test if the folio was referenced. * @folio: The folio to test. * @is_locked: Caller holds lock on the folio. * @memcg: target memory cgroup * @vm_flags: A combination of all the vma->vm_flags which referenced the folio. * * Quick test_and_clear_referenced for all mappings of a folio, * * Return: The number of mappings which referenced the folio. Return -1 if * the function bailed out due to rmap lock contention. */ int folio_referenced(struct folio *folio, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags) { bool we_locked = false; struct folio_referenced_arg pra = { .mapcount = folio_mapcount(folio), .memcg = memcg, }; struct rmap_walk_control rwc = { .rmap_one = folio_referenced_one, .arg = (void *)&pra, .anon_lock = folio_lock_anon_vma_read, .try_lock = true, .invalid_vma = invalid_folio_referenced_vma, }; *vm_flags = 0; if (!pra.mapcount) return 0; if (!folio_raw_mapping(folio)) return 0; if (!is_locked && (!folio_test_anon(folio) || folio_test_ksm(folio))) { we_locked = folio_trylock(folio); if (!we_locked) return 1; } rmap_walk(folio, &rwc); *vm_flags = pra.vm_flags; if (we_locked) folio_unlock(folio); return rwc.contended ? -1 : pra.referenced; } static int page_vma_mkclean_one(struct page_vma_mapped_walk *pvmw) { int cleaned = 0; struct vm_area_struct *vma = pvmw->vma; struct mmu_notifier_range range; unsigned long address = pvmw->address; /* * We have to assume the worse case ie pmd for invalidation. Note that * the folio can not be freed from this function. */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, vma->vm_mm, address, vma_address_end(pvmw)); mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(pvmw)) { int ret = 0; address = pvmw->address; if (pvmw->pte) { pte_t *pte = pvmw->pte; pte_t entry = ptep_get(pte); if (!pte_dirty(entry) && !pte_write(entry)) continue; flush_cache_page(vma, address, pte_pfn(entry)); 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_range(vma, address, address + HPAGE_PMD_SIZE); 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 folio? */ WARN_ON_ONCE(1); #endif } if (ret) cleaned++; } mmu_notifier_invalidate_range_end(&range); return cleaned; } static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, PVMW_SYNC); int *cleaned = arg; *cleaned += page_vma_mkclean_one(&pvmw); 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 folio_mkclean(struct folio *folio) { 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(!folio_test_locked(folio)); if (!folio_mapped(folio)) return 0; mapping = folio_mapping(folio); if (!mapping) return 0; rmap_walk(folio, &rwc); return cleaned; } EXPORT_SYMBOL_GPL(folio_mkclean); /** * pfn_mkclean_range - Cleans the PTEs (including PMDs) mapped with range of * [@pfn, @pfn + @nr_pages) at the specific offset (@pgoff) * within the @vma of shared mappings. And since clean PTEs * should also be readonly, write protects them too. * @pfn: start pfn. * @nr_pages: number of physically contiguous pages srarting with @pfn. * @pgoff: page offset that the @pfn mapped with. * @vma: vma that @pfn mapped within. * * Returns the number of cleaned PTEs (including PMDs). */ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, struct vm_area_struct *vma) { struct page_vma_mapped_walk pvmw = { .pfn = pfn, .nr_pages = nr_pages, .pgoff = pgoff, .vma = vma, .flags = PVMW_SYNC, }; if (invalid_mkclean_vma(vma, NULL)) return 0; pvmw.address = vma_address(vma, pgoff, nr_pages); VM_BUG_ON_VMA(pvmw.address == -EFAULT, vma); return page_vma_mkclean_one(&pvmw); } static __always_inline unsigned int __folio_add_rmap(struct folio *folio, struct page *page, int nr_pages, enum rmap_level level, int *nr_pmdmapped) { atomic_t *mapped = &folio->_nr_pages_mapped; const int orig_nr_pages = nr_pages; int first = 0, nr = 0; __folio_rmap_sanity_checks(folio, page, nr_pages, level); switch (level) { case RMAP_LEVEL_PTE: if (!folio_test_large(folio)) { nr = atomic_inc_and_test(&folio->_mapcount); break; } do { first += atomic_inc_and_test(&page->_mapcount); } while (page++, --nr_pages > 0); if (first && atomic_add_return_relaxed(first, mapped) < ENTIRELY_MAPPED) nr = first; atomic_add(orig_nr_pages, &folio->_large_mapcount); break; case RMAP_LEVEL_PMD: first = atomic_inc_and_test(&folio->_entire_mapcount); if (first) { nr = atomic_add_return_relaxed(ENTIRELY_MAPPED, mapped); if (likely(nr < ENTIRELY_MAPPED + ENTIRELY_MAPPED)) { *nr_pmdmapped = folio_nr_pages(folio); nr = *nr_pmdmapped - (nr & FOLIO_PAGES_MAPPED); /* Raced ahead of a remove and another add? */ if (unlikely(nr < 0)) nr = 0; } else { /* Raced ahead of a remove of ENTIRELY_MAPPED */ nr = 0; } } atomic_inc(&folio->_large_mapcount); break; } return nr; } /** * folio_move_anon_rmap - move a folio to our anon_vma * @folio: The folio to move to our anon_vma * @vma: The vma the folio belongs to * * When a folio belongs exclusively to one process after a COW event, * that folio 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 folio_move_anon_rmap(struct folio *folio, struct vm_area_struct *vma) { void *anon_vma = vma->anon_vma; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_VMA(!anon_vma, vma); anon_vma += PAGE_MAPPING_ANON; /* * Ensure that anon_vma and the PAGE_MAPPING_ANON bit are written * simultaneously, so a concurrent reader (eg folio_referenced()'s * folio_test_anon()) will not see one without the other. */ WRITE_ONCE(folio->mapping, anon_vma); } /** * __folio_set_anon - set up a new anonymous rmap for a folio * @folio: The folio to set up the new anonymous rmap for. * @vma: VM area to add the folio to. * @address: User virtual address of the mapping * @exclusive: Whether the folio is exclusive to the process. */ static void __folio_set_anon(struct folio *folio, struct vm_area_struct *vma, unsigned long address, bool exclusive) { struct anon_vma *anon_vma = vma->anon_vma; BUG_ON(!anon_vma); /* * If the folio isn't exclusive to this vma, we must use the _oldest_ * possible anon_vma for the folio mapping! */ if (!exclusive) anon_vma = anon_vma->root; /* * page_idle does a lockless/optimistic rmap scan on folio->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(folio->mapping, (struct address_space *) anon_vma); folio->index = linear_page_index(vma, address); } /** * __page_check_anon_rmap - sanity check anonymous rmap addition * @folio: The folio containing @page. * @page: the page to check the mapping of * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped */ static void __page_check_anon_rmap(const struct folio *folio, const 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 folio_add_anon_rmap_*() because the caller * always holds the page locked. * * We have exclusion against folio_add_new_anon_rmap because those pages * are initially only visible via the pagetables, and the pte is locked * over the call to folio_add_new_anon_rmap. */ VM_BUG_ON_FOLIO(folio_anon_vma(folio)->root != vma->anon_vma->root, folio); VM_BUG_ON_PAGE(page_pgoff(folio, page) != linear_page_index(vma, address), page); } static void __folio_mod_stat(struct folio *folio, int nr, int nr_pmdmapped) { int idx; if (nr) { idx = folio_test_anon(folio) ? NR_ANON_MAPPED : NR_FILE_MAPPED; __lruvec_stat_mod_folio(folio, idx, nr); } if (nr_pmdmapped) { if (folio_test_anon(folio)) { idx = NR_ANON_THPS; __lruvec_stat_mod_folio(folio, idx, nr_pmdmapped); } else { /* NR_*_PMDMAPPED are not maintained per-memcg */ idx = folio_test_swapbacked(folio) ? NR_SHMEM_PMDMAPPED : NR_FILE_PMDMAPPED; __mod_node_page_state(folio_pgdat(folio), idx, nr_pmdmapped); } } } static __always_inline void __folio_add_anon_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, unsigned long address, rmap_t flags, enum rmap_level level) { int i, nr, nr_pmdmapped = 0; VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); nr = __folio_add_rmap(folio, page, nr_pages, level, &nr_pmdmapped); if (likely(!folio_test_ksm(folio))) __page_check_anon_rmap(folio, page, vma, address); __folio_mod_stat(folio, nr, nr_pmdmapped); if (flags & RMAP_EXCLUSIVE) { switch (level) { case RMAP_LEVEL_PTE: for (i = 0; i < nr_pages; i++) SetPageAnonExclusive(page + i); break; case RMAP_LEVEL_PMD: SetPageAnonExclusive(page); break; } } for (i = 0; i < nr_pages; i++) { struct page *cur_page = page + i; /* While PTE-mapping a THP we have a PMD and a PTE mapping. */ VM_WARN_ON_FOLIO((atomic_read(&cur_page->_mapcount) > 0 || (folio_test_large(folio) && folio_entire_mapcount(folio) > 1)) && PageAnonExclusive(cur_page), folio); } /* * For large folio, only mlock it if it's fully mapped to VMA. It's * not easy to check whether the large folio is fully mapped to VMA * here. Only mlock normal 4K folio and leave page reclaim to handle * large folio. */ if (!folio_test_large(folio)) mlock_vma_folio(folio, vma); } /** * folio_add_anon_rmap_ptes - add PTE mappings to a page range of an anon folio * @folio: The folio to add the mappings to * @page: The first page to add * @nr_pages: The number of pages which will be mapped * @vma: The vm area in which the mappings are added * @address: The user virtual address of the first page to map * @flags: The rmap flags * * The page range of folio is defined by [first_page, first_page + nr_pages) * * The caller needs to hold the page table lock, and the page must be locked in * the anon_vma case: to serialize mapping,index checking after setting, * and to ensure that an anon folio is not being upgraded racily to a KSM folio * (but KSM folios are never downgraded). */ void folio_add_anon_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { __folio_add_anon_rmap(folio, page, nr_pages, vma, address, flags, RMAP_LEVEL_PTE); } /** * folio_add_anon_rmap_pmd - add a PMD mapping to a page range of an anon folio * @folio: The folio to add the mapping to * @page: The first page to add * @vma: The vm area in which the mapping is added * @address: The user virtual address of the first page to map * @flags: The rmap flags * * The page range of folio is defined by [first_page, first_page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock, and the page must be locked in * the anon_vma case: to serialize mapping,index checking after setting. */ void folio_add_anon_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_add_anon_rmap(folio, page, HPAGE_PMD_NR, vma, address, flags, RMAP_LEVEL_PMD); #else WARN_ON_ONCE(true); #endif } /** * folio_add_new_anon_rmap - Add mapping to a new anonymous folio. * @folio: The folio to add the mapping to. * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped * @flags: The rmap flags * * Like folio_add_anon_rmap_*() but must only be called on *new* folios. * This means the inc-and-test can be bypassed. * The folio doesn't necessarily need to be locked while it's exclusive * unless two threads map it concurrently. However, the folio must be * locked if it's shared. * * If the folio is pmd-mappable, it is accounted as a THP. */ void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { const int nr = folio_nr_pages(folio); const bool exclusive = flags & RMAP_EXCLUSIVE; int nr_pmdmapped = 0; VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); VM_WARN_ON_FOLIO(!exclusive && !folio_test_locked(folio), folio); VM_BUG_ON_VMA(address < vma->vm_start || address + (nr << PAGE_SHIFT) > vma->vm_end, vma); /* * VM_DROPPABLE mappings don't swap; instead they're just dropped when * under memory pressure. */ if (!folio_test_swapbacked(folio) && !(vma->vm_flags & VM_DROPPABLE)) __folio_set_swapbacked(folio); __folio_set_anon(folio, vma, address, exclusive); if (likely(!folio_test_large(folio))) { /* increment count (starts at -1) */ atomic_set(&folio->_mapcount, 0); if (exclusive) SetPageAnonExclusive(&folio->page); } else if (!folio_test_pmd_mappable(folio)) { int i; for (i = 0; i < nr; i++) { struct page *page = folio_page(folio, i); /* increment count (starts at -1) */ atomic_set(&page->_mapcount, 0); if (exclusive) SetPageAnonExclusive(page); } /* increment count (starts at -1) */ atomic_set(&folio->_large_mapcount, nr - 1); atomic_set(&folio->_nr_pages_mapped, nr); } else { /* increment count (starts at -1) */ atomic_set(&folio->_entire_mapcount, 0); /* increment count (starts at -1) */ atomic_set(&folio->_large_mapcount, 0); atomic_set(&folio->_nr_pages_mapped, ENTIRELY_MAPPED); if (exclusive) SetPageAnonExclusive(&folio->page); nr_pmdmapped = nr; } __folio_mod_stat(folio, nr, nr_pmdmapped); mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON, 1); } static __always_inline void __folio_add_file_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, enum rmap_level level) { int nr, nr_pmdmapped = 0; VM_WARN_ON_FOLIO(folio_test_anon(folio), folio); nr = __folio_add_rmap(folio, page, nr_pages, level, &nr_pmdmapped); __folio_mod_stat(folio, nr, nr_pmdmapped); /* See comments in folio_add_anon_rmap_*() */ if (!folio_test_large(folio)) mlock_vma_folio(folio, vma); } /** * folio_add_file_rmap_ptes - add PTE mappings to a page range of a folio * @folio: The folio to add the mappings to * @page: The first page to add * @nr_pages: The number of pages that will be mapped using PTEs * @vma: The vm area in which the mappings are added * * The page range of the folio is defined by [page, page + nr_pages) * * The caller needs to hold the page table lock. */ void folio_add_file_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma) { __folio_add_file_rmap(folio, page, nr_pages, vma, RMAP_LEVEL_PTE); } /** * folio_add_file_rmap_pmd - add a PMD mapping to a page range of a folio * @folio: The folio to add the mapping to * @page: The first page to add * @vma: The vm area in which the mapping is added * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock. */ void folio_add_file_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_add_file_rmap(folio, page, HPAGE_PMD_NR, vma, RMAP_LEVEL_PMD); #else WARN_ON_ONCE(true); #endif } static __always_inline void __folio_remove_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, enum rmap_level level) { atomic_t *mapped = &folio->_nr_pages_mapped; int last = 0, nr = 0, nr_pmdmapped = 0; bool partially_mapped = false; __folio_rmap_sanity_checks(folio, page, nr_pages, level); switch (level) { case RMAP_LEVEL_PTE: if (!folio_test_large(folio)) { nr = atomic_add_negative(-1, &folio->_mapcount); break; } atomic_sub(nr_pages, &folio->_large_mapcount); do { last += atomic_add_negative(-1, &page->_mapcount); } while (page++, --nr_pages > 0); if (last && atomic_sub_return_relaxed(last, mapped) < ENTIRELY_MAPPED) nr = last; partially_mapped = nr && atomic_read(mapped); break; case RMAP_LEVEL_PMD: atomic_dec(&folio->_large_mapcount); last = atomic_add_negative(-1, &folio->_entire_mapcount); if (last) { nr = atomic_sub_return_relaxed(ENTIRELY_MAPPED, mapped); if (likely(nr < ENTIRELY_MAPPED)) { nr_pmdmapped = folio_nr_pages(folio); nr = nr_pmdmapped - (nr & FOLIO_PAGES_MAPPED); /* Raced ahead of another remove and an add? */ if (unlikely(nr < 0)) nr = 0; } else { /* An add of ENTIRELY_MAPPED raced ahead */ nr = 0; } } partially_mapped = nr && nr < nr_pmdmapped; break; } /* * Queue anon large folio for deferred split if at least one page of * the folio is unmapped and at least one page is still mapped. * * Check partially_mapped first to ensure it is a large folio. */ if (partially_mapped && folio_test_anon(folio) && !folio_test_partially_mapped(folio)) deferred_split_folio(folio, true); __folio_mod_stat(folio, -nr, -nr_pmdmapped); /* * It would be tidy to reset folio_test_anon mapping when fully * unmapped, but that might overwrite a racing folio_add_anon_rmap_*() * which increments mapcount after us but sets mapping before us: * so leave the reset to free_pages_prepare, and remember that * it's only reliable while mapped. */ munlock_vma_folio(folio, vma); } /** * folio_remove_rmap_ptes - remove PTE mappings from a page range of a folio * @folio: The folio to remove the mappings from * @page: The first page to remove * @nr_pages: The number of pages that will be removed from the mapping * @vma: The vm area from which the mappings are removed * * The page range of the folio is defined by [page, page + nr_pages) * * The caller needs to hold the page table lock. */ void folio_remove_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma) { __folio_remove_rmap(folio, page, nr_pages, vma, RMAP_LEVEL_PTE); } /** * folio_remove_rmap_pmd - remove a PMD mapping from a page range of a folio * @folio: The folio to remove the mapping from * @page: The first page to remove * @vma: The vm area from which the mapping is removed * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock. */ void folio_remove_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_remove_rmap(folio, page, HPAGE_PMD_NR, vma, RMAP_LEVEL_PMD); #else WARN_ON_ONCE(true); #endif } /* * @arg: enum ttu_flags will be passed to this argument */ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); pte_t pteval; struct page *subpage; bool anon_exclusive, ret = true; struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; unsigned long pfn; unsigned long hsz = 0; /* * When racing against e.g. zap_pte_range() on another cpu, * in between its ptep_get_and_clear_full() and folio_remove_rmap_*(), * try_to_unmap() may return before page_mapped() has become false, * if page table locking is skipped: use TTU_SYNC to wait for that. */ if (flags & TTU_SYNC) pvmw.flags = PVMW_SYNC; /* * 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 folio can not be freed in this function as call of * try_to_unmap() must hold a reference on the folio. */ range.end = vma_address_end(&pvmw); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address, range.end); if (folio_test_hugetlb(folio)) { /* * If sharing is possible, start and end will be adjusted * accordingly. */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); /* We need the huge page size for set_huge_pte_at() */ hsz = huge_page_size(hstate_vma(vma)); } mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { /* * If the folio is in an mlock()d vma, we must not swap it out. */ if (!(flags & TTU_IGNORE_MLOCK) && (vma->vm_flags & VM_LOCKED)) { /* Restore the mlock which got missed */ if (!folio_test_large(folio)) mlock_vma_folio(folio, vma); goto walk_abort; } if (!pvmw.pte) { if (unmap_huge_pmd_locked(vma, pvmw.address, pvmw.pmd, folio)) goto walk_done; if (flags & TTU_SPLIT_HUGE_PMD) { /* * We temporarily have to drop the PTL and * restart so we can process the PTE-mapped THP. */ split_huge_pmd_locked(vma, pvmw.address, pvmw.pmd, false, folio); flags &= ~TTU_SPLIT_HUGE_PMD; page_vma_mapped_walk_restart(&pvmw); continue; } } /* Unexpected PMD-mapped THP? */ VM_BUG_ON_FOLIO(!pvmw.pte, folio); pfn = pte_pfn(ptep_get(pvmw.pte)); subpage = folio_page(folio, pfn - folio_pfn(folio)); address = pvmw.address; anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(subpage); if (folio_test_hugetlb(folio)) { bool anon = folio_test_anon(folio); /* * The try_to_unmap() is only passed a hugetlb page * in the case where the hugetlb page is poisoned. */ VM_BUG_ON_PAGE(!PageHWPoison(subpage), subpage); /* * huge_pmd_unshare may unmap 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); /* * To call huge_pmd_unshare, i_mmap_rwsem must be * held in write mode. Caller needs to explicitly * do this outside rmap routines. * * We also must hold hugetlb vma_lock in write mode. * Lock order dictates acquiring vma_lock BEFORE * i_mmap_rwsem. We can only try lock here and fail * if unsuccessful. */ if (!anon) { VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) goto walk_abort; if (huge_pmd_unshare(mm, vma, address, pvmw.pte)) { hugetlb_vma_unlock_write(vma); flush_tlb_range(vma, 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. */ goto walk_done; } hugetlb_vma_unlock_write(vma); } pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); } else { flush_cache_page(vma, address, pfn); /* Nuke the page table entry. */ 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 folio. * 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, pteval, address); } else { pteval = ptep_clear_flush(vma, address, pvmw.pte); } } /* * Now the pte is cleared. If this pte was uffd-wp armed, * we may want to replace a none pte with a marker pte if * it's file-backed, so we don't lose the tracking info. */ pte_install_uffd_wp_if_needed(vma, address, pvmw.pte, pteval); /* Set the dirty flag on the folio now the pte is gone. */ if (pte_dirty(pteval)) folio_mark_dirty(folio); /* Update high watermark before we lower rss */ update_hiwater_rss(mm); if (PageHWPoison(subpage) && (flags & TTU_HWPOISON)) { pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { hugetlb_count_sub(folio_nr_pages(folio), mm); set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); } else { dec_mm_counter(mm, mm_counter(folio)); 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(folio)); } else if (folio_test_anon(folio)) { swp_entry_t entry = page_swap_entry(subpage); pte_t swp_pte; /* * Store the swap location in the pte. * See handle_pte_fault() ... */ if (unlikely(folio_test_swapbacked(folio) != folio_test_swapcache(folio))) { WARN_ON_ONCE(1); goto walk_abort; } /* MADV_FREE page check */ if (!folio_test_swapbacked(folio)) { int ref_count, map_count; /* * Synchronize with gup_pte_range(): * - clear PTE; barrier; read refcount * - inc refcount; barrier; read PTE */ smp_mb(); ref_count = folio_ref_count(folio); map_count = folio_mapcount(folio); /* * Order reads for page refcount and dirty flag * (see comments in __remove_mapping()). */ smp_rmb(); /* * The only page refs must be one from isolation * plus the rmap(s) (dropped by discard:). */ if (ref_count == 1 + map_count && (!folio_test_dirty(folio) || /* * Unlike MADV_FREE mappings, VM_DROPPABLE * ones can be dropped even if they've * been dirtied. */ (vma->vm_flags & VM_DROPPABLE))) { dec_mm_counter(mm, MM_ANONPAGES); goto discard; } /* * If the folio was redirtied, it cannot be * discarded. Remap the page to page table. */ set_pte_at(mm, address, pvmw.pte, pteval); /* * Unlike MADV_FREE mappings, VM_DROPPABLE ones * never get swap backed on failure to drop. */ if (!(vma->vm_flags & VM_DROPPABLE)) folio_set_swapbacked(folio); goto walk_abort; } if (swap_duplicate(entry) < 0) { set_pte_at(mm, address, pvmw.pte, pteval); goto walk_abort; } if (arch_unmap_one(mm, vma, address, pteval) < 0) { swap_free(entry); set_pte_at(mm, address, pvmw.pte, pteval); goto walk_abort; } /* See folio_try_share_anon_rmap(): clear PTE first. */ if (anon_exclusive && folio_try_share_anon_rmap_pte(folio, subpage)) { swap_free(entry); set_pte_at(mm, address, pvmw.pte, pteval); goto walk_abort; } 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 (anon_exclusive) swp_pte = pte_swp_mkexclusive(swp_pte); 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); } else { /* * This is a locked file-backed folio, * so it cannot be removed from the page * cache and replaced by a new folio before * mmu_notifier_invalidate_range_end, so no * concurrent thread might update its page table * to point at a new folio while a device is * still using this folio. * * See Documentation/mm/mmu_notifier.rst */ dec_mm_counter(mm, mm_counter_file(folio)); } discard: if (unlikely(folio_test_hugetlb(folio))) hugetlb_remove_rmap(folio); else folio_remove_rmap_pte(folio, subpage, vma); if (vma->vm_flags & VM_LOCKED) mlock_drain_local(); folio_put(folio); continue; walk_abort: ret = false; walk_done: page_vma_mapped_walk_done(&pvmw); break; } 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 folio_not_mapped(struct folio *folio) { return !folio_mapped(folio); } /** * try_to_unmap - Try to remove all page table mappings to a folio. * @folio: The folio to unmap. * @flags: action and flags * * Tries to remove all the page table entries which are mapping this * folio. It is the caller's responsibility to check if the folio is * still mapped if needed (use TTU_SYNC to prevent accounting races). * * Context: Caller must hold the folio lock. */ void try_to_unmap(struct folio *folio, enum ttu_flags flags) { struct rmap_walk_control rwc = { .rmap_one = try_to_unmap_one, .arg = (void *)flags, .done = folio_not_mapped, .anon_lock = folio_lock_anon_vma_read, }; if (flags & TTU_RMAP_LOCKED) rmap_walk_locked(folio, &rwc); else rmap_walk(folio, &rwc); } /* * @arg: enum ttu_flags will be passed to this argument. * * If TTU_SPLIT_HUGE_PMD is specified any PMD mappings will be split into PTEs * containing migration entries. */ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); pte_t pteval; struct page *subpage; bool anon_exclusive, ret = true; struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; unsigned long pfn; unsigned long hsz = 0; /* * When racing against e.g. zap_pte_range() on another cpu, * in between its ptep_get_and_clear_full() and folio_remove_rmap_*(), * try_to_migrate() may return before page_mapped() has become false, * if page table locking is skipped: use TTU_SYNC to wait for that. */ if (flags & TTU_SYNC) pvmw.flags = PVMW_SYNC; /* * unmap_page() in mm/huge_memory.c is the only user of migration with * TTU_SPLIT_HUGE_PMD and it wants to freeze. */ if (flags & TTU_SPLIT_HUGE_PMD) split_huge_pmd_address(vma, address, true, folio); /* * 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. */ range.end = vma_address_end(&pvmw); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address, range.end); if (folio_test_hugetlb(folio)) { /* * If sharing is possible, start and end will be adjusted * accordingly. */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); /* We need the huge page size for set_huge_pte_at() */ hsz = huge_page_size(hstate_vma(vma)); } 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) { subpage = folio_page(folio, pmd_pfn(*pvmw.pmd) - folio_pfn(folio)); VM_BUG_ON_FOLIO(folio_test_hugetlb(folio) || !folio_test_pmd_mappable(folio), folio); if (set_pmd_migration_entry(&pvmw, subpage)) { ret = false; page_vma_mapped_walk_done(&pvmw); break; } continue; } #endif /* Unexpected PMD-mapped THP? */ VM_BUG_ON_FOLIO(!pvmw.pte, folio); pfn = pte_pfn(ptep_get(pvmw.pte)); if (folio_is_zone_device(folio)) { /* * Our PTE is a non-present device exclusive entry and * calculating the subpage as for the common case would * result 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. */ VM_BUG_ON_FOLIO(folio_nr_pages(folio) > 1, folio); subpage = &folio->page; } else { subpage = folio_page(folio, pfn - folio_pfn(folio)); } address = pvmw.address; anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(subpage); if (folio_test_hugetlb(folio)) { bool anon = folio_test_anon(folio); /* * huge_pmd_unshare may unmap 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); /* * To call huge_pmd_unshare, i_mmap_rwsem must be * held in write mode. Caller needs to explicitly * do this outside rmap routines. * * We also must hold hugetlb vma_lock in write mode. * Lock order dictates acquiring vma_lock BEFORE * i_mmap_rwsem. We can only try lock here and * fail if unsuccessful. */ if (!anon) { VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) { page_vma_mapped_walk_done(&pvmw); ret = false; break; } if (huge_pmd_unshare(mm, vma, address, pvmw.pte)) { hugetlb_vma_unlock_write(vma); flush_tlb_range(vma, 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; } hugetlb_vma_unlock_write(vma); } /* Nuke the hugetlb page table entry */ pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); } else { flush_cache_page(vma, address, pfn); /* Nuke the page table entry. */ 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 folio. * 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, pteval, address); } else { pteval = ptep_clear_flush(vma, address, pvmw.pte); } } /* Set the dirty flag on the folio now the pte is gone. */ if (pte_dirty(pteval)) folio_mark_dirty(folio); /* Update high watermark before we lower rss */ update_hiwater_rss(mm); if (folio_is_device_private(folio)) { unsigned long pfn = folio_pfn(folio); swp_entry_t entry; pte_t swp_pte; if (anon_exclusive) WARN_ON_ONCE(folio_try_share_anon_rmap_pte(folio, subpage)); /* * 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 = pte_to_swp_entry(pteval); if (is_writable_device_private_entry(entry)) entry = make_writable_migration_entry(pfn); else if (anon_exclusive) entry = make_readable_exclusive_migration_entry(pfn); else entry = make_readable_migration_entry(pfn); 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); trace_set_migration_pte(pvmw.address, pte_val(swp_pte), folio_order(folio)); /* * No need to invalidate here it will synchronize on * against the special swap migration pte. */ } else if (PageHWPoison(subpage)) { pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { hugetlb_count_sub(folio_nr_pages(folio), mm); set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); } else { dec_mm_counter(mm, mm_counter(folio)); 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(folio)); } else { swp_entry_t entry; pte_t swp_pte; if (arch_unmap_one(mm, vma, address, pteval) < 0) { if (folio_test_hugetlb(folio)) set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); else set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } VM_BUG_ON_PAGE(pte_write(pteval) && folio_test_anon(folio) && !anon_exclusive, subpage); /* See folio_try_share_anon_rmap_pte(): clear PTE first. */ if (folio_test_hugetlb(folio)) { if (anon_exclusive && hugetlb_try_share_anon_rmap(folio)) { set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); ret = false; page_vma_mapped_walk_done(&pvmw); break; } } else if (anon_exclusive && folio_try_share_anon_rmap_pte(folio, subpage)) { 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. */ if (pte_write(pteval)) entry = make_writable_migration_entry( page_to_pfn(subpage)); else if (anon_exclusive) entry = make_readable_exclusive_migration_entry( page_to_pfn(subpage)); else entry = make_readable_migration_entry( page_to_pfn(subpage)); if (pte_young(pteval)) entry = make_migration_entry_young(entry); if (pte_dirty(pteval)) entry = make_migration_entry_dirty(entry); 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); if (folio_test_hugetlb(folio)) set_huge_pte_at(mm, address, pvmw.pte, swp_pte, hsz); else set_pte_at(mm, address, pvmw.pte, swp_pte); trace_set_migration_pte(address, pte_val(swp_pte), folio_order(folio)); /* * No need to invalidate here it will synchronize on * against the special swap migration pte. */ } if (unlikely(folio_test_hugetlb(folio))) hugetlb_remove_rmap(folio); else folio_remove_rmap_pte(folio, subpage, vma); if (vma->vm_flags & VM_LOCKED) mlock_drain_local(); folio_put(folio); } mmu_notifier_invalidate_range_end(&range); return ret; } /** * try_to_migrate - try to replace all page table mappings with swap entries * @folio: the folio to replace page table entries for * @flags: action and flags * * Tries to remove all the page table entries which are mapping this folio and * replace them with special swap entries. Caller must hold the folio lock. */ void try_to_migrate(struct folio *folio, enum ttu_flags flags) { struct rmap_walk_control rwc = { .rmap_one = try_to_migrate_one, .arg = (void *)flags, .done = folio_not_mapped, .anon_lock = folio_lock_anon_vma_read, }; /* * Migration always ignores mlock and only supports TTU_RMAP_LOCKED and * TTU_SPLIT_HUGE_PMD, TTU_SYNC, and TTU_BATCH_FLUSH flags. */ if (WARN_ON_ONCE(flags & ~(TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | TTU_SYNC | TTU_BATCH_FLUSH))) return; if (folio_is_zone_device(folio) && (!folio_is_device_private(folio) && !folio_is_device_coherent(folio))) return; /* * 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 (!folio_test_ksm(folio) && folio_test_anon(folio)) rwc.invalid_vma = invalid_migration_vma; if (flags & TTU_RMAP_LOCKED) rmap_walk_locked(folio, &rwc); else rmap_walk(folio, &rwc); } #ifdef CONFIG_DEVICE_PRIVATE struct make_exclusive_args { struct mm_struct *mm; unsigned long address; void *owner; bool valid; }; static bool page_make_device_exclusive_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *priv) { struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); struct make_exclusive_args *args = priv; pte_t pteval; struct page *subpage; bool ret = true; struct mmu_notifier_range range; swp_entry_t entry; pte_t swp_pte; pte_t ptent; mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma->vm_mm, address, min(vma->vm_end, address + folio_size(folio)), args->owner); mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { /* Unexpected PMD-mapped THP? */ VM_BUG_ON_FOLIO(!pvmw.pte, folio); ptent = ptep_get(pvmw.pte); if (!pte_present(ptent)) { ret = false; page_vma_mapped_walk_done(&pvmw); break; } subpage = folio_page(folio, pte_pfn(ptent) - folio_pfn(folio)); address = pvmw.address; /* Nuke the page table entry. */ flush_cache_page(vma, address, pte_pfn(ptent)); pteval = ptep_clear_flush(vma, address, pvmw.pte); /* Set the dirty flag on the folio now the pte is gone. */ if (pte_dirty(pteval)) folio_mark_dirty(folio); /* * Check that our target page is still mapped at the expected * address. */ if (args->mm == mm && args->address == address && pte_write(pteval)) args->valid = true; /* * 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. */ if (pte_write(pteval)) entry = make_writable_device_exclusive_entry( page_to_pfn(subpage)); else entry = make_readable_device_exclusive_entry( page_to_pfn(subpage)); 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); /* * There is a reference on the page for the swap entry which has * been removed, so shouldn't take another. */ folio_remove_rmap_pte(folio, subpage, vma); } mmu_notifier_invalidate_range_end(&range); return ret; } /** * folio_make_device_exclusive - Mark the folio exclusively owned by a device. * @folio: The folio to replace page table entries for. * @mm: The mm_struct where the folio is expected to be mapped. * @address: Address where the folio is expected to be mapped. * @owner: passed to MMU_NOTIFY_EXCLUSIVE range notifier callbacks * * Tries to remove all the page table entries which are mapping this * folio and replace them with special device exclusive swap entries to * grant a device exclusive access to the folio. * * Context: Caller must hold the folio lock. * Return: false if the page is still mapped, or if it could not be unmapped * from the expected address. Otherwise returns true (success). */ static bool folio_make_device_exclusive(struct folio *folio, struct mm_struct *mm, unsigned long address, void *owner) { struct make_exclusive_args args = { .mm = mm, .address = address, .owner = owner, .valid = false, }; struct rmap_walk_control rwc = { .rmap_one = page_make_device_exclusive_one, .done = folio_not_mapped, .anon_lock = folio_lock_anon_vma_read, .arg = &args, }; /* * Restrict to anonymous folios for now to avoid potential writeback * issues. */ if (!folio_test_anon(folio)) return false; rmap_walk(folio, &rwc); return args.valid && !folio_mapcount(folio); } /** * make_device_exclusive_range() - Mark a range for exclusive use by a device * @mm: mm_struct of associated target process * @start: start of the region to mark for exclusive device access * @end: end address of region * @pages: returns the pages which were successfully marked for exclusive access * @owner: passed to MMU_NOTIFY_EXCLUSIVE range notifier to allow filtering * * Returns: number of pages found in the range by GUP. A page is marked for * exclusive access only if the page pointer is non-NULL. * * This function finds ptes mapping page(s) to the given address range, locks * them and replaces mappings with special swap entries preventing userspace CPU * access. On fault these entries are replaced with the original mapping after * calling MMU notifiers. * * A driver using this to program access from a device must use a mmu notifier * critical section to hold a device specific lock during programming. Once * programming is complete it should drop the page lock and reference after * which point CPU access to the page will revoke the exclusive access. */ int make_device_exclusive_range(struct mm_struct *mm, unsigned long start, unsigned long end, struct page **pages, void *owner) { long npages = (end - start) >> PAGE_SHIFT; long i; npages = get_user_pages_remote(mm, start, npages, FOLL_GET | FOLL_WRITE | FOLL_SPLIT_PMD, pages, NULL); if (npages < 0) return npages; for (i = 0; i < npages; i++, start += PAGE_SIZE) { struct folio *folio = page_folio(pages[i]); if (PageTail(pages[i]) || !folio_trylock(folio)) { folio_put(folio); pages[i] = NULL; continue; } if (!folio_make_device_exclusive(folio, mm, start, owner)) { folio_unlock(folio); folio_put(folio); pages[i] = NULL; } } return npages; } EXPORT_SYMBOL_GPL(make_device_exclusive_range); #endif 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(const struct folio *folio, struct rmap_walk_control *rwc) { struct anon_vma *anon_vma; if (rwc->anon_lock) return rwc->anon_lock(folio, rwc); /* * Note: remove_migration_ptes() cannot use folio_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 = folio_anon_vma(folio); if (!anon_vma) return NULL; if (anon_vma_trylock_read(anon_vma)) goto out; if (rwc->try_lock) { anon_vma = NULL; rwc->contended = true; goto out; } anon_vma_lock_read(anon_vma); out: return anon_vma; } /* * rmap_walk_anon - do something to anonymous page using the object-based * rmap method * @folio: the folio to be handled * @rwc: control variable according to each walk type * @locked: caller holds relevant rmap lock * * Find all the mappings of a folio using the mapping pointer and the vma * chains contained in the anon_vma struct it points to. */ static void rmap_walk_anon(struct folio *folio, 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 = folio_anon_vma(folio); /* anon_vma disappear under us? */ VM_BUG_ON_FOLIO(!anon_vma, folio); } else { anon_vma = rmap_walk_anon_lock(folio, rwc); } if (!anon_vma) return; pgoff_start = folio_pgoff(folio); pgoff_end = pgoff_start + folio_nr_pages(folio) - 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(vma, pgoff_start, folio_nr_pages(folio)); VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; if (!rwc->rmap_one(folio, vma, address, rwc->arg)) break; if (rwc->done && rwc->done(folio)) break; } if (!locked) anon_vma_unlock_read(anon_vma); } /* * rmap_walk_file - do something to file page using the object-based rmap method * @folio: the folio to be handled * @rwc: control variable according to each walk type * @locked: caller holds relevant rmap lock * * Find all the mappings of a folio using the mapping pointer and the vma chains * contained in the address_space struct it points to. */ static void rmap_walk_file(struct folio *folio, struct rmap_walk_control *rwc, bool locked) { struct address_space *mapping = folio_mapping(folio); 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_FOLIO(!folio_test_locked(folio), folio); if (!mapping) return; pgoff_start = folio_pgoff(folio); pgoff_end = pgoff_start + folio_nr_pages(folio) - 1; if (!locked) { if (i_mmap_trylock_read(mapping)) goto lookup; if (rwc->try_lock) { rwc->contended = true; return; } i_mmap_lock_read(mapping); } lookup: vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff_start, pgoff_end) { unsigned long address = vma_address(vma, pgoff_start, folio_nr_pages(folio)); VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; if (!rwc->rmap_one(folio, vma, address, rwc->arg)) goto done; if (rwc->done && rwc->done(folio)) goto done; } done: if (!locked) i_mmap_unlock_read(mapping); } void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc) { if (unlikely(folio_test_ksm(folio))) rmap_walk_ksm(folio, rwc); else if (folio_test_anon(folio)) rmap_walk_anon(folio, rwc, false); else rmap_walk_file(folio, rwc, false); } /* Like rmap_walk, but caller holds relevant rmap lock */ void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc) { /* no ksm support for now */ VM_BUG_ON_FOLIO(folio_test_ksm(folio), folio); if (folio_test_anon(folio)) rmap_walk_anon(folio, rwc, true); else rmap_walk_file(folio, 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 hugetlb_add_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); atomic_inc(&folio->_entire_mapcount); atomic_inc(&folio->_large_mapcount); if (flags & RMAP_EXCLUSIVE) SetPageAnonExclusive(&folio->page); VM_WARN_ON_FOLIO(folio_entire_mapcount(folio) > 1 && PageAnonExclusive(&folio->page), folio); } void hugetlb_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address) { VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); BUG_ON(address < vma->vm_start || address >= vma->vm_end); /* increment count (starts at -1) */ atomic_set(&folio->_entire_mapcount, 0); atomic_set(&folio->_large_mapcount, 0); folio_clear_hugetlb_restore_reserve(folio); __folio_set_anon(folio, vma, address, true); SetPageAnonExclusive(&folio->page); } #endif /* CONFIG_HUGETLB_PAGE */ |
| 262 262 1 1 261 223 40 3 262 263 263 262 263 1 1 173 16 189 1 189 239 240 190 189 188 239 239 239 239 225 14 240 239 240 240 39 14 14 37 39 14 226 225 226 223 223 223 223 223 223 223 223 223 223 223 3 3 3 3 3 3 3 260 261 6 7 3 3 1 1 1 1 1 1 1 1 3 3 3 246 13 1 13 2 5 2 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 23 |