| 12 39 38 79 39 39 78 4 4 39 36 36 36 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/anon_inodes.c * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * * Thanks to Arnd Bergmann for code review and suggestions. * More changes for Thomas Gleixner suggestions. * */ #include <linux/cred.h> #include <linux/file.h> #include <linux/poll.h> #include <linux/sched.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/magic.h> #include <linux/anon_inodes.h> #include <linux/pseudo_fs.h> #include <linux/uaccess.h> static struct vfsmount *anon_inode_mnt __ro_after_init; static struct inode *anon_inode_inode __ro_after_init; /* * anon_inodefs_dname() is called from d_path(). */ static char *anon_inodefs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(buffer, buflen, "anon_inode:%s", dentry->d_name.name); } static const struct dentry_operations anon_inodefs_dentry_operations = { .d_dname = anon_inodefs_dname, }; static int anon_inodefs_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx = init_pseudo(fc, ANON_INODE_FS_MAGIC); if (!ctx) return -ENOMEM; ctx->dops = &anon_inodefs_dentry_operations; return 0; } static struct file_system_type anon_inode_fs_type = { .name = "anon_inodefs", .init_fs_context = anon_inodefs_init_fs_context, .kill_sb = kill_anon_super, }; static struct inode *anon_inode_make_secure_inode( const char *name, const struct inode *context_inode) { struct inode *inode; int error; inode = alloc_anon_inode(anon_inode_mnt->mnt_sb); if (IS_ERR(inode)) return inode; inode->i_flags &= ~S_PRIVATE; error = security_inode_init_security_anon(inode, &QSTR(name), context_inode); if (error) { iput(inode); return ERR_PTR(error); } return inode; } static struct file *__anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode, bool make_inode) { struct inode *inode; struct file *file; if (fops->owner && !try_module_get(fops->owner)) return ERR_PTR(-ENOENT); if (make_inode) { inode = anon_inode_make_secure_inode(name, context_inode); if (IS_ERR(inode)) { file = ERR_CAST(inode); goto err; } } else { inode = anon_inode_inode; if (IS_ERR(inode)) { file = ERR_PTR(-ENODEV); goto err; } /* * We know the anon_inode inode count is always * greater than zero, so ihold() is safe. */ ihold(inode); } file = alloc_file_pseudo(inode, anon_inode_mnt, name, flags & (O_ACCMODE | O_NONBLOCK), fops); if (IS_ERR(file)) goto err_iput; file->f_mapping = inode->i_mapping; file->private_data = priv; return file; err_iput: iput(inode); err: module_put(fops->owner); return file; } /** * anon_inode_getfile - creates a new file instance by hooking it up to an * anonymous inode, and a dentry that describe the "class" * of the file * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * * Creates a new file by hooking it on a single inode. This is useful for files * that do not need to have a full-fledged inode in order to operate correctly. * All the files created with anon_inode_getfile() will share a single inode, * hence saving memory and avoiding code duplication for the file/inode/dentry * setup. Returns the newly created file* or an error pointer. */ struct file *anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags) { return __anon_inode_getfile(name, fops, priv, flags, NULL, false); } EXPORT_SYMBOL_GPL(anon_inode_getfile); /** * anon_inode_getfile_fmode - creates a new file instance by hooking it up to an * anonymous inode, and a dentry that describe the "class" * of the file * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * @f_mode: [in] fmode * * Creates a new file by hooking it on a single inode. This is useful for files * that do not need to have a full-fledged inode in order to operate correctly. * All the files created with anon_inode_getfile() will share a single inode, * hence saving memory and avoiding code duplication for the file/inode/dentry * setup. Allows setting the fmode. Returns the newly created file* or an error * pointer. */ struct file *anon_inode_getfile_fmode(const char *name, const struct file_operations *fops, void *priv, int flags, fmode_t f_mode) { struct file *file; file = __anon_inode_getfile(name, fops, priv, flags, NULL, false); if (!IS_ERR(file)) file->f_mode |= f_mode; return file; } EXPORT_SYMBOL_GPL(anon_inode_getfile_fmode); /** * anon_inode_create_getfile - Like anon_inode_getfile(), but creates a new * !S_PRIVATE anon inode rather than reuse the * singleton anon inode and calls the * inode_init_security_anon() LSM hook. * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * @context_inode: * [in] the logical relationship with the new inode (optional) * * Create a new anonymous inode and file pair. This can be done for two * reasons: * * - for the inode to have its own security context, so that LSMs can enforce * policy on the inode's creation; * * - if the caller needs a unique inode, for example in order to customize * the size returned by fstat() * * The LSM may use @context_inode in inode_init_security_anon(), but a * reference to it is not held. * * Returns the newly created file* or an error pointer. */ struct file *anon_inode_create_getfile(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode) { return __anon_inode_getfile(name, fops, priv, flags, context_inode, true); } EXPORT_SYMBOL_GPL(anon_inode_create_getfile); static int __anon_inode_getfd(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode, bool make_inode) { int error, fd; struct file *file; error = get_unused_fd_flags(flags); if (error < 0) return error; fd = error; file = __anon_inode_getfile(name, fops, priv, flags, context_inode, make_inode); if (IS_ERR(file)) { error = PTR_ERR(file); goto err_put_unused_fd; } fd_install(fd, file); return fd; err_put_unused_fd: put_unused_fd(fd); return error; } /** * anon_inode_getfd - creates a new file instance by hooking it up to * an anonymous inode and a dentry that describe * the "class" of the file * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * * Creates a new file by hooking it on a single inode. This is * useful for files that do not need to have a full-fledged inode in * order to operate correctly. All the files created with * anon_inode_getfd() will use the same singleton inode, reducing * memory use and avoiding code duplication for the file/inode/dentry * setup. Returns a newly created file descriptor or an error code. */ int anon_inode_getfd(const char *name, const struct file_operations *fops, void *priv, int flags) { return __anon_inode_getfd(name, fops, priv, flags, NULL, false); } EXPORT_SYMBOL_GPL(anon_inode_getfd); /** * anon_inode_create_getfd - Like anon_inode_getfd(), but creates a new * !S_PRIVATE anon inode rather than reuse the singleton anon inode, and calls * the inode_init_security_anon() LSM hook. * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * @context_inode: * [in] the logical relationship with the new inode (optional) * * Create a new anonymous inode and file pair. This can be done for two * reasons: * * - for the inode to have its own security context, so that LSMs can enforce * policy on the inode's creation; * * - if the caller needs a unique inode, for example in order to customize * the size returned by fstat() * * The LSM may use @context_inode in inode_init_security_anon(), but a * reference to it is not held. * * Returns a newly created file descriptor or an error code. */ int anon_inode_create_getfd(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode) { return __anon_inode_getfd(name, fops, priv, flags, context_inode, true); } static int __init anon_inode_init(void) { anon_inode_mnt = kern_mount(&anon_inode_fs_type); if (IS_ERR(anon_inode_mnt)) panic("anon_inode_init() kernel mount failed (%ld)\n", PTR_ERR(anon_inode_mnt)); anon_inode_inode = alloc_anon_inode(anon_inode_mnt->mnt_sb); if (IS_ERR(anon_inode_inode)) panic("anon_inode_init() inode allocation failed (%ld)\n", PTR_ERR(anon_inode_inode)); return 0; } fs_initcall(anon_inode_init); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_NSPROXY_H #define _LINUX_NSPROXY_H #include <linux/refcount.h> #include <linux/spinlock.h> #include <linux/sched.h> struct mnt_namespace; struct uts_namespace; struct ipc_namespace; struct pid_namespace; struct cgroup_namespace; struct fs_struct; /* * A structure to contain pointers to all per-process * namespaces - fs (mount), uts, network, sysvipc, etc. * * The pid namespace is an exception -- it's accessed using * task_active_pid_ns. The pid namespace here is the * namespace that children will use. * * 'count' is the number of tasks holding a reference. * The count for each namespace, then, will be the number * of nsproxies pointing to it, not the number of tasks. * * The nsproxy is shared by tasks which share all namespaces. * As soon as a single namespace is cloned or unshared, the * nsproxy is copied. */ struct nsproxy { refcount_t count; struct uts_namespace *uts_ns; struct ipc_namespace *ipc_ns; struct mnt_namespace *mnt_ns; struct pid_namespace *pid_ns_for_children; struct net *net_ns; struct time_namespace *time_ns; struct time_namespace *time_ns_for_children; struct cgroup_namespace *cgroup_ns; }; extern struct nsproxy init_nsproxy; #define to_ns_common(__ns) \ _Generic((__ns), \ struct cgroup_namespace *: &(__ns->ns), \ struct ipc_namespace *: &(__ns->ns), \ struct net *: &(__ns->ns), \ struct pid_namespace *: &(__ns->ns), \ struct mnt_namespace *: &(__ns->ns), \ struct time_namespace *: &(__ns->ns), \ struct user_namespace *: &(__ns->ns), \ struct uts_namespace *: &(__ns->ns)) /* * A structure to encompass all bits needed to install * a partial or complete new set of namespaces. * * If a new user namespace is requested cred will * point to a modifiable set of credentials. If a pointer * to a modifiable set is needed nsset_cred() must be * used and tested. */ struct nsset { unsigned flags; struct nsproxy *nsproxy; struct fs_struct *fs; const struct cred *cred; }; static inline struct cred *nsset_cred(struct nsset *set) { if (set->flags & CLONE_NEWUSER) return (struct cred *)set->cred; return NULL; } /* * the namespaces access rules are: * * 1. only current task is allowed to change tsk->nsproxy pointer or * any pointer on the nsproxy itself. Current must hold the task_lock * when changing tsk->nsproxy. * * 2. when accessing (i.e. reading) current task's namespaces - no * precautions should be taken - just dereference the pointers * * 3. the access to other task namespaces is performed like this * task_lock(task); * nsproxy = task->nsproxy; * if (nsproxy != NULL) { * / * * * work with the namespaces here * * e.g. get the reference on one of them * * / * } / * * * NULL task->nsproxy means that this task is * * almost dead (zombie) * * / * task_unlock(task); * */ int copy_namespaces(unsigned long flags, struct task_struct *tsk); void exit_task_namespaces(struct task_struct *tsk); void switch_task_namespaces(struct task_struct *tsk, struct nsproxy *new); int exec_task_namespaces(void); void free_nsproxy(struct nsproxy *ns); int unshare_nsproxy_namespaces(unsigned long, struct nsproxy **, struct cred *, struct fs_struct *); int __init nsproxy_cache_init(void); static inline void put_nsproxy(struct nsproxy *ns) { if (refcount_dec_and_test(&ns->count)) free_nsproxy(ns); } static inline void get_nsproxy(struct nsproxy *ns) { refcount_inc(&ns->count); } DEFINE_FREE(put_nsproxy, struct nsproxy *, if (_T) put_nsproxy(_T)) #endif |
| 248 249 1276 3 1278 4 1265 26 457 13 150 415 64 61 16 28 14 307 507 68 456 222 1 302 506 627 16 162 591 61 78 18 22 479 674 98 600 228 1 475 672 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/readdir.c * * Copyright (C) 1995 Linus Torvalds */ #include <linux/stddef.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/time.h> #include <linux/mm.h> #include <linux/errno.h> #include <linux/stat.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/fsnotify.h> #include <linux/dirent.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/unistd.h> #include <linux/compat.h> #include <linux/uaccess.h> /* * Some filesystems were never converted to '->iterate_shared()' * and their directory iterators want the inode lock held for * writing. This wrapper allows for converting from the shared * semantics to the exclusive inode use. */ int wrap_directory_iterator(struct file *file, struct dir_context *ctx, int (*iter)(struct file *, struct dir_context *)) { struct inode *inode = file_inode(file); int ret; /* * We'd love to have an 'inode_upgrade_trylock()' operation, * see the comment in mmap_upgrade_trylock() in mm/memory.c. * * But considering this is for "filesystems that never got * converted", it really doesn't matter. * * Also note that since we have to return with the lock held * for reading, we can't use the "killable()" locking here, * since we do need to get the lock even if we're dying. * * We could do the write part killably and then get the read * lock unconditionally if it mattered, but see above on why * this does the very simplistic conversion. */ up_read(&inode->i_rwsem); down_write(&inode->i_rwsem); /* * Since we dropped the inode lock, we should do the * DEADDIR test again. See 'iterate_dir()' below. * * Note that we don't need to re-do the f_pos games, * since the file must be locked wrt f_pos anyway. */ ret = -ENOENT; if (!IS_DEADDIR(inode)) ret = iter(file, ctx); downgrade_write(&inode->i_rwsem); return ret; } EXPORT_SYMBOL(wrap_directory_iterator); /* * Note the "unsafe_put_user()" semantics: we goto a * label for errors. */ #define unsafe_copy_dirent_name(_dst, _src, _len, label) do { \ char __user *dst = (_dst); \ const char *src = (_src); \ size_t len = (_len); \ unsafe_put_user(0, dst+len, label); \ unsafe_copy_to_user(dst, src, len, label); \ } while (0) int iterate_dir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); int res = -ENOTDIR; if (!file->f_op->iterate_shared) goto out; res = security_file_permission(file, MAY_READ); if (res) goto out; res = fsnotify_file_perm(file, MAY_READ); if (res) goto out; res = down_read_killable(&inode->i_rwsem); if (res) goto out; res = -ENOENT; if (!IS_DEADDIR(inode)) { ctx->pos = file->f_pos; res = file->f_op->iterate_shared(file, ctx); file->f_pos = ctx->pos; fsnotify_access(file); file_accessed(file); } inode_unlock_shared(inode); out: return res; } EXPORT_SYMBOL(iterate_dir); /* * POSIX says that a dirent name cannot contain NULL or a '/'. * * It's not 100% clear what we should really do in this case. * The filesystem is clearly corrupted, but returning a hard * error means that you now don't see any of the other names * either, so that isn't a perfect alternative. * * And if you return an error, what error do you use? Several * filesystems seem to have decided on EUCLEAN being the error * code for EFSCORRUPTED, and that may be the error to use. Or * just EIO, which is perhaps more obvious to users. * * In order to see the other file names in the directory, the * caller might want to make this a "soft" error: skip the * entry, and return the error at the end instead. * * Note that this should likely do a "memchr(name, 0, len)" * check too, since that would be filesystem corruption as * well. However, that case can't actually confuse user space, * which has to do a strlen() on the name anyway to find the * filename length, and the above "soft error" worry means * that it's probably better left alone until we have that * issue clarified. * * Note the PATH_MAX check - it's arbitrary but the real * kernel limit on a possible path component, not NAME_MAX, * which is the technical standard limit. */ static int verify_dirent_name(const char *name, int len) { if (len <= 0 || len >= PATH_MAX) return -EIO; if (memchr(name, '/', len)) return -EIO; return 0; } /* * Traditional linux readdir() handling.. * * "count=1" is a special case, meaning that the buffer is one * dirent-structure in size and that the code can't handle more * anyway. Thus the special "fillonedir()" function for that * case (the low-level handlers don't need to care about this). */ #ifdef __ARCH_WANT_OLD_READDIR struct old_linux_dirent { unsigned long d_ino; unsigned long d_offset; unsigned short d_namlen; char d_name[]; }; struct readdir_callback { struct dir_context ctx; struct old_linux_dirent __user * dirent; int result; }; static bool fillonedir(struct dir_context *ctx, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type) { struct readdir_callback *buf = container_of(ctx, struct readdir_callback, ctx); struct old_linux_dirent __user * dirent; unsigned long d_ino; if (buf->result) return false; buf->result = verify_dirent_name(name, namlen); if (buf->result) return false; d_ino = ino; if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) { buf->result = -EOVERFLOW; return false; } buf->result++; dirent = buf->dirent; if (!user_write_access_begin(dirent, (unsigned long)(dirent->d_name + namlen + 1) - (unsigned long)dirent)) goto efault; unsafe_put_user(d_ino, &dirent->d_ino, efault_end); unsafe_put_user(offset, &dirent->d_offset, efault_end); unsafe_put_user(namlen, &dirent->d_namlen, efault_end); unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end); user_write_access_end(); return true; efault_end: user_write_access_end(); efault: buf->result = -EFAULT; return false; } SYSCALL_DEFINE3(old_readdir, unsigned int, fd, struct old_linux_dirent __user *, dirent, unsigned int, count) { int error; CLASS(fd_pos, f)(fd); struct readdir_callback buf = { .ctx.actor = fillonedir, .dirent = dirent }; if (fd_empty(f)) return -EBADF; error = iterate_dir(fd_file(f), &buf.ctx); if (buf.result) error = buf.result; return error; } #endif /* __ARCH_WANT_OLD_READDIR */ /* * New, all-improved, singing, dancing, iBCS2-compliant getdents() * interface. */ struct linux_dirent { unsigned long d_ino; unsigned long d_off; unsigned short d_reclen; char d_name[]; }; struct getdents_callback { struct dir_context ctx; struct linux_dirent __user * current_dir; int prev_reclen; int count; int error; }; static bool filldir(struct dir_context *ctx, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type) { struct linux_dirent __user *dirent, *prev; struct getdents_callback *buf = container_of(ctx, struct getdents_callback, ctx); unsigned long d_ino; int reclen = ALIGN(offsetof(struct linux_dirent, d_name) + namlen + 2, sizeof(long)); int prev_reclen; buf->error = verify_dirent_name(name, namlen); if (unlikely(buf->error)) return false; buf->error = -EINVAL; /* only used if we fail.. */ if (reclen > buf->count) return false; d_ino = ino; if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) { buf->error = -EOVERFLOW; return false; } prev_reclen = buf->prev_reclen; if (prev_reclen && signal_pending(current)) return false; dirent = buf->current_dir; prev = (void __user *) dirent - prev_reclen; if (!user_write_access_begin(prev, reclen + prev_reclen)) goto efault; /* This might be 'dirent->d_off', but if so it will get overwritten */ unsafe_put_user(offset, &prev->d_off, efault_end); unsafe_put_user(d_ino, &dirent->d_ino, efault_end); unsafe_put_user(reclen, &dirent->d_reclen, efault_end); unsafe_put_user(d_type, (char __user *) dirent + reclen - 1, efault_end); unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end); user_write_access_end(); buf->current_dir = (void __user *)dirent + reclen; buf->prev_reclen = reclen; buf->count -= reclen; return true; efault_end: user_write_access_end(); efault: buf->error = -EFAULT; return false; } SYSCALL_DEFINE3(getdents, unsigned int, fd, struct linux_dirent __user *, dirent, unsigned int, count) { CLASS(fd_pos, f)(fd); struct getdents_callback buf = { .ctx.actor = filldir, .count = count, .current_dir = dirent }; int error; if (fd_empty(f)) return -EBADF; error = iterate_dir(fd_file(f), &buf.ctx); if (error >= 0) error = buf.error; if (buf.prev_reclen) { struct linux_dirent __user * lastdirent; lastdirent = (void __user *)buf.current_dir - buf.prev_reclen; if (put_user(buf.ctx.pos, &lastdirent->d_off)) error = -EFAULT; else error = count - buf.count; } return error; } struct getdents_callback64 { struct dir_context ctx; struct linux_dirent64 __user * current_dir; int prev_reclen; int count; int error; }; static bool filldir64(struct dir_context *ctx, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type) { struct linux_dirent64 __user *dirent, *prev; struct getdents_callback64 *buf = container_of(ctx, struct getdents_callback64, ctx); int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1, sizeof(u64)); int prev_reclen; buf->error = verify_dirent_name(name, namlen); if (unlikely(buf->error)) return false; buf->error = -EINVAL; /* only used if we fail.. */ if (reclen > buf->count) return false; prev_reclen = buf->prev_reclen; if (prev_reclen && signal_pending(current)) return false; dirent = buf->current_dir; prev = (void __user *)dirent - prev_reclen; if (!user_write_access_begin(prev, reclen + prev_reclen)) goto efault; /* This might be 'dirent->d_off', but if so it will get overwritten */ unsafe_put_user(offset, &prev->d_off, efault_end); unsafe_put_user(ino, &dirent->d_ino, efault_end); unsafe_put_user(reclen, &dirent->d_reclen, efault_end); unsafe_put_user(d_type, &dirent->d_type, efault_end); unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end); user_write_access_end(); buf->prev_reclen = reclen; buf->current_dir = (void __user *)dirent + reclen; buf->count -= reclen; return true; efault_end: user_write_access_end(); efault: buf->error = -EFAULT; return false; } SYSCALL_DEFINE3(getdents64, unsigned int, fd, struct linux_dirent64 __user *, dirent, unsigned int, count) { CLASS(fd_pos, f)(fd); struct getdents_callback64 buf = { .ctx.actor = filldir64, .count = count, .current_dir = dirent }; int error; if (fd_empty(f)) return -EBADF; error = iterate_dir(fd_file(f), &buf.ctx); if (error >= 0) error = buf.error; if (buf.prev_reclen) { struct linux_dirent64 __user * lastdirent; typeof(lastdirent->d_off) d_off = buf.ctx.pos; lastdirent = (void __user *) buf.current_dir - buf.prev_reclen; if (put_user(d_off, &lastdirent->d_off)) error = -EFAULT; else error = count - buf.count; } return error; } #ifdef CONFIG_COMPAT struct compat_old_linux_dirent { compat_ulong_t d_ino; compat_ulong_t d_offset; unsigned short d_namlen; char d_name[]; }; struct compat_readdir_callback { struct dir_context ctx; struct compat_old_linux_dirent __user *dirent; int result; }; static bool compat_fillonedir(struct dir_context *ctx, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type) { struct compat_readdir_callback *buf = container_of(ctx, struct compat_readdir_callback, ctx); struct compat_old_linux_dirent __user *dirent; compat_ulong_t d_ino; if (buf->result) return false; buf->result = verify_dirent_name(name, namlen); if (buf->result) return false; d_ino = ino; if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) { buf->result = -EOVERFLOW; return false; } buf->result++; dirent = buf->dirent; if (!user_write_access_begin(dirent, (unsigned long)(dirent->d_name + namlen + 1) - (unsigned long)dirent)) goto efault; unsafe_put_user(d_ino, &dirent->d_ino, efault_end); unsafe_put_user(offset, &dirent->d_offset, efault_end); unsafe_put_user(namlen, &dirent->d_namlen, efault_end); unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end); user_write_access_end(); return true; efault_end: user_write_access_end(); efault: buf->result = -EFAULT; return false; } COMPAT_SYSCALL_DEFINE3(old_readdir, unsigned int, fd, struct compat_old_linux_dirent __user *, dirent, unsigned int, count) { int error; CLASS(fd_pos, f)(fd); struct compat_readdir_callback buf = { .ctx.actor = compat_fillonedir, .dirent = dirent }; if (fd_empty(f)) return -EBADF; error = iterate_dir(fd_file(f), &buf.ctx); if (buf.result) error = buf.result; return error; } struct compat_linux_dirent { compat_ulong_t d_ino; compat_ulong_t d_off; unsigned short d_reclen; char d_name[]; }; struct compat_getdents_callback { struct dir_context ctx; struct compat_linux_dirent __user *current_dir; int prev_reclen; int count; int error; }; static bool compat_filldir(struct dir_context *ctx, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type) { struct compat_linux_dirent __user *dirent, *prev; struct compat_getdents_callback *buf = container_of(ctx, struct compat_getdents_callback, ctx); compat_ulong_t d_ino; int reclen = ALIGN(offsetof(struct compat_linux_dirent, d_name) + namlen + 2, sizeof(compat_long_t)); int prev_reclen; buf->error = verify_dirent_name(name, namlen); if (unlikely(buf->error)) return false; buf->error = -EINVAL; /* only used if we fail.. */ if (reclen > buf->count) return false; d_ino = ino; if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) { buf->error = -EOVERFLOW; return false; } prev_reclen = buf->prev_reclen; if (prev_reclen && signal_pending(current)) return false; dirent = buf->current_dir; prev = (void __user *) dirent - prev_reclen; if (!user_write_access_begin(prev, reclen + prev_reclen)) goto efault; unsafe_put_user(offset, &prev->d_off, efault_end); unsafe_put_user(d_ino, &dirent->d_ino, efault_end); unsafe_put_user(reclen, &dirent->d_reclen, efault_end); unsafe_put_user(d_type, (char __user *) dirent + reclen - 1, efault_end); unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end); user_write_access_end(); buf->prev_reclen = reclen; buf->current_dir = (void __user *)dirent + reclen; buf->count -= reclen; return true; efault_end: user_write_access_end(); efault: buf->error = -EFAULT; return false; } COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd, struct compat_linux_dirent __user *, dirent, unsigned int, count) { CLASS(fd_pos, f)(fd); struct compat_getdents_callback buf = { .ctx.actor = compat_filldir, .current_dir = dirent, .count = count }; int error; if (fd_empty(f)) return -EBADF; error = iterate_dir(fd_file(f), &buf.ctx); if (error >= 0) error = buf.error; if (buf.prev_reclen) { struct compat_linux_dirent __user * lastdirent; lastdirent = (void __user *)buf.current_dir - buf.prev_reclen; if (put_user(buf.ctx.pos, &lastdirent->d_off)) error = -EFAULT; else error = count - buf.count; } return error; } #endif |
| 1483 1487 158 158 158 158 9 158 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/exit.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/mm.h> #include <linux/slab.h> #include <linux/sched/autogroup.h> #include <linux/sched/mm.h> #include <linux/sched/stat.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/sched/cputime.h> #include <linux/interrupt.h> #include <linux/module.h> #include <linux/capability.h> #include <linux/completion.h> #include <linux/personality.h> #include <linux/tty.h> #include <linux/iocontext.h> #include <linux/key.h> #include <linux/cpu.h> #include <linux/acct.h> #include <linux/tsacct_kern.h> #include <linux/file.h> #include <linux/freezer.h> #include <linux/binfmts.h> #include <linux/nsproxy.h> #include <linux/pid_namespace.h> #include <linux/ptrace.h> #include <linux/profile.h> #include <linux/mount.h> #include <linux/proc_fs.h> #include <linux/kthread.h> #include <linux/mempolicy.h> #include <linux/taskstats_kern.h> #include <linux/delayacct.h> #include <linux/cgroup.h> #include <linux/syscalls.h> #include <linux/signal.h> #include <linux/posix-timers.h> #include <linux/cn_proc.h> #include <linux/mutex.h> #include <linux/futex.h> #include <linux/pipe_fs_i.h> #include <linux/audit.h> /* for audit_free() */ #include <linux/resource.h> #include <linux/task_io_accounting_ops.h> #include <linux/blkdev.h> #include <linux/task_work.h> #include <linux/fs_struct.h> #include <linux/init_task.h> #include <linux/perf_event.h> #include <trace/events/sched.h> #include <linux/hw_breakpoint.h> #include <linux/oom.h> #include <linux/writeback.h> #include <linux/shm.h> #include <linux/kcov.h> #include <linux/kmsan.h> #include <linux/random.h> #include <linux/rcuwait.h> #include <linux/compat.h> #include <linux/io_uring.h> #include <linux/kprobes.h> #include <linux/rethook.h> #include <linux/sysfs.h> #include <linux/user_events.h> #include <linux/uaccess.h> #include <linux/pidfs.h> #include <uapi/linux/wait.h> #include <asm/unistd.h> #include <asm/mmu_context.h> #include "exit.h" /* * The default value should be high enough to not crash a system that randomly * crashes its kernel from time to time, but low enough to at least not permit * overflowing 32-bit refcounts or the ldsem writer count. */ static unsigned int oops_limit = 10000; #ifdef CONFIG_SYSCTL static const struct ctl_table kern_exit_table[] = { { .procname = "oops_limit", .data = &oops_limit, .maxlen = sizeof(oops_limit), .mode = 0644, .proc_handler = proc_douintvec, }, }; static __init int kernel_exit_sysctls_init(void) { register_sysctl_init("kernel", kern_exit_table); return 0; } late_initcall(kernel_exit_sysctls_init); #endif static atomic_t oops_count = ATOMIC_INIT(0); #ifdef CONFIG_SYSFS static ssize_t oops_count_show(struct kobject *kobj, struct kobj_attribute *attr, char *page) { return sysfs_emit(page, "%d\n", atomic_read(&oops_count)); } static struct kobj_attribute oops_count_attr = __ATTR_RO(oops_count); static __init int kernel_exit_sysfs_init(void) { sysfs_add_file_to_group(kernel_kobj, &oops_count_attr.attr, NULL); return 0; } late_initcall(kernel_exit_sysfs_init); #endif /* * For things release_task() would like to do *after* tasklist_lock is released. */ struct release_task_post { struct pid *pids[PIDTYPE_MAX]; }; static void __unhash_process(struct release_task_post *post, struct task_struct *p, bool group_dead) { nr_threads--; detach_pid(post->pids, p, PIDTYPE_PID); if (group_dead) { detach_pid(post->pids, p, PIDTYPE_TGID); detach_pid(post->pids, p, PIDTYPE_PGID); detach_pid(post->pids, p, PIDTYPE_SID); list_del_rcu(&p->tasks); list_del_init(&p->sibling); __this_cpu_dec(process_counts); } list_del_rcu(&p->thread_node); } /* * This function expects the tasklist_lock write-locked. */ static void __exit_signal(struct release_task_post *post, struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; bool group_dead = thread_group_leader(tsk); struct sighand_struct *sighand; struct tty_struct *tty; u64 utime, stime; sighand = rcu_dereference_check(tsk->sighand, lockdep_tasklist_lock_is_held()); spin_lock(&sighand->siglock); #ifdef CONFIG_POSIX_TIMERS posix_cpu_timers_exit(tsk); if (group_dead) posix_cpu_timers_exit_group(tsk); #endif if (group_dead) { tty = sig->tty; sig->tty = NULL; } else { /* * If there is any task waiting for the group exit * then notify it: */ if (sig->notify_count > 0 && !--sig->notify_count) wake_up_process(sig->group_exec_task); if (tsk == sig->curr_target) sig->curr_target = next_thread(tsk); } /* * Accumulate here the counters for all threads as they die. We could * skip the group leader because it is the last user of signal_struct, * but we want to avoid the race with thread_group_cputime() which can * see the empty ->thread_head list. */ task_cputime(tsk, &utime, &stime); write_seqlock(&sig->stats_lock); sig->utime += utime; sig->stime += stime; sig->gtime += task_gtime(tsk); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; sig->nvcsw += tsk->nvcsw; sig->nivcsw += tsk->nivcsw; sig->inblock += task_io_get_inblock(tsk); sig->oublock += task_io_get_oublock(tsk); task_io_accounting_add(&sig->ioac, &tsk->ioac); sig->sum_sched_runtime += tsk->se.sum_exec_runtime; sig->nr_threads--; __unhash_process(post, tsk, group_dead); write_sequnlock(&sig->stats_lock); tsk->sighand = NULL; spin_unlock(&sighand->siglock); __cleanup_sighand(sighand); if (group_dead) tty_kref_put(tty); } static void delayed_put_task_struct(struct rcu_head *rhp) { struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); kprobe_flush_task(tsk); rethook_flush_task(tsk); perf_event_delayed_put(tsk); trace_sched_process_free(tsk); put_task_struct(tsk); } void put_task_struct_rcu_user(struct task_struct *task) { if (refcount_dec_and_test(&task->rcu_users)) call_rcu(&task->rcu, delayed_put_task_struct); } void __weak release_thread(struct task_struct *dead_task) { } void release_task(struct task_struct *p) { struct release_task_post post; struct task_struct *leader; struct pid *thread_pid; int zap_leader; repeat: memset(&post, 0, sizeof(post)); /* don't need to get the RCU readlock here - the process is dead and * can't be modifying its own credentials. But shut RCU-lockdep up */ rcu_read_lock(); dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); rcu_read_unlock(); pidfs_exit(p); cgroup_release(p); thread_pid = get_pid(p->thread_pid); write_lock_irq(&tasklist_lock); ptrace_release_task(p); __exit_signal(&post, p); /* * If we are the last non-leader member of the thread * group, and the leader is zombie, then notify the * group leader's parent process. (if it wants notification.) */ zap_leader = 0; leader = p->group_leader; if (leader != p && thread_group_empty(leader) && leader->exit_state == EXIT_ZOMBIE) { /* for pidfs_exit() and do_notify_parent() */ if (leader->signal->flags & SIGNAL_GROUP_EXIT) leader->exit_code = leader->signal->group_exit_code; /* * If we were the last child thread and the leader has * exited already, and the leader's parent ignores SIGCHLD, * then we are the one who should release the leader. */ zap_leader = do_notify_parent(leader, leader->exit_signal); if (zap_leader) leader->exit_state = EXIT_DEAD; } write_unlock_irq(&tasklist_lock); proc_flush_pid(thread_pid); put_pid(thread_pid); add_device_randomness(&p->se.sum_exec_runtime, sizeof(p->se.sum_exec_runtime)); free_pids(post.pids); release_thread(p); /* * This task was already removed from the process/thread/pid lists * and lock_task_sighand(p) can't succeed. Nobody else can touch * ->pending or, if group dead, signal->shared_pending. We can call * flush_sigqueue() lockless. */ flush_sigqueue(&p->pending); if (thread_group_leader(p)) flush_sigqueue(&p->signal->shared_pending); put_task_struct_rcu_user(p); p = leader; if (unlikely(zap_leader)) goto repeat; } int rcuwait_wake_up(struct rcuwait *w) { int ret = 0; struct task_struct *task; rcu_read_lock(); /* * Order condition vs @task, such that everything prior to the load * of @task is visible. This is the condition as to why the user called * rcuwait_wake() in the first place. Pairs with set_current_state() * barrier (A) in rcuwait_wait_event(). * * WAIT WAKE * [S] tsk = current [S] cond = true * MB (A) MB (B) * [L] cond [L] tsk */ smp_mb(); /* (B) */ task = rcu_dereference(w->task); if (task) ret = wake_up_process(task); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(rcuwait_wake_up); /* * Determine if a process group is "orphaned", according to the POSIX * definition in 2.2.2.52. Orphaned process groups are not to be affected * by terminal-generated stop signals. Newly orphaned process groups are * to receive a SIGHUP and a SIGCONT. * * "I ask you, have you ever known what it is to be an orphan?" */ static int will_become_orphaned_pgrp(struct pid *pgrp, struct task_struct *ignored_task) { struct task_struct *p; do_each_pid_task(pgrp, PIDTYPE_PGID, p) { if ((p == ignored_task) || (p->exit_state && thread_group_empty(p)) || is_global_init(p->real_parent)) continue; if (task_pgrp(p->real_parent) != pgrp && task_session(p->real_parent) == task_session(p)) return 0; } while_each_pid_task(pgrp, PIDTYPE_PGID, p); return 1; } int is_current_pgrp_orphaned(void) { int retval; read_lock(&tasklist_lock); retval = will_become_orphaned_pgrp(task_pgrp(current), NULL); read_unlock(&tasklist_lock); return retval; } static bool has_stopped_jobs(struct pid *pgrp) { struct task_struct *p; do_each_pid_task(pgrp, PIDTYPE_PGID, p) { if (p->signal->flags & SIGNAL_STOP_STOPPED) return true; } while_each_pid_task(pgrp, PIDTYPE_PGID, p); return false; } /* * Check to see if any process groups have become orphaned as * a result of our exiting, and if they have any stopped jobs, * send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2) */ static void kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent) { struct pid *pgrp = task_pgrp(tsk); struct task_struct *ignored_task = tsk; if (!parent) /* exit: our father is in a different pgrp than * we are and we were the only connection outside. */ parent = tsk->real_parent; else /* reparent: our child is in a different pgrp than * we are, and it was the only connection outside. */ ignored_task = NULL; if (task_pgrp(parent) != pgrp && task_session(parent) == task_session(tsk) && will_become_orphaned_pgrp(pgrp, ignored_task) && has_stopped_jobs(pgrp)) { __kill_pgrp_info(SIGHUP, SEND_SIG_PRIV, pgrp); __kill_pgrp_info(SIGCONT, SEND_SIG_PRIV, pgrp); } } static void coredump_task_exit(struct task_struct *tsk) { struct core_state *core_state; /* * Serialize with any possible pending coredump. * We must hold siglock around checking core_state * and setting PF_POSTCOREDUMP. The core-inducing thread * will increment ->nr_threads for each thread in the * group without PF_POSTCOREDUMP set. */ spin_lock_irq(&tsk->sighand->siglock); tsk->flags |= PF_POSTCOREDUMP; core_state = tsk->signal->core_state; spin_unlock_irq(&tsk->sighand->siglock); if (core_state) { struct core_thread self; self.task = current; if (self.task->flags & PF_SIGNALED) self.next = xchg(&core_state->dumper.next, &self); else self.task = NULL; /* * Implies mb(), the result of xchg() must be visible * to core_state->dumper. */ if (atomic_dec_and_test(&core_state->nr_threads)) complete(&core_state->startup); for (;;) { set_current_state(TASK_IDLE|TASK_FREEZABLE); if (!self.task) /* see coredump_finish() */ break; schedule(); } __set_current_state(TASK_RUNNING); } } #ifdef CONFIG_MEMCG /* drops tasklist_lock if succeeds */ static bool __try_to_set_owner(struct task_struct *tsk, struct mm_struct *mm) { bool ret = false; task_lock(tsk); if (likely(tsk->mm == mm)) { /* tsk can't pass exit_mm/exec_mmap and exit */ read_unlock(&tasklist_lock); WRITE_ONCE(mm->owner, tsk); lru_gen_migrate_mm(mm); ret = true; } task_unlock(tsk); return ret; } static bool try_to_set_owner(struct task_struct *g, struct mm_struct *mm) { struct task_struct *t; for_each_thread(g, t) { struct mm_struct *t_mm = READ_ONCE(t->mm); if (t_mm == mm) { if (__try_to_set_owner(t, mm)) return true; } else if (t_mm) break; } return false; } /* * A task is exiting. If it owned this mm, find a new owner for the mm. */ void mm_update_next_owner(struct mm_struct *mm) { struct task_struct *g, *p = current; /* * If the exiting or execing task is not the owner, it's * someone else's problem. */ if (mm->owner != p) return; /* * The current owner is exiting/execing and there are no other * candidates. Do not leave the mm pointing to a possibly * freed task structure. */ if (atomic_read(&mm->mm_users) <= 1) { WRITE_ONCE(mm->owner, NULL); return; } read_lock(&tasklist_lock); /* * Search in the children */ list_for_each_entry(g, &p->children, sibling) { if (try_to_set_owner(g, mm)) goto ret; } /* * Search in the siblings */ list_for_each_entry(g, &p->real_parent->children, sibling) { if (try_to_set_owner(g, mm)) goto ret; } /* * Search through everything else, we should not get here often. */ for_each_process(g) { if (atomic_read(&mm->mm_users) <= 1) break; if (g->flags & PF_KTHREAD) continue; if (try_to_set_owner(g, mm)) goto ret; } read_unlock(&tasklist_lock); /* * We found no owner yet mm_users > 1: this implies that we are * most likely racing with swapoff (try_to_unuse()) or /proc or * ptrace or page migration (get_task_mm()). Mark owner as NULL. */ WRITE_ONCE(mm->owner, NULL); ret: return; } #endif /* CONFIG_MEMCG */ /* * Turn us into a lazy TLB process if we * aren't already.. */ static void exit_mm(void) { struct mm_struct *mm = current->mm; exit_mm_release(current, mm); if (!mm) return; mmap_read_lock(mm); mmgrab_lazy_tlb(mm); BUG_ON(mm != current->active_mm); /* more a memory barrier than a real lock */ task_lock(current); /* * When a thread stops operating on an address space, the loop * in membarrier_private_expedited() may not observe that * tsk->mm, and the loop in membarrier_global_expedited() may * not observe a MEMBARRIER_STATE_GLOBAL_EXPEDITED * rq->membarrier_state, so those would not issue an IPI. * Membarrier requires a memory barrier after accessing * user-space memory, before clearing tsk->mm or the * rq->membarrier_state. */ smp_mb__after_spinlock(); local_irq_disable(); current->mm = NULL; membarrier_update_current_mm(NULL); enter_lazy_tlb(mm, current); local_irq_enable(); task_unlock(current); mmap_read_unlock(mm); mm_update_next_owner(mm); mmput(mm); if (test_thread_flag(TIF_MEMDIE)) exit_oom_victim(); } static struct task_struct *find_alive_thread(struct task_struct *p) { struct task_struct *t; for_each_thread(p, t) { if (!(t->flags & PF_EXITING)) return t; } return NULL; } static struct task_struct *find_child_reaper(struct task_struct *father, struct list_head *dead) __releases(&tasklist_lock) __acquires(&tasklist_lock) { struct pid_namespace *pid_ns = task_active_pid_ns(father); struct task_struct *reaper = pid_ns->child_reaper; struct task_struct *p, *n; if (likely(reaper != father)) return reaper; reaper = find_alive_thread(father); if (reaper) { pid_ns->child_reaper = reaper; return reaper; } write_unlock_irq(&tasklist_lock); list_for_each_entry_safe(p, n, dead, ptrace_entry) { list_del_init(&p->ptrace_entry); release_task(p); } zap_pid_ns_processes(pid_ns); write_lock_irq(&tasklist_lock); return father; } /* * When we die, we re-parent all our children, and try to: * 1. give them to another thread in our thread group, if such a member exists * 2. give it to the first ancestor process which prctl'd itself as a * child_subreaper for its children (like a service manager) * 3. give it to the init process (PID 1) in our pid namespace */ static struct task_struct *find_new_reaper(struct task_struct *father, struct task_struct *child_reaper) { struct task_struct *thread, *reaper; thread = find_alive_thread(father); if (thread) return thread; if (father->signal->has_child_subreaper) { unsigned int ns_level = task_pid(father)->level; /* * Find the first ->is_child_subreaper ancestor in our pid_ns. * We can't check reaper != child_reaper to ensure we do not * cross the namespaces, the exiting parent could be injected * by setns() + fork(). * We check pid->level, this is slightly more efficient than * task_active_pid_ns(reaper) != task_active_pid_ns(father). */ for (reaper = father->real_parent; task_pid(reaper)->level == ns_level; reaper = reaper->real_parent) { if (reaper == &init_task) break; if (!reaper->signal->is_child_subreaper) continue; thread = find_alive_thread(reaper); if (thread) return thread; } } return child_reaper; } /* * Any that need to be release_task'd are put on the @dead list. */ static void reparent_leader(struct task_struct *father, struct task_struct *p, struct list_head *dead) { if (unlikely(p->exit_state == EXIT_DEAD)) return; /* We don't want people slaying init. */ p->exit_signal = SIGCHLD; /* If it has exited notify the new parent about this child's death. */ if (!p->ptrace && p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) { if (do_notify_parent(p, p->exit_signal)) { p->exit_state = EXIT_DEAD; list_add(&p->ptrace_entry, dead); } } kill_orphaned_pgrp(p, father); } /* * This does two things: * * A. Make init inherit all the child processes * B. Check to see if any process groups have become orphaned * as a result of our exiting, and if they have any stopped * jobs, send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2) */ static void forget_original_parent(struct task_struct *father, struct list_head *dead) { struct task_struct *p, *t, *reaper; if (unlikely(!list_empty(&father->ptraced))) exit_ptrace(father, dead); /* Can drop and reacquire tasklist_lock */ reaper = find_child_reaper(father, dead); if (list_empty(&father->children)) return; reaper = find_new_reaper(father, reaper); list_for_each_entry(p, &father->children, sibling) { for_each_thread(p, t) { RCU_INIT_POINTER(t->real_parent, reaper); BUG_ON((!t->ptrace) != (rcu_access_pointer(t->parent) == father)); if (likely(!t->ptrace)) t->parent = t->real_parent; if (t->pdeath_signal) group_send_sig_info(t->pdeath_signal, SEND_SIG_NOINFO, t, PIDTYPE_TGID); } /* * If this is a threaded reparent there is no need to * notify anyone anything has happened. */ if (!same_thread_group(reaper, father)) reparent_leader(father, p, dead); } list_splice_tail_init(&father->children, &reaper->children); } /* * Send signals to all our closest relatives so that they know * to properly mourn us.. */ static void exit_notify(struct task_struct *tsk, int group_dead) { bool autoreap; struct task_struct *p, *n; LIST_HEAD(dead); write_lock_irq(&tasklist_lock); forget_original_parent(tsk, &dead); if (group_dead) kill_orphaned_pgrp(tsk->group_leader, NULL); tsk->exit_state = EXIT_ZOMBIE; if (unlikely(tsk->ptrace)) { int sig = thread_group_leader(tsk) && thread_group_empty(tsk) && !ptrace_reparented(tsk) ? tsk->exit_signal : SIGCHLD; autoreap = do_notify_parent(tsk, sig); } else if (thread_group_leader(tsk)) { autoreap = thread_group_empty(tsk) && do_notify_parent(tsk, tsk->exit_signal); } else { autoreap = true; /* untraced sub-thread */ do_notify_pidfd(tsk); } if (autoreap) { tsk->exit_state = EXIT_DEAD; list_add(&tsk->ptrace_entry, &dead); } /* mt-exec, de_thread() is waiting for group leader */ if (unlikely(tsk->signal->notify_count < 0)) wake_up_process(tsk->signal->group_exec_task); write_unlock_irq(&tasklist_lock); list_for_each_entry_safe(p, n, &dead, ptrace_entry) { list_del_init(&p->ptrace_entry); release_task(p); } } #ifdef CONFIG_DEBUG_STACK_USAGE unsigned long stack_not_used(struct task_struct *p) { unsigned long *n = end_of_stack(p); do { /* Skip over canary */ # ifdef CONFIG_STACK_GROWSUP n--; # else n++; # endif } while (!*n); # ifdef CONFIG_STACK_GROWSUP return (unsigned long)end_of_stack(p) - (unsigned long)n; # else return (unsigned long)n - (unsigned long)end_of_stack(p); # endif } /* Count the maximum pages reached in kernel stacks */ static inline void kstack_histogram(unsigned long used_stack) { #ifdef CONFIG_VM_EVENT_COUNTERS if (used_stack <= 1024) count_vm_event(KSTACK_1K); #if THREAD_SIZE > 1024 else if (used_stack <= 2048) count_vm_event(KSTACK_2K); #endif #if THREAD_SIZE > 2048 else if (used_stack <= 4096) count_vm_event(KSTACK_4K); #endif #if THREAD_SIZE > 4096 else if (used_stack <= 8192) count_vm_event(KSTACK_8K); #endif #if THREAD_SIZE > 8192 else if (used_stack <= 16384) count_vm_event(KSTACK_16K); #endif #if THREAD_SIZE > 16384 else if (used_stack <= 32768) count_vm_event(KSTACK_32K); #endif #if THREAD_SIZE > 32768 else if (used_stack <= 65536) count_vm_event(KSTACK_64K); #endif #if THREAD_SIZE > 65536 else count_vm_event(KSTACK_REST); #endif #endif /* CONFIG_VM_EVENT_COUNTERS */ } static void check_stack_usage(void) { static DEFINE_SPINLOCK(low_water_lock); static int lowest_to_date = THREAD_SIZE; unsigned long free; free = stack_not_used(current); kstack_histogram(THREAD_SIZE - free); if (free >= lowest_to_date) return; spin_lock(&low_water_lock); if (free < lowest_to_date) { pr_info("%s (%d) used greatest stack depth: %lu bytes left\n", current->comm, task_pid_nr(current), free); lowest_to_date = free; } spin_unlock(&low_water_lock); } #else static inline void check_stack_usage(void) {} #endif static void synchronize_group_exit(struct task_struct *tsk, long code) { struct sighand_struct *sighand = tsk->sighand; struct signal_struct *signal = tsk->signal; spin_lock_irq(&sighand->siglock); signal->quick_threads--; if ((signal->quick_threads == 0) && !(signal->flags & SIGNAL_GROUP_EXIT)) { signal->flags = SIGNAL_GROUP_EXIT; signal->group_exit_code = code; signal->group_stop_count = 0; } spin_unlock_irq(&sighand->siglock); } void __noreturn do_exit(long code) { struct task_struct *tsk = current; int group_dead; WARN_ON(irqs_disabled()); synchronize_group_exit(tsk, code); WARN_ON(tsk->plug); kcov_task_exit(tsk); kmsan_task_exit(tsk); coredump_task_exit(tsk); ptrace_event(PTRACE_EVENT_EXIT, code); user_events_exit(tsk); io_uring_files_cancel(); exit_signals(tsk); /* sets PF_EXITING */ seccomp_filter_release(tsk); acct_update_integrals(tsk); group_dead = atomic_dec_and_test(&tsk->signal->live); if (group_dead) { /* * If the last thread of global init has exited, panic * immediately to get a useable coredump. */ if (unlikely(is_global_init(tsk))) panic("Attempted to kill init! exitcode=0x%08x\n", tsk->signal->group_exit_code ?: (int)code); #ifdef CONFIG_POSIX_TIMERS hrtimer_cancel(&tsk->signal->real_timer); exit_itimers(tsk); #endif if (tsk->mm) setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm); } acct_collect(code, group_dead); if (group_dead) tty_audit_exit(); audit_free(tsk); tsk->exit_code = code; taskstats_exit(tsk, group_dead); exit_mm(); if (group_dead) acct_process(); trace_sched_process_exit(tsk); exit_sem(tsk); exit_shm(tsk); exit_files(tsk); exit_fs(tsk); if (group_dead) disassociate_ctty(1); exit_task_namespaces(tsk); exit_task_work(tsk); exit_thread(tsk); /* * Flush inherited counters to the parent - before the parent * gets woken up by child-exit notifications. * * because of cgroup mode, must be called before cgroup_exit() */ perf_event_exit_task(tsk); sched_autogroup_exit_task(tsk); cgroup_exit(tsk); /* * FIXME: do that only when needed, using sched_exit tracepoint */ flush_ptrace_hw_breakpoint(tsk); exit_tasks_rcu_start(); exit_notify(tsk, group_dead); proc_exit_connector(tsk); mpol_put_task_policy(tsk); #ifdef CONFIG_FUTEX if (unlikely(current->pi_state_cache)) kfree(current->pi_state_cache); #endif /* * Make sure we are holding no locks: */ debug_check_no_locks_held(); if (tsk->io_context) exit_io_context(tsk); if (tsk->splice_pipe) free_pipe_info(tsk->splice_pipe); if (tsk->task_frag.page) put_page(tsk->task_frag.page); exit_task_stack_account(tsk); check_stack_usage(); preempt_disable(); if (tsk->nr_dirtied) __this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied); exit_rcu(); exit_tasks_rcu_finish(); lockdep_free_task(tsk); do_task_dead(); } void __noreturn make_task_dead(int signr) { /* * Take the task off the cpu after something catastrophic has * happened. * * We can get here from a kernel oops, sometimes with preemption off. * Start by checking for critical errors. * Then fix up important state like USER_DS and preemption. * Then do everything else. */ struct task_struct *tsk = current; unsigned int limit; if (unlikely(in_interrupt())) panic("Aiee, killing interrupt handler!"); if (unlikely(!tsk->pid)) panic("Attempted to kill the idle task!"); if (unlikely(irqs_disabled())) { pr_info("note: %s[%d] exited with irqs disabled\n", current->comm, task_pid_nr(current)); local_irq_enable(); } if (unlikely(in_atomic())) { pr_info("note: %s[%d] exited with preempt_count %d\n", current->comm, task_pid_nr(current), preempt_count()); preempt_count_set(PREEMPT_ENABLED); } /* * Every time the system oopses, if the oops happens while a reference * to an object was held, the reference leaks. * If the oops doesn't also leak memory, repeated oopsing can cause * reference counters to wrap around (if they're not using refcount_t). * This means that repeated oopsing can make unexploitable-looking bugs * exploitable through repeated oopsing. * To make sure this can't happen, place an upper bound on how often the * kernel may oops without panic(). */ limit = READ_ONCE(oops_limit); if (atomic_inc_return(&oops_count) >= limit && limit) panic("Oopsed too often (kernel.oops_limit is %d)", limit); /* * We're taking recursive faults here in make_task_dead. Safest is to just * leave this task alone and wait for reboot. */ if (unlikely(tsk->flags & PF_EXITING)) { pr_alert("Fixing recursive fault but reboot is needed!\n"); futex_exit_recursive(tsk); tsk->exit_state = EXIT_DEAD; refcount_inc(&tsk->rcu_users); do_task_dead(); } do_exit(signr); } SYSCALL_DEFINE1(exit, int, error_code) { do_exit((error_code&0xff)<<8); } /* * Take down every thread in the group. This is called by fatal signals * as well as by sys_exit_group (below). */ void __noreturn do_group_exit(int exit_code) { struct signal_struct *sig = current->signal; if (sig->flags & SIGNAL_GROUP_EXIT) exit_code = sig->group_exit_code; else if (sig->group_exec_task) exit_code = 0; else { struct sighand_struct *const sighand = current->sighand; spin_lock_irq(&sighand->siglock); if (sig->flags & SIGNAL_GROUP_EXIT) /* Another thread got here before we took the lock. */ exit_code = sig->group_exit_code; else if (sig->group_exec_task) exit_code = 0; else { sig->group_exit_code = exit_code; sig->flags = SIGNAL_GROUP_EXIT; zap_other_threads(current); } spin_unlock_irq(&sighand->siglock); } do_exit(exit_code); /* NOTREACHED */ } /* * this kills every thread in the thread group. Note that any externally * wait4()-ing process will get the correct exit code - even if this * thread is not the thread group leader. */ SYSCALL_DEFINE1(exit_group, int, error_code) { do_group_exit((error_code & 0xff) << 8); /* NOTREACHED */ return 0; } static int eligible_pid(struct wait_opts *wo, struct task_struct *p) { return wo->wo_type == PIDTYPE_MAX || task_pid_type(p, wo->wo_type) == wo->wo_pid; } static int eligible_child(struct wait_opts *wo, bool ptrace, struct task_struct *p) { if (!eligible_pid(wo, p)) return 0; /* * Wait for all children (clone and not) if __WALL is set or * if it is traced by us. */ if (ptrace || (wo->wo_flags & __WALL)) return 1; /* * Otherwise, wait for clone children *only* if __WCLONE is set; * otherwise, wait for non-clone children *only*. * * Note: a "clone" child here is one that reports to its parent * using a signal other than SIGCHLD, or a non-leader thread which * we can only see if it is traced by us. */ if ((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE)) return 0; return 1; } /* * Handle sys_wait4 work for one task in state EXIT_ZOMBIE. We hold * read_lock(&tasklist_lock) on entry. If we return zero, we still hold * the lock and this task is uninteresting. If we return nonzero, we have * released the lock and the system call should return. */ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) { int state, status; pid_t pid = task_pid_vnr(p); uid_t uid = from_kuid_munged(current_user_ns(), task_uid(p)); struct waitid_info *infop; if (!likely(wo->wo_flags & WEXITED)) return 0; if (unlikely(wo->wo_flags & WNOWAIT)) { status = (p->signal->flags & SIGNAL_GROUP_EXIT) ? p->signal->group_exit_code : p->exit_code; get_task_struct(p); read_unlock(&tasklist_lock); sched_annotate_sleep(); if (wo->wo_rusage) getrusage(p, RUSAGE_BOTH, wo->wo_rusage); put_task_struct(p); goto out_info; } /* * Move the task's state to DEAD/TRACE, only one thread can do this. */ state = (ptrace_reparented(p) && thread_group_leader(p)) ? EXIT_TRACE : EXIT_DEAD; if (cmpxchg(&p->exit_state, EXIT_ZOMBIE, state) != EXIT_ZOMBIE) return 0; /* * We own this thread, nobody else can reap it. */ read_unlock(&tasklist_lock); sched_annotate_sleep(); /* * Check thread_group_leader() to exclude the traced sub-threads. */ if (state == EXIT_DEAD && thread_group_leader(p)) { struct signal_struct *sig = p->signal; struct signal_struct *psig = current->signal; unsigned long maxrss; u64 tgutime, tgstime; /* * The resource counters for the group leader are in its * own task_struct. Those for dead threads in the group * are in its signal_struct, as are those for the child * processes it has previously reaped. All these * accumulate in the parent's signal_struct c* fields. * * We don't bother to take a lock here to protect these * p->signal fields because the whole thread group is dead * and nobody can change them. * * psig->stats_lock also protects us from our sub-threads * which can reap other children at the same time. * * We use thread_group_cputime_adjusted() to get times for * the thread group, which consolidates times for all threads * in the group including the group leader. */ thread_group_cputime_adjusted(p, &tgutime, &tgstime); write_seqlock_irq(&psig->stats_lock); psig->cutime += tgutime + sig->cutime; psig->cstime += tgstime + sig->cstime; psig->cgtime += task_gtime(p) + sig->gtime + sig->cgtime; psig->cmin_flt += p->min_flt + sig->min_flt + sig->cmin_flt; psig->cmaj_flt += p->maj_flt + sig->maj_flt + sig->cmaj_flt; psig->cnvcsw += p->nvcsw + sig->nvcsw + sig->cnvcsw; psig->cnivcsw += p->nivcsw + sig->nivcsw + sig->cnivcsw; psig->cinblock += task_io_get_inblock(p) + sig->inblock + sig->cinblock; psig->coublock += task_io_get_oublock(p) + sig->oublock + sig->coublock; maxrss = max(sig->maxrss, sig->cmaxrss); if (psig->cmaxrss < maxrss) psig->cmaxrss = maxrss; task_io_accounting_add(&psig->ioac, &p->ioac); task_io_accounting_add(&psig->ioac, &sig->ioac); write_sequnlock_irq(&psig->stats_lock); } if (wo->wo_rusage) getrusage(p, RUSAGE_BOTH, wo->wo_rusage); status = (p->signal->flags & SIGNAL_GROUP_EXIT) ? p->signal->group_exit_code : p->exit_code; wo->wo_stat = status; if (state == EXIT_TRACE) { write_lock_irq(&tasklist_lock); /* We dropped tasklist, ptracer could die and untrace */ ptrace_unlink(p); /* If parent wants a zombie, don't release it now */ state = EXIT_ZOMBIE; if (do_notify_parent(p, p->exit_signal)) state = EXIT_DEAD; p->exit_state = state; write_unlock_irq(&tasklist_lock); } if (state == EXIT_DEAD) release_task(p); out_info: infop = wo->wo_info; if (infop) { if ((status & 0x7f) == 0) { infop->cause = CLD_EXITED; infop->status = status >> 8; } else { infop->cause = (status & 0x80) ? CLD_DUMPED : CLD_KILLED; infop->status = status & 0x7f; } infop->pid = pid; infop->uid = uid; } return pid; } static int *task_stopped_code(struct task_struct *p, bool ptrace) { if (ptrace) { if (task_is_traced(p) && !(p->jobctl & JOBCTL_LISTENING)) return &p->exit_code; } else { if (p->signal->flags & SIGNAL_STOP_STOPPED) return &p->signal->group_exit_code; } return NULL; } /** * wait_task_stopped - Wait for %TASK_STOPPED or %TASK_TRACED * @wo: wait options * @ptrace: is the wait for ptrace * @p: task to wait for * * Handle sys_wait4() work for %p in state %TASK_STOPPED or %TASK_TRACED. * * CONTEXT: * read_lock(&tasklist_lock), which is released if return value is * non-zero. Also, grabs and releases @p->sighand->siglock. * * RETURNS: * 0 if wait condition didn't exist and search for other wait conditions * should continue. Non-zero return, -errno on failure and @p's pid on * success, implies that tasklist_lock is released and wait condition * search should terminate. */ static int wait_task_stopped(struct wait_opts *wo, int ptrace, struct task_struct *p) { struct waitid_info *infop; int exit_code, *p_code, why; uid_t uid = 0; /* unneeded, required by compiler */ pid_t pid; /* * Traditionally we see ptrace'd stopped tasks regardless of options. */ if (!ptrace && !(wo->wo_flags & WUNTRACED)) return 0; if (!task_stopped_code(p, ptrace)) return 0; exit_code = 0; spin_lock_irq(&p->sighand->siglock); p_code = task_stopped_code(p, ptrace); if (unlikely(!p_code)) goto unlock_sig; exit_code = *p_code; if (!exit_code) goto unlock_sig; if (!unlikely(wo->wo_flags & WNOWAIT)) *p_code = 0; uid = from_kuid_munged(current_user_ns(), task_uid(p)); unlock_sig: spin_unlock_irq(&p->sighand->siglock); if (!exit_code) return 0; /* * Now we are pretty sure this task is interesting. * Make sure it doesn't get reaped out from under us while we * give up the lock and then examine it below. We don't want to * keep holding onto the tasklist_lock while we call getrusage and * possibly take page faults for user memory. */ get_task_struct(p); pid = task_pid_vnr(p); why = ptrace ? CLD_TRAPPED : CLD_STOPPED; read_unlock(&tasklist_lock); sched_annotate_sleep(); if (wo->wo_rusage) getrusage(p, RUSAGE_BOTH, wo->wo_rusage); put_task_struct(p); if (likely(!(wo->wo_flags & WNOWAIT))) wo->wo_stat = (exit_code << 8) | 0x7f; infop = wo->wo_info; if (infop) { infop->cause = why; infop->status = exit_code; infop->pid = pid; infop->uid = uid; } return pid; } /* * Handle do_wait work for one task in a live, non-stopped state. * read_lock(&tasklist_lock) on entry. If we return zero, we still hold * the lock and this task is uninteresting. If we return nonzero, we have * released the lock and the system call should return. */ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p) { struct waitid_info *infop; pid_t pid; uid_t uid; if (!unlikely(wo->wo_flags & WCONTINUED)) return 0; if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) return 0; spin_lock_irq(&p->sighand->siglock); /* Re-check with the lock held. */ if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) { spin_unlock_irq(&p->sighand->siglock); return 0; } if (!unlikely(wo->wo_flags & WNOWAIT)) p->signal->flags &= ~SIGNAL_STOP_CONTINUED; uid = from_kuid_munged(current_user_ns(), task_uid(p)); spin_unlock_irq(&p->sighand->siglock); pid = task_pid_vnr(p); get_task_struct(p); read_unlock(&tasklist_lock); sched_annotate_sleep(); if (wo->wo_rusage) getrusage(p, RUSAGE_BOTH, wo->wo_rusage); put_task_struct(p); infop = wo->wo_info; if (!infop) { wo->wo_stat = 0xffff; } else { infop->cause = CLD_CONTINUED; infop->pid = pid; infop->uid = uid; infop->status = SIGCONT; } return pid; } /* * Consider @p for a wait by @parent. * * -ECHILD should be in ->notask_error before the first call. * Returns nonzero for a final return, when we have unlocked tasklist_lock. * Returns zero if the search for a child should continue; * then ->notask_error is 0 if @p is an eligible child, * or still -ECHILD. */ static int wait_consider_task(struct wait_opts *wo, int ptrace, struct task_struct *p) { /* * We can race with wait_task_zombie() from another thread. * Ensure that EXIT_ZOMBIE -> EXIT_DEAD/EXIT_TRACE transition * can't confuse the checks below. */ int exit_state = READ_ONCE(p->exit_state); int ret; if (unlikely(exit_state == EXIT_DEAD)) return 0; ret = eligible_child(wo, ptrace, p); if (!ret) return ret; if (unlikely(exit_state == EXIT_TRACE)) { /* * ptrace == 0 means we are the natural parent. In this case * we should clear notask_error, debugger will notify us. */ if (likely(!ptrace)) wo->notask_error = 0; return 0; } if (likely(!ptrace) && unlikely(p->ptrace)) { /* * If it is traced by its real parent's group, just pretend * the caller is ptrace_do_wait() and reap this child if it * is zombie. * * This also hides group stop state from real parent; otherwise * a single stop can be reported twice as group and ptrace stop. * If a ptracer wants to distinguish these two events for its * own children it should create a separate process which takes * the role of real parent. */ if (!ptrace_reparented(p)) ptrace = 1; } /* slay zombie? */ if (exit_state == EXIT_ZOMBIE) { /* we don't reap group leaders with subthreads */ if (!delay_group_leader(p)) { /* * A zombie ptracee is only visible to its ptracer. * Notification and reaping will be cascaded to the * real parent when the ptracer detaches. */ if (unlikely(ptrace) || likely(!p->ptrace)) return wait_task_zombie(wo, p); } /* * Allow access to stopped/continued state via zombie by * falling through. Clearing of notask_error is complex. * * When !@ptrace: * * If WEXITED is set, notask_error should naturally be * cleared. If not, subset of WSTOPPED|WCONTINUED is set, * so, if there are live subthreads, there are events to * wait for. If all subthreads are dead, it's still safe * to clear - this function will be called again in finite * amount time once all the subthreads are released and * will then return without clearing. * * When @ptrace: * * Stopped state is per-task and thus can't change once the * target task dies. Only continued and exited can happen. * Clear notask_error if WCONTINUED | WEXITED. */ if (likely(!ptrace) || (wo->wo_flags & (WCONTINUED | WEXITED))) wo->notask_error = 0; } else { /* * @p is alive and it's gonna stop, continue or exit, so * there always is something to wait for. */ wo->notask_error = 0; } /* * Wait for stopped. Depending on @ptrace, different stopped state * is used and the two don't interact with each other. */ ret = wait_task_stopped(wo, ptrace, p); if (ret) return ret; /* * Wait for continued. There's only one continued state and the * ptracer can consume it which can confuse the real parent. Don't * use WCONTINUED from ptracer. You don't need or want it. */ return wait_task_continued(wo, p); } /* * Do the work of do_wait() for one thread in the group, @tsk. * * -ECHILD should be in ->notask_error before the first call. * Returns nonzero for a final return, when we have unlocked tasklist_lock. * Returns zero if the search for a child should continue; then * ->notask_error is 0 if there were any eligible children, * or still -ECHILD. */ static int do_wait_thread(struct wait_opts *wo, struct task_struct *tsk) { struct task_struct *p; list_for_each_entry(p, &tsk->children, sibling) { int ret = wait_consider_task(wo, 0, p); if (ret) return ret; } return 0; } static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk) { struct task_struct *p; list_for_each_entry(p, &tsk->ptraced, ptrace_entry) { int ret = wait_consider_task(wo, 1, p); if (ret) return ret; } return 0; } bool pid_child_should_wake(struct wait_opts *wo, struct task_struct *p) { if (!eligible_pid(wo, p)) return false; if ((wo->wo_flags & __WNOTHREAD) && wo->child_wait.private != p->parent) return false; return true; } static int child_wait_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct wait_opts *wo = container_of(wait, struct wait_opts, child_wait); struct task_struct *p = key; if (pid_child_should_wake(wo, p)) return default_wake_function(wait, mode, sync, key); return 0; } void __wake_up_parent(struct task_struct *p, struct task_struct *parent) { __wake_up_sync_key(&parent->signal->wait_chldexit, TASK_INTERRUPTIBLE, p); } static bool is_effectively_child(struct wait_opts *wo, bool ptrace, struct task_struct *target) { struct task_struct *parent = !ptrace ? target->real_parent : target->parent; return current == parent || (!(wo->wo_flags & __WNOTHREAD) && same_thread_group(current, parent)); } /* * Optimization for waiting on PIDTYPE_PID. No need to iterate through child * and tracee lists to find the target task. */ static int do_wait_pid(struct wait_opts *wo) { bool ptrace; struct task_struct *target; int retval; ptrace = false; target = pid_task(wo->wo_pid, PIDTYPE_TGID); if (target && is_effectively_child(wo, ptrace, target)) { retval = wait_consider_task(wo, ptrace, target); if (retval) return retval; } ptrace = true; target = pid_task(wo->wo_pid, PIDTYPE_PID); if (target && target->ptrace && is_effectively_child(wo, ptrace, target)) { retval = wait_consider_task(wo, ptrace, target); if (retval) return retval; } return 0; } long __do_wait(struct wait_opts *wo) { long retval; /* * If there is nothing that can match our criteria, just get out. * We will clear ->notask_error to zero if we see any child that * might later match our criteria, even if we are not able to reap * it yet. */ wo->notask_error = -ECHILD; if ((wo->wo_type < PIDTYPE_MAX) && (!wo->wo_pid || !pid_has_task(wo->wo_pid, wo->wo_type))) goto notask; read_lock(&tasklist_lock); if (wo->wo_type == PIDTYPE_PID) { retval = do_wait_pid(wo); if (retval) return retval; } else { struct task_struct *tsk = current; do { retval = do_wait_thread(wo, tsk); if (retval) return retval; retval = ptrace_do_wait(wo, tsk); if (retval) return retval; if (wo->wo_flags & __WNOTHREAD) break; } while_each_thread(current, tsk); } read_unlock(&tasklist_lock); notask: retval = wo->notask_error; if (!retval && !(wo->wo_flags & WNOHANG)) return -ERESTARTSYS; return retval; } static long do_wait(struct wait_opts *wo) { int retval; trace_sched_process_wait(wo->wo_pid); init_waitqueue_func_entry(&wo->child_wait, child_wait_callback); wo->child_wait.private = current; add_wait_queue(¤t->signal->wait_chldexit, &wo->child_wait); do { set_current_state(TASK_INTERRUPTIBLE); retval = __do_wait(wo); if (retval != -ERESTARTSYS) break; if (signal_pending(current)) break; schedule(); } while (1); __set_current_state(TASK_RUNNING); remove_wait_queue(¤t->signal->wait_chldexit, &wo->child_wait); return retval; } int kernel_waitid_prepare(struct wait_opts *wo, int which, pid_t upid, struct waitid_info *infop, int options, struct rusage *ru) { unsigned int f_flags = 0; struct pid *pid = NULL; enum pid_type type; if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED| __WNOTHREAD|__WCLONE|__WALL)) return -EINVAL; if (!(options & (WEXITED|WSTOPPED|WCONTINUED))) return -EINVAL; switch (which) { case P_ALL: type = PIDTYPE_MAX; break; case P_PID: type = PIDTYPE_PID; if (upid <= 0) return -EINVAL; pid = find_get_pid(upid); break; case P_PGID: type = PIDTYPE_PGID; if (upid < 0) return -EINVAL; if (upid) pid = find_get_pid(upid); else pid = get_task_pid(current, PIDTYPE_PGID); break; case P_PIDFD: type = PIDTYPE_PID; if (upid < 0) return -EINVAL; pid = pidfd_get_pid(upid, &f_flags); if (IS_ERR(pid)) return PTR_ERR(pid); break; default: return -EINVAL; } wo->wo_type = type; wo->wo_pid = pid; wo->wo_flags = options; wo->wo_info = infop; wo->wo_rusage = ru; if (f_flags & O_NONBLOCK) wo->wo_flags |= WNOHANG; return 0; } static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop, int options, struct rusage *ru) { struct wait_opts wo; long ret; ret = kernel_waitid_prepare(&wo, which, upid, infop, options, ru); if (ret) return ret; ret = do_wait(&wo); if (!ret && !(options & WNOHANG) && (wo.wo_flags & WNOHANG)) ret = -EAGAIN; put_pid(wo.wo_pid); return ret; } SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, infop, int, options, struct rusage __user *, ru) { struct rusage r; struct waitid_info info = {.status = 0}; long err = kernel_waitid(which, upid, &info, options, ru ? &r : NULL); int signo = 0; if (err > 0) { signo = SIGCHLD; err = 0; if (ru && copy_to_user(ru, &r, sizeof(struct rusage))) return -EFAULT; } if (!infop) return err; if (!user_write_access_begin(infop, sizeof(*infop))) return -EFAULT; unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); unsafe_put_user(info.cause, &infop->si_code, Efault); unsafe_put_user(info.pid, &infop->si_pid, Efault); unsafe_put_user(info.uid, &infop->si_uid, Efault); unsafe_put_user(info.status, &infop->si_status, Efault); user_write_access_end(); return err; Efault: user_write_access_end(); return -EFAULT; } long kernel_wait4(pid_t upid, int __user *stat_addr, int options, struct rusage *ru) { struct wait_opts wo; struct pid *pid = NULL; enum pid_type type; long ret; if (options & ~(WNOHANG|WUNTRACED|WCONTINUED| __WNOTHREAD|__WCLONE|__WALL)) return -EINVAL; /* -INT_MIN is not defined */ if (upid == INT_MIN) return -ESRCH; if (upid == -1) type = PIDTYPE_MAX; else if (upid < 0) { type = PIDTYPE_PGID; pid = find_get_pid(-upid); } else if (upid == 0) { type = PIDTYPE_PGID; pid = get_task_pid(current, PIDTYPE_PGID); } else /* upid > 0 */ { type = PIDTYPE_PID; pid = find_get_pid(upid); } wo.wo_type = type; wo.wo_pid = pid; wo.wo_flags = options | WEXITED; wo.wo_info = NULL; wo.wo_stat = 0; wo.wo_rusage = ru; ret = do_wait(&wo); put_pid(pid); if (ret > 0 && stat_addr && put_user(wo.wo_stat, stat_addr)) ret = -EFAULT; return ret; } int kernel_wait(pid_t pid, int *stat) { struct wait_opts wo = { .wo_type = PIDTYPE_PID, .wo_pid = find_get_pid(pid), .wo_flags = WEXITED, }; int ret; ret = do_wait(&wo); if (ret > 0 && wo.wo_stat) *stat = wo.wo_stat; put_pid(wo.wo_pid); return ret; } SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr, int, options, struct rusage __user *, ru) { struct rusage r; long err = kernel_wait4(upid, stat_addr, options, ru ? &r : NULL); if (err > 0) { if (ru && copy_to_user(ru, &r, sizeof(struct rusage))) return -EFAULT; } return err; } #ifdef __ARCH_WANT_SYS_WAITPID /* * sys_waitpid() remains for compatibility. waitpid() should be * implemented by calling sys_wait4() from libc.a. */ SYSCALL_DEFINE3(waitpid, pid_t, pid, int __user *, stat_addr, int, options) { return kernel_wait4(pid, stat_addr, options, NULL); } #endif #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(wait4, compat_pid_t, pid, compat_uint_t __user *, stat_addr, int, options, struct compat_rusage __user *, ru) { struct rusage r; long err = kernel_wait4(pid, stat_addr, options, ru ? &r : NULL); if (err > 0) { if (ru && put_compat_rusage(&r, ru)) return -EFAULT; } return err; } COMPAT_SYSCALL_DEFINE5(waitid, int, which, compat_pid_t, pid, struct compat_siginfo __user *, infop, int, options, struct compat_rusage __user *, uru) { struct rusage ru; struct waitid_info info = {.status = 0}; long err = kernel_waitid(which, pid, &info, options, uru ? &ru : NULL); int signo = 0; if (err > 0) { signo = SIGCHLD; err = 0; if (uru) { /* kernel_waitid() overwrites everything in ru */ if (COMPAT_USE_64BIT_TIME) err = copy_to_user(uru, &ru, sizeof(ru)); else err = put_compat_rusage(&ru, uru); if (err) return -EFAULT; } } if (!infop) return err; if (!user_write_access_begin(infop, sizeof(*infop))) return -EFAULT; unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); unsafe_put_user(info.cause, &infop->si_code, Efault); unsafe_put_user(info.pid, &infop->si_pid, Efault); unsafe_put_user(info.uid, &infop->si_uid, Efault); unsafe_put_user(info.status, &infop->si_status, Efault); user_write_access_end(); return err; Efault: user_write_access_end(); return -EFAULT; } #endif /* * This needs to be __function_aligned as GCC implicitly makes any * implementation of abort() cold and drops alignment specified by * -falign-functions=N. * * See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88345#c11 */ __weak __function_aligned void abort(void) { BUG(); /* if that doesn't kill us, halt */ panic("Oops failed to kill thread"); } EXPORT_SYMBOL(abort); |
| 2 2 1 1 2 1 1 2 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/profile.c * Simple profiling. Manages a direct-mapped profile hit count buffer, * with configurable resolution, support for restricting the cpus on * which profiling is done, and switching between cpu time and * schedule() calls via kernel command line parameters passed at boot. * * Scheduler profiling support, Arjan van de Ven and Ingo Molnar, * Red Hat, July 2004 * Consolidation of architecture support code for profiling, * Nadia Yvette Chambers, Oracle, July 2004 * Amortized hit count accounting via per-cpu open-addressed hashtables * to resolve timer interrupt livelocks, Nadia Yvette Chambers, * Oracle, 2004 */ #include <linux/export.h> #include <linux/profile.h> #include <linux/memblock.h> #include <linux/notifier.h> #include <linux/mm.h> #include <linux/cpumask.h> #include <linux/cpu.h> #include <linux/highmem.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/sched/stat.h> #include <asm/sections.h> #include <asm/irq_regs.h> #include <asm/ptrace.h> struct profile_hit { u32 pc, hits; }; #define PROFILE_GRPSHIFT 3 #define PROFILE_GRPSZ (1 << PROFILE_GRPSHIFT) #define NR_PROFILE_HIT (PAGE_SIZE/sizeof(struct profile_hit)) #define NR_PROFILE_GRP (NR_PROFILE_HIT/PROFILE_GRPSZ) static atomic_t *prof_buffer; static unsigned long prof_len; static unsigned short int prof_shift; int prof_on __read_mostly; EXPORT_SYMBOL_GPL(prof_on); int profile_setup(char *str) { static const char schedstr[] = "schedule"; static const char kvmstr[] = "kvm"; const char *select = NULL; int par; if (!strncmp(str, schedstr, strlen(schedstr))) { prof_on = SCHED_PROFILING; select = schedstr; } else if (!strncmp(str, kvmstr, strlen(kvmstr))) { prof_on = KVM_PROFILING; select = kvmstr; } else if (get_option(&str, &par)) { prof_shift = clamp(par, 0, BITS_PER_LONG - 1); prof_on = CPU_PROFILING; pr_info("kernel profiling enabled (shift: %u)\n", prof_shift); } if (select) { if (str[strlen(select)] == ',') str += strlen(select) + 1; if (get_option(&str, &par)) prof_shift = clamp(par, 0, BITS_PER_LONG - 1); pr_info("kernel %s profiling enabled (shift: %u)\n", select, prof_shift); } return 1; } __setup("profile=", profile_setup); int __ref profile_init(void) { int buffer_bytes; if (!prof_on) return 0; /* only text is profiled */ prof_len = (_etext - _stext) >> prof_shift; if (!prof_len) { pr_warn("profiling shift: %u too large\n", prof_shift); prof_on = 0; return -EINVAL; } buffer_bytes = prof_len*sizeof(atomic_t); prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL|__GFP_NOWARN); if (prof_buffer) return 0; prof_buffer = alloc_pages_exact(buffer_bytes, GFP_KERNEL|__GFP_ZERO|__GFP_NOWARN); if (prof_buffer) return 0; prof_buffer = vzalloc(buffer_bytes); if (prof_buffer) return 0; return -ENOMEM; } static void do_profile_hits(int type, void *__pc, unsigned int nr_hits) { unsigned long pc; pc = ((unsigned long)__pc - (unsigned long)_stext) >> prof_shift; if (pc < prof_len) atomic_add(nr_hits, &prof_buffer[pc]); } void profile_hits(int type, void *__pc, unsigned int nr_hits) { if (prof_on != type || !prof_buffer) return; do_profile_hits(type, __pc, nr_hits); } EXPORT_SYMBOL_GPL(profile_hits); void profile_tick(int type) { struct pt_regs *regs = get_irq_regs(); /* This is the old kernel-only legacy profiling */ if (!user_mode(regs)) profile_hit(type, (void *)profile_pc(regs)); } #ifdef CONFIG_PROC_FS #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/uaccess.h> /* * This function accesses profiling information. The returned data is * binary: the sampling step and the actual contents of the profile * buffer. Use of the program readprofile is recommended in order to * get meaningful info out of these data. */ static ssize_t read_profile(struct file *file, char __user *buf, size_t count, loff_t *ppos) { unsigned long p = *ppos; ssize_t read; char *pnt; unsigned long sample_step = 1UL << prof_shift; if (p >= (prof_len+1)*sizeof(unsigned int)) return 0; if (count > (prof_len+1)*sizeof(unsigned int) - p) count = (prof_len+1)*sizeof(unsigned int) - p; read = 0; while (p < sizeof(unsigned int) && count > 0) { if (put_user(*((char *)(&sample_step)+p), buf)) return -EFAULT; buf++; p++; count--; read++; } pnt = (char *)prof_buffer + p - sizeof(atomic_t); if (copy_to_user(buf, (void *)pnt, count)) return -EFAULT; read += count; *ppos += read; return read; } /* default is to not implement this call */ int __weak setup_profiling_timer(unsigned mult) { return -EINVAL; } /* * Writing to /proc/profile resets the counters * * Writing a 'profiling multiplier' value into it also re-sets the profiling * interrupt frequency, on architectures that support this. */ static ssize_t write_profile(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { #ifdef CONFIG_SMP if (count == sizeof(int)) { unsigned int multiplier; if (copy_from_user(&multiplier, buf, sizeof(int))) return -EFAULT; if (setup_profiling_timer(multiplier)) return -EINVAL; } #endif memset(prof_buffer, 0, prof_len * sizeof(atomic_t)); return count; } static const struct proc_ops profile_proc_ops = { .proc_read = read_profile, .proc_write = write_profile, .proc_lseek = default_llseek, }; int __ref create_proc_profile(void) { struct proc_dir_entry *entry; int err = 0; if (!prof_on) return 0; entry = proc_create("profile", S_IWUSR | S_IRUGO, NULL, &profile_proc_ops); if (entry) proc_set_size(entry, (1 + prof_len) * sizeof(atomic_t)); return err; } subsys_initcall(create_proc_profile); #endif /* CONFIG_PROC_FS */ |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* Bluetooth HCI driver model support. */ #include <linux/module.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> static const struct class bt_class = { .name = "bluetooth", }; static void bt_link_release(struct device *dev) { struct hci_conn *conn = to_hci_conn(dev); kfree(conn); } static const struct device_type bt_link = { .name = "link", .release = bt_link_release, }; void hci_conn_init_sysfs(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; bt_dev_dbg(hdev, "conn %p", conn); conn->dev.type = &bt_link; conn->dev.class = &bt_class; conn->dev.parent = &hdev->dev; device_initialize(&conn->dev); } void hci_conn_add_sysfs(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; bt_dev_dbg(hdev, "conn %p", conn); if (device_is_registered(&conn->dev)) return; dev_set_name(&conn->dev, "%s:%d", hdev->name, conn->handle); if (device_add(&conn->dev) < 0) bt_dev_err(hdev, "failed to register connection device"); } void hci_conn_del_sysfs(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; bt_dev_dbg(hdev, "conn %p", conn); if (!device_is_registered(&conn->dev)) { /* If device_add() has *not* succeeded, use *only* put_device() * to drop the reference count. */ put_device(&conn->dev); return; } /* If there are devices using the connection as parent reset it to NULL * before unregistering the device. */ while (1) { struct device *dev; dev = device_find_any_child(&conn->dev); if (!dev) break; device_move(dev, NULL, DPM_ORDER_DEV_LAST); put_device(dev); } device_unregister(&conn->dev); } static void bt_host_release(struct device *dev) { struct hci_dev *hdev = to_hci_dev(dev); if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) hci_release_dev(hdev); else kfree(hdev); module_put(THIS_MODULE); } static ssize_t reset_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct hci_dev *hdev = to_hci_dev(dev); if (hdev->reset) hdev->reset(hdev); return count; } static DEVICE_ATTR_WO(reset); static struct attribute *bt_host_attrs[] = { &dev_attr_reset.attr, NULL, }; ATTRIBUTE_GROUPS(bt_host); static const struct device_type bt_host = { .name = "host", .release = bt_host_release, .groups = bt_host_groups, }; void hci_init_sysfs(struct hci_dev *hdev) { struct device *dev = &hdev->dev; dev->type = &bt_host; dev->class = &bt_class; __module_get(THIS_MODULE); device_initialize(dev); } int __init bt_sysfs_init(void) { return class_register(&bt_class); } void bt_sysfs_cleanup(void) { class_unregister(&bt_class); } |
| 2 2 2 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 | // SPDX-License-Identifier: GPL-2.0 /* * CPU <-> hardware queue mapping helpers * * Copyright (C) 2013-2014 Jens Axboe */ #include <linux/kernel.h> #include <linux/threads.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/smp.h> #include <linux/cpu.h> #include <linux/group_cpus.h> #include <linux/device/bus.h> #include "blk.h" #include "blk-mq.h" void blk_mq_map_queues(struct blk_mq_queue_map *qmap) { const struct cpumask *masks; unsigned int queue, cpu; masks = group_cpus_evenly(qmap->nr_queues); if (!masks) { for_each_possible_cpu(cpu) qmap->mq_map[cpu] = qmap->queue_offset; return; } for (queue = 0; queue < qmap->nr_queues; queue++) { for_each_cpu(cpu, &masks[queue]) qmap->mq_map[cpu] = qmap->queue_offset + queue; } kfree(masks); } EXPORT_SYMBOL_GPL(blk_mq_map_queues); /** * blk_mq_hw_queue_to_node - Look up the memory node for a hardware queue index * @qmap: CPU to hardware queue map. * @index: hardware queue index. * * We have no quick way of doing reverse lookups. This is only used at * queue init time, so runtime isn't important. */ int blk_mq_hw_queue_to_node(struct blk_mq_queue_map *qmap, unsigned int index) { int i; for_each_possible_cpu(i) { if (index == qmap->mq_map[i]) return cpu_to_node(i); } return NUMA_NO_NODE; } /** * blk_mq_map_hw_queues - Create CPU to hardware queue mapping * @qmap: CPU to hardware queue map * @dev: The device to map queues * @offset: Queue offset to use for the device * * Create a CPU to hardware queue mapping in @qmap. The struct bus_type * irq_get_affinity callback will be used to retrieve the affinity. */ void blk_mq_map_hw_queues(struct blk_mq_queue_map *qmap, struct device *dev, unsigned int offset) { const struct cpumask *mask; unsigned int queue, cpu; if (!dev->bus->irq_get_affinity) goto fallback; for (queue = 0; queue < qmap->nr_queues; queue++) { mask = dev->bus->irq_get_affinity(dev, queue + offset); if (!mask) goto fallback; for_each_cpu(cpu, mask) qmap->mq_map[cpu] = qmap->queue_offset + queue; } return; fallback: blk_mq_map_queues(qmap); } EXPORT_SYMBOL_GPL(blk_mq_map_hw_queues); |
| 4 4 4 5 5 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * TCP over IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Based on: * linux/net/ipv4/tcp.c * linux/net/ipv4/tcp_input.c * linux/net/ipv4/tcp_output.c * * Fixes: * Hideaki YOSHIFUJI : sin6_scope_id support * YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which * Alexey Kuznetsov allow both IPv4 and IPv6 sockets to bind * a single port at the same time. * YOSHIFUJI Hideaki @USAGI: convert /proc/net/tcp6 to seq_file. */ #include <linux/bottom_half.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/jiffies.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/init.h> #include <linux/jhash.h> #include <linux/ipsec.h> #include <linux/times.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> #include <linux/random.h> #include <linux/indirect_call_wrapper.h> #include <net/tcp.h> #include <net/ndisc.h> #include <net/inet6_hashtables.h> #include <net/inet6_connection_sock.h> #include <net/ipv6.h> #include <net/transp_v6.h> #include <net/addrconf.h> #include <net/ip6_route.h> #include <net/ip6_checksum.h> #include <net/inet_ecn.h> #include <net/protocol.h> #include <net/xfrm.h> #include <net/snmp.h> #include <net/dsfield.h> #include <net/timewait_sock.h> #include <net/inet_common.h> #include <net/secure_seq.h> #include <net/hotdata.h> #include <net/busy_poll.h> #include <net/rstreason.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <crypto/hash.h> #include <linux/scatterlist.h> #include <trace/events/tcp.h> static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb, enum sk_rst_reason reason); static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req); INDIRECT_CALLABLE_SCOPE int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb); static const struct inet_connection_sock_af_ops ipv6_mapped; const struct inet_connection_sock_af_ops ipv6_specific; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) static const struct tcp_sock_af_ops tcp_sock_ipv6_specific; static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific; #endif /* Helper returning the inet6 address from a given tcp socket. * It can be used in TCP stack instead of inet6_sk(sk). * This avoids a dereference and allow compiler optimizations. * It is a specialized version of inet6_sk_generic(). */ #define tcp_inet6_sk(sk) (&container_of_const(tcp_sk(sk), \ struct tcp6_sock, tcp)->inet6) static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); if (dst && dst_hold_safe(dst)) { rcu_assign_pointer(sk->sk_rx_dst, dst); sk->sk_rx_dst_ifindex = skb->skb_iif; sk->sk_rx_dst_cookie = rt6_get_cookie(dst_rt6_info(dst)); } } static u32 tcp_v6_init_seq(const struct sk_buff *skb) { return secure_tcpv6_seq(ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32, tcp_hdr(skb)->dest, tcp_hdr(skb)->source); } static u32 tcp_v6_init_ts_off(const struct net *net, const struct sk_buff *skb) { return secure_tcpv6_ts_off(net, ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32); } static int tcp_v6_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { /* This check is replicated from tcp_v6_connect() and intended to * prevent BPF program called below from accessing bytes that are out * of the bound specified by user in addr_len. */ if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; sock_owned_by_me(sk); return BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, &addr_len); } static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; struct inet_connection_sock *icsk = inet_csk(sk); struct in6_addr *saddr = NULL, *final_p, final; struct inet_timewait_death_row *tcp_death_row; struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct inet_sock *inet = inet_sk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); struct ipv6_txoptions *opt; struct dst_entry *dst; struct flowi6 fl6; int addr_type; int err; if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; if (usin->sin6_family != AF_INET6) return -EAFNOSUPPORT; memset(&fl6, 0, sizeof(fl6)); if (inet6_test_bit(SNDFLOW, sk)) { fl6.flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK; IP6_ECN_flow_init(fl6.flowlabel); if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { struct ip6_flowlabel *flowlabel; flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; fl6_sock_release(flowlabel); } } /* * connect() to INADDR_ANY means loopback (BSD'ism). */ if (ipv6_addr_any(&usin->sin6_addr)) { if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK), &usin->sin6_addr); else usin->sin6_addr = in6addr_loopback; } addr_type = ipv6_addr_type(&usin->sin6_addr); if (addr_type & IPV6_ADDR_MULTICAST) return -ENETUNREACH; if (addr_type&IPV6_ADDR_LINKLOCAL) { if (addr_len >= sizeof(struct sockaddr_in6) && usin->sin6_scope_id) { /* If interface is set while binding, indices * must coincide. */ if (!sk_dev_equal_l3scope(sk, usin->sin6_scope_id)) return -EINVAL; sk->sk_bound_dev_if = usin->sin6_scope_id; } /* Connect to link-local address requires an interface */ if (!sk->sk_bound_dev_if) return -EINVAL; } if (tp->rx_opt.ts_recent_stamp && !ipv6_addr_equal(&sk->sk_v6_daddr, &usin->sin6_addr)) { tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; WRITE_ONCE(tp->write_seq, 0); } sk->sk_v6_daddr = usin->sin6_addr; np->flow_label = fl6.flowlabel; /* * TCP over IPv4 */ if (addr_type & IPV6_ADDR_MAPPED) { u32 exthdrlen = icsk->icsk_ext_hdr_len; struct sockaddr_in sin; if (ipv6_only_sock(sk)) return -ENETUNREACH; sin.sin_family = AF_INET; sin.sin_port = usin->sin6_port; sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3]; /* Paired with READ_ONCE() in tcp_(get|set)sockopt() */ WRITE_ONCE(icsk->icsk_af_ops, &ipv6_mapped); if (sk_is_mptcp(sk)) mptcpv6_handle_mapped(sk, true); sk->sk_backlog_rcv = tcp_v4_do_rcv; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) tp->af_specific = &tcp_sock_ipv6_mapped_specific; #endif err = tcp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin)); if (err) { icsk->icsk_ext_hdr_len = exthdrlen; /* Paired with READ_ONCE() in tcp_(get|set)sockopt() */ WRITE_ONCE(icsk->icsk_af_ops, &ipv6_specific); if (sk_is_mptcp(sk)) mptcpv6_handle_mapped(sk, false); sk->sk_backlog_rcv = tcp_v6_do_rcv; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) tp->af_specific = &tcp_sock_ipv6_specific; #endif goto failure; } np->saddr = sk->sk_v6_rcv_saddr; return err; } if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) saddr = &sk->sk_v6_rcv_saddr; fl6.flowi6_proto = IPPROTO_TCP; fl6.daddr = sk->sk_v6_daddr; fl6.saddr = saddr ? *saddr : np->saddr; fl6.flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label); fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_dport = usin->sin6_port; fl6.fl6_sport = inet->inet_sport; fl6.flowi6_uid = sk->sk_uid; opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk)); final_p = fl6_update_dst(&fl6, opt, &final); security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); dst = ip6_dst_lookup_flow(net, sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto failure; } tp->tcp_usec_ts = dst_tcp_usec_ts(dst); tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; if (!saddr) { saddr = &fl6.saddr; err = inet_bhash2_update_saddr(sk, saddr, AF_INET6); if (err) goto failure; } /* set the source address */ np->saddr = *saddr; inet->inet_rcv_saddr = LOOPBACK4_IPV6; sk->sk_gso_type = SKB_GSO_TCPV6; ip6_dst_store(sk, dst, NULL, NULL); icsk->icsk_ext_hdr_len = 0; if (opt) icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen; tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); inet->inet_dport = usin->sin6_port; tcp_set_state(sk, TCP_SYN_SENT); err = inet6_hash_connect(tcp_death_row, sk); if (err) goto late_failure; sk_set_txhash(sk); if (likely(!tp->repair)) { if (!tp->write_seq) WRITE_ONCE(tp->write_seq, secure_tcpv6_seq(np->saddr.s6_addr32, sk->sk_v6_daddr.s6_addr32, inet->inet_sport, inet->inet_dport)); tp->tsoffset = secure_tcpv6_ts_off(net, np->saddr.s6_addr32, sk->sk_v6_daddr.s6_addr32); } if (tcp_fastopen_defer_connect(sk, &err)) return err; if (err) goto late_failure; err = tcp_connect(sk); if (err) goto late_failure; return 0; late_failure: tcp_set_state(sk, TCP_CLOSE); inet_bhash2_reset_saddr(sk); failure: inet->inet_dport = 0; sk->sk_route_caps = 0; return err; } static void tcp_v6_mtu_reduced(struct sock *sk) { struct dst_entry *dst; u32 mtu; if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) return; mtu = READ_ONCE(tcp_sk(sk)->mtu_info); /* Drop requests trying to increase our current mss. * Check done in __ip6_rt_update_pmtu() is too late. */ if (tcp_mtu_to_mss(sk, mtu) >= tcp_sk(sk)->mss_cache) return; dst = inet6_csk_update_pmtu(sk, mtu); if (!dst) return; if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) { tcp_sync_mss(sk, dst_mtu(dst)); tcp_simple_retransmit(sk); } } static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; const struct tcphdr *th = (struct tcphdr *)(skb->data+offset); struct net *net = dev_net_rcu(skb->dev); struct request_sock *fastopen; struct ipv6_pinfo *np; struct tcp_sock *tp; __u32 seq, snd_una; struct sock *sk; bool fatal; int err; sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, &hdr->daddr, th->dest, &hdr->saddr, ntohs(th->source), skb->dev->ifindex, inet6_sdif(skb)); if (!sk) { __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return -ENOENT; } if (sk->sk_state == TCP_TIME_WAIT) { /* To increase the counter of ignored icmps for TCP-AO */ tcp_ao_ignore_icmp(sk, AF_INET6, type, code); inet_twsk_put(inet_twsk(sk)); return 0; } seq = ntohl(th->seq); fatal = icmpv6_err_convert(type, code, &err); if (sk->sk_state == TCP_NEW_SYN_RECV) { tcp_req_err(sk, seq, fatal); return 0; } if (tcp_ao_ignore_icmp(sk, AF_INET6, type, code)) { sock_put(sk); return 0; } bh_lock_sock(sk); if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG) __NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == TCP_CLOSE) goto out; if (static_branch_unlikely(&ip6_min_hopcount)) { /* min_hopcount can be changed concurrently from do_ipv6_setsockopt() */ if (ipv6_hdr(skb)->hop_limit < READ_ONCE(tcp_inet6_sk(sk)->min_hopcount)) { __NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP); goto out; } } tp = tcp_sk(sk); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ fastopen = rcu_dereference(tp->fastopen_rsk); snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; if (sk->sk_state != TCP_LISTEN && !between(seq, snd_una, tp->snd_nxt)) { __NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } np = tcp_inet6_sk(sk); if (type == NDISC_REDIRECT) { if (!sock_owned_by_user(sk)) { struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); if (dst) dst->ops->redirect(dst, sk, skb); } goto out; } if (type == ICMPV6_PKT_TOOBIG) { u32 mtu = ntohl(info); /* We are not interested in TCP_LISTEN and open_requests * (SYN-ACKs send out by Linux are always <576bytes so * they should go through unfragmented). */ if (sk->sk_state == TCP_LISTEN) goto out; if (!ip6_sk_accept_pmtu(sk)) goto out; if (mtu < IPV6_MIN_MTU) goto out; WRITE_ONCE(tp->mtu_info, mtu); if (!sock_owned_by_user(sk)) tcp_v6_mtu_reduced(sk); else if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, &sk->sk_tsq_flags)) sock_hold(sk); goto out; } /* Might be for an request_sock */ switch (sk->sk_state) { case TCP_SYN_SENT: case TCP_SYN_RECV: /* Only in fast or simultaneous open. If a fast open socket is * already accepted it is treated as a connected one below. */ if (fastopen && !fastopen->sk) break; ipv6_icmp_error(sk, skb, err, th->dest, ntohl(info), (u8 *)th); if (!sock_owned_by_user(sk)) tcp_done_with_error(sk, err); else WRITE_ONCE(sk->sk_err_soft, err); goto out; case TCP_LISTEN: break; default: /* check if this ICMP message allows revert of backoff. * (see RFC 6069) */ if (!fastopen && type == ICMPV6_DEST_UNREACH && code == ICMPV6_NOROUTE) tcp_ld_RTO_revert(sk, seq); } if (!sock_owned_by_user(sk) && inet6_test_bit(RECVERR6, sk)) { WRITE_ONCE(sk->sk_err, err); sk_error_report(sk); } else { WRITE_ONCE(sk->sk_err_soft, err); } out: bh_unlock_sock(sk); sock_put(sk); return 0; } static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb) { struct inet_request_sock *ireq = inet_rsk(req); const struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct ipv6_txoptions *opt; struct flowi6 *fl6 = &fl->u.ip6; struct sk_buff *skb; int err = -ENOMEM; u8 tclass; /* First, grab a route. */ if (!dst && (dst = inet6_csk_route_req(sk, fl6, req, IPPROTO_TCP)) == NULL) goto done; skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb); if (skb) { __tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr, &ireq->ir_v6_rmt_addr); fl6->daddr = ireq->ir_v6_rmt_addr; if (inet6_test_bit(REPFLOW, sk) && ireq->pktopts) fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts)); tclass = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ? (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) | (np->tclass & INET_ECN_MASK) : np->tclass; if (!INET_ECN_is_capable(tclass) && tcp_bpf_ca_needs_ecn((struct sock *)req)) tclass |= INET_ECN_ECT_0; rcu_read_lock(); opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); err = ip6_xmit(sk, skb, fl6, skb->mark ? : READ_ONCE(sk->sk_mark), opt, tclass, READ_ONCE(sk->sk_priority)); rcu_read_unlock(); err = net_xmit_eval(err); } done: return err; } static void tcp_v6_reqsk_destructor(struct request_sock *req) { kfree(inet_rsk(req)->ipv6_opt); consume_skb(inet_rsk(req)->pktopts); } #ifdef CONFIG_TCP_MD5SIG static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(const struct sock *sk, const struct in6_addr *addr, int l3index) { return tcp_md5_do_lookup(sk, l3index, (union tcp_md5_addr *)addr, AF_INET6); } static struct tcp_md5sig_key *tcp_v6_md5_lookup(const struct sock *sk, const struct sock *addr_sk) { int l3index; l3index = l3mdev_master_ifindex_by_index(sock_net(sk), addr_sk->sk_bound_dev_if); return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_daddr, l3index); } static int tcp_v6_parse_md5_keys(struct sock *sk, int optname, sockptr_t optval, int optlen) { struct tcp_md5sig cmd; struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr; union tcp_ao_addr *addr; int l3index = 0; u8 prefixlen; bool l3flag; u8 flags; if (optlen < sizeof(cmd)) return -EINVAL; if (copy_from_sockptr(&cmd, optval, sizeof(cmd))) return -EFAULT; if (sin6->sin6_family != AF_INET6) return -EINVAL; flags = cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX; l3flag = cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX; if (optname == TCP_MD5SIG_EXT && cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) { prefixlen = cmd.tcpm_prefixlen; if (prefixlen > 128 || (ipv6_addr_v4mapped(&sin6->sin6_addr) && prefixlen > 32)) return -EINVAL; } else { prefixlen = ipv6_addr_v4mapped(&sin6->sin6_addr) ? 32 : 128; } if (optname == TCP_MD5SIG_EXT && cmd.tcpm_ifindex && cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX) { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), cmd.tcpm_ifindex); if (dev && netif_is_l3_master(dev)) l3index = dev->ifindex; rcu_read_unlock(); /* ok to reference set/not set outside of rcu; * right now device MUST be an L3 master */ if (!dev || !l3index) return -EINVAL; } if (!cmd.tcpm_keylen) { if (ipv6_addr_v4mapped(&sin6->sin6_addr)) return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3], AF_INET, prefixlen, l3index, flags); return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr, AF_INET6, prefixlen, l3index, flags); } if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) return -EINVAL; if (ipv6_addr_v4mapped(&sin6->sin6_addr)) { addr = (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3]; /* Don't allow keys for peers that have a matching TCP-AO key. * See the comment in tcp_ao_add_cmd() */ if (tcp_ao_required(sk, addr, AF_INET, l3flag ? l3index : -1, false)) return -EKEYREJECTED; return tcp_md5_do_add(sk, addr, AF_INET, prefixlen, l3index, flags, cmd.tcpm_key, cmd.tcpm_keylen); } addr = (union tcp_md5_addr *)&sin6->sin6_addr; /* Don't allow keys for peers that have a matching TCP-AO key. * See the comment in tcp_ao_add_cmd() */ if (tcp_ao_required(sk, addr, AF_INET6, l3flag ? l3index : -1, false)) return -EKEYREJECTED; return tcp_md5_do_add(sk, addr, AF_INET6, prefixlen, l3index, flags, cmd.tcpm_key, cmd.tcpm_keylen); } static int tcp_v6_md5_hash_headers(struct tcp_sigpool *hp, const struct in6_addr *daddr, const struct in6_addr *saddr, const struct tcphdr *th, int nbytes) { struct tcp6_pseudohdr *bp; struct scatterlist sg; struct tcphdr *_th; bp = hp->scratch; /* 1. TCP pseudo-header (RFC2460) */ bp->saddr = *saddr; bp->daddr = *daddr; bp->protocol = cpu_to_be32(IPPROTO_TCP); bp->len = cpu_to_be32(nbytes); _th = (struct tcphdr *)(bp + 1); memcpy(_th, th, sizeof(*th)); _th->check = 0; sg_init_one(&sg, bp, sizeof(*bp) + sizeof(*th)); ahash_request_set_crypt(hp->req, &sg, NULL, sizeof(*bp) + sizeof(*th)); return crypto_ahash_update(hp->req); } static int tcp_v6_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, const struct in6_addr *daddr, struct in6_addr *saddr, const struct tcphdr *th) { struct tcp_sigpool hp; if (tcp_sigpool_start(tcp_md5_sigpool_id, &hp)) goto clear_hash_nostart; if (crypto_ahash_init(hp.req)) goto clear_hash; if (tcp_v6_md5_hash_headers(&hp, daddr, saddr, th, th->doff << 2)) goto clear_hash; if (tcp_md5_hash_key(&hp, key)) goto clear_hash; ahash_request_set_crypt(hp.req, NULL, md5_hash, 0); if (crypto_ahash_final(hp.req)) goto clear_hash; tcp_sigpool_end(&hp); return 0; clear_hash: tcp_sigpool_end(&hp); clear_hash_nostart: memset(md5_hash, 0, 16); return 1; } static int tcp_v6_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, const struct sock *sk, const struct sk_buff *skb) { const struct tcphdr *th = tcp_hdr(skb); const struct in6_addr *saddr, *daddr; struct tcp_sigpool hp; if (sk) { /* valid for establish/request sockets */ saddr = &sk->sk_v6_rcv_saddr; daddr = &sk->sk_v6_daddr; } else { const struct ipv6hdr *ip6h = ipv6_hdr(skb); saddr = &ip6h->saddr; daddr = &ip6h->daddr; } if (tcp_sigpool_start(tcp_md5_sigpool_id, &hp)) goto clear_hash_nostart; if (crypto_ahash_init(hp.req)) goto clear_hash; if (tcp_v6_md5_hash_headers(&hp, daddr, saddr, th, skb->len)) goto clear_hash; if (tcp_sigpool_hash_skb_data(&hp, skb, th->doff << 2)) goto clear_hash; if (tcp_md5_hash_key(&hp, key)) goto clear_hash; ahash_request_set_crypt(hp.req, NULL, md5_hash, 0); if (crypto_ahash_final(hp.req)) goto clear_hash; tcp_sigpool_end(&hp); return 0; clear_hash: tcp_sigpool_end(&hp); clear_hash_nostart: memset(md5_hash, 0, 16); return 1; } #endif static void tcp_v6_init_req(struct request_sock *req, const struct sock *sk_listener, struct sk_buff *skb, u32 tw_isn) { bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags); struct inet_request_sock *ireq = inet_rsk(req); const struct ipv6_pinfo *np = tcp_inet6_sk(sk_listener); ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; ireq->ir_rmt_addr = LOOPBACK4_IPV6; ireq->ir_loc_addr = LOOPBACK4_IPV6; /* So that link locals have meaning */ if ((!sk_listener->sk_bound_dev_if || l3_slave) && ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) ireq->ir_iif = tcp_v6_iif(skb); if (!tw_isn && (ipv6_opt_accepted(sk_listener, skb, &TCP_SKB_CB(skb)->header.h6) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim || inet6_test_bit(REPFLOW, sk_listener))) { refcount_inc(&skb->users); ireq->pktopts = skb; } } static struct dst_entry *tcp_v6_route_req(const struct sock *sk, struct sk_buff *skb, struct flowi *fl, struct request_sock *req, u32 tw_isn) { tcp_v6_init_req(req, sk, skb, tw_isn); if (security_inet_conn_request(sk, skb, req)) return NULL; return inet6_csk_route_req(sk, &fl->u.ip6, req, IPPROTO_TCP); } struct request_sock_ops tcp6_request_sock_ops __read_mostly = { .family = AF_INET6, .obj_size = sizeof(struct tcp6_request_sock), .rtx_syn_ack = tcp_rtx_synack, .send_ack = tcp_v6_reqsk_send_ack, .destructor = tcp_v6_reqsk_destructor, .send_reset = tcp_v6_send_reset, .syn_ack_timeout = tcp_syn_ack_timeout, }; const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { .mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr), #ifdef CONFIG_TCP_MD5SIG .req_md5_lookup = tcp_v6_md5_lookup, .calc_md5_hash = tcp_v6_md5_hash_skb, #endif #ifdef CONFIG_TCP_AO .ao_lookup = tcp_v6_ao_lookup_rsk, .ao_calc_key = tcp_v6_ao_calc_key_rsk, .ao_synack_hash = tcp_v6_ao_synack_hash, #endif #ifdef CONFIG_SYN_COOKIES .cookie_init_seq = cookie_v6_init_sequence, #endif .route_req = tcp_v6_route_req, .init_seq = tcp_v6_init_seq, .init_ts_off = tcp_v6_init_ts_off, .send_synack = tcp_v6_send_synack, }; static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, int rst, u8 tclass, __be32 label, u32 priority, u32 txhash, struct tcp_key *key) { struct net *net = sk ? sock_net(sk) : dev_net_rcu(skb_dst(skb)->dev); unsigned int tot_len = sizeof(struct tcphdr); struct sock *ctl_sk = net->ipv6.tcp_sk; const struct tcphdr *th = tcp_hdr(skb); __be32 mrst = 0, *topt; struct dst_entry *dst; struct sk_buff *buff; struct tcphdr *t1; struct flowi6 fl6; u32 mark = 0; if (tsecr) tot_len += TCPOLEN_TSTAMP_ALIGNED; if (tcp_key_is_md5(key)) tot_len += TCPOLEN_MD5SIG_ALIGNED; if (tcp_key_is_ao(key)) tot_len += tcp_ao_len_aligned(key->ao_key); #ifdef CONFIG_MPTCP if (rst && !tcp_key_is_md5(key)) { mrst = mptcp_reset_option(skb); if (mrst) tot_len += sizeof(__be32); } #endif buff = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC); if (!buff) return; skb_reserve(buff, MAX_TCP_HEADER); t1 = skb_push(buff, tot_len); skb_reset_transport_header(buff); /* Swap the send and the receive. */ memset(t1, 0, sizeof(*t1)); t1->dest = th->source; t1->source = th->dest; t1->doff = tot_len / 4; t1->seq = htonl(seq); t1->ack_seq = htonl(ack); t1->ack = !rst || !th->ack; t1->rst = rst; t1->window = htons(win); topt = (__be32 *)(t1 + 1); if (tsecr) { *topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); *topt++ = htonl(tsval); *topt++ = htonl(tsecr); } if (mrst) *topt++ = mrst; #ifdef CONFIG_TCP_MD5SIG if (tcp_key_is_md5(key)) { *topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG); tcp_v6_md5_hash_hdr((__u8 *)topt, key->md5_key, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, t1); } #endif #ifdef CONFIG_TCP_AO if (tcp_key_is_ao(key)) { *topt++ = htonl((TCPOPT_AO << 24) | (tcp_ao_len(key->ao_key) << 16) | (key->ao_key->sndid << 8) | (key->rcv_next)); tcp_ao_hash_hdr(AF_INET6, (char *)topt, key->ao_key, key->traffic_key, (union tcp_ao_addr *)&ipv6_hdr(skb)->saddr, (union tcp_ao_addr *)&ipv6_hdr(skb)->daddr, t1, key->sne); } #endif memset(&fl6, 0, sizeof(fl6)); fl6.daddr = ipv6_hdr(skb)->saddr; fl6.saddr = ipv6_hdr(skb)->daddr; fl6.flowlabel = label; buff->ip_summed = CHECKSUM_PARTIAL; __tcp_v6_send_check(buff, &fl6.saddr, &fl6.daddr); fl6.flowi6_proto = IPPROTO_TCP; if (rt6_need_strict(&fl6.daddr) && !oif) fl6.flowi6_oif = tcp_v6_iif(skb); else { if (!oif && netif_index_is_l3_master(net, skb->skb_iif)) oif = skb->skb_iif; fl6.flowi6_oif = oif; } if (sk) { /* unconstify the socket only to attach it to buff with care. */ skb_set_owner_edemux(buff, (struct sock *)sk); if (sk->sk_state == TCP_TIME_WAIT) mark = inet_twsk(sk)->tw_mark; else mark = READ_ONCE(sk->sk_mark); skb_set_delivery_time(buff, tcp_transmit_time(sk), SKB_CLOCK_MONOTONIC); } if (txhash) { /* autoflowlabel/skb_get_hash_flowi6 rely on buff->hash */ skb_set_hash(buff, txhash, PKT_HASH_TYPE_L4); } fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark) ?: mark; fl6.fl6_dport = t1->dest; fl6.fl6_sport = t1->source; fl6.flowi6_uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL); security_skb_classify_flow(skb, flowi6_to_flowi_common(&fl6)); /* Pass a socket to ip6_dst_lookup either it is for RST * Underlying function will use this to retrieve the network * namespace */ if (sk && sk->sk_state != TCP_TIME_WAIT) dst = ip6_dst_lookup_flow(net, sk, &fl6, NULL); /*sk's xfrm_policy can be referred*/ else dst = ip6_dst_lookup_flow(net, ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(buff, dst); ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass, priority); TCP_INC_STATS(net, TCP_MIB_OUTSEGS); if (rst) TCP_INC_STATS(net, TCP_MIB_OUTRSTS); return; } kfree_skb(buff); } static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb, enum sk_rst_reason reason) { const struct tcphdr *th = tcp_hdr(skb); struct ipv6hdr *ipv6h = ipv6_hdr(skb); const __u8 *md5_hash_location = NULL; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) bool allocated_traffic_key = false; #endif const struct tcp_ao_hdr *aoh; struct tcp_key key = {}; u32 seq = 0, ack_seq = 0; __be32 label = 0; u32 priority = 0; struct net *net; u32 txhash = 0; int oif = 0; #ifdef CONFIG_TCP_MD5SIG unsigned char newhash[16]; int genhash; struct sock *sk1 = NULL; #endif if (th->rst) return; /* If sk not NULL, it means we did a successful lookup and incoming * route had to be correct. prequeue might have dropped our dst. */ if (!sk && !ipv6_unicast_destination(skb)) return; net = sk ? sock_net(sk) : dev_net_rcu(skb_dst(skb)->dev); /* Invalid TCP option size or twice included auth */ if (tcp_parse_auth_options(th, &md5_hash_location, &aoh)) return; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) rcu_read_lock(); #endif #ifdef CONFIG_TCP_MD5SIG if (sk && sk_fullsock(sk)) { int l3index; /* sdif set, means packet ingressed via a device * in an L3 domain and inet_iif is set to it. */ l3index = tcp_v6_sdif(skb) ? tcp_v6_iif_l3_slave(skb) : 0; key.md5_key = tcp_v6_md5_do_lookup(sk, &ipv6h->saddr, l3index); if (key.md5_key) key.type = TCP_KEY_MD5; } else if (md5_hash_location) { int dif = tcp_v6_iif_l3_slave(skb); int sdif = tcp_v6_sdif(skb); int l3index; /* * active side is lost. Try to find listening socket through * source port, and then find md5 key through listening socket. * we are not loose security here: * Incoming packet is checked with md5 hash with finding key, * no RST generated if md5 hash doesn't match. */ sk1 = inet6_lookup_listener(net, net->ipv4.tcp_death_row.hashinfo, NULL, 0, &ipv6h->saddr, th->source, &ipv6h->daddr, ntohs(th->source), dif, sdif); if (!sk1) goto out; /* sdif set, means packet ingressed via a device * in an L3 domain and dif is set to it. */ l3index = tcp_v6_sdif(skb) ? dif : 0; key.md5_key = tcp_v6_md5_do_lookup(sk1, &ipv6h->saddr, l3index); if (!key.md5_key) goto out; key.type = TCP_KEY_MD5; genhash = tcp_v6_md5_hash_skb(newhash, key.md5_key, NULL, skb); if (genhash || memcmp(md5_hash_location, newhash, 16) != 0) goto out; } #endif if (th->ack) seq = ntohl(th->ack_seq); else ack_seq = ntohl(th->seq) + th->syn + th->fin + skb->len - (th->doff << 2); #ifdef CONFIG_TCP_AO if (aoh) { int l3index; l3index = tcp_v6_sdif(skb) ? tcp_v6_iif_l3_slave(skb) : 0; if (tcp_ao_prepare_reset(sk, skb, aoh, l3index, seq, &key.ao_key, &key.traffic_key, &allocated_traffic_key, &key.rcv_next, &key.sne)) goto out; key.type = TCP_KEY_AO; } #endif if (sk) { oif = sk->sk_bound_dev_if; if (sk_fullsock(sk)) { if (inet6_test_bit(REPFLOW, sk)) label = ip6_flowlabel(ipv6h); priority = READ_ONCE(sk->sk_priority); txhash = sk->sk_txhash; } if (sk->sk_state == TCP_TIME_WAIT) { label = cpu_to_be32(inet_twsk(sk)->tw_flowlabel); priority = inet_twsk(sk)->tw_priority; txhash = inet_twsk(sk)->tw_txhash; } } else { if (net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_TCP_RESET) label = ip6_flowlabel(ipv6h); } trace_tcp_send_reset(sk, skb, reason); tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, 1, ipv6_get_dsfield(ipv6h) & ~INET_ECN_MASK, label, priority, txhash, &key); #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) out: if (allocated_traffic_key) kfree(key.traffic_key); rcu_read_unlock(); #endif } static void tcp_v6_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_key *key, u8 tclass, __be32 label, u32 priority, u32 txhash) { tcp_v6_send_response(sk, skb, seq, ack, win, tsval, tsecr, oif, 0, tclass, label, priority, txhash, key); } static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb, enum tcp_tw_status tw_status) { struct inet_timewait_sock *tw = inet_twsk(sk); struct tcp_timewait_sock *tcptw = tcp_twsk(sk); u8 tclass = tw->tw_tclass; struct tcp_key key = {}; if (tw_status == TCP_TW_ACK_OOW) tclass &= ~INET_ECN_MASK; #ifdef CONFIG_TCP_AO struct tcp_ao_info *ao_info; if (static_branch_unlikely(&tcp_ao_needed.key)) { /* FIXME: the segment to-be-acked is not verified yet */ ao_info = rcu_dereference(tcptw->ao_info); if (ao_info) { const struct tcp_ao_hdr *aoh; /* Invalid TCP option size or twice included auth */ if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh)) goto out; if (aoh) key.ao_key = tcp_ao_established_key(sk, ao_info, aoh->rnext_keyid, -1); } } if (key.ao_key) { struct tcp_ao_key *rnext_key; key.traffic_key = snd_other_key(key.ao_key); /* rcv_next switches to our rcv_next */ rnext_key = READ_ONCE(ao_info->rnext_key); key.rcv_next = rnext_key->rcvid; key.sne = READ_ONCE(ao_info->snd_sne); key.type = TCP_KEY_AO; #else if (0) { #endif #ifdef CONFIG_TCP_MD5SIG } else if (static_branch_unlikely(&tcp_md5_needed.key)) { key.md5_key = tcp_twsk_md5_key(tcptw); if (key.md5_key) key.type = TCP_KEY_MD5; #endif } tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, READ_ONCE(tcptw->tw_rcv_nxt), tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_tw_tsval(tcptw), READ_ONCE(tcptw->tw_ts_recent), tw->tw_bound_dev_if, &key, tclass, cpu_to_be32(tw->tw_flowlabel), tw->tw_priority, tw->tw_txhash); #ifdef CONFIG_TCP_AO out: #endif inet_twsk_put(tw); } static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { struct tcp_key key = {}; #ifdef CONFIG_TCP_AO if (static_branch_unlikely(&tcp_ao_needed.key) && tcp_rsk_used_ao(req)) { const struct in6_addr *addr = &ipv6_hdr(skb)->saddr; const struct tcp_ao_hdr *aoh; int l3index; l3index = tcp_v6_sdif(skb) ? tcp_v6_iif_l3_slave(skb) : 0; /* Invalid TCP option size or twice included auth */ if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh)) return; if (!aoh) return; key.ao_key = tcp_ao_do_lookup(sk, l3index, (union tcp_ao_addr *)addr, AF_INET6, aoh->rnext_keyid, -1); if (unlikely(!key.ao_key)) { /* Send ACK with any matching MKT for the peer */ key.ao_key = tcp_ao_do_lookup(sk, l3index, (union tcp_ao_addr *)addr, AF_INET6, -1, -1); /* Matching key disappeared (user removed the key?) * let the handshake timeout. */ if (!key.ao_key) { net_info_ratelimited("TCP-AO key for (%pI6, %d)->(%pI6, %d) suddenly disappeared, won't ACK new connection\n", addr, ntohs(tcp_hdr(skb)->source), &ipv6_hdr(skb)->daddr, ntohs(tcp_hdr(skb)->dest)); return; } } key.traffic_key = kmalloc(tcp_ao_digest_size(key.ao_key), GFP_ATOMIC); if (!key.traffic_key) return; key.type = TCP_KEY_AO; key.rcv_next = aoh->keyid; tcp_v6_ao_calc_key_rsk(key.ao_key, key.traffic_key, req); #else if (0) { #endif #ifdef CONFIG_TCP_MD5SIG } else if (static_branch_unlikely(&tcp_md5_needed.key)) { int l3index = tcp_v6_sdif(skb) ? tcp_v6_iif_l3_slave(skb) : 0; key.md5_key = tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index); if (key.md5_key) key.type = TCP_KEY_MD5; #endif } /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. */ tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, tcp_rsk(req)->rcv_nxt, tcp_synack_window(req) >> inet_rsk(req)->rcv_wscale, tcp_rsk_tsval(tcp_rsk(req)), req->ts_recent, sk->sk_bound_dev_if, &key, ipv6_get_dsfield(ipv6_hdr(skb)) & ~INET_ECN_MASK, 0, READ_ONCE(sk->sk_priority), READ_ONCE(tcp_rsk(req)->txhash)); if (tcp_key_is_ao(&key)) kfree(key.traffic_key); } static struct sock *tcp_v6_cookie_check(struct sock *sk, struct sk_buff *skb) { #ifdef CONFIG_SYN_COOKIES const struct tcphdr *th = tcp_hdr(skb); if (!th->syn) sk = cookie_v6_check(sk, skb); #endif return sk; } u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph, struct tcphdr *th, u32 *cookie) { u16 mss = 0; #ifdef CONFIG_SYN_COOKIES mss = tcp_get_syncookie_mss(&tcp6_request_sock_ops, &tcp_request_sock_ipv6_ops, sk, th); if (mss) { *cookie = __cookie_v6_init_sequence(iph, th, &mss); tcp_synq_overflow(sk); } #endif return mss; } static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) { if (skb->protocol == htons(ETH_P_IP)) return tcp_v4_conn_request(sk, skb); if (!ipv6_unicast_destination(skb)) goto drop; if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) { __IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS); return 0; } return tcp_conn_request(&tcp6_request_sock_ops, &tcp_request_sock_ipv6_ops, sk, skb); drop: tcp_listendrop(sk); return 0; /* don't send reset */ } static void tcp_v6_restore_cb(struct sk_buff *skb) { /* We need to move header back to the beginning if xfrm6_policy_check() * and tcp_v6_fill_cb() are going to be called again. * ip6_datagram_recv_specific_ctl() also expects IP6CB to be there. */ memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6, sizeof(struct inet6_skb_parm)); } static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst, struct request_sock *req_unhash, bool *own_req) { struct inet_request_sock *ireq; struct ipv6_pinfo *newnp; const struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct ipv6_txoptions *opt; struct inet_sock *newinet; bool found_dup_sk = false; struct tcp_sock *newtp; struct sock *newsk; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *key; int l3index; #endif struct flowi6 fl6; if (skb->protocol == htons(ETH_P_IP)) { /* * v6 mapped */ newsk = tcp_v4_syn_recv_sock(sk, skb, req, dst, req_unhash, own_req); if (!newsk) return NULL; inet_sk(newsk)->pinet6 = tcp_inet6_sk(newsk); newnp = tcp_inet6_sk(newsk); newtp = tcp_sk(newsk); memcpy(newnp, np, sizeof(struct ipv6_pinfo)); newnp->saddr = newsk->sk_v6_rcv_saddr; inet_csk(newsk)->icsk_af_ops = &ipv6_mapped; if (sk_is_mptcp(newsk)) mptcpv6_handle_mapped(newsk, true); newsk->sk_backlog_rcv = tcp_v4_do_rcv; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) newtp->af_specific = &tcp_sock_ipv6_mapped_specific; #endif newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; newnp->ipv6_fl_list = NULL; newnp->pktoptions = NULL; newnp->opt = NULL; newnp->mcast_oif = inet_iif(skb); newnp->mcast_hops = ip_hdr(skb)->ttl; newnp->rcv_flowinfo = 0; if (inet6_test_bit(REPFLOW, sk)) newnp->flow_label = 0; /* * No need to charge this sock to the relevant IPv6 refcnt debug socks count * here, tcp_create_openreq_child now does this for us, see the comment in * that function for the gory details. -acme */ /* It is tricky place. Until this moment IPv4 tcp worked with IPv6 icsk.icsk_af_ops. Sync it now. */ tcp_sync_mss(newsk, inet_csk(newsk)->icsk_pmtu_cookie); return newsk; } ireq = inet_rsk(req); if (sk_acceptq_is_full(sk)) goto out_overflow; if (!dst) { dst = inet6_csk_route_req(sk, &fl6, req, IPPROTO_TCP); if (!dst) goto out; } newsk = tcp_create_openreq_child(sk, req, skb); if (!newsk) goto out_nonewsk; /* * No need to charge this sock to the relevant IPv6 refcnt debug socks * count here, tcp_create_openreq_child now does this for us, see the * comment in that function for the gory details. -acme */ newsk->sk_gso_type = SKB_GSO_TCPV6; inet6_sk_rx_dst_set(newsk, skb); inet_sk(newsk)->pinet6 = tcp_inet6_sk(newsk); newtp = tcp_sk(newsk); newinet = inet_sk(newsk); newnp = tcp_inet6_sk(newsk); memcpy(newnp, np, sizeof(struct ipv6_pinfo)); ip6_dst_store(newsk, dst, NULL, NULL); newnp->saddr = ireq->ir_v6_loc_addr; /* Now IPv6 options... First: no IPv4 options. */ newinet->inet_opt = NULL; newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; newnp->ipv6_fl_list = NULL; /* Clone RX bits */ newnp->rxopt.all = np->rxopt.all; newnp->pktoptions = NULL; newnp->opt = NULL; newnp->mcast_oif = tcp_v6_iif(skb); newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb)); if (inet6_test_bit(REPFLOW, sk)) newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb)); /* Set ToS of the new socket based upon the value of incoming SYN. * ECT bits are set later in tcp_init_transfer(). */ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)) newnp->tclass = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK; /* Clone native IPv6 options from listening socket (if any) Yes, keeping reference count would be much more clever, but we make one more one thing there: reattach optmem to newsk. */ opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); if (opt) { opt = ipv6_dup_options(newsk, opt); RCU_INIT_POINTER(newnp->opt, opt); } inet_csk(newsk)->icsk_ext_hdr_len = 0; if (opt) inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen + opt->opt_flen; tcp_ca_openreq_child(newsk, dst); tcp_sync_mss(newsk, dst_mtu(dst)); newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst)); tcp_initialize_rcv_mss(newsk); #ifdef CONFIG_TCP_MD5SIG l3index = l3mdev_master_ifindex_by_index(sock_net(sk), ireq->ir_iif); if (!tcp_rsk_used_ao(req)) { /* Copy over the MD5 key from the original socket */ key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr, l3index); if (key) { const union tcp_md5_addr *addr; addr = (union tcp_md5_addr *)&newsk->sk_v6_daddr; if (tcp_md5_key_copy(newsk, addr, AF_INET6, 128, l3index, key)) { inet_csk_prepare_forced_close(newsk); tcp_done(newsk); goto out; } } } #endif #ifdef CONFIG_TCP_AO /* Copy over tcp_ao_info if any */ if (tcp_ao_copy_all_matching(sk, newsk, req, skb, AF_INET6)) goto out; /* OOM */ #endif if (__inet_inherit_port(sk, newsk) < 0) { inet_csk_prepare_forced_close(newsk); tcp_done(newsk); goto out; } *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), &found_dup_sk); if (*own_req) { tcp_move_syn(newtp, req); /* Clone pktoptions received with SYN, if we own the req */ if (ireq->pktopts) { newnp->pktoptions = skb_clone_and_charge_r(ireq->pktopts, newsk); consume_skb(ireq->pktopts); ireq->pktopts = NULL; if (newnp->pktoptions) tcp_v6_restore_cb(newnp->pktoptions); } } else { if (!req_unhash && found_dup_sk) { /* This code path should only be executed in the * syncookie case only */ bh_unlock_sock(newsk); sock_put(newsk); newsk = NULL; } } return newsk; out_overflow: __NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); out_nonewsk: dst_release(dst); out: tcp_listendrop(sk); return NULL; } INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, u32)); /* The socket must have it's spinlock held when we get * here, unless it is a TCP_LISTEN socket. * * We have a potential double-lock case here, so even when * doing backlog processing we use the BH locking scheme. * This is because we cannot sleep with the original spinlock * held. */ INDIRECT_CALLABLE_SCOPE int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) { struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct sk_buff *opt_skb = NULL; enum skb_drop_reason reason; struct tcp_sock *tp; /* Imagine: socket is IPv6. IPv4 packet arrives, goes to IPv4 receive handler and backlogged. From backlog it always goes here. Kerboom... Fortunately, tcp_rcv_established and rcv_established handle them correctly, but it is not case with tcp_v6_hnd_req and tcp_v6_send_reset(). --ANK */ if (skb->protocol == htons(ETH_P_IP)) return tcp_v4_do_rcv(sk, skb); /* * socket locking is here for SMP purposes as backlog rcv * is currently called with bh processing disabled. */ /* Do Stevens' IPV6_PKTOPTIONS. Yes, guys, it is the only place in our code, where we may make it not affecting IPv4. The rest of code is protocol independent, and I do not like idea to uglify IPv4. Actually, all the idea behind IPV6_PKTOPTIONS looks not very well thought. For now we latch options, received in the last packet, enqueued by tcp. Feel free to propose better solution. --ANK (980728) */ if (np->rxopt.all && sk->sk_state != TCP_LISTEN) opt_skb = skb_clone_and_charge_r(skb, sk); if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ struct dst_entry *dst; dst = rcu_dereference_protected(sk->sk_rx_dst, lockdep_sock_is_held(sk)); sock_rps_save_rxhash(sk, skb); sk_mark_napi_id(sk, skb); if (dst) { if (sk->sk_rx_dst_ifindex != skb->skb_iif || INDIRECT_CALL_1(dst->ops->check, ip6_dst_check, dst, sk->sk_rx_dst_cookie) == NULL) { RCU_INIT_POINTER(sk->sk_rx_dst, NULL); dst_release(dst); } } tcp_rcv_established(sk, skb); if (opt_skb) goto ipv6_pktoptions; return 0; } if (tcp_checksum_complete(skb)) goto csum_err; if (sk->sk_state == TCP_LISTEN) { struct sock *nsk = tcp_v6_cookie_check(sk, skb); if (nsk != sk) { if (nsk) { reason = tcp_child_process(sk, nsk, skb); if (reason) goto reset; } return 0; } } else sock_rps_save_rxhash(sk, skb); reason = tcp_rcv_state_process(sk, skb); if (reason) goto reset; if (opt_skb) goto ipv6_pktoptions; return 0; reset: tcp_v6_send_reset(sk, skb, sk_rst_convert_drop_reason(reason)); discard: if (opt_skb) __kfree_skb(opt_skb); sk_skb_reason_drop(sk, skb, reason); return 0; csum_err: reason = SKB_DROP_REASON_TCP_CSUM; trace_tcp_bad_csum(skb); TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); goto discard; ipv6_pktoptions: /* Do you ask, what is it? 1. skb was enqueued by tcp. 2. skb is added to tail of read queue, rather than out of order. 3. socket is not in passive state. 4. Finally, it really contains options, which user wants to receive. */ tp = tcp_sk(sk); if (TCP_SKB_CB(opt_skb)->end_seq == tp->rcv_nxt && !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { if (np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo) WRITE_ONCE(np->mcast_oif, tcp_v6_iif(opt_skb)); if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) WRITE_ONCE(np->mcast_hops, ipv6_hdr(opt_skb)->hop_limit); if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass) np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb)); if (inet6_test_bit(REPFLOW, sk)) np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb)); if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) { tcp_v6_restore_cb(opt_skb); opt_skb = xchg(&np->pktoptions, opt_skb); } else { __kfree_skb(opt_skb); opt_skb = xchg(&np->pktoptions, NULL); } } consume_skb(opt_skb); return 0; } static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr, const struct tcphdr *th) { /* This is tricky: we move IP6CB at its correct location into * TCP_SKB_CB(). It must be done after xfrm6_policy_check(), because * _decode_session6() uses IP6CB(). * barrier() makes sure compiler won't play aliasing games. */ memmove(&TCP_SKB_CB(skb)->header.h6, IP6CB(skb), sizeof(struct inet6_skb_parm)); barrier(); TCP_SKB_CB(skb)->seq = ntohl(th->seq); TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin + skb->len - th->doff*4); TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); TCP_SKB_CB(skb)->tcp_flags = tcp_flags_ntohs(th); TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr); TCP_SKB_CB(skb)->sacked = 0; TCP_SKB_CB(skb)->has_rxtstamp = skb->tstamp || skb_hwtstamps(skb)->hwtstamp; } INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) { struct net *net = dev_net_rcu(skb->dev); enum skb_drop_reason drop_reason; enum tcp_tw_status tw_status; int sdif = inet6_sdif(skb); int dif = inet6_iif(skb); const struct tcphdr *th; const struct ipv6hdr *hdr; struct sock *sk = NULL; bool refcounted; int ret; u32 isn; drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; if (skb->pkt_type != PACKET_HOST) goto discard_it; /* * Count it even if it's bad. */ __TCP_INC_STATS(net, TCP_MIB_INSEGS); if (!pskb_may_pull(skb, sizeof(struct tcphdr))) goto discard_it; th = (const struct tcphdr *)skb->data; if (unlikely(th->doff < sizeof(struct tcphdr) / 4)) { drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL; goto bad_packet; } if (!pskb_may_pull(skb, th->doff*4)) goto discard_it; if (skb_checksum_init(skb, IPPROTO_TCP, ip6_compute_pseudo)) goto csum_error; th = (const struct tcphdr *)skb->data; hdr = ipv6_hdr(skb); lookup: sk = __inet6_lookup_skb(net->ipv4.tcp_death_row.hashinfo, skb, __tcp_hdrlen(th), th->source, th->dest, inet6_iif(skb), sdif, &refcounted); if (!sk) goto no_tcp_socket; if (sk->sk_state == TCP_TIME_WAIT) goto do_time_wait; if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); bool req_stolen = false; struct sock *nsk; sk = req->rsk_listener; if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) drop_reason = SKB_DROP_REASON_XFRM_POLICY; else drop_reason = tcp_inbound_hash(sk, req, skb, &hdr->saddr, &hdr->daddr, AF_INET6, dif, sdif); if (drop_reason) { sk_drops_add(sk, skb); reqsk_put(req); goto discard_it; } if (tcp_checksum_complete(skb)) { reqsk_put(req); goto csum_error; } if (unlikely(sk->sk_state != TCP_LISTEN)) { nsk = reuseport_migrate_sock(sk, req_to_sk(req), skb); if (!nsk) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } sk = nsk; /* reuseport_migrate_sock() has already held one sk_refcnt * before returning. */ } else { sock_hold(sk); } refcounted = true; nsk = NULL; if (!tcp_filter(sk, skb)) { th = (const struct tcphdr *)skb->data; hdr = ipv6_hdr(skb); tcp_v6_fill_cb(skb, hdr, th); nsk = tcp_check_req(sk, skb, req, false, &req_stolen, &drop_reason); } else { drop_reason = SKB_DROP_REASON_SOCKET_FILTER; } if (!nsk) { reqsk_put(req); if (req_stolen) { /* Another cpu got exclusive access to req * and created a full blown socket. * Try to feed this packet to this socket * instead of discarding it. */ tcp_v6_restore_cb(skb); sock_put(sk); goto lookup; } goto discard_and_relse; } nf_reset_ct(skb); if (nsk == sk) { reqsk_put(req); tcp_v6_restore_cb(skb); } else { drop_reason = tcp_child_process(sk, nsk, skb); if (drop_reason) { enum sk_rst_reason rst_reason; rst_reason = sk_rst_convert_drop_reason(drop_reason); tcp_v6_send_reset(nsk, skb, rst_reason); goto discard_and_relse; } sock_put(sk); return 0; } } process: if (static_branch_unlikely(&ip6_min_hopcount)) { /* min_hopcount can be changed concurrently from do_ipv6_setsockopt() */ if (unlikely(hdr->hop_limit < READ_ONCE(tcp_inet6_sk(sk)->min_hopcount))) { __NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP); drop_reason = SKB_DROP_REASON_TCP_MINTTL; goto discard_and_relse; } } if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) { drop_reason = SKB_DROP_REASON_XFRM_POLICY; goto discard_and_relse; } drop_reason = tcp_inbound_hash(sk, NULL, skb, &hdr->saddr, &hdr->daddr, AF_INET6, dif, sdif); if (drop_reason) goto discard_and_relse; nf_reset_ct(skb); if (tcp_filter(sk, skb)) { drop_reason = SKB_DROP_REASON_SOCKET_FILTER; goto discard_and_relse; } th = (const struct tcphdr *)skb->data; hdr = ipv6_hdr(skb); tcp_v6_fill_cb(skb, hdr, th); skb->dev = NULL; if (sk->sk_state == TCP_LISTEN) { ret = tcp_v6_do_rcv(sk, skb); goto put_and_return; } sk_incoming_cpu_update(sk); bh_lock_sock_nested(sk); tcp_segs_in(tcp_sk(sk), skb); ret = 0; if (!sock_owned_by_user(sk)) { ret = tcp_v6_do_rcv(sk, skb); } else { if (tcp_add_backlog(sk, skb, &drop_reason)) goto discard_and_relse; } bh_unlock_sock(sk); put_and_return: if (refcounted) sock_put(sk); return ret ? -1 : 0; no_tcp_socket: drop_reason = SKB_DROP_REASON_NO_SOCKET; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard_it; tcp_v6_fill_cb(skb, hdr, th); if (tcp_checksum_complete(skb)) { csum_error: drop_reason = SKB_DROP_REASON_TCP_CSUM; trace_tcp_bad_csum(skb); __TCP_INC_STATS(net, TCP_MIB_CSUMERRORS); bad_packet: __TCP_INC_STATS(net, TCP_MIB_INERRS); } else { tcp_v6_send_reset(NULL, skb, sk_rst_convert_drop_reason(drop_reason)); } discard_it: SKB_DR_OR(drop_reason, NOT_SPECIFIED); sk_skb_reason_drop(sk, skb, drop_reason); return 0; discard_and_relse: sk_drops_add(sk, skb); if (refcounted) sock_put(sk); goto discard_it; do_time_wait: if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { drop_reason = SKB_DROP_REASON_XFRM_POLICY; inet_twsk_put(inet_twsk(sk)); goto discard_it; } tcp_v6_fill_cb(skb, hdr, th); if (tcp_checksum_complete(skb)) { inet_twsk_put(inet_twsk(sk)); goto csum_error; } tw_status = tcp_timewait_state_process(inet_twsk(sk), skb, th, &isn); switch (tw_status) { case TCP_TW_SYN: { struct sock *sk2; sk2 = inet6_lookup_listener(net, net->ipv4.tcp_death_row.hashinfo, skb, __tcp_hdrlen(th), &ipv6_hdr(skb)->saddr, th->source, &ipv6_hdr(skb)->daddr, ntohs(th->dest), tcp_v6_iif_l3_slave(skb), sdif); if (sk2) { struct inet_timewait_sock *tw = inet_twsk(sk); inet_twsk_deschedule_put(tw); sk = sk2; tcp_v6_restore_cb(skb); refcounted = false; __this_cpu_write(tcp_tw_isn, isn); goto process; } } /* to ACK */ fallthrough; case TCP_TW_ACK: case TCP_TW_ACK_OOW: tcp_v6_timewait_ack(sk, skb, tw_status); break; case TCP_TW_RST: tcp_v6_send_reset(sk, skb, SK_RST_REASON_TCP_TIMEWAIT_SOCKET); inet_twsk_deschedule_put(inet_twsk(sk)); goto discard_it; case TCP_TW_SUCCESS: ; } goto discard_it; } void tcp_v6_early_demux(struct sk_buff *skb) { struct net *net = dev_net_rcu(skb->dev); const struct ipv6hdr *hdr; const struct tcphdr *th; struct sock *sk; if (skb->pkt_type != PACKET_HOST) return; if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr))) return; hdr = ipv6_hdr(skb); th = tcp_hdr(skb); if (th->doff < sizeof(struct tcphdr) / 4) return; /* Note : We use inet6_iif() here, not tcp_v6_iif() */ sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, &hdr->saddr, th->source, &hdr->daddr, ntohs(th->dest), inet6_iif(skb), inet6_sdif(skb)); if (sk) { skb->sk = sk; skb->destructor = sock_edemux; if (sk_fullsock(sk)) { struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, sk->sk_rx_dst_cookie); if (dst && sk->sk_rx_dst_ifindex == skb->skb_iif) skb_dst_set_noref(skb, dst); } } } static struct timewait_sock_ops tcp6_timewait_sock_ops = { .twsk_obj_size = sizeof(struct tcp6_timewait_sock), .twsk_destructor = tcp_twsk_destructor, }; INDIRECT_CALLABLE_SCOPE void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb) { __tcp_v6_send_check(skb, &sk->sk_v6_rcv_saddr, &sk->sk_v6_daddr); } const struct inet_connection_sock_af_ops ipv6_specific = { .queue_xmit = inet6_csk_xmit, .send_check = tcp_v6_send_check, .rebuild_header = inet6_sk_rebuild_header, .sk_rx_dst_set = inet6_sk_rx_dst_set, .conn_request = tcp_v6_conn_request, .syn_recv_sock = tcp_v6_syn_recv_sock, .net_header_len = sizeof(struct ipv6hdr), .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, .mtu_reduced = tcp_v6_mtu_reduced, }; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) static const struct tcp_sock_af_ops tcp_sock_ipv6_specific = { #ifdef CONFIG_TCP_MD5SIG .md5_lookup = tcp_v6_md5_lookup, .calc_md5_hash = tcp_v6_md5_hash_skb, .md5_parse = tcp_v6_parse_md5_keys, #endif #ifdef CONFIG_TCP_AO .ao_lookup = tcp_v6_ao_lookup, .calc_ao_hash = tcp_v6_ao_hash_skb, .ao_parse = tcp_v6_parse_ao, .ao_calc_key_sk = tcp_v6_ao_calc_key_sk, #endif }; #endif /* * TCP over IPv4 via INET6 API */ static const struct inet_connection_sock_af_ops ipv6_mapped = { .queue_xmit = ip_queue_xmit, .send_check = tcp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, .sk_rx_dst_set = inet_sk_rx_dst_set, .conn_request = tcp_v6_conn_request, .syn_recv_sock = tcp_v6_syn_recv_sock, .net_header_len = sizeof(struct iphdr), .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, .mtu_reduced = tcp_v4_mtu_reduced, }; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific = { #ifdef CONFIG_TCP_MD5SIG .md5_lookup = tcp_v4_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, .md5_parse = tcp_v6_parse_md5_keys, #endif #ifdef CONFIG_TCP_AO .ao_lookup = tcp_v6_ao_lookup, .calc_ao_hash = tcp_v4_ao_hash_skb, .ao_parse = tcp_v6_parse_ao, .ao_calc_key_sk = tcp_v4_ao_calc_key_sk, #endif }; #endif /* NOTE: A lot of things set to zero explicitly by call to * sk_alloc() so need not be done here. */ static int tcp_v6_init_sock(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); tcp_init_sock(sk); icsk->icsk_af_ops = &ipv6_specific; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) tcp_sk(sk)->af_specific = &tcp_sock_ipv6_specific; #endif return 0; } #ifdef CONFIG_PROC_FS /* Proc filesystem TCPv6 sock list dumping. */ static void get_openreq6(struct seq_file *seq, const struct request_sock *req, int i) { long ttd = req->rsk_timer.expires - jiffies; const struct in6_addr *src = &inet_rsk(req)->ir_v6_loc_addr; const struct in6_addr *dest = &inet_rsk(req)->ir_v6_rmt_addr; if (ttd < 0) ttd = 0; seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5u %8d %d %d %pK\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], inet_rsk(req)->ir_num, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], ntohs(inet_rsk(req)->ir_rmt_port), TCP_SYN_RECV, 0, 0, /* could print option size, but that is af dependent. */ 1, /* timers active (only the expire timer) */ jiffies_to_clock_t(ttd), req->num_timeout, from_kuid_munged(seq_user_ns(seq), sock_i_uid(req->rsk_listener)), 0, /* non standard timer */ 0, /* open_requests have no inode */ 0, req); } static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) { const struct in6_addr *dest, *src; __u16 destp, srcp; int timer_active; unsigned long timer_expires; const struct inet_sock *inet = inet_sk(sp); const struct tcp_sock *tp = tcp_sk(sp); const struct inet_connection_sock *icsk = inet_csk(sp); const struct fastopen_queue *fastopenq = &icsk->icsk_accept_queue.fastopenq; u8 icsk_pending; int rx_queue; int state; dest = &sp->sk_v6_daddr; src = &sp->sk_v6_rcv_saddr; destp = ntohs(inet->inet_dport); srcp = ntohs(inet->inet_sport); icsk_pending = smp_load_acquire(&icsk->icsk_pending); if (icsk_pending == ICSK_TIME_RETRANS || icsk_pending == ICSK_TIME_REO_TIMEOUT || icsk_pending == ICSK_TIME_LOSS_PROBE) { timer_active = 1; timer_expires = icsk_timeout(icsk); } else if (icsk_pending == ICSK_TIME_PROBE0) { timer_active = 4; timer_expires = icsk_timeout(icsk); } else if (timer_pending(&sp->sk_timer)) { timer_active = 2; timer_expires = sp->sk_timer.expires; } else { timer_active = 0; timer_expires = jiffies; } state = inet_sk_state_load(sp); if (state == TCP_LISTEN) rx_queue = READ_ONCE(sp->sk_ack_backlog); else /* Because we don't lock the socket, * we might find a transient negative value. */ rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq), 0); seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %lu %lu %u %u %d\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], srcp, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, state, READ_ONCE(tp->write_seq) - tp->snd_una, rx_queue, timer_active, jiffies_delta_to_clock_t(timer_expires - jiffies), icsk->icsk_retransmits, from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), icsk->icsk_probes_out, sock_i_ino(sp), refcount_read(&sp->sk_refcnt), sp, jiffies_to_clock_t(icsk->icsk_rto), jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1) | inet_csk_in_pingpong_mode(sp), tcp_snd_cwnd(tp), state == TCP_LISTEN ? fastopenq->max_qlen : (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh) ); } static void get_timewait6_sock(struct seq_file *seq, struct inet_timewait_sock *tw, int i) { long delta = tw->tw_timer.expires - jiffies; const struct in6_addr *dest, *src; __u16 destp, srcp; dest = &tw->tw_v6_daddr; src = &tw->tw_v6_rcv_saddr; destp = ntohs(tw->tw_dport); srcp = ntohs(tw->tw_sport); seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], srcp, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, READ_ONCE(tw->tw_substate), 0, 0, 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, refcount_read(&tw->tw_refcnt), tw); } static int tcp6_seq_show(struct seq_file *seq, void *v) { struct tcp_iter_state *st; struct sock *sk = v; if (v == SEQ_START_TOKEN) { seq_puts(seq, " sl " "local_address " "remote_address " "st tx_queue rx_queue tr tm->when retrnsmt" " uid timeout inode\n"); goto out; } st = seq->private; if (sk->sk_state == TCP_TIME_WAIT) get_timewait6_sock(seq, v, st->num); else if (sk->sk_state == TCP_NEW_SYN_RECV) get_openreq6(seq, v, st->num); else get_tcp6_sock(seq, v, st->num); out: return 0; } static const struct seq_operations tcp6_seq_ops = { .show = tcp6_seq_show, .start = tcp_seq_start, .next = tcp_seq_next, .stop = tcp_seq_stop, }; static struct tcp_seq_afinfo tcp6_seq_afinfo = { .family = AF_INET6, }; int __net_init tcp6_proc_init(struct net *net) { if (!proc_create_net_data("tcp6", 0444, net->proc_net, &tcp6_seq_ops, sizeof(struct tcp_iter_state), &tcp6_seq_afinfo)) return -ENOMEM; return 0; } void tcp6_proc_exit(struct net *net) { remove_proc_entry("tcp6", net->proc_net); } #endif struct proto tcpv6_prot = { .name = "TCPv6", .owner = THIS_MODULE, .close = tcp_close, .pre_connect = tcp_v6_pre_connect, .connect = tcp_v6_connect, .disconnect = tcp_disconnect, .accept = inet_csk_accept, .ioctl = tcp_ioctl, .init = tcp_v6_init_sock, .destroy = tcp_v4_destroy_sock, .shutdown = tcp_shutdown, .setsockopt = tcp_setsockopt, .getsockopt = tcp_getsockopt, .bpf_bypass_getsockopt = tcp_bpf_bypass_getsockopt, .keepalive = tcp_set_keepalive, .recvmsg = tcp_recvmsg, .sendmsg = tcp_sendmsg, .splice_eof = tcp_splice_eof, .backlog_rcv = tcp_v6_do_rcv, .release_cb = tcp_release_cb, .hash = inet6_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, .put_port = inet_put_port, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = tcp_bpf_update_proto, #endif .enter_memory_pressure = tcp_enter_memory_pressure, .leave_memory_pressure = tcp_leave_memory_pressure, .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, .memory_allocated = &tcp_memory_allocated, .per_cpu_fw_alloc = &tcp_memory_per_cpu_fw_alloc, .memory_pressure = &tcp_memory_pressure, .orphan_count = &tcp_orphan_count, .sysctl_mem = sysctl_tcp_mem, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem), .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp6_sock), .ipv6_pinfo_offset = offsetof(struct tcp6_sock, inet6), .slab_flags = SLAB_TYPESAFE_BY_RCU, .twsk_prot = &tcp6_timewait_sock_ops, .rsk_prot = &tcp6_request_sock_ops, .h.hashinfo = NULL, .no_autobind = true, .diag_destroy = tcp_abort, }; EXPORT_SYMBOL_GPL(tcpv6_prot); static struct inet_protosw tcpv6_protosw = { .type = SOCK_STREAM, .protocol = IPPROTO_TCP, .prot = &tcpv6_prot, .ops = &inet6_stream_ops, .flags = INET_PROTOSW_PERMANENT | INET_PROTOSW_ICSK, }; static int __net_init tcpv6_net_init(struct net *net) { int res; res = inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6, SOCK_RAW, IPPROTO_TCP, net); if (!res) net->ipv6.tcp_sk->sk_clockid = CLOCK_MONOTONIC; return res; } static void __net_exit tcpv6_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.tcp_sk); } static struct pernet_operations tcpv6_net_ops = { .init = tcpv6_net_init, .exit = tcpv6_net_exit, }; int __init tcpv6_init(void) { int ret; net_hotdata.tcpv6_protocol = (struct inet6_protocol) { .handler = tcp_v6_rcv, .err_handler = tcp_v6_err, .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL, }; ret = inet6_add_protocol(&net_hotdata.tcpv6_protocol, IPPROTO_TCP); if (ret) goto out; /* register inet6 protocol */ ret = inet6_register_protosw(&tcpv6_protosw); if (ret) goto out_tcpv6_protocol; ret = register_pernet_subsys(&tcpv6_net_ops); if (ret) goto out_tcpv6_protosw; ret = mptcpv6_init(); if (ret) goto out_tcpv6_pernet_subsys; out: return ret; out_tcpv6_pernet_subsys: unregister_pernet_subsys(&tcpv6_net_ops); out_tcpv6_protosw: inet6_unregister_protosw(&tcpv6_protosw); out_tcpv6_protocol: inet6_del_protocol(&net_hotdata.tcpv6_protocol, IPPROTO_TCP); goto out; } void tcpv6_exit(void) { unregister_pernet_subsys(&tcpv6_net_ops); inet6_unregister_protosw(&tcpv6_protosw); inet6_del_protocol(&net_hotdata.tcpv6_protocol, IPPROTO_TCP); } |
| 86 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHEFS_JOURNAL_SEQ_BLACKLIST_H #define _BCACHEFS_JOURNAL_SEQ_BLACKLIST_H static inline unsigned blacklist_nr_entries(struct bch_sb_field_journal_seq_blacklist *bl) { return bl ? ((vstruct_end(&bl->field) - (void *) &bl->start[0]) / sizeof(struct journal_seq_blacklist_entry)) : 0; } bool bch2_journal_seq_is_blacklisted(struct bch_fs *, u64, bool); int bch2_journal_seq_blacklist_add(struct bch_fs *c, u64, u64); int bch2_blacklist_table_initialize(struct bch_fs *); extern const struct bch_sb_field_ops bch_sb_field_ops_journal_seq_blacklist; bool bch2_blacklist_entries_gc(struct bch_fs *); #endif /* _BCACHEFS_JOURNAL_SEQ_BLACKLIST_H */ |
| 15 6 50 11 6 5 56 23 23 7 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/buffer_head.h> #include <linux/slab.h> #include "minix.h" enum {DEPTH = 3, DIRECT = 7}; /* Only double indirect */ typedef u16 block_t; /* 16 bit, host order */ static inline unsigned long block_to_cpu(block_t n) { return n; } static inline block_t cpu_to_block(unsigned long n) { return n; } static inline block_t *i_data(struct inode *inode) { return (block_t *)minix_i(inode)->u.i1_data; } static int block_to_path(struct inode * inode, long block, int offsets[DEPTH]) { int n = 0; if (block < 0) { printk("MINIX-fs: block_to_path: block %ld < 0 on dev %pg\n", block, inode->i_sb->s_bdev); return 0; } if ((u64)block * BLOCK_SIZE >= inode->i_sb->s_maxbytes) return 0; if (block < 7) { offsets[n++] = block; } else if ((block -= 7) < 512) { offsets[n++] = 7; offsets[n++] = block; } else { block -= 512; offsets[n++] = 8; offsets[n++] = block>>9; offsets[n++] = block & 511; } return n; } #include "itree_common.c" int V1_minix_get_block(struct inode * inode, long block, struct buffer_head *bh_result, int create) { return get_block(inode, block, bh_result, create); } void V1_minix_truncate(struct inode * inode) { truncate(inode); } unsigned V1_minix_blocks(loff_t size, struct super_block *sb) { return nblocks(size, sb); } |
| 2 2 2 2 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 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 | // SPDX-License-Identifier: GPL-2.0 /* * This file contains functions which emulate a local clock-event * device via a broadcast event source. * * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner */ #include <linux/cpu.h> #include <linux/err.h> #include <linux/hrtimer.h> #include <linux/interrupt.h> #include <linux/percpu.h> #include <linux/profile.h> #include <linux/sched.h> #include <linux/smp.h> #include <linux/module.h> #include "tick-internal.h" /* * Broadcast support for broken x86 hardware, where the local apic * timer stops in C3 state. */ static struct tick_device tick_broadcast_device; static cpumask_var_t tick_broadcast_mask __cpumask_var_read_mostly; static cpumask_var_t tick_broadcast_on __cpumask_var_read_mostly; static cpumask_var_t tmpmask __cpumask_var_read_mostly; static int tick_broadcast_forced; static __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(tick_broadcast_lock); #ifdef CONFIG_TICK_ONESHOT static DEFINE_PER_CPU(struct clock_event_device *, tick_oneshot_wakeup_device); static void tick_broadcast_setup_oneshot(struct clock_event_device *bc, bool from_periodic); static void tick_broadcast_clear_oneshot(int cpu); static void tick_resume_broadcast_oneshot(struct clock_event_device *bc); # ifdef CONFIG_HOTPLUG_CPU static void tick_broadcast_oneshot_offline(unsigned int cpu); # endif #else static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc, bool from_periodic) { BUG(); } static inline void tick_broadcast_clear_oneshot(int cpu) { } static inline void tick_resume_broadcast_oneshot(struct clock_event_device *bc) { } # ifdef CONFIG_HOTPLUG_CPU static inline void tick_broadcast_oneshot_offline(unsigned int cpu) { } # endif #endif /* * Debugging: see timer_list.c */ struct tick_device *tick_get_broadcast_device(void) { return &tick_broadcast_device; } struct cpumask *tick_get_broadcast_mask(void) { return tick_broadcast_mask; } static struct clock_event_device *tick_get_oneshot_wakeup_device(int cpu); const struct clock_event_device *tick_get_wakeup_device(int cpu) { return tick_get_oneshot_wakeup_device(cpu); } /* * Start the device in periodic mode */ static void tick_broadcast_start_periodic(struct clock_event_device *bc) { if (bc) tick_setup_periodic(bc, 1); } /* * Check, if the device can be utilized as broadcast device: */ static bool tick_check_broadcast_device(struct clock_event_device *curdev, struct clock_event_device *newdev) { if ((newdev->features & CLOCK_EVT_FEAT_DUMMY) || (newdev->features & CLOCK_EVT_FEAT_PERCPU) || (newdev->features & CLOCK_EVT_FEAT_C3STOP)) return false; if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT && !(newdev->features & CLOCK_EVT_FEAT_ONESHOT)) return false; return !curdev || newdev->rating > curdev->rating; } #ifdef CONFIG_TICK_ONESHOT static struct clock_event_device *tick_get_oneshot_wakeup_device(int cpu) { return per_cpu(tick_oneshot_wakeup_device, cpu); } static void tick_oneshot_wakeup_handler(struct clock_event_device *wd) { /* * If we woke up early and the tick was reprogrammed in the * meantime then this may be spurious but harmless. */ tick_receive_broadcast(); } static bool tick_set_oneshot_wakeup_device(struct clock_event_device *newdev, int cpu) { struct clock_event_device *curdev = tick_get_oneshot_wakeup_device(cpu); if (!newdev) goto set_device; if ((newdev->features & CLOCK_EVT_FEAT_DUMMY) || (newdev->features & CLOCK_EVT_FEAT_C3STOP)) return false; if (!(newdev->features & CLOCK_EVT_FEAT_PERCPU) || !(newdev->features & CLOCK_EVT_FEAT_ONESHOT)) return false; if (!cpumask_equal(newdev->cpumask, cpumask_of(cpu))) return false; if (curdev && newdev->rating <= curdev->rating) return false; if (!try_module_get(newdev->owner)) return false; newdev->event_handler = tick_oneshot_wakeup_handler; set_device: clockevents_exchange_device(curdev, newdev); per_cpu(tick_oneshot_wakeup_device, cpu) = newdev; return true; } #else static struct clock_event_device *tick_get_oneshot_wakeup_device(int cpu) { return NULL; } static bool tick_set_oneshot_wakeup_device(struct clock_event_device *newdev, int cpu) { return false; } #endif /* * Conditionally install/replace broadcast device */ void tick_install_broadcast_device(struct clock_event_device *dev, int cpu) { struct clock_event_device *cur = tick_broadcast_device.evtdev; if (tick_set_oneshot_wakeup_device(dev, cpu)) return; if (!tick_check_broadcast_device(cur, dev)) return; if (!try_module_get(dev->owner)) return; clockevents_exchange_device(cur, dev); if (cur) cur->event_handler = clockevents_handle_noop; tick_broadcast_device.evtdev = dev; if (!cpumask_empty(tick_broadcast_mask)) tick_broadcast_start_periodic(dev); if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT)) return; /* * If the system already runs in oneshot mode, switch the newly * registered broadcast device to oneshot mode explicitly. */ if (tick_broadcast_oneshot_active()) { tick_broadcast_switch_to_oneshot(); return; } /* * Inform all cpus about this. We might be in a situation * where we did not switch to oneshot mode because the per cpu * devices are affected by CLOCK_EVT_FEAT_C3STOP and the lack * of a oneshot capable broadcast device. Without that * notification the systems stays stuck in periodic mode * forever. */ tick_clock_notify(); } /* * Check, if the device is the broadcast device */ int tick_is_broadcast_device(struct clock_event_device *dev) { return (dev && tick_broadcast_device.evtdev == dev); } int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq) { int ret = -ENODEV; if (tick_is_broadcast_device(dev)) { raw_spin_lock(&tick_broadcast_lock); ret = __clockevents_update_freq(dev, freq); raw_spin_unlock(&tick_broadcast_lock); } return ret; } static void err_broadcast(const struct cpumask *mask) { pr_crit_once("Failed to broadcast timer tick. Some CPUs may be unresponsive.\n"); } static void tick_device_setup_broadcast_func(struct clock_event_device *dev) { if (!dev->broadcast) dev->broadcast = tick_broadcast; if (!dev->broadcast) { pr_warn_once("%s depends on broadcast, but no broadcast function available\n", dev->name); dev->broadcast = err_broadcast; } } /* * Check, if the device is dysfunctional and a placeholder, which * needs to be handled by the broadcast device. */ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) { struct clock_event_device *bc = tick_broadcast_device.evtdev; unsigned long flags; int ret = 0; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); /* * Devices might be registered with both periodic and oneshot * mode disabled. This signals, that the device needs to be * operated from the broadcast device and is a placeholder for * the cpu local device. */ if (!tick_device_is_functional(dev)) { dev->event_handler = tick_handle_periodic; tick_device_setup_broadcast_func(dev); cpumask_set_cpu(cpu, tick_broadcast_mask); if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) tick_broadcast_start_periodic(bc); else tick_broadcast_setup_oneshot(bc, false); ret = 1; } else { /* * Clear the broadcast bit for this cpu if the * device is not power state affected. */ if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) cpumask_clear_cpu(cpu, tick_broadcast_mask); else tick_device_setup_broadcast_func(dev); /* * Clear the broadcast bit if the CPU is not in * periodic broadcast on state. */ if (!cpumask_test_cpu(cpu, tick_broadcast_on)) cpumask_clear_cpu(cpu, tick_broadcast_mask); switch (tick_broadcast_device.mode) { case TICKDEV_MODE_ONESHOT: /* * If the system is in oneshot mode we can * unconditionally clear the oneshot mask bit, * because the CPU is running and therefore * not in an idle state which causes the power * state affected device to stop. Let the * caller initialize the device. */ tick_broadcast_clear_oneshot(cpu); ret = 0; break; case TICKDEV_MODE_PERIODIC: /* * If the system is in periodic mode, check * whether the broadcast device can be * switched off now. */ if (cpumask_empty(tick_broadcast_mask) && bc) clockevents_shutdown(bc); /* * If we kept the cpu in the broadcast mask, * tell the caller to leave the per cpu device * in shutdown state. The periodic interrupt * is delivered by the broadcast device, if * the broadcast device exists and is not * hrtimer based. */ if (bc && !(bc->features & CLOCK_EVT_FEAT_HRTIMER)) ret = cpumask_test_cpu(cpu, tick_broadcast_mask); break; default: break; } } raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); return ret; } int tick_receive_broadcast(void) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); struct clock_event_device *evt = td->evtdev; if (!evt) return -ENODEV; if (!evt->event_handler) return -EINVAL; evt->event_handler(evt); return 0; } /* * Broadcast the event to the cpus, which are set in the mask (mangled). */ static bool tick_do_broadcast(struct cpumask *mask) { int cpu = smp_processor_id(); struct tick_device *td; bool local = false; /* * Check, if the current cpu is in the mask */ if (cpumask_test_cpu(cpu, mask)) { struct clock_event_device *bc = tick_broadcast_device.evtdev; cpumask_clear_cpu(cpu, mask); /* * We only run the local handler, if the broadcast * device is not hrtimer based. Otherwise we run into * a hrtimer recursion. * * local timer_interrupt() * local_handler() * expire_hrtimers() * bc_handler() * local_handler() * expire_hrtimers() */ local = !(bc->features & CLOCK_EVT_FEAT_HRTIMER); } if (!cpumask_empty(mask)) { /* * It might be necessary to actually check whether the devices * have different broadcast functions. For now, just use the * one of the first device. This works as long as we have this * misfeature only on x86 (lapic) */ td = &per_cpu(tick_cpu_device, cpumask_first(mask)); td->evtdev->broadcast(mask); } return local; } /* * Periodic broadcast: * - invoke the broadcast handlers */ static bool tick_do_periodic_broadcast(void) { cpumask_and(tmpmask, cpu_online_mask, tick_broadcast_mask); return tick_do_broadcast(tmpmask); } /* * Event handler for periodic broadcast ticks */ static void tick_handle_periodic_broadcast(struct clock_event_device *dev) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); bool bc_local; raw_spin_lock(&tick_broadcast_lock); /* Handle spurious interrupts gracefully */ if (clockevent_state_shutdown(tick_broadcast_device.evtdev)) { raw_spin_unlock(&tick_broadcast_lock); return; } bc_local = tick_do_periodic_broadcast(); if (clockevent_state_oneshot(dev)) { ktime_t next = ktime_add_ns(dev->next_event, TICK_NSEC); clockevents_program_event(dev, next, true); } raw_spin_unlock(&tick_broadcast_lock); /* * We run the handler of the local cpu after dropping * tick_broadcast_lock because the handler might deadlock when * trying to switch to oneshot mode. */ if (bc_local) td->evtdev->event_handler(td->evtdev); } /** * tick_broadcast_control - Enable/disable or force broadcast mode * @mode: The selected broadcast mode * * Called when the system enters a state where affected tick devices * might stop. Note: TICK_BROADCAST_FORCE cannot be undone. */ void tick_broadcast_control(enum tick_broadcast_mode mode) { struct clock_event_device *bc, *dev; struct tick_device *td; int cpu, bc_stopped; unsigned long flags; /* Protects also the local clockevent device. */ raw_spin_lock_irqsave(&tick_broadcast_lock, flags); td = this_cpu_ptr(&tick_cpu_device); dev = td->evtdev; /* * Is the device not affected by the powerstate ? */ if (!dev || !(dev->features & CLOCK_EVT_FEAT_C3STOP)) goto out; if (!tick_device_is_functional(dev)) goto out; cpu = smp_processor_id(); bc = tick_broadcast_device.evtdev; bc_stopped = cpumask_empty(tick_broadcast_mask); switch (mode) { case TICK_BROADCAST_FORCE: tick_broadcast_forced = 1; fallthrough; case TICK_BROADCAST_ON: cpumask_set_cpu(cpu, tick_broadcast_on); if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) { /* * Only shutdown the cpu local device, if: * * - the broadcast device exists * - the broadcast device is not a hrtimer based one * - the broadcast device is in periodic mode to * avoid a hiccup during switch to oneshot mode */ if (bc && !(bc->features & CLOCK_EVT_FEAT_HRTIMER) && tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) clockevents_shutdown(dev); } break; case TICK_BROADCAST_OFF: if (tick_broadcast_forced) break; cpumask_clear_cpu(cpu, tick_broadcast_on); if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_mask)) { if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) tick_setup_periodic(dev, 0); } break; } if (bc) { if (cpumask_empty(tick_broadcast_mask)) { if (!bc_stopped) clockevents_shutdown(bc); } else if (bc_stopped) { if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) tick_broadcast_start_periodic(bc); else tick_broadcast_setup_oneshot(bc, false); } } out: raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } EXPORT_SYMBOL_GPL(tick_broadcast_control); /* * Set the periodic handler depending on broadcast on/off */ void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast) { if (!broadcast) dev->event_handler = tick_handle_periodic; else dev->event_handler = tick_handle_periodic_broadcast; } #ifdef CONFIG_HOTPLUG_CPU static void tick_shutdown_broadcast(void) { struct clock_event_device *bc = tick_broadcast_device.evtdev; if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) { if (bc && cpumask_empty(tick_broadcast_mask)) clockevents_shutdown(bc); } } /* * Remove a CPU from broadcasting */ void tick_broadcast_offline(unsigned int cpu) { raw_spin_lock(&tick_broadcast_lock); cpumask_clear_cpu(cpu, tick_broadcast_mask); cpumask_clear_cpu(cpu, tick_broadcast_on); tick_broadcast_oneshot_offline(cpu); tick_shutdown_broadcast(); raw_spin_unlock(&tick_broadcast_lock); } #endif void tick_suspend_broadcast(void) { struct clock_event_device *bc; unsigned long flags; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); bc = tick_broadcast_device.evtdev; if (bc) clockevents_shutdown(bc); raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } /* * This is called from tick_resume_local() on a resuming CPU. That's * called from the core resume function, tick_unfreeze() and the magic XEN * resume hackery. * * In none of these cases the broadcast device mode can change and the * bit of the resuming CPU in the broadcast mask is safe as well. */ bool tick_resume_check_broadcast(void) { if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT) return false; else return cpumask_test_cpu(smp_processor_id(), tick_broadcast_mask); } void tick_resume_broadcast(void) { struct clock_event_device *bc; unsigned long flags; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); bc = tick_broadcast_device.evtdev; if (bc) { clockevents_tick_resume(bc); switch (tick_broadcast_device.mode) { case TICKDEV_MODE_PERIODIC: if (!cpumask_empty(tick_broadcast_mask)) tick_broadcast_start_periodic(bc); break; case TICKDEV_MODE_ONESHOT: if (!cpumask_empty(tick_broadcast_mask)) tick_resume_broadcast_oneshot(bc); break; } } raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } #ifdef CONFIG_TICK_ONESHOT static cpumask_var_t tick_broadcast_oneshot_mask __cpumask_var_read_mostly; static cpumask_var_t tick_broadcast_pending_mask __cpumask_var_read_mostly; static cpumask_var_t tick_broadcast_force_mask __cpumask_var_read_mostly; /* * Exposed for debugging: see timer_list.c */ struct cpumask *tick_get_broadcast_oneshot_mask(void) { return tick_broadcast_oneshot_mask; } /* * Called before going idle with interrupts disabled. Checks whether a * broadcast event from the other core is about to happen. We detected * that in tick_broadcast_oneshot_control(). The callsite can use this * to avoid a deep idle transition as we are about to get the * broadcast IPI right away. */ noinstr int tick_check_broadcast_expired(void) { #ifdef _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H return arch_test_bit(smp_processor_id(), cpumask_bits(tick_broadcast_force_mask)); #else return cpumask_test_cpu(smp_processor_id(), tick_broadcast_force_mask); #endif } /* * Set broadcast interrupt affinity */ static void tick_broadcast_set_affinity(struct clock_event_device *bc, const struct cpumask *cpumask) { if (!(bc->features & CLOCK_EVT_FEAT_DYNIRQ)) return; if (cpumask_equal(bc->cpumask, cpumask)) return; bc->cpumask = cpumask; irq_set_affinity(bc->irq, bc->cpumask); } static void tick_broadcast_set_event(struct clock_event_device *bc, int cpu, ktime_t expires) { if (!clockevent_state_oneshot(bc)) clockevents_switch_state(bc, CLOCK_EVT_STATE_ONESHOT); clockevents_program_event(bc, expires, 1); tick_broadcast_set_affinity(bc, cpumask_of(cpu)); } static void tick_resume_broadcast_oneshot(struct clock_event_device *bc) { clockevents_switch_state(bc, CLOCK_EVT_STATE_ONESHOT); } /* * Called from irq_enter() when idle was interrupted to reenable the * per cpu device. */ void tick_check_oneshot_broadcast_this_cpu(void) { if (cpumask_test_cpu(smp_processor_id(), tick_broadcast_oneshot_mask)) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); /* * We might be in the middle of switching over from * periodic to oneshot. If the CPU has not yet * switched over, leave the device alone. */ if (td->mode == TICKDEV_MODE_ONESHOT) { clockevents_switch_state(td->evtdev, CLOCK_EVT_STATE_ONESHOT); } } } /* * Handle oneshot mode broadcasting */ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev) { struct tick_device *td; ktime_t now, next_event; int cpu, next_cpu = 0; bool bc_local; raw_spin_lock(&tick_broadcast_lock); dev->next_event = KTIME_MAX; next_event = KTIME_MAX; cpumask_clear(tmpmask); now = ktime_get(); /* Find all expired events */ for_each_cpu(cpu, tick_broadcast_oneshot_mask) { /* * Required for !SMP because for_each_cpu() reports * unconditionally CPU0 as set on UP kernels. */ if (!IS_ENABLED(CONFIG_SMP) && cpumask_empty(tick_broadcast_oneshot_mask)) break; td = &per_cpu(tick_cpu_device, cpu); if (td->evtdev->next_event <= now) { cpumask_set_cpu(cpu, tmpmask); /* * Mark the remote cpu in the pending mask, so * it can avoid reprogramming the cpu local * timer in tick_broadcast_oneshot_control(). */ cpumask_set_cpu(cpu, tick_broadcast_pending_mask); } else if (td->evtdev->next_event < next_event) { next_event = td->evtdev->next_event; next_cpu = cpu; } } /* * Remove the current cpu from the pending mask. The event is * delivered immediately in tick_do_broadcast() ! */ cpumask_clear_cpu(smp_processor_id(), tick_broadcast_pending_mask); /* Take care of enforced broadcast requests */ cpumask_or(tmpmask, tmpmask, tick_broadcast_force_mask); cpumask_clear(tick_broadcast_force_mask); /* * Sanity check. Catch the case where we try to broadcast to * offline cpus. */ if (WARN_ON_ONCE(!cpumask_subset(tmpmask, cpu_online_mask))) cpumask_and(tmpmask, tmpmask, cpu_online_mask); /* * Wakeup the cpus which have an expired event. */ bc_local = tick_do_broadcast(tmpmask); /* * Two reasons for reprogram: * * - The global event did not expire any CPU local * events. This happens in dyntick mode, as the maximum PIT * delta is quite small. * * - There are pending events on sleeping CPUs which were not * in the event mask */ if (next_event != KTIME_MAX) tick_broadcast_set_event(dev, next_cpu, next_event); raw_spin_unlock(&tick_broadcast_lock); if (bc_local) { td = this_cpu_ptr(&tick_cpu_device); td->evtdev->event_handler(td->evtdev); } } static int broadcast_needs_cpu(struct clock_event_device *bc, int cpu) { if (!(bc->features & CLOCK_EVT_FEAT_HRTIMER)) return 0; if (bc->next_event == KTIME_MAX) return 0; return bc->bound_on == cpu ? -EBUSY : 0; } static void broadcast_shutdown_local(struct clock_event_device *bc, struct clock_event_device *dev) { /* * For hrtimer based broadcasting we cannot shutdown the cpu * local device if our own event is the first one to expire or * if we own the broadcast timer. */ if (bc->features & CLOCK_EVT_FEAT_HRTIMER) { if (broadcast_needs_cpu(bc, smp_processor_id())) return; if (dev->next_event < bc->next_event) return; } clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN); } static int ___tick_broadcast_oneshot_control(enum tick_broadcast_state state, struct tick_device *td, int cpu) { struct clock_event_device *bc, *dev = td->evtdev; int ret = 0; ktime_t now; raw_spin_lock(&tick_broadcast_lock); bc = tick_broadcast_device.evtdev; if (state == TICK_BROADCAST_ENTER) { /* * If the current CPU owns the hrtimer broadcast * mechanism, it cannot go deep idle and we do not add * the CPU to the broadcast mask. We don't have to go * through the EXIT path as the local timer is not * shutdown. */ ret = broadcast_needs_cpu(bc, cpu); if (ret) goto out; /* * If the broadcast device is in periodic mode, we * return. */ if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) { /* If it is a hrtimer based broadcast, return busy */ if (bc->features & CLOCK_EVT_FEAT_HRTIMER) ret = -EBUSY; goto out; } if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) { WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask)); /* Conditionally shut down the local timer. */ broadcast_shutdown_local(bc, dev); /* * We only reprogram the broadcast timer if we * did not mark ourself in the force mask and * if the cpu local event is earlier than the * broadcast event. If the current CPU is in * the force mask, then we are going to be * woken by the IPI right away; we return * busy, so the CPU does not try to go deep * idle. */ if (cpumask_test_cpu(cpu, tick_broadcast_force_mask)) { ret = -EBUSY; } else if (dev->next_event < bc->next_event) { tick_broadcast_set_event(bc, cpu, dev->next_event); /* * In case of hrtimer broadcasts the * programming might have moved the * timer to this cpu. If yes, remove * us from the broadcast mask and * return busy. */ ret = broadcast_needs_cpu(bc, cpu); if (ret) { cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask); } } } } else { if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) { clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT); /* * The cpu which was handling the broadcast * timer marked this cpu in the broadcast * pending mask and fired the broadcast * IPI. So we are going to handle the expired * event anyway via the broadcast IPI * handler. No need to reprogram the timer * with an already expired event. */ if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_pending_mask)) goto out; /* * Bail out if there is no next event. */ if (dev->next_event == KTIME_MAX) goto out; /* * If the pending bit is not set, then we are * either the CPU handling the broadcast * interrupt or we got woken by something else. * * We are no longer in the broadcast mask, so * if the cpu local expiry time is already * reached, we would reprogram the cpu local * timer with an already expired event. * * This can lead to a ping-pong when we return * to idle and therefore rearm the broadcast * timer before the cpu local timer was able * to fire. This happens because the forced * reprogramming makes sure that the event * will happen in the future and depending on * the min_delta setting this might be far * enough out that the ping-pong starts. * * If the cpu local next_event has expired * then we know that the broadcast timer * next_event has expired as well and * broadcast is about to be handled. So we * avoid reprogramming and enforce that the * broadcast handler, which did not run yet, * will invoke the cpu local handler. * * We cannot call the handler directly from * here, because we might be in a NOHZ phase * and we did not go through the irq_enter() * nohz fixups. */ now = ktime_get(); if (dev->next_event <= now) { cpumask_set_cpu(cpu, tick_broadcast_force_mask); goto out; } /* * We got woken by something else. Reprogram * the cpu local timer device. */ tick_program_event(dev->next_event, 1); } } out: raw_spin_unlock(&tick_broadcast_lock); return ret; } static int tick_oneshot_wakeup_control(enum tick_broadcast_state state, struct tick_device *td, int cpu) { struct clock_event_device *dev, *wd; dev = td->evtdev; if (td->mode != TICKDEV_MODE_ONESHOT) return -EINVAL; wd = tick_get_oneshot_wakeup_device(cpu); if (!wd) return -ENODEV; switch (state) { case TICK_BROADCAST_ENTER: clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT_STOPPED); clockevents_switch_state(wd, CLOCK_EVT_STATE_ONESHOT); clockevents_program_event(wd, dev->next_event, 1); break; case TICK_BROADCAST_EXIT: /* We may have transitioned to oneshot mode while idle */ if (clockevent_get_state(wd) != CLOCK_EVT_STATE_ONESHOT) return -ENODEV; } return 0; } int __tick_broadcast_oneshot_control(enum tick_broadcast_state state) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); int cpu = smp_processor_id(); if (!tick_oneshot_wakeup_control(state, td, cpu)) return 0; if (tick_broadcast_device.evtdev) return ___tick_broadcast_oneshot_control(state, td, cpu); /* * If there is no broadcast or wakeup device, tell the caller not * to go into deep idle. */ return -EBUSY; } /* * Reset the one shot broadcast for a cpu * * Called with tick_broadcast_lock held */ static void tick_broadcast_clear_oneshot(int cpu) { cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask); cpumask_clear_cpu(cpu, tick_broadcast_pending_mask); } static void tick_broadcast_init_next_event(struct cpumask *mask, ktime_t expires) { struct tick_device *td; int cpu; for_each_cpu(cpu, mask) { td = &per_cpu(tick_cpu_device, cpu); if (td->evtdev) td->evtdev->next_event = expires; } } static inline ktime_t tick_get_next_period(void) { ktime_t next; /* * Protect against concurrent updates (store /load tearing on * 32bit). It does not matter if the time is already in the * past. The broadcast device which is about to be programmed will * fire in any case. */ raw_spin_lock(&jiffies_lock); next = tick_next_period; raw_spin_unlock(&jiffies_lock); return next; } /** * tick_broadcast_setup_oneshot - setup the broadcast device * @bc: the broadcast device * @from_periodic: true if called from periodic mode */ static void tick_broadcast_setup_oneshot(struct clock_event_device *bc, bool from_periodic) { int cpu = smp_processor_id(); ktime_t nexttick = 0; if (!bc) return; /* * When the broadcast device was switched to oneshot by the first * CPU handling the NOHZ change, the other CPUs will reach this * code via hrtimer_run_queues() -> tick_check_oneshot_change() * too. Set up the broadcast device only once! */ if (bc->event_handler == tick_handle_oneshot_broadcast) { /* * The CPU which switched from periodic to oneshot mode * set the broadcast oneshot bit for all other CPUs which * are in the general (periodic) broadcast mask to ensure * that CPUs which wait for the periodic broadcast are * woken up. * * Clear the bit for the local CPU as the set bit would * prevent the first tick_broadcast_enter() after this CPU * switched to oneshot state to program the broadcast * device. * * This code can also be reached via tick_broadcast_control(), * but this cannot avoid the tick_broadcast_clear_oneshot() * as that would break the periodic to oneshot transition of * secondary CPUs. But that's harmless as the below only * clears already cleared bits. */ tick_broadcast_clear_oneshot(cpu); return; } bc->event_handler = tick_handle_oneshot_broadcast; bc->next_event = KTIME_MAX; /* * When the tick mode is switched from periodic to oneshot it must * be ensured that CPUs which are waiting for periodic broadcast * get their wake-up at the next tick. This is achieved by ORing * tick_broadcast_mask into tick_broadcast_oneshot_mask. * * For other callers, e.g. broadcast device replacement, * tick_broadcast_oneshot_mask must not be touched as this would * set bits for CPUs which are already NOHZ, but not idle. Their * next tick_broadcast_enter() would observe the bit set and fail * to update the expiry time and the broadcast event device. */ if (from_periodic) { cpumask_copy(tmpmask, tick_broadcast_mask); /* Remove the local CPU as it is obviously not idle */ cpumask_clear_cpu(cpu, tmpmask); cpumask_or(tick_broadcast_oneshot_mask, tick_broadcast_oneshot_mask, tmpmask); /* * Ensure that the oneshot broadcast handler will wake the * CPUs which are still waiting for periodic broadcast. */ nexttick = tick_get_next_period(); tick_broadcast_init_next_event(tmpmask, nexttick); /* * If the underlying broadcast clock event device is * already in oneshot state, then there is nothing to do. * The device was already armed for the next tick * in tick_handle_broadcast_periodic() */ if (clockevent_state_oneshot(bc)) return; } /* * When switching from periodic to oneshot mode arm the broadcast * device for the next tick. * * If the broadcast device has been replaced in oneshot mode and * the oneshot broadcast mask is not empty, then arm it to expire * immediately in order to reevaluate the next expiring timer. * @nexttick is 0 and therefore in the past which will cause the * clockevent code to force an event. * * For both cases the programming can be avoided when the oneshot * broadcast mask is empty. * * tick_broadcast_set_event() implicitly switches the broadcast * device to oneshot state. */ if (!cpumask_empty(tick_broadcast_oneshot_mask)) tick_broadcast_set_event(bc, cpu, nexttick); } /* * Select oneshot operating mode for the broadcast device */ void tick_broadcast_switch_to_oneshot(void) { struct clock_event_device *bc; enum tick_device_mode oldmode; unsigned long flags; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); oldmode = tick_broadcast_device.mode; tick_broadcast_device.mode = TICKDEV_MODE_ONESHOT; bc = tick_broadcast_device.evtdev; if (bc) tick_broadcast_setup_oneshot(bc, oldmode == TICKDEV_MODE_PERIODIC); raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } #ifdef CONFIG_HOTPLUG_CPU void hotplug_cpu__broadcast_tick_pull(int deadcpu) { struct clock_event_device *bc; unsigned long flags; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); bc = tick_broadcast_device.evtdev; if (bc && broadcast_needs_cpu(bc, deadcpu)) { /* * If the broadcast force bit of the current CPU is set, * then the current CPU has not yet reprogrammed the local * timer device to avoid a ping-pong race. See * ___tick_broadcast_oneshot_control(). * * If the broadcast device is hrtimer based then * programming the broadcast event below does not have any * effect because the local clockevent device is not * running and not programmed because the broadcast event * is not earlier than the pending event of the local clock * event device. As a consequence all CPUs waiting for a * broadcast event are stuck forever. * * Detect this condition and reprogram the cpu local timer * device to avoid the starvation. */ if (tick_check_broadcast_expired()) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); cpumask_clear_cpu(smp_processor_id(), tick_broadcast_force_mask); tick_program_event(td->evtdev->next_event, 1); } /* This moves the broadcast assignment to this CPU: */ clockevents_program_event(bc, bc->next_event, 1); } raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } /* * Remove a dying CPU from broadcasting */ static void tick_broadcast_oneshot_offline(unsigned int cpu) { if (tick_get_oneshot_wakeup_device(cpu)) tick_set_oneshot_wakeup_device(NULL, cpu); /* * Clear the broadcast masks for the dead cpu, but do not stop * the broadcast device! */ cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask); cpumask_clear_cpu(cpu, tick_broadcast_pending_mask); cpumask_clear_cpu(cpu, tick_broadcast_force_mask); } #endif /* * Check, whether the broadcast device is in one shot mode */ int tick_broadcast_oneshot_active(void) { return tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT; } /* * Check whether the broadcast device supports oneshot. */ bool tick_broadcast_oneshot_available(void) { struct clock_event_device *bc = tick_broadcast_device.evtdev; return bc ? bc->features & CLOCK_EVT_FEAT_ONESHOT : false; } #else int __tick_broadcast_oneshot_control(enum tick_broadcast_state state) { struct clock_event_device *bc = tick_broadcast_device.evtdev; if (!bc || (bc->features & CLOCK_EVT_FEAT_HRTIMER)) return -EBUSY; return 0; } #endif void __init tick_broadcast_init(void) { zalloc_cpumask_var(&tick_broadcast_mask, GFP_NOWAIT); zalloc_cpumask_var(&tick_broadcast_on, GFP_NOWAIT); zalloc_cpumask_var(&tmpmask, GFP_NOWAIT); #ifdef CONFIG_TICK_ONESHOT zalloc_cpumask_var(&tick_broadcast_oneshot_mask, GFP_NOWAIT); zalloc_cpumask_var(&tick_broadcast_pending_mask, GFP_NOWAIT); zalloc_cpumask_var(&tick_broadcast_force_mask, GFP_NOWAIT); #endif } |
| 1 1 1 1 1 1 1 1 1 3 3 1 1 1 2 2 2 3 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2009 Red Hat, Inc. * Author: Michael S. Tsirkin <mst@redhat.com> * * virtio-net server in host kernel. */ #include <linux/compat.h> #include <linux/eventfd.h> #include <linux/vhost.h> #include <linux/virtio_net.h> #include <linux/miscdevice.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/mutex.h> #include <linux/workqueue.h> #include <linux/file.h> #include <linux/slab.h> #include <linux/sched/clock.h> #include <linux/sched/signal.h> #include <linux/vmalloc.h> #include <linux/net.h> #include <linux/if_packet.h> #include <linux/if_arp.h> #include <linux/if_tun.h> #include <linux/if_macvlan.h> #include <linux/if_tap.h> #include <linux/if_vlan.h> #include <linux/skb_array.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/xdp.h> #include "vhost.h" static int experimental_zcopytx = 0; module_param(experimental_zcopytx, int, 0444); MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;" " 1 -Enable; 0 - Disable"); /* Max number of bytes transferred before requeueing the job. * Using this limit prevents one virtqueue from starving others. */ #define VHOST_NET_WEIGHT 0x80000 /* Max number of packets transferred before requeueing the job. * Using this limit prevents one virtqueue from starving others with small * pkts. */ #define VHOST_NET_PKT_WEIGHT 256 /* MAX number of TX used buffers for outstanding zerocopy */ #define VHOST_MAX_PEND 128 #define VHOST_GOODCOPY_LEN 256 /* * For transmit, used buffer len is unused; we override it to track buffer * status internally; used for zerocopy tx only. */ /* Lower device DMA failed */ #define VHOST_DMA_FAILED_LEN ((__force __virtio32)3) /* Lower device DMA done */ #define VHOST_DMA_DONE_LEN ((__force __virtio32)2) /* Lower device DMA in progress */ #define VHOST_DMA_IN_PROGRESS ((__force __virtio32)1) /* Buffer unused */ #define VHOST_DMA_CLEAR_LEN ((__force __virtio32)0) #define VHOST_DMA_IS_DONE(len) ((__force u32)(len) >= (__force u32)VHOST_DMA_DONE_LEN) enum { VHOST_NET_FEATURES = VHOST_FEATURES | (1ULL << VHOST_NET_F_VIRTIO_NET_HDR) | (1ULL << VIRTIO_NET_F_MRG_RXBUF) | (1ULL << VIRTIO_F_ACCESS_PLATFORM) | (1ULL << VIRTIO_F_RING_RESET) }; enum { VHOST_NET_BACKEND_FEATURES = (1ULL << VHOST_BACKEND_F_IOTLB_MSG_V2) }; enum { VHOST_NET_VQ_RX = 0, VHOST_NET_VQ_TX = 1, VHOST_NET_VQ_MAX = 2, }; struct vhost_net_ubuf_ref { /* refcount follows semantics similar to kref: * 0: object is released * 1: no outstanding ubufs * >1: outstanding ubufs */ atomic_t refcount; wait_queue_head_t wait; struct vhost_virtqueue *vq; }; #define VHOST_NET_BATCH 64 struct vhost_net_buf { void **queue; int tail; int head; }; struct vhost_net_virtqueue { struct vhost_virtqueue vq; size_t vhost_hlen; size_t sock_hlen; /* vhost zerocopy support fields below: */ /* last used idx for outstanding DMA zerocopy buffers */ int upend_idx; /* For TX, first used idx for DMA done zerocopy buffers * For RX, number of batched heads */ int done_idx; /* Number of XDP frames batched */ int batched_xdp; /* an array of userspace buffers info */ struct ubuf_info_msgzc *ubuf_info; /* Reference counting for outstanding ubufs. * Protected by vq mutex. Writers must also take device mutex. */ struct vhost_net_ubuf_ref *ubufs; struct ptr_ring *rx_ring; struct vhost_net_buf rxq; /* Batched XDP buffs */ struct xdp_buff *xdp; }; struct vhost_net { struct vhost_dev dev; struct vhost_net_virtqueue vqs[VHOST_NET_VQ_MAX]; struct vhost_poll poll[VHOST_NET_VQ_MAX]; /* Number of TX recently submitted. * Protected by tx vq lock. */ unsigned tx_packets; /* Number of times zerocopy TX recently failed. * Protected by tx vq lock. */ unsigned tx_zcopy_err; /* Flush in progress. Protected by tx vq lock. */ bool tx_flush; /* Private page frag cache */ struct page_frag_cache pf_cache; }; static unsigned vhost_net_zcopy_mask __read_mostly; static void *vhost_net_buf_get_ptr(struct vhost_net_buf *rxq) { if (rxq->tail != rxq->head) return rxq->queue[rxq->head]; else return NULL; } static int vhost_net_buf_get_size(struct vhost_net_buf *rxq) { return rxq->tail - rxq->head; } static int vhost_net_buf_is_empty(struct vhost_net_buf *rxq) { return rxq->tail == rxq->head; } static void *vhost_net_buf_consume(struct vhost_net_buf *rxq) { void *ret = vhost_net_buf_get_ptr(rxq); ++rxq->head; return ret; } static int vhost_net_buf_produce(struct vhost_net_virtqueue *nvq) { struct vhost_net_buf *rxq = &nvq->rxq; rxq->head = 0; rxq->tail = ptr_ring_consume_batched(nvq->rx_ring, rxq->queue, VHOST_NET_BATCH); return rxq->tail; } static void vhost_net_buf_unproduce(struct vhost_net_virtqueue *nvq) { struct vhost_net_buf *rxq = &nvq->rxq; if (nvq->rx_ring && !vhost_net_buf_is_empty(rxq)) { ptr_ring_unconsume(nvq->rx_ring, rxq->queue + rxq->head, vhost_net_buf_get_size(rxq), tun_ptr_free); rxq->head = rxq->tail = 0; } } static int vhost_net_buf_peek_len(void *ptr) { if (tun_is_xdp_frame(ptr)) { struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr); return xdpf->len; } return __skb_array_len_with_tag(ptr); } static int vhost_net_buf_peek(struct vhost_net_virtqueue *nvq) { struct vhost_net_buf *rxq = &nvq->rxq; if (!vhost_net_buf_is_empty(rxq)) goto out; if (!vhost_net_buf_produce(nvq)) return 0; out: return vhost_net_buf_peek_len(vhost_net_buf_get_ptr(rxq)); } static void vhost_net_buf_init(struct vhost_net_buf *rxq) { rxq->head = rxq->tail = 0; } static void vhost_net_enable_zcopy(int vq) { vhost_net_zcopy_mask |= 0x1 << vq; } static struct vhost_net_ubuf_ref * vhost_net_ubuf_alloc(struct vhost_virtqueue *vq, bool zcopy) { struct vhost_net_ubuf_ref *ubufs; /* No zero copy backend? Nothing to count. */ if (!zcopy) return NULL; ubufs = kmalloc(sizeof(*ubufs), GFP_KERNEL); if (!ubufs) return ERR_PTR(-ENOMEM); atomic_set(&ubufs->refcount, 1); init_waitqueue_head(&ubufs->wait); ubufs->vq = vq; return ubufs; } static int vhost_net_ubuf_put(struct vhost_net_ubuf_ref *ubufs) { int r = atomic_sub_return(1, &ubufs->refcount); if (unlikely(!r)) wake_up(&ubufs->wait); return r; } static void vhost_net_ubuf_put_and_wait(struct vhost_net_ubuf_ref *ubufs) { vhost_net_ubuf_put(ubufs); wait_event(ubufs->wait, !atomic_read(&ubufs->refcount)); } static void vhost_net_ubuf_put_wait_and_free(struct vhost_net_ubuf_ref *ubufs) { vhost_net_ubuf_put_and_wait(ubufs); kfree(ubufs); } static void vhost_net_clear_ubuf_info(struct vhost_net *n) { int i; for (i = 0; i < VHOST_NET_VQ_MAX; ++i) { kfree(n->vqs[i].ubuf_info); n->vqs[i].ubuf_info = NULL; } } static int vhost_net_set_ubuf_info(struct vhost_net *n) { bool zcopy; int i; for (i = 0; i < VHOST_NET_VQ_MAX; ++i) { zcopy = vhost_net_zcopy_mask & (0x1 << i); if (!zcopy) continue; n->vqs[i].ubuf_info = kmalloc_array(UIO_MAXIOV, sizeof(*n->vqs[i].ubuf_info), GFP_KERNEL); if (!n->vqs[i].ubuf_info) goto err; } return 0; err: vhost_net_clear_ubuf_info(n); return -ENOMEM; } static void vhost_net_vq_reset(struct vhost_net *n) { int i; vhost_net_clear_ubuf_info(n); for (i = 0; i < VHOST_NET_VQ_MAX; i++) { n->vqs[i].done_idx = 0; n->vqs[i].upend_idx = 0; n->vqs[i].ubufs = NULL; n->vqs[i].vhost_hlen = 0; n->vqs[i].sock_hlen = 0; vhost_net_buf_init(&n->vqs[i].rxq); } } static void vhost_net_tx_packet(struct vhost_net *net) { ++net->tx_packets; if (net->tx_packets < 1024) return; net->tx_packets = 0; net->tx_zcopy_err = 0; } static void vhost_net_tx_err(struct vhost_net *net) { ++net->tx_zcopy_err; } static bool vhost_net_tx_select_zcopy(struct vhost_net *net) { /* TX flush waits for outstanding DMAs to be done. * Don't start new DMAs. */ return !net->tx_flush && net->tx_packets / 64 >= net->tx_zcopy_err; } static bool vhost_sock_zcopy(struct socket *sock) { return unlikely(experimental_zcopytx) && sock_flag(sock->sk, SOCK_ZEROCOPY); } static bool vhost_sock_xdp(struct socket *sock) { return sock_flag(sock->sk, SOCK_XDP); } /* In case of DMA done not in order in lower device driver for some reason. * upend_idx is used to track end of used idx, done_idx is used to track head * of used idx. Once lower device DMA done contiguously, we will signal KVM * guest used idx. */ static void vhost_zerocopy_signal_used(struct vhost_net *net, struct vhost_virtqueue *vq) { struct vhost_net_virtqueue *nvq = container_of(vq, struct vhost_net_virtqueue, vq); int i, add; int j = 0; for (i = nvq->done_idx; i != nvq->upend_idx; i = (i + 1) % UIO_MAXIOV) { if (vq->heads[i].len == VHOST_DMA_FAILED_LEN) vhost_net_tx_err(net); if (VHOST_DMA_IS_DONE(vq->heads[i].len)) { vq->heads[i].len = VHOST_DMA_CLEAR_LEN; ++j; } else break; } while (j) { add = min(UIO_MAXIOV - nvq->done_idx, j); vhost_add_used_and_signal_n(vq->dev, vq, &vq->heads[nvq->done_idx], add); nvq->done_idx = (nvq->done_idx + add) % UIO_MAXIOV; j -= add; } } static void vhost_zerocopy_complete(struct sk_buff *skb, struct ubuf_info *ubuf_base, bool success) { struct ubuf_info_msgzc *ubuf = uarg_to_msgzc(ubuf_base); struct vhost_net_ubuf_ref *ubufs = ubuf->ctx; struct vhost_virtqueue *vq = ubufs->vq; int cnt; rcu_read_lock_bh(); /* set len to mark this desc buffers done DMA */ vq->heads[ubuf->desc].len = success ? VHOST_DMA_DONE_LEN : VHOST_DMA_FAILED_LEN; cnt = vhost_net_ubuf_put(ubufs); /* * Trigger polling thread if guest stopped submitting new buffers: * in this case, the refcount after decrement will eventually reach 1. * We also trigger polling periodically after each 16 packets * (the value 16 here is more or less arbitrary, it's tuned to trigger * less than 10% of times). */ if (cnt <= 1 || !(cnt % 16)) vhost_poll_queue(&vq->poll); rcu_read_unlock_bh(); } static const struct ubuf_info_ops vhost_ubuf_ops = { .complete = vhost_zerocopy_complete, }; static inline unsigned long busy_clock(void) { return local_clock() >> 10; } static bool vhost_can_busy_poll(unsigned long endtime) { return likely(!need_resched() && !time_after(busy_clock(), endtime) && !signal_pending(current)); } static void vhost_net_disable_vq(struct vhost_net *n, struct vhost_virtqueue *vq) { struct vhost_net_virtqueue *nvq = container_of(vq, struct vhost_net_virtqueue, vq); struct vhost_poll *poll = n->poll + (nvq - n->vqs); if (!vhost_vq_get_backend(vq)) return; vhost_poll_stop(poll); } static int vhost_net_enable_vq(struct vhost_net *n, struct vhost_virtqueue *vq) { struct vhost_net_virtqueue *nvq = container_of(vq, struct vhost_net_virtqueue, vq); struct vhost_poll *poll = n->poll + (nvq - n->vqs); struct socket *sock; sock = vhost_vq_get_backend(vq); if (!sock) return 0; return vhost_poll_start(poll, sock->file); } static void vhost_net_signal_used(struct vhost_net_virtqueue *nvq) { struct vhost_virtqueue *vq = &nvq->vq; struct vhost_dev *dev = vq->dev; if (!nvq->done_idx) return; vhost_add_used_and_signal_n(dev, vq, vq->heads, nvq->done_idx); nvq->done_idx = 0; } static void vhost_tx_batch(struct vhost_net *net, struct vhost_net_virtqueue *nvq, struct socket *sock, struct msghdr *msghdr) { struct tun_msg_ctl ctl = { .type = TUN_MSG_PTR, .num = nvq->batched_xdp, .ptr = nvq->xdp, }; int i, err; if (nvq->batched_xdp == 0) goto signal_used; msghdr->msg_control = &ctl; msghdr->msg_controllen = sizeof(ctl); err = sock->ops->sendmsg(sock, msghdr, 0); if (unlikely(err < 0)) { vq_err(&nvq->vq, "Fail to batch sending packets\n"); /* free pages owned by XDP; since this is an unlikely error path, * keep it simple and avoid more complex bulk update for the * used pages */ for (i = 0; i < nvq->batched_xdp; ++i) put_page(virt_to_head_page(nvq->xdp[i].data)); nvq->batched_xdp = 0; nvq->done_idx = 0; return; } signal_used: vhost_net_signal_used(nvq); nvq->batched_xdp = 0; } static int sock_has_rx_data(struct socket *sock) { if (unlikely(!sock)) return 0; if (sock->ops->peek_len) return sock->ops->peek_len(sock); return skb_queue_empty(&sock->sk->sk_receive_queue); } static void vhost_net_busy_poll_try_queue(struct vhost_net *net, struct vhost_virtqueue *vq) { if (!vhost_vq_avail_empty(&net->dev, vq)) { vhost_poll_queue(&vq->poll); } else if (unlikely(vhost_enable_notify(&net->dev, vq))) { vhost_disable_notify(&net->dev, vq); vhost_poll_queue(&vq->poll); } } static void vhost_net_busy_poll(struct vhost_net *net, struct vhost_virtqueue *rvq, struct vhost_virtqueue *tvq, bool *busyloop_intr, bool poll_rx) { unsigned long busyloop_timeout; unsigned long endtime; struct socket *sock; struct vhost_virtqueue *vq = poll_rx ? tvq : rvq; /* Try to hold the vq mutex of the paired virtqueue. We can't * use mutex_lock() here since we could not guarantee a * consistenet lock ordering. */ if (!mutex_trylock(&vq->mutex)) return; vhost_disable_notify(&net->dev, vq); sock = vhost_vq_get_backend(rvq); busyloop_timeout = poll_rx ? rvq->busyloop_timeout: tvq->busyloop_timeout; preempt_disable(); endtime = busy_clock() + busyloop_timeout; while (vhost_can_busy_poll(endtime)) { if (vhost_vq_has_work(vq)) { *busyloop_intr = true; break; } if ((sock_has_rx_data(sock) && !vhost_vq_avail_empty(&net->dev, rvq)) || !vhost_vq_avail_empty(&net->dev, tvq)) break; cpu_relax(); } preempt_enable(); if (poll_rx || sock_has_rx_data(sock)) vhost_net_busy_poll_try_queue(net, vq); else if (!poll_rx) /* On tx here, sock has no rx data. */ vhost_enable_notify(&net->dev, rvq); mutex_unlock(&vq->mutex); } static int vhost_net_tx_get_vq_desc(struct vhost_net *net, struct vhost_net_virtqueue *tnvq, unsigned int *out_num, unsigned int *in_num, struct msghdr *msghdr, bool *busyloop_intr) { struct vhost_net_virtqueue *rnvq = &net->vqs[VHOST_NET_VQ_RX]; struct vhost_virtqueue *rvq = &rnvq->vq; struct vhost_virtqueue *tvq = &tnvq->vq; int r = vhost_get_vq_desc(tvq, tvq->iov, ARRAY_SIZE(tvq->iov), out_num, in_num, NULL, NULL); if (r == tvq->num && tvq->busyloop_timeout) { /* Flush batched packets first */ if (!vhost_sock_zcopy(vhost_vq_get_backend(tvq))) vhost_tx_batch(net, tnvq, vhost_vq_get_backend(tvq), msghdr); vhost_net_busy_poll(net, rvq, tvq, busyloop_intr, false); r = vhost_get_vq_desc(tvq, tvq->iov, ARRAY_SIZE(tvq->iov), out_num, in_num, NULL, NULL); } return r; } static bool vhost_exceeds_maxpend(struct vhost_net *net) { struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX]; struct vhost_virtqueue *vq = &nvq->vq; return (nvq->upend_idx + UIO_MAXIOV - nvq->done_idx) % UIO_MAXIOV > min_t(unsigned int, VHOST_MAX_PEND, vq->num >> 2); } static size_t init_iov_iter(struct vhost_virtqueue *vq, struct iov_iter *iter, size_t hdr_size, int out) { /* Skip header. TODO: support TSO. */ size_t len = iov_length(vq->iov, out); iov_iter_init(iter, ITER_SOURCE, vq->iov, out, len); iov_iter_advance(iter, hdr_size); return iov_iter_count(iter); } static int get_tx_bufs(struct vhost_net *net, struct vhost_net_virtqueue *nvq, struct msghdr *msg, unsigned int *out, unsigned int *in, size_t *len, bool *busyloop_intr) { struct vhost_virtqueue *vq = &nvq->vq; int ret; ret = vhost_net_tx_get_vq_desc(net, nvq, out, in, msg, busyloop_intr); if (ret < 0 || ret == vq->num) return ret; if (*in) { vq_err(vq, "Unexpected descriptor format for TX: out %d, int %d\n", *out, *in); return -EFAULT; } /* Sanity check */ *len = init_iov_iter(vq, &msg->msg_iter, nvq->vhost_hlen, *out); if (*len == 0) { vq_err(vq, "Unexpected header len for TX: %zd expected %zd\n", *len, nvq->vhost_hlen); return -EFAULT; } return ret; } static bool tx_can_batch(struct vhost_virtqueue *vq, size_t total_len) { return total_len < VHOST_NET_WEIGHT && !vhost_vq_avail_empty(vq->dev, vq); } #define VHOST_NET_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD) static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, struct iov_iter *from) { struct vhost_virtqueue *vq = &nvq->vq; struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev); struct socket *sock = vhost_vq_get_backend(vq); struct virtio_net_hdr *gso; struct xdp_buff *xdp = &nvq->xdp[nvq->batched_xdp]; struct tun_xdp_hdr *hdr; size_t len = iov_iter_count(from); int headroom = vhost_sock_xdp(sock) ? XDP_PACKET_HEADROOM : 0; int buflen = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); int pad = SKB_DATA_ALIGN(VHOST_NET_RX_PAD + headroom + nvq->sock_hlen); int sock_hlen = nvq->sock_hlen; void *buf; int copied; int ret; if (unlikely(len < nvq->sock_hlen)) return -EFAULT; if (SKB_DATA_ALIGN(len + pad) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) > PAGE_SIZE) return -ENOSPC; buflen += SKB_DATA_ALIGN(len + pad); buf = page_frag_alloc_align(&net->pf_cache, buflen, GFP_KERNEL, SMP_CACHE_BYTES); if (unlikely(!buf)) return -ENOMEM; copied = copy_from_iter(buf + offsetof(struct tun_xdp_hdr, gso), sock_hlen, from); if (copied != sock_hlen) { ret = -EFAULT; goto err; } hdr = buf; gso = &hdr->gso; if (!sock_hlen) memset(buf, 0, pad); if ((gso->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && vhost16_to_cpu(vq, gso->csum_start) + vhost16_to_cpu(vq, gso->csum_offset) + 2 > vhost16_to_cpu(vq, gso->hdr_len)) { gso->hdr_len = cpu_to_vhost16(vq, vhost16_to_cpu(vq, gso->csum_start) + vhost16_to_cpu(vq, gso->csum_offset) + 2); if (vhost16_to_cpu(vq, gso->hdr_len) > len) { ret = -EINVAL; goto err; } } len -= sock_hlen; copied = copy_from_iter(buf + pad, len, from); if (copied != len) { ret = -EFAULT; goto err; } xdp_init_buff(xdp, buflen, NULL); xdp_prepare_buff(xdp, buf, pad, len, true); hdr->buflen = buflen; ++nvq->batched_xdp; return 0; err: page_frag_free(buf); return ret; } static void handle_tx_copy(struct vhost_net *net, struct socket *sock) { struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX]; struct vhost_virtqueue *vq = &nvq->vq; unsigned out, in; int head; struct msghdr msg = { .msg_name = NULL, .msg_namelen = 0, .msg_control = NULL, .msg_controllen = 0, .msg_flags = MSG_DONTWAIT, }; size_t len, total_len = 0; int err; int sent_pkts = 0; bool sock_can_batch = (sock->sk->sk_sndbuf == INT_MAX); do { bool busyloop_intr = false; if (nvq->done_idx == VHOST_NET_BATCH) vhost_tx_batch(net, nvq, sock, &msg); head = get_tx_bufs(net, nvq, &msg, &out, &in, &len, &busyloop_intr); /* On error, stop handling until the next kick. */ if (unlikely(head < 0)) break; /* Nothing new? Wait for eventfd to tell us they refilled. */ if (head == vq->num) { if (unlikely(busyloop_intr)) { vhost_poll_queue(&vq->poll); } else if (unlikely(vhost_enable_notify(&net->dev, vq))) { vhost_disable_notify(&net->dev, vq); continue; } break; } total_len += len; /* For simplicity, TX batching is only enabled if * sndbuf is unlimited. */ if (sock_can_batch) { err = vhost_net_build_xdp(nvq, &msg.msg_iter); if (!err) { goto done; } else if (unlikely(err != -ENOSPC)) { vhost_tx_batch(net, nvq, sock, &msg); vhost_discard_vq_desc(vq, 1); vhost_net_enable_vq(net, vq); break; } /* We can't build XDP buff, go for single * packet path but let's flush batched * packets. */ vhost_tx_batch(net, nvq, sock, &msg); msg.msg_control = NULL; } else { if (tx_can_batch(vq, total_len)) msg.msg_flags |= MSG_MORE; else msg.msg_flags &= ~MSG_MORE; } err = sock->ops->sendmsg(sock, &msg, len); if (unlikely(err < 0)) { if (err == -EAGAIN || err == -ENOMEM || err == -ENOBUFS) { vhost_discard_vq_desc(vq, 1); vhost_net_enable_vq(net, vq); break; } pr_debug("Fail to send packet: err %d", err); } else if (unlikely(err != len)) pr_debug("Truncated TX packet: len %d != %zd\n", err, len); done: vq->heads[nvq->done_idx].id = cpu_to_vhost32(vq, head); vq->heads[nvq->done_idx].len = 0; ++nvq->done_idx; } while (likely(!vhost_exceeds_weight(vq, ++sent_pkts, total_len))); vhost_tx_batch(net, nvq, sock, &msg); } static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) { struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX]; struct vhost_virtqueue *vq = &nvq->vq; unsigned out, in; int head; struct msghdr msg = { .msg_name = NULL, .msg_namelen = 0, .msg_control = NULL, .msg_controllen = 0, .msg_flags = MSG_DONTWAIT, }; struct tun_msg_ctl ctl; size_t len, total_len = 0; int err; struct vhost_net_ubuf_ref *ubufs; struct ubuf_info_msgzc *ubuf; bool zcopy_used; int sent_pkts = 0; do { bool busyloop_intr; /* Release DMAs done buffers first */ vhost_zerocopy_signal_used(net, vq); busyloop_intr = false; head = get_tx_bufs(net, nvq, &msg, &out, &in, &len, &busyloop_intr); /* On error, stop handling until the next kick. */ if (unlikely(head < 0)) break; /* Nothing new? Wait for eventfd to tell us they refilled. */ if (head == vq->num) { if (unlikely(busyloop_intr)) { vhost_poll_queue(&vq->poll); } else if (unlikely(vhost_enable_notify(&net->dev, vq))) { vhost_disable_notify(&net->dev, vq); continue; } break; } zcopy_used = len >= VHOST_GOODCOPY_LEN && !vhost_exceeds_maxpend(net) && vhost_net_tx_select_zcopy(net); /* use msg_control to pass vhost zerocopy ubuf info to skb */ if (zcopy_used) { ubuf = nvq->ubuf_info + nvq->upend_idx; vq->heads[nvq->upend_idx].id = cpu_to_vhost32(vq, head); vq->heads[nvq->upend_idx].len = VHOST_DMA_IN_PROGRESS; ubuf->ctx = nvq->ubufs; ubuf->desc = nvq->upend_idx; ubuf->ubuf.ops = &vhost_ubuf_ops; ubuf->ubuf.flags = SKBFL_ZEROCOPY_FRAG; refcount_set(&ubuf->ubuf.refcnt, 1); msg.msg_control = &ctl; ctl.type = TUN_MSG_UBUF; ctl.ptr = &ubuf->ubuf; msg.msg_controllen = sizeof(ctl); ubufs = nvq->ubufs; atomic_inc(&ubufs->refcount); nvq->upend_idx = (nvq->upend_idx + 1) % UIO_MAXIOV; } else { msg.msg_control = NULL; ubufs = NULL; } total_len += len; if (tx_can_batch(vq, total_len) && likely(!vhost_exceeds_maxpend(net))) { msg.msg_flags |= MSG_MORE; } else { msg.msg_flags &= ~MSG_MORE; } err = sock->ops->sendmsg(sock, &msg, len); if (unlikely(err < 0)) { bool retry = err == -EAGAIN || err == -ENOMEM || err == -ENOBUFS; if (zcopy_used) { if (vq->heads[ubuf->desc].len == VHOST_DMA_IN_PROGRESS) vhost_net_ubuf_put(ubufs); if (retry) nvq->upend_idx = ((unsigned)nvq->upend_idx - 1) % UIO_MAXIOV; else vq->heads[ubuf->desc].len = VHOST_DMA_DONE_LEN; } if (retry) { vhost_discard_vq_desc(vq, 1); vhost_net_enable_vq(net, vq); break; } pr_debug("Fail to send packet: err %d", err); } else if (unlikely(err != len)) pr_debug("Truncated TX packet: " " len %d != %zd\n", err, len); if (!zcopy_used) vhost_add_used_and_signal(&net->dev, vq, head, 0); else vhost_zerocopy_signal_used(net, vq); vhost_net_tx_packet(net); } while (likely(!vhost_exceeds_weight(vq, ++sent_pkts, total_len))); } /* Expects to be always run from workqueue - which acts as * read-size critical section for our kind of RCU. */ static void handle_tx(struct vhost_net *net) { struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX]; struct vhost_virtqueue *vq = &nvq->vq; struct socket *sock; mutex_lock_nested(&vq->mutex, VHOST_NET_VQ_TX); sock = vhost_vq_get_backend(vq); if (!sock) goto out; if (!vq_meta_prefetch(vq)) goto out; vhost_disable_notify(&net->dev, vq); vhost_net_disable_vq(net, vq); if (vhost_sock_zcopy(sock)) handle_tx_zerocopy(net, sock); else handle_tx_copy(net, sock); out: mutex_unlock(&vq->mutex); } static int peek_head_len(struct vhost_net_virtqueue *rvq, struct sock *sk) { struct sk_buff *head; int len = 0; unsigned long flags; if (rvq->rx_ring) return vhost_net_buf_peek(rvq); spin_lock_irqsave(&sk->sk_receive_queue.lock, flags); head = skb_peek(&sk->sk_receive_queue); if (likely(head)) { len = head->len; if (skb_vlan_tag_present(head)) len += VLAN_HLEN; } spin_unlock_irqrestore(&sk->sk_receive_queue.lock, flags); return len; } static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk, bool *busyloop_intr) { struct vhost_net_virtqueue *rnvq = &net->vqs[VHOST_NET_VQ_RX]; struct vhost_net_virtqueue *tnvq = &net->vqs[VHOST_NET_VQ_TX]; struct vhost_virtqueue *rvq = &rnvq->vq; struct vhost_virtqueue *tvq = &tnvq->vq; int len = peek_head_len(rnvq, sk); if (!len && rvq->busyloop_timeout) { /* Flush batched heads first */ vhost_net_signal_used(rnvq); /* Both tx vq and rx socket were polled here */ vhost_net_busy_poll(net, rvq, tvq, busyloop_intr, true); len = peek_head_len(rnvq, sk); } return len; } /* This is a multi-buffer version of vhost_get_desc, that works if * vq has read descriptors only. * @vq - the relevant virtqueue * @datalen - data length we'll be reading * @iovcount - returned count of io vectors we fill * @log - vhost log * @log_num - log offset * @quota - headcount quota, 1 for big buffer * returns number of buffer heads allocated, negative on error */ static int get_rx_bufs(struct vhost_virtqueue *vq, struct vring_used_elem *heads, int datalen, unsigned *iovcount, struct vhost_log *log, unsigned *log_num, unsigned int quota) { unsigned int out, in; int seg = 0; int headcount = 0; unsigned d; int r, nlogs = 0; /* len is always initialized before use since we are always called with * datalen > 0. */ u32 len; while (datalen > 0 && headcount < quota) { if (unlikely(seg >= UIO_MAXIOV)) { r = -ENOBUFS; goto err; } r = vhost_get_vq_desc(vq, vq->iov + seg, ARRAY_SIZE(vq->iov) - seg, &out, &in, log, log_num); if (unlikely(r < 0)) goto err; d = r; if (d == vq->num) { r = 0; goto err; } if (unlikely(out || in <= 0)) { vq_err(vq, "unexpected descriptor format for RX: " "out %d, in %d\n", out, in); r = -EINVAL; goto err; } if (unlikely(log)) { nlogs += *log_num; log += *log_num; } heads[headcount].id = cpu_to_vhost32(vq, d); len = iov_length(vq->iov + seg, in); heads[headcount].len = cpu_to_vhost32(vq, len); datalen -= len; ++headcount; seg += in; } heads[headcount - 1].len = cpu_to_vhost32(vq, len + datalen); *iovcount = seg; if (unlikely(log)) *log_num = nlogs; /* Detect overrun */ if (unlikely(datalen > 0)) { r = UIO_MAXIOV + 1; goto err; } return headcount; err: vhost_discard_vq_desc(vq, headcount); return r; } /* Expects to be always run from workqueue - which acts as * read-size critical section for our kind of RCU. */ static void handle_rx(struct vhost_net *net) { struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_RX]; struct vhost_virtqueue *vq = &nvq->vq; unsigned in, log; struct vhost_log *vq_log; struct msghdr msg = { .msg_name = NULL, .msg_namelen = 0, .msg_control = NULL, /* FIXME: get and handle RX aux data. */ .msg_controllen = 0, .msg_flags = MSG_DONTWAIT, }; struct virtio_net_hdr hdr = { .flags = 0, .gso_type = VIRTIO_NET_HDR_GSO_NONE }; size_t total_len = 0; int err, mergeable; s16 headcount; size_t vhost_hlen, sock_hlen; size_t vhost_len, sock_len; bool busyloop_intr = false; bool set_num_buffers; struct socket *sock; struct iov_iter fixup; __virtio16 num_buffers; int recv_pkts = 0; mutex_lock_nested(&vq->mutex, VHOST_NET_VQ_RX); sock = vhost_vq_get_backend(vq); if (!sock) goto out; if (!vq_meta_prefetch(vq)) goto out; vhost_disable_notify(&net->dev, vq); vhost_net_disable_vq(net, vq); vhost_hlen = nvq->vhost_hlen; sock_hlen = nvq->sock_hlen; vq_log = unlikely(vhost_has_feature(vq, VHOST_F_LOG_ALL)) ? vq->log : NULL; mergeable = vhost_has_feature(vq, VIRTIO_NET_F_MRG_RXBUF); set_num_buffers = mergeable || vhost_has_feature(vq, VIRTIO_F_VERSION_1); do { sock_len = vhost_net_rx_peek_head_len(net, sock->sk, &busyloop_intr); if (!sock_len) break; sock_len += sock_hlen; vhost_len = sock_len + vhost_hlen; headcount = get_rx_bufs(vq, vq->heads + nvq->done_idx, vhost_len, &in, vq_log, &log, likely(mergeable) ? UIO_MAXIOV : 1); /* On error, stop handling until the next kick. */ if (unlikely(headcount < 0)) goto out; /* OK, now we need to know about added descriptors. */ if (!headcount) { if (unlikely(busyloop_intr)) { vhost_poll_queue(&vq->poll); } else if (unlikely(vhost_enable_notify(&net->dev, vq))) { /* They have slipped one in as we were * doing that: check again. */ vhost_disable_notify(&net->dev, vq); continue; } /* Nothing new? Wait for eventfd to tell us * they refilled. */ goto out; } busyloop_intr = false; if (nvq->rx_ring) msg.msg_control = vhost_net_buf_consume(&nvq->rxq); /* On overrun, truncate and discard */ if (unlikely(headcount > UIO_MAXIOV)) { iov_iter_init(&msg.msg_iter, ITER_DEST, vq->iov, 1, 1); err = sock->ops->recvmsg(sock, &msg, 1, MSG_DONTWAIT | MSG_TRUNC); pr_debug("Discarded rx packet: len %zd\n", sock_len); continue; } /* We don't need to be notified again. */ iov_iter_init(&msg.msg_iter, ITER_DEST, vq->iov, in, vhost_len); fixup = msg.msg_iter; if (unlikely((vhost_hlen))) { /* We will supply the header ourselves * TODO: support TSO. */ iov_iter_advance(&msg.msg_iter, vhost_hlen); } err = sock->ops->recvmsg(sock, &msg, sock_len, MSG_DONTWAIT | MSG_TRUNC); /* Userspace might have consumed the packet meanwhile: * it's not supposed to do this usually, but might be hard * to prevent. Discard data we got (if any) and keep going. */ if (unlikely(err != sock_len)) { pr_debug("Discarded rx packet: " " len %d, expected %zd\n", err, sock_len); vhost_discard_vq_desc(vq, headcount); continue; } /* Supply virtio_net_hdr if VHOST_NET_F_VIRTIO_NET_HDR */ if (unlikely(vhost_hlen)) { if (copy_to_iter(&hdr, sizeof(hdr), &fixup) != sizeof(hdr)) { vq_err(vq, "Unable to write vnet_hdr " "at addr %p\n", vq->iov->iov_base); goto out; } } else { /* Header came from socket; we'll need to patch * ->num_buffers over if VIRTIO_NET_F_MRG_RXBUF */ iov_iter_advance(&fixup, sizeof(hdr)); } /* TODO: Should check and handle checksum. */ num_buffers = cpu_to_vhost16(vq, headcount); if (likely(set_num_buffers) && copy_to_iter(&num_buffers, sizeof num_buffers, &fixup) != sizeof num_buffers) { vq_err(vq, "Failed num_buffers write"); vhost_discard_vq_desc(vq, headcount); goto out; } nvq->done_idx += headcount; if (nvq->done_idx > VHOST_NET_BATCH) vhost_net_signal_used(nvq); if (unlikely(vq_log)) vhost_log_write(vq, vq_log, log, vhost_len, vq->iov, in); total_len += vhost_len; } while (likely(!vhost_exceeds_weight(vq, ++recv_pkts, total_len))); if (unlikely(busyloop_intr)) vhost_poll_queue(&vq->poll); else if (!sock_len) vhost_net_enable_vq(net, vq); out: vhost_net_signal_used(nvq); mutex_unlock(&vq->mutex); } static void handle_tx_kick(struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue, poll.work); struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev); handle_tx(net); } static void handle_rx_kick(struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue, poll.work); struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev); handle_rx(net); } static void handle_tx_net(struct vhost_work *work) { struct vhost_net *net = container_of(work, struct vhost_net, poll[VHOST_NET_VQ_TX].work); handle_tx(net); } static void handle_rx_net(struct vhost_work *work) { struct vhost_net *net = container_of(work, struct vhost_net, poll[VHOST_NET_VQ_RX].work); handle_rx(net); } static int vhost_net_open(struct inode *inode, struct file *f) { struct vhost_net *n; struct vhost_dev *dev; struct vhost_virtqueue **vqs; void **queue; struct xdp_buff *xdp; int i; n = kvmalloc(sizeof *n, GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!n) return -ENOMEM; vqs = kmalloc_array(VHOST_NET_VQ_MAX, sizeof(*vqs), GFP_KERNEL); if (!vqs) { kvfree(n); return -ENOMEM; } queue = kmalloc_array(VHOST_NET_BATCH, sizeof(void *), GFP_KERNEL); if (!queue) { kfree(vqs); kvfree(n); return -ENOMEM; } n->vqs[VHOST_NET_VQ_RX].rxq.queue = queue; xdp = kmalloc_array(VHOST_NET_BATCH, sizeof(*xdp), GFP_KERNEL); if (!xdp) { kfree(vqs); kvfree(n); kfree(queue); return -ENOMEM; } n->vqs[VHOST_NET_VQ_TX].xdp = xdp; dev = &n->dev; vqs[VHOST_NET_VQ_TX] = &n->vqs[VHOST_NET_VQ_TX].vq; vqs[VHOST_NET_VQ_RX] = &n->vqs[VHOST_NET_VQ_RX].vq; n->vqs[VHOST_NET_VQ_TX].vq.handle_kick = handle_tx_kick; n->vqs[VHOST_NET_VQ_RX].vq.handle_kick = handle_rx_kick; for (i = 0; i < VHOST_NET_VQ_MAX; i++) { n->vqs[i].ubufs = NULL; n->vqs[i].ubuf_info = NULL; n->vqs[i].upend_idx = 0; n->vqs[i].done_idx = 0; n->vqs[i].batched_xdp = 0; n->vqs[i].vhost_hlen = 0; n->vqs[i].sock_hlen = 0; n->vqs[i].rx_ring = NULL; vhost_net_buf_init(&n->vqs[i].rxq); } vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX, UIO_MAXIOV + VHOST_NET_BATCH, VHOST_NET_PKT_WEIGHT, VHOST_NET_WEIGHT, true, NULL); vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, EPOLLOUT, dev, vqs[VHOST_NET_VQ_TX]); vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, EPOLLIN, dev, vqs[VHOST_NET_VQ_RX]); f->private_data = n; page_frag_cache_init(&n->pf_cache); return 0; } static struct socket *vhost_net_stop_vq(struct vhost_net *n, struct vhost_virtqueue *vq) { struct socket *sock; struct vhost_net_virtqueue *nvq = container_of(vq, struct vhost_net_virtqueue, vq); mutex_lock(&vq->mutex); sock = vhost_vq_get_backend(vq); vhost_net_disable_vq(n, vq); vhost_vq_set_backend(vq, NULL); vhost_net_buf_unproduce(nvq); nvq->rx_ring = NULL; mutex_unlock(&vq->mutex); return sock; } static void vhost_net_stop(struct vhost_net *n, struct socket **tx_sock, struct socket **rx_sock) { *tx_sock = vhost_net_stop_vq(n, &n->vqs[VHOST_NET_VQ_TX].vq); *rx_sock = vhost_net_stop_vq(n, &n->vqs[VHOST_NET_VQ_RX].vq); } static void vhost_net_flush(struct vhost_net *n) { vhost_dev_flush(&n->dev); if (n->vqs[VHOST_NET_VQ_TX].ubufs) { mutex_lock(&n->vqs[VHOST_NET_VQ_TX].vq.mutex); n->tx_flush = true; mutex_unlock(&n->vqs[VHOST_NET_VQ_TX].vq.mutex); /* Wait for all lower device DMAs done. */ vhost_net_ubuf_put_and_wait(n->vqs[VHOST_NET_VQ_TX].ubufs); mutex_lock(&n->vqs[VHOST_NET_VQ_TX].vq.mutex); n->tx_flush = false; atomic_set(&n->vqs[VHOST_NET_VQ_TX].ubufs->refcount, 1); mutex_unlock(&n->vqs[VHOST_NET_VQ_TX].vq.mutex); } } static int vhost_net_release(struct inode *inode, struct file *f) { struct vhost_net *n = f->private_data; struct socket *tx_sock; struct socket *rx_sock; vhost_net_stop(n, &tx_sock, &rx_sock); vhost_net_flush(n); vhost_dev_stop(&n->dev); vhost_dev_cleanup(&n->dev); vhost_net_vq_reset(n); if (tx_sock) sockfd_put(tx_sock); if (rx_sock) sockfd_put(rx_sock); /* Make sure no callbacks are outstanding */ synchronize_rcu(); /* We do an extra flush before freeing memory, * since jobs can re-queue themselves. */ vhost_net_flush(n); kfree(n->vqs[VHOST_NET_VQ_RX].rxq.queue); kfree(n->vqs[VHOST_NET_VQ_TX].xdp); kfree(n->dev.vqs); page_frag_cache_drain(&n->pf_cache); kvfree(n); return 0; } static struct socket *get_raw_socket(int fd) { int r; struct socket *sock = sockfd_lookup(fd, &r); if (!sock) return ERR_PTR(-ENOTSOCK); /* Parameter checking */ if (sock->sk->sk_type != SOCK_RAW) { r = -ESOCKTNOSUPPORT; goto err; } if (sock->sk->sk_family != AF_PACKET) { r = -EPFNOSUPPORT; goto err; } return sock; err: sockfd_put(sock); return ERR_PTR(r); } static struct ptr_ring *get_tap_ptr_ring(struct file *file) { struct ptr_ring *ring; ring = tun_get_tx_ring(file); if (!IS_ERR(ring)) goto out; ring = tap_get_ptr_ring(file); if (!IS_ERR(ring)) goto out; ring = NULL; out: return ring; } static struct socket *get_tap_socket(int fd) { struct file *file = fget(fd); struct socket *sock; if (!file) return ERR_PTR(-EBADF); sock = tun_get_socket(file); if (!IS_ERR(sock)) return sock; sock = tap_get_socket(file); if (IS_ERR(sock)) fput(file); return sock; } static struct socket *get_socket(int fd) { struct socket *sock; /* special case to disable backend */ if (fd == -1) return NULL; sock = get_raw_socket(fd); if (!IS_ERR(sock)) return sock; sock = get_tap_socket(fd); if (!IS_ERR(sock)) return sock; return ERR_PTR(-ENOTSOCK); } static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) { struct socket *sock, *oldsock; struct vhost_virtqueue *vq; struct vhost_net_virtqueue *nvq; struct vhost_net_ubuf_ref *ubufs, *oldubufs = NULL; int r; mutex_lock(&n->dev.mutex); r = vhost_dev_check_owner(&n->dev); if (r) goto err; if (index >= VHOST_NET_VQ_MAX) { r = -ENOBUFS; goto err; } vq = &n->vqs[index].vq; nvq = &n->vqs[index]; mutex_lock(&vq->mutex); if (fd == -1) vhost_clear_msg(&n->dev); /* Verify that ring has been setup correctly. */ if (!vhost_vq_access_ok(vq)) { r = -EFAULT; goto err_vq; } sock = get_socket(fd); if (IS_ERR(sock)) { r = PTR_ERR(sock); goto err_vq; } /* start polling new socket */ oldsock = vhost_vq_get_backend(vq); if (sock != oldsock) { ubufs = vhost_net_ubuf_alloc(vq, sock && vhost_sock_zcopy(sock)); if (IS_ERR(ubufs)) { r = PTR_ERR(ubufs); goto err_ubufs; } vhost_net_disable_vq(n, vq); vhost_vq_set_backend(vq, sock); vhost_net_buf_unproduce(nvq); r = vhost_vq_init_access(vq); if (r) goto err_used; r = vhost_net_enable_vq(n, vq); if (r) goto err_used; if (index == VHOST_NET_VQ_RX) { if (sock) nvq->rx_ring = get_tap_ptr_ring(sock->file); else nvq->rx_ring = NULL; } oldubufs = nvq->ubufs; nvq->ubufs = ubufs; n->tx_packets = 0; n->tx_zcopy_err = 0; n->tx_flush = false; } mutex_unlock(&vq->mutex); if (oldubufs) { vhost_net_ubuf_put_wait_and_free(oldubufs); mutex_lock(&vq->mutex); vhost_zerocopy_signal_used(n, vq); mutex_unlock(&vq->mutex); } if (oldsock) { vhost_dev_flush(&n->dev); sockfd_put(oldsock); } mutex_unlock(&n->dev.mutex); return 0; err_used: vhost_vq_set_backend(vq, oldsock); vhost_net_enable_vq(n, vq); if (ubufs) vhost_net_ubuf_put_wait_and_free(ubufs); err_ubufs: if (sock) sockfd_put(sock); err_vq: mutex_unlock(&vq->mutex); err: mutex_unlock(&n->dev.mutex); return r; } static long vhost_net_reset_owner(struct vhost_net *n) { struct socket *tx_sock = NULL; struct socket *rx_sock = NULL; long err; struct vhost_iotlb *umem; mutex_lock(&n->dev.mutex); err = vhost_dev_check_owner(&n->dev); if (err) goto done; umem = vhost_dev_reset_owner_prepare(); if (!umem) { err = -ENOMEM; goto done; } vhost_net_stop(n, &tx_sock, &rx_sock); vhost_net_flush(n); vhost_dev_stop(&n->dev); vhost_dev_reset_owner(&n->dev, umem); vhost_net_vq_reset(n); done: mutex_unlock(&n->dev.mutex); if (tx_sock) sockfd_put(tx_sock); if (rx_sock) sockfd_put(rx_sock); return err; } static int vhost_net_set_features(struct vhost_net *n, u64 features) { size_t vhost_hlen, sock_hlen, hdr_len; int i; hdr_len = (features & ((1ULL << VIRTIO_NET_F_MRG_RXBUF) | (1ULL << VIRTIO_F_VERSION_1))) ? sizeof(struct virtio_net_hdr_mrg_rxbuf) : sizeof(struct virtio_net_hdr); if (features & (1 << VHOST_NET_F_VIRTIO_NET_HDR)) { /* vhost provides vnet_hdr */ vhost_hlen = hdr_len; sock_hlen = 0; } else { /* socket provides vnet_hdr */ vhost_hlen = 0; sock_hlen = hdr_len; } mutex_lock(&n->dev.mutex); if ((features & (1 << VHOST_F_LOG_ALL)) && !vhost_log_access_ok(&n->dev)) goto out_unlock; if ((features & (1ULL << VIRTIO_F_ACCESS_PLATFORM))) { if (vhost_init_device_iotlb(&n->dev)) goto out_unlock; } for (i = 0; i < VHOST_NET_VQ_MAX; ++i) { mutex_lock(&n->vqs[i].vq.mutex); n->vqs[i].vq.acked_features = features; n->vqs[i].vhost_hlen = vhost_hlen; n->vqs[i].sock_hlen = sock_hlen; mutex_unlock(&n->vqs[i].vq.mutex); } mutex_unlock(&n->dev.mutex); return 0; out_unlock: mutex_unlock(&n->dev.mutex); return -EFAULT; } static long vhost_net_set_owner(struct vhost_net *n) { int r; mutex_lock(&n->dev.mutex); if (vhost_dev_has_owner(&n->dev)) { r = -EBUSY; goto out; } r = vhost_net_set_ubuf_info(n); if (r) goto out; r = vhost_dev_set_owner(&n->dev); if (r) vhost_net_clear_ubuf_info(n); vhost_net_flush(n); out: mutex_unlock(&n->dev.mutex); return r; } static long vhost_net_ioctl(struct file *f, unsigned int ioctl, unsigned long arg) { struct vhost_net *n = f->private_data; void __user *argp = (void __user *)arg; u64 __user *featurep = argp; struct vhost_vring_file backend; u64 features; int r; switch (ioctl) { case VHOST_NET_SET_BACKEND: if (copy_from_user(&backend, argp, sizeof backend)) return -EFAULT; return vhost_net_set_backend(n, backend.index, backend.fd); case VHOST_GET_FEATURES: features = VHOST_NET_FEATURES; if (copy_to_user(featurep, &features, sizeof features)) return -EFAULT; return 0; case VHOST_SET_FEATURES: if (copy_from_user(&features, featurep, sizeof features)) return -EFAULT; if (features & ~VHOST_NET_FEATURES) return -EOPNOTSUPP; return vhost_net_set_features(n, features); case VHOST_GET_BACKEND_FEATURES: features = VHOST_NET_BACKEND_FEATURES; if (copy_to_user(featurep, &features, sizeof(features))) return -EFAULT; return 0; case VHOST_SET_BACKEND_FEATURES: if (copy_from_user(&features, featurep, sizeof(features))) return -EFAULT; if (features & ~VHOST_NET_BACKEND_FEATURES) return -EOPNOTSUPP; vhost_set_backend_features(&n->dev, features); return 0; case VHOST_RESET_OWNER: return vhost_net_reset_owner(n); case VHOST_SET_OWNER: return vhost_net_set_owner(n); default: mutex_lock(&n->dev.mutex); r = vhost_dev_ioctl(&n->dev, ioctl, argp); if (r == -ENOIOCTLCMD) r = vhost_vring_ioctl(&n->dev, ioctl, argp); else vhost_net_flush(n); mutex_unlock(&n->dev.mutex); return r; } } static ssize_t vhost_net_chr_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct vhost_net *n = file->private_data; struct vhost_dev *dev = &n->dev; int noblock = file->f_flags & O_NONBLOCK; return vhost_chr_read_iter(dev, to, noblock); } static ssize_t vhost_net_chr_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct vhost_net *n = file->private_data; struct vhost_dev *dev = &n->dev; return vhost_chr_write_iter(dev, from); } static __poll_t vhost_net_chr_poll(struct file *file, poll_table *wait) { struct vhost_net *n = file->private_data; struct vhost_dev *dev = &n->dev; return vhost_chr_poll(file, dev, wait); } static const struct file_operations vhost_net_fops = { .owner = THIS_MODULE, .release = vhost_net_release, .read_iter = vhost_net_chr_read_iter, .write_iter = vhost_net_chr_write_iter, .poll = vhost_net_chr_poll, .unlocked_ioctl = vhost_net_ioctl, .compat_ioctl = compat_ptr_ioctl, .open = vhost_net_open, .llseek = noop_llseek, }; static struct miscdevice vhost_net_misc = { .minor = VHOST_NET_MINOR, .name = "vhost-net", .fops = &vhost_net_fops, }; static int __init vhost_net_init(void) { if (experimental_zcopytx) vhost_net_enable_zcopy(VHOST_NET_VQ_TX); return misc_register(&vhost_net_misc); } module_init(vhost_net_init); static void __exit vhost_net_exit(void) { misc_deregister(&vhost_net_misc); } module_exit(vhost_net_exit); MODULE_VERSION("0.0.1"); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Michael S. Tsirkin"); MODULE_DESCRIPTION("Host kernel accelerator for virtio net"); MODULE_ALIAS_MISCDEV(VHOST_NET_MINOR); MODULE_ALIAS("devname:vhost-net"); |
| 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * LAPB release 002 * * This code REQUIRES 2.1.15 or higher/ NET3.038 * * History * LAPB 001 Jonathan Naylor Started Coding * LAPB 002 Jonathan Naylor New timer architecture. * 2000-10-29 Henner Eisen lapb_data_indication() return status. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/inet.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <net/sock.h> #include <linux/uaccess.h> #include <linux/fcntl.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/stat.h> #include <linux/init.h> #include <net/lapb.h> static LIST_HEAD(lapb_list); static DEFINE_RWLOCK(lapb_list_lock); /* * Free an allocated lapb control block. */ static void lapb_free_cb(struct lapb_cb *lapb) { kfree(lapb); } static __inline__ void lapb_hold(struct lapb_cb *lapb) { refcount_inc(&lapb->refcnt); } static __inline__ void lapb_put(struct lapb_cb *lapb) { if (refcount_dec_and_test(&lapb->refcnt)) lapb_free_cb(lapb); } /* * Socket removal during an interrupt is now safe. */ static void __lapb_remove_cb(struct lapb_cb *lapb) { if (lapb->node.next) { list_del(&lapb->node); lapb_put(lapb); } } /* * Add a socket to the bound sockets list. */ static void __lapb_insert_cb(struct lapb_cb *lapb) { list_add(&lapb->node, &lapb_list); lapb_hold(lapb); } static struct lapb_cb *__lapb_devtostruct(struct net_device *dev) { struct lapb_cb *lapb, *use = NULL; list_for_each_entry(lapb, &lapb_list, node) { if (lapb->dev == dev) { use = lapb; break; } } if (use) lapb_hold(use); return use; } static struct lapb_cb *lapb_devtostruct(struct net_device *dev) { struct lapb_cb *rc; read_lock_bh(&lapb_list_lock); rc = __lapb_devtostruct(dev); read_unlock_bh(&lapb_list_lock); return rc; } /* * Create an empty LAPB control block. */ static struct lapb_cb *lapb_create_cb(void) { struct lapb_cb *lapb = kzalloc(sizeof(*lapb), GFP_ATOMIC); if (!lapb) goto out; skb_queue_head_init(&lapb->write_queue); skb_queue_head_init(&lapb->ack_queue); timer_setup(&lapb->t1timer, NULL, 0); timer_setup(&lapb->t2timer, NULL, 0); lapb->t1timer_running = false; lapb->t2timer_running = false; lapb->t1 = LAPB_DEFAULT_T1; lapb->t2 = LAPB_DEFAULT_T2; lapb->n2 = LAPB_DEFAULT_N2; lapb->mode = LAPB_DEFAULT_MODE; lapb->window = LAPB_DEFAULT_WINDOW; lapb->state = LAPB_STATE_0; spin_lock_init(&lapb->lock); refcount_set(&lapb->refcnt, 1); out: return lapb; } int lapb_register(struct net_device *dev, const struct lapb_register_struct *callbacks) { struct lapb_cb *lapb; int rc = LAPB_BADTOKEN; write_lock_bh(&lapb_list_lock); lapb = __lapb_devtostruct(dev); if (lapb) { lapb_put(lapb); goto out; } lapb = lapb_create_cb(); rc = LAPB_NOMEM; if (!lapb) goto out; lapb->dev = dev; lapb->callbacks = callbacks; __lapb_insert_cb(lapb); lapb_start_t1timer(lapb); rc = LAPB_OK; out: write_unlock_bh(&lapb_list_lock); return rc; } EXPORT_SYMBOL(lapb_register); int lapb_unregister(struct net_device *dev) { struct lapb_cb *lapb; int rc = LAPB_BADTOKEN; write_lock_bh(&lapb_list_lock); lapb = __lapb_devtostruct(dev); if (!lapb) goto out; lapb_put(lapb); /* Wait for other refs to "lapb" to drop */ while (refcount_read(&lapb->refcnt) > 2) usleep_range(1, 10); spin_lock_bh(&lapb->lock); lapb_stop_t1timer(lapb); lapb_stop_t2timer(lapb); lapb_clear_queues(lapb); spin_unlock_bh(&lapb->lock); /* Wait for running timers to stop */ timer_delete_sync(&lapb->t1timer); timer_delete_sync(&lapb->t2timer); __lapb_remove_cb(lapb); lapb_put(lapb); rc = LAPB_OK; out: write_unlock_bh(&lapb_list_lock); return rc; } EXPORT_SYMBOL(lapb_unregister); int lapb_getparms(struct net_device *dev, struct lapb_parms_struct *parms) { int rc = LAPB_BADTOKEN; struct lapb_cb *lapb = lapb_devtostruct(dev); if (!lapb) goto out; spin_lock_bh(&lapb->lock); parms->t1 = lapb->t1 / HZ; parms->t2 = lapb->t2 / HZ; parms->n2 = lapb->n2; parms->n2count = lapb->n2count; parms->state = lapb->state; parms->window = lapb->window; parms->mode = lapb->mode; if (!timer_pending(&lapb->t1timer)) parms->t1timer = 0; else parms->t1timer = (lapb->t1timer.expires - jiffies) / HZ; if (!timer_pending(&lapb->t2timer)) parms->t2timer = 0; else parms->t2timer = (lapb->t2timer.expires - jiffies) / HZ; spin_unlock_bh(&lapb->lock); lapb_put(lapb); rc = LAPB_OK; out: return rc; } EXPORT_SYMBOL(lapb_getparms); int lapb_setparms(struct net_device *dev, struct lapb_parms_struct *parms) { int rc = LAPB_BADTOKEN; struct lapb_cb *lapb = lapb_devtostruct(dev); if (!lapb) goto out; spin_lock_bh(&lapb->lock); rc = LAPB_INVALUE; if (parms->t1 < 1 || parms->t2 < 1 || parms->n2 < 1) goto out_put; if (lapb->state == LAPB_STATE_0) { if (parms->mode & LAPB_EXTENDED) { if (parms->window < 1 || parms->window > 127) goto out_put; } else { if (parms->window < 1 || parms->window > 7) goto out_put; } lapb->mode = parms->mode; lapb->window = parms->window; } lapb->t1 = parms->t1 * HZ; lapb->t2 = parms->t2 * HZ; lapb->n2 = parms->n2; rc = LAPB_OK; out_put: spin_unlock_bh(&lapb->lock); lapb_put(lapb); out: return rc; } EXPORT_SYMBOL(lapb_setparms); int lapb_connect_request(struct net_device *dev) { struct lapb_cb *lapb = lapb_devtostruct(dev); int rc = LAPB_BADTOKEN; if (!lapb) goto out; spin_lock_bh(&lapb->lock); rc = LAPB_OK; if (lapb->state == LAPB_STATE_1) goto out_put; rc = LAPB_CONNECTED; if (lapb->state == LAPB_STATE_3 || lapb->state == LAPB_STATE_4) goto out_put; lapb_establish_data_link(lapb); lapb_dbg(0, "(%p) S0 -> S1\n", lapb->dev); lapb->state = LAPB_STATE_1; rc = LAPB_OK; out_put: spin_unlock_bh(&lapb->lock); lapb_put(lapb); out: return rc; } EXPORT_SYMBOL(lapb_connect_request); static int __lapb_disconnect_request(struct lapb_cb *lapb) { switch (lapb->state) { case LAPB_STATE_0: return LAPB_NOTCONNECTED; case LAPB_STATE_1: lapb_dbg(1, "(%p) S1 TX DISC(1)\n", lapb->dev); lapb_dbg(0, "(%p) S1 -> S0\n", lapb->dev); lapb_send_control(lapb, LAPB_DISC, LAPB_POLLON, LAPB_COMMAND); lapb->state = LAPB_STATE_0; lapb_start_t1timer(lapb); return LAPB_NOTCONNECTED; case LAPB_STATE_2: return LAPB_OK; } lapb_clear_queues(lapb); lapb->n2count = 0; lapb_send_control(lapb, LAPB_DISC, LAPB_POLLON, LAPB_COMMAND); lapb_start_t1timer(lapb); lapb_stop_t2timer(lapb); lapb->state = LAPB_STATE_2; lapb_dbg(1, "(%p) S3 DISC(1)\n", lapb->dev); lapb_dbg(0, "(%p) S3 -> S2\n", lapb->dev); return LAPB_OK; } int lapb_disconnect_request(struct net_device *dev) { struct lapb_cb *lapb = lapb_devtostruct(dev); int rc = LAPB_BADTOKEN; if (!lapb) goto out; spin_lock_bh(&lapb->lock); rc = __lapb_disconnect_request(lapb); spin_unlock_bh(&lapb->lock); lapb_put(lapb); out: return rc; } EXPORT_SYMBOL(lapb_disconnect_request); int lapb_data_request(struct net_device *dev, struct sk_buff *skb) { struct lapb_cb *lapb = lapb_devtostruct(dev); int rc = LAPB_BADTOKEN; if (!lapb) goto out; spin_lock_bh(&lapb->lock); rc = LAPB_NOTCONNECTED; if (lapb->state != LAPB_STATE_3 && lapb->state != LAPB_STATE_4) goto out_put; skb_queue_tail(&lapb->write_queue, skb); lapb_kick(lapb); rc = LAPB_OK; out_put: spin_unlock_bh(&lapb->lock); lapb_put(lapb); out: return rc; } EXPORT_SYMBOL(lapb_data_request); int lapb_data_received(struct net_device *dev, struct sk_buff *skb) { struct lapb_cb *lapb = lapb_devtostruct(dev); int rc = LAPB_BADTOKEN; if (lapb) { spin_lock_bh(&lapb->lock); lapb_data_input(lapb, skb); spin_unlock_bh(&lapb->lock); lapb_put(lapb); rc = LAPB_OK; } return rc; } EXPORT_SYMBOL(lapb_data_received); void lapb_connect_confirmation(struct lapb_cb *lapb, int reason) { if (lapb->callbacks->connect_confirmation) lapb->callbacks->connect_confirmation(lapb->dev, reason); } void lapb_connect_indication(struct lapb_cb *lapb, int reason) { if (lapb->callbacks->connect_indication) lapb->callbacks->connect_indication(lapb->dev, reason); } void lapb_disconnect_confirmation(struct lapb_cb *lapb, int reason) { if (lapb->callbacks->disconnect_confirmation) lapb->callbacks->disconnect_confirmation(lapb->dev, reason); } void lapb_disconnect_indication(struct lapb_cb *lapb, int reason) { if (lapb->callbacks->disconnect_indication) lapb->callbacks->disconnect_indication(lapb->dev, reason); } int lapb_data_indication(struct lapb_cb *lapb, struct sk_buff *skb) { if (lapb->callbacks->data_indication) return lapb->callbacks->data_indication(lapb->dev, skb); kfree_skb(skb); return NET_RX_SUCCESS; /* For now; must be != NET_RX_DROP */ } int lapb_data_transmit(struct lapb_cb *lapb, struct sk_buff *skb) { int used = 0; if (lapb->callbacks->data_transmit) { lapb->callbacks->data_transmit(lapb->dev, skb); used = 1; } return used; } /* Handle device status changes. */ static int lapb_device_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct lapb_cb *lapb; if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; if (dev->type != ARPHRD_X25) return NOTIFY_DONE; lapb = lapb_devtostruct(dev); if (!lapb) return NOTIFY_DONE; spin_lock_bh(&lapb->lock); switch (event) { case NETDEV_UP: lapb_dbg(0, "(%p) Interface up: %s\n", dev, dev->name); if (netif_carrier_ok(dev)) { lapb_dbg(0, "(%p): Carrier is already up: %s\n", dev, dev->name); if (lapb->mode & LAPB_DCE) { lapb_start_t1timer(lapb); } else { if (lapb->state == LAPB_STATE_0) { lapb->state = LAPB_STATE_1; lapb_establish_data_link(lapb); } } } break; case NETDEV_GOING_DOWN: if (netif_carrier_ok(dev)) __lapb_disconnect_request(lapb); break; case NETDEV_DOWN: lapb_dbg(0, "(%p) Interface down: %s\n", dev, dev->name); lapb_dbg(0, "(%p) S%d -> S0\n", dev, lapb->state); lapb_clear_queues(lapb); lapb->state = LAPB_STATE_0; lapb->n2count = 0; lapb_stop_t1timer(lapb); lapb_stop_t2timer(lapb); break; case NETDEV_CHANGE: if (netif_carrier_ok(dev)) { lapb_dbg(0, "(%p): Carrier detected: %s\n", dev, dev->name); if (lapb->mode & LAPB_DCE) { lapb_start_t1timer(lapb); } else { if (lapb->state == LAPB_STATE_0) { lapb->state = LAPB_STATE_1; lapb_establish_data_link(lapb); } } } else { lapb_dbg(0, "(%p) Carrier lost: %s\n", dev, dev->name); lapb_dbg(0, "(%p) S%d -> S0\n", dev, lapb->state); lapb_clear_queues(lapb); lapb->state = LAPB_STATE_0; lapb->n2count = 0; lapb_stop_t1timer(lapb); lapb_stop_t2timer(lapb); } break; } spin_unlock_bh(&lapb->lock); lapb_put(lapb); return NOTIFY_DONE; } static struct notifier_block lapb_dev_notifier = { .notifier_call = lapb_device_event, }; static int __init lapb_init(void) { return register_netdevice_notifier(&lapb_dev_notifier); } static void __exit lapb_exit(void) { WARN_ON(!list_empty(&lapb_list)); unregister_netdevice_notifier(&lapb_dev_notifier); } MODULE_AUTHOR("Jonathan Naylor <g4klx@g4klx.demon.co.uk>"); MODULE_DESCRIPTION("The X.25 Link Access Procedure B link layer protocol"); MODULE_LICENSE("GPL"); module_init(lapb_init); module_exit(lapb_exit); |
| 9 244 2 2 2 2 2 2 1 1 258 258 24 24 255 256 244 244 244 244 244 244 244 244 9 9 9 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2005 Silicon Graphics, Inc. * All Rights Reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_bit.h" #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_alloc.h" #include "xfs_bmap.h" #include "xfs_bmap_btree.h" #include "xfs_bmap_util.h" #include "xfs_trans.h" #include "xfs_trans_space.h" #include "xfs_icache.h" #include "xfs_rtalloc.h" #include "xfs_sb.h" #include "xfs_rtbitmap.h" #include "xfs_rtrmap_btree.h" #include "xfs_quota.h" #include "xfs_log_priv.h" #include "xfs_health.h" #include "xfs_da_format.h" #include "xfs_metafile.h" #include "xfs_rtgroup.h" #include "xfs_error.h" #include "xfs_trace.h" #include "xfs_rtrefcount_btree.h" #include "xfs_reflink.h" #include "xfs_zone_alloc.h" /* * Return whether there are any free extents in the size range given * by low and high, for the bitmap block bbno. */ STATIC int xfs_rtany_summary( struct xfs_rtalloc_args *args, int low, /* low log2 extent size */ int high, /* high log2 extent size */ xfs_fileoff_t bbno, /* bitmap block number */ int *maxlog) /* out: max log2 extent size free */ { uint8_t *rsum_cache = args->rtg->rtg_rsum_cache; int error; int log; /* loop counter, log2 of ext. size */ xfs_suminfo_t sum; /* summary data */ /* There are no extents at levels >= rsum_cache[bbno]. */ if (rsum_cache) { high = min(high, rsum_cache[bbno] - 1); if (low > high) { *maxlog = -1; return 0; } } /* * Loop over logs of extent sizes. */ for (log = high; log >= low; log--) { /* * Get one summary datum. */ error = xfs_rtget_summary(args, log, bbno, &sum); if (error) { return error; } /* * If there are any, return success. */ if (sum) { *maxlog = log; goto out; } } /* * Found nothing, return failure. */ *maxlog = -1; out: /* There were no extents at levels > log. */ if (rsum_cache && log + 1 < rsum_cache[bbno]) rsum_cache[bbno] = log + 1; return 0; } /* * Copy and transform the summary file, given the old and new * parameters in the mount structures. */ STATIC int xfs_rtcopy_summary( struct xfs_rtalloc_args *oargs, struct xfs_rtalloc_args *nargs) { xfs_fileoff_t bbno; /* bitmap block number */ int error; int log; /* summary level number (log length) */ xfs_suminfo_t sum; /* summary data */ for (log = oargs->mp->m_rsumlevels - 1; log >= 0; log--) { for (bbno = oargs->mp->m_sb.sb_rbmblocks - 1; (xfs_srtblock_t)bbno >= 0; bbno--) { error = xfs_rtget_summary(oargs, log, bbno, &sum); if (error) goto out; if (sum == 0) continue; error = xfs_rtmodify_summary(oargs, log, bbno, -sum); if (error) goto out; error = xfs_rtmodify_summary(nargs, log, bbno, sum); if (error) goto out; ASSERT(sum > 0); } } error = 0; out: xfs_rtbuf_cache_relse(oargs); return 0; } /* * Mark an extent specified by start and len allocated. * Updates all the summary information as well as the bitmap. */ STATIC int xfs_rtallocate_range( struct xfs_rtalloc_args *args, xfs_rtxnum_t start, /* start rtext to allocate */ xfs_rtxlen_t len) /* in/out: summary block number */ { struct xfs_mount *mp = args->mp; xfs_rtxnum_t end; /* end of the allocated rtext */ int error; xfs_rtxnum_t postblock = 0; /* first rtext allocated > end */ xfs_rtxnum_t preblock = 0; /* first rtext allocated < start */ end = start + len - 1; /* * Assume we're allocating out of the middle of a free extent. * We need to find the beginning and end of the extent so we can * properly update the summary. */ error = xfs_rtfind_back(args, start, &preblock); if (error) return error; /* * Find the next allocated block (end of free extent). */ error = xfs_rtfind_forw(args, end, args->rtg->rtg_extents - 1, &postblock); if (error) return error; /* * Decrement the summary information corresponding to the entire * (old) free extent. */ error = xfs_rtmodify_summary(args, xfs_highbit64(postblock + 1 - preblock), xfs_rtx_to_rbmblock(mp, preblock), -1); if (error) return error; /* * If there are blocks not being allocated at the front of the * old extent, add summary data for them to be free. */ if (preblock < start) { error = xfs_rtmodify_summary(args, xfs_highbit64(start - preblock), xfs_rtx_to_rbmblock(mp, preblock), 1); if (error) return error; } /* * If there are blocks not being allocated at the end of the * old extent, add summary data for them to be free. */ if (postblock > end) { error = xfs_rtmodify_summary(args, xfs_highbit64(postblock - end), xfs_rtx_to_rbmblock(mp, end + 1), 1); if (error) return error; } /* * Modify the bitmap to mark this extent allocated. */ return xfs_rtmodify_range(args, start, len, 0); } /* Reduce @rtxlen until it is a multiple of @prod. */ static inline xfs_rtxlen_t xfs_rtalloc_align_len( xfs_rtxlen_t rtxlen, xfs_rtxlen_t prod) { if (unlikely(prod > 1)) return rounddown(rtxlen, prod); return rtxlen; } /* * Make sure we don't run off the end of the rt volume. Be careful that * adjusting maxlen downwards doesn't cause us to fail the alignment checks. */ static inline xfs_rtxlen_t xfs_rtallocate_clamp_len( struct xfs_rtgroup *rtg, xfs_rtxnum_t startrtx, xfs_rtxlen_t rtxlen, xfs_rtxlen_t prod) { xfs_rtxlen_t ret; ret = min(rtg->rtg_extents, startrtx + rtxlen) - startrtx; return xfs_rtalloc_align_len(ret, prod); } /* * Attempt to allocate an extent minlen<=len<=maxlen starting from * bitmap block bbno. If we don't get maxlen then use prod to trim * the length, if given. Returns error; returns starting block in *rtx. * The lengths are all in rtextents. */ STATIC int xfs_rtallocate_extent_block( struct xfs_rtalloc_args *args, xfs_fileoff_t bbno, /* bitmap block number */ xfs_rtxlen_t minlen, /* minimum length to allocate */ xfs_rtxlen_t maxlen, /* maximum length to allocate */ xfs_rtxlen_t *len, /* out: actual length allocated */ xfs_rtxnum_t *nextp, /* out: next rtext to try */ xfs_rtxlen_t prod, /* extent product factor */ xfs_rtxnum_t *rtx) /* out: start rtext allocated */ { struct xfs_mount *mp = args->mp; xfs_rtxnum_t besti = -1; /* best rtext found so far */ xfs_rtxnum_t end; /* last rtext in chunk */ xfs_rtxnum_t i; /* current rtext trying */ xfs_rtxnum_t next; /* next rtext to try */ xfs_rtxlen_t scanlen; /* number of free rtx to look for */ xfs_rtxlen_t bestlen = 0; /* best length found so far */ int stat; /* status from internal calls */ int error; /* * Loop over all the extents starting in this bitmap block up to the * end of the rt volume, looking for one that's long enough. */ end = min(args->rtg->rtg_extents, xfs_rbmblock_to_rtx(mp, bbno + 1)) - 1; for (i = xfs_rbmblock_to_rtx(mp, bbno); i <= end; i++) { /* Make sure we don't scan off the end of the rt volume. */ scanlen = xfs_rtallocate_clamp_len(args->rtg, i, maxlen, prod); if (scanlen < minlen) break; /* * See if there's a free extent of scanlen starting at i. * If it's not so then next will contain the first non-free. */ error = xfs_rtcheck_range(args, i, scanlen, 1, &next, &stat); if (error) return error; if (stat) { /* * i to scanlen is all free, allocate and return that. */ *len = scanlen; *rtx = i; return 0; } /* * In the case where we have a variable-sized allocation * request, figure out how big this free piece is, * and if it's big enough for the minimum, and the best * so far, remember it. */ if (minlen < maxlen) { xfs_rtxnum_t thislen; /* this extent size */ thislen = next - i; if (thislen >= minlen && thislen > bestlen) { besti = i; bestlen = thislen; } } /* * If not done yet, find the start of the next free space. */ if (next >= end) break; error = xfs_rtfind_forw(args, next, end, &i); if (error) return error; } /* Searched the whole thing & didn't find a maxlen free extent. */ if (besti == -1) goto nospace; /* * Ensure bestlen is a multiple of prod, but don't return a too-short * extent. */ bestlen = xfs_rtalloc_align_len(bestlen, prod); if (bestlen < minlen) goto nospace; /* * Pick besti for bestlen & return that. */ *len = bestlen; *rtx = besti; return 0; nospace: /* Allocation failed. Set *nextp to the next block to try. */ *nextp = next; return -ENOSPC; } /* * Allocate an extent of length minlen<=len<=maxlen, starting at block * bno. If we don't get maxlen then use prod to trim the length, if given. * Returns error; returns starting block in *rtx. * The lengths are all in rtextents. */ STATIC int xfs_rtallocate_extent_exact( struct xfs_rtalloc_args *args, xfs_rtxnum_t start, /* starting rtext number to allocate */ xfs_rtxlen_t minlen, /* minimum length to allocate */ xfs_rtxlen_t maxlen, /* maximum length to allocate */ xfs_rtxlen_t *len, /* out: actual length allocated */ xfs_rtxlen_t prod, /* extent product factor */ xfs_rtxnum_t *rtx) /* out: start rtext allocated */ { xfs_rtxnum_t next; /* next rtext to try (dummy) */ xfs_rtxlen_t alloclen; /* candidate length */ xfs_rtxlen_t scanlen; /* number of free rtx to look for */ int isfree; /* extent is free */ int error; ASSERT(minlen % prod == 0); ASSERT(maxlen % prod == 0); /* Make sure we don't run off the end of the rt volume. */ scanlen = xfs_rtallocate_clamp_len(args->rtg, start, maxlen, prod); if (scanlen < minlen) return -ENOSPC; /* Check if the range in question (for scanlen) is free. */ error = xfs_rtcheck_range(args, start, scanlen, 1, &next, &isfree); if (error) return error; if (isfree) { /* start to scanlen is all free; allocate it. */ *len = scanlen; *rtx = start; return 0; } /* * If not, allocate what there is, if it's at least minlen. */ alloclen = next - start; if (alloclen < minlen) return -ENOSPC; /* Ensure alloclen is a multiple of prod. */ alloclen = xfs_rtalloc_align_len(alloclen, prod); if (alloclen < minlen) return -ENOSPC; *len = alloclen; *rtx = start; return 0; } /* * Allocate an extent of length minlen<=len<=maxlen, starting as near * to start as possible. If we don't get maxlen then use prod to trim * the length, if given. The lengths are all in rtextents. */ STATIC int xfs_rtallocate_extent_near( struct xfs_rtalloc_args *args, xfs_rtxnum_t start, /* starting rtext number to allocate */ xfs_rtxlen_t minlen, /* minimum length to allocate */ xfs_rtxlen_t maxlen, /* maximum length to allocate */ xfs_rtxlen_t *len, /* out: actual length allocated */ xfs_rtxlen_t prod, /* extent product factor */ xfs_rtxnum_t *rtx) /* out: start rtext allocated */ { struct xfs_mount *mp = args->mp; int maxlog; /* max useful extent from summary */ xfs_fileoff_t bbno; /* bitmap block number */ int error; int i; /* bitmap block offset (loop control) */ int j; /* secondary loop control */ int log2len; /* log2 of minlen */ xfs_rtxnum_t n; /* next rtext to try */ ASSERT(minlen % prod == 0); ASSERT(maxlen % prod == 0); /* * If the block number given is off the end, silently set it to the last * block. */ start = min(start, args->rtg->rtg_extents - 1); /* * Try the exact allocation first. */ error = xfs_rtallocate_extent_exact(args, start, minlen, maxlen, len, prod, rtx); if (error != -ENOSPC) return error; bbno = xfs_rtx_to_rbmblock(mp, start); i = 0; j = -1; ASSERT(minlen != 0); log2len = xfs_highbit32(minlen); /* * Loop over all bitmap blocks (bbno + i is current block). */ for (;;) { /* * Get summary information of extents of all useful levels * starting in this bitmap block. */ error = xfs_rtany_summary(args, log2len, mp->m_rsumlevels - 1, bbno + i, &maxlog); if (error) return error; /* * If there are any useful extents starting here, try * allocating one. */ if (maxlog >= 0) { xfs_extlen_t maxavail = min_t(xfs_rtblock_t, maxlen, (1ULL << (maxlog + 1)) - 1); /* * On the positive side of the starting location. */ if (i >= 0) { /* * Try to allocate an extent starting in * this block. */ error = xfs_rtallocate_extent_block(args, bbno + i, minlen, maxavail, len, &n, prod, rtx); if (error != -ENOSPC) return error; } /* * On the negative side of the starting location. */ else { /* i < 0 */ int maxblocks; /* * Loop backwards to find the end of the extent * we found in the realtime summary. * * maxblocks is the maximum possible number of * bitmap blocks from the start of the extent * to the end of the extent. */ if (maxlog == 0) maxblocks = 0; else if (maxlog < mp->m_blkbit_log) maxblocks = 1; else maxblocks = 2 << (maxlog - mp->m_blkbit_log); /* * We need to check bbno + i + maxblocks down to * bbno + i. We already checked bbno down to * bbno + j + 1, so we don't need to check those * again. */ j = min(i + maxblocks, j); for (; j >= i; j--) { error = xfs_rtallocate_extent_block(args, bbno + j, minlen, maxavail, len, &n, prod, rtx); if (error != -ENOSPC) return error; } } } /* * Loop control. If we were on the positive side, and there's * still more blocks on the negative side, go there. */ if (i > 0 && (int)bbno - i >= 0) i = -i; /* * If positive, and no more negative, but there are more * positive, go there. */ else if (i > 0 && (int)bbno + i < mp->m_sb.sb_rbmblocks - 1) i++; /* * If negative or 0 (just started), and there are positive * blocks to go, go there. The 0 case moves to block 1. */ else if (i <= 0 && (int)bbno - i < mp->m_sb.sb_rbmblocks - 1) i = 1 - i; /* * If negative or 0 and there are more negative blocks, * go there. */ else if (i <= 0 && (int)bbno + i > 0) i--; /* * Must be done. Return failure. */ else break; } return -ENOSPC; } static int xfs_rtalloc_sumlevel( struct xfs_rtalloc_args *args, int l, /* level number */ xfs_rtxlen_t minlen, /* minimum length to allocate */ xfs_rtxlen_t maxlen, /* maximum length to allocate */ xfs_rtxlen_t prod, /* extent product factor */ xfs_rtxlen_t *len, /* out: actual length allocated */ xfs_rtxnum_t *rtx) /* out: start rtext allocated */ { xfs_fileoff_t i; /* bitmap block number */ int error; for (i = 0; i < args->mp->m_sb.sb_rbmblocks; i++) { xfs_suminfo_t sum; /* summary information for extents */ xfs_rtxnum_t n; /* next rtext to be tried */ error = xfs_rtget_summary(args, l, i, &sum); if (error) return error; /* * Nothing there, on to the next block. */ if (!sum) continue; /* * Try allocating the extent. */ error = xfs_rtallocate_extent_block(args, i, minlen, maxlen, len, &n, prod, rtx); if (error != -ENOSPC) return error; /* * If the "next block to try" returned from the allocator is * beyond the next bitmap block, skip to that bitmap block. */ if (xfs_rtx_to_rbmblock(args->mp, n) > i + 1) i = xfs_rtx_to_rbmblock(args->mp, n) - 1; } return -ENOSPC; } /* * Allocate an extent of length minlen<=len<=maxlen, with no position * specified. If we don't get maxlen then use prod to trim * the length, if given. The lengths are all in rtextents. */ static int xfs_rtallocate_extent_size( struct xfs_rtalloc_args *args, xfs_rtxlen_t minlen, /* minimum length to allocate */ xfs_rtxlen_t maxlen, /* maximum length to allocate */ xfs_rtxlen_t *len, /* out: actual length allocated */ xfs_rtxlen_t prod, /* extent product factor */ xfs_rtxnum_t *rtx) /* out: start rtext allocated */ { int error; int l; /* level number (loop control) */ ASSERT(minlen % prod == 0); ASSERT(maxlen % prod == 0); ASSERT(maxlen != 0); /* * Loop over all the levels starting with maxlen. * * At each level, look at all the bitmap blocks, to see if there are * extents starting there that are long enough (>= maxlen). * * Note, only on the initial level can the allocation fail if the * summary says there's an extent. */ for (l = xfs_highbit32(maxlen); l < args->mp->m_rsumlevels; l++) { error = xfs_rtalloc_sumlevel(args, l, minlen, maxlen, prod, len, rtx); if (error != -ENOSPC) return error; } /* * Didn't find any maxlen blocks. Try smaller ones, unless we are * looking for a fixed size extent. */ if (minlen > --maxlen) return -ENOSPC; ASSERT(minlen != 0); ASSERT(maxlen != 0); /* * Loop over sizes, from maxlen down to minlen. * * This time, when we do the allocations, allow smaller ones to succeed, * but make sure the specified minlen/maxlen are in the possible range * for this summary level. */ for (l = xfs_highbit32(maxlen); l >= xfs_highbit32(minlen); l--) { error = xfs_rtalloc_sumlevel(args, l, max_t(xfs_rtxlen_t, minlen, 1 << l), min_t(xfs_rtxlen_t, maxlen, (1 << (l + 1)) - 1), prod, len, rtx); if (error != -ENOSPC) return error; } return -ENOSPC; } static void xfs_rtunmount_rtg( struct xfs_rtgroup *rtg) { int i; for (i = 0; i < XFS_RTGI_MAX; i++) xfs_rtginode_irele(&rtg->rtg_inodes[i]); if (!xfs_has_zoned(rtg_mount(rtg))) kvfree(rtg->rtg_rsum_cache); } static int xfs_alloc_rsum_cache( struct xfs_rtgroup *rtg, xfs_extlen_t rbmblocks) { /* * The rsum cache is initialized to the maximum value, which is * trivially an upper bound on the maximum level with any free extents. */ rtg->rtg_rsum_cache = kvmalloc(rbmblocks, GFP_KERNEL); if (!rtg->rtg_rsum_cache) return -ENOMEM; memset(rtg->rtg_rsum_cache, -1, rbmblocks); return 0; } /* * If we changed the rt extent size (meaning there was no rt volume previously) * and the root directory had EXTSZINHERIT and RTINHERIT set, it's possible * that the extent size hint on the root directory is no longer congruent with * the new rt extent size. Log the rootdir inode to fix this. */ static int xfs_growfs_rt_fixup_extsize( struct xfs_mount *mp) { struct xfs_inode *ip = mp->m_rootip; struct xfs_trans *tp; int error = 0; xfs_ilock(ip, XFS_IOLOCK_EXCL); if (!(ip->i_diflags & XFS_DIFLAG_RTINHERIT) || !(ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT)) goto out_iolock; error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_ichange, 0, 0, false, &tp); if (error) goto out_iolock; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); error = xfs_trans_commit(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); out_iolock: xfs_iunlock(ip, XFS_IOLOCK_EXCL); return error; } /* Ensure that the rtgroup metadata inode is loaded, creating it if neeeded. */ static int xfs_rtginode_ensure( struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type) { struct xfs_trans *tp; int error; if (rtg->rtg_inodes[type]) return 0; error = xfs_trans_alloc_empty(rtg_mount(rtg), &tp); if (error) return error; error = xfs_rtginode_load(rtg, type, tp); xfs_trans_cancel(tp); if (error != -ENOENT) return 0; return xfs_rtginode_create(rtg, type, true); } static struct xfs_mount * xfs_growfs_rt_alloc_fake_mount( const struct xfs_mount *mp, xfs_rfsblock_t rblocks, xfs_agblock_t rextsize) { struct xfs_mount *nmp; nmp = kmemdup(mp, sizeof(*mp), GFP_KERNEL); if (!nmp) return NULL; xfs_mount_sb_set_rextsize(nmp, &nmp->m_sb, rextsize); nmp->m_sb.sb_rblocks = rblocks; nmp->m_sb.sb_rextents = xfs_blen_to_rtbxlen(nmp, nmp->m_sb.sb_rblocks); nmp->m_sb.sb_rbmblocks = xfs_rtbitmap_blockcount(nmp); nmp->m_sb.sb_rextslog = xfs_compute_rextslog(nmp->m_sb.sb_rextents); if (xfs_has_rtgroups(nmp)) nmp->m_sb.sb_rgcount = howmany_64(nmp->m_sb.sb_rextents, nmp->m_sb.sb_rgextents); else nmp->m_sb.sb_rgcount = 1; nmp->m_rsumblocks = xfs_rtsummary_blockcount(nmp, &nmp->m_rsumlevels); if (rblocks > 0) nmp->m_features |= XFS_FEAT_REALTIME; /* recompute growfsrt reservation from new rsumsize */ xfs_trans_resv_calc(nmp, &nmp->m_resv); return nmp; } /* Free all the new space and return the number of extents actually freed. */ static int xfs_growfs_rt_free_new( struct xfs_rtgroup *rtg, struct xfs_rtalloc_args *nargs, xfs_rtbxlen_t *freed_rtx) { struct xfs_mount *mp = rtg_mount(rtg); xfs_rgnumber_t rgno = rtg_rgno(rtg); xfs_rtxnum_t start_rtx = 0, end_rtx; if (rgno < mp->m_sb.sb_rgcount) start_rtx = xfs_rtgroup_extents(mp, rgno); end_rtx = xfs_rtgroup_extents(nargs->mp, rgno); /* * Compute the first new extent that we want to free, being careful to * skip past a realtime superblock at the start of the realtime volume. */ if (xfs_has_rtsb(nargs->mp) && rgno == 0 && start_rtx == 0) start_rtx++; *freed_rtx = end_rtx - start_rtx; return xfs_rtfree_range(nargs, start_rtx, *freed_rtx); } static xfs_rfsblock_t xfs_growfs_rt_nrblocks( struct xfs_rtgroup *rtg, xfs_rfsblock_t nrblocks, xfs_agblock_t rextsize, xfs_fileoff_t bmbno) { struct xfs_mount *mp = rtg_mount(rtg); xfs_rfsblock_t step; step = (bmbno + 1) * mp->m_rtx_per_rbmblock * rextsize; if (xfs_has_rtgroups(mp)) { xfs_rfsblock_t rgblocks = mp->m_sb.sb_rgextents * rextsize; step = min(rgblocks, step) + rgblocks * rtg_rgno(rtg); } return min(nrblocks, step); } /* * If the post-grow filesystem will have an rtsb; we're initializing the first * rtgroup; and the filesystem didn't have a realtime section, write the rtsb * now, and attach the rtsb buffer to the real mount. */ static int xfs_growfs_rt_init_rtsb( const struct xfs_rtalloc_args *nargs, const struct xfs_rtgroup *rtg, const struct xfs_rtalloc_args *args) { struct xfs_mount *mp = args->mp; struct xfs_buf *rtsb_bp; int error; if (!xfs_has_rtsb(nargs->mp)) return 0; if (rtg_rgno(rtg) > 0) return 0; if (mp->m_sb.sb_rblocks) return 0; error = xfs_buf_get_uncached(mp->m_rtdev_targp, XFS_FSB_TO_BB(mp, 1), &rtsb_bp); if (error) return error; rtsb_bp->b_maps[0].bm_bn = XFS_RTSB_DADDR; rtsb_bp->b_ops = &xfs_rtsb_buf_ops; xfs_update_rtsb(rtsb_bp, mp->m_sb_bp); mp->m_rtsb_bp = rtsb_bp; error = xfs_bwrite(rtsb_bp); xfs_buf_unlock(rtsb_bp); if (error) return error; /* Initialize the rtrmap to reflect the rtsb. */ if (rtg_rmap(args->rtg) != NULL) error = xfs_rtrmapbt_init_rtsb(nargs->mp, args->rtg, args->tp); return error; } static void xfs_growfs_rt_sb_fields( struct xfs_trans *tp, const struct xfs_mount *nmp) { struct xfs_mount *mp = tp->t_mountp; if (nmp->m_sb.sb_rextsize != mp->m_sb.sb_rextsize) xfs_trans_mod_sb(tp, XFS_TRANS_SB_REXTSIZE, nmp->m_sb.sb_rextsize - mp->m_sb.sb_rextsize); if (nmp->m_sb.sb_rbmblocks != mp->m_sb.sb_rbmblocks) xfs_trans_mod_sb(tp, XFS_TRANS_SB_RBMBLOCKS, nmp->m_sb.sb_rbmblocks - mp->m_sb.sb_rbmblocks); if (nmp->m_sb.sb_rblocks != mp->m_sb.sb_rblocks) xfs_trans_mod_sb(tp, XFS_TRANS_SB_RBLOCKS, nmp->m_sb.sb_rblocks - mp->m_sb.sb_rblocks); if (nmp->m_sb.sb_rextents != mp->m_sb.sb_rextents) xfs_trans_mod_sb(tp, XFS_TRANS_SB_REXTENTS, nmp->m_sb.sb_rextents - mp->m_sb.sb_rextents); if (nmp->m_sb.sb_rextslog != mp->m_sb.sb_rextslog) xfs_trans_mod_sb(tp, XFS_TRANS_SB_REXTSLOG, nmp->m_sb.sb_rextslog - mp->m_sb.sb_rextslog); if (nmp->m_sb.sb_rgcount != mp->m_sb.sb_rgcount) xfs_trans_mod_sb(tp, XFS_TRANS_SB_RGCOUNT, nmp->m_sb.sb_rgcount - mp->m_sb.sb_rgcount); } static int xfs_growfs_rt_zoned( struct xfs_rtgroup *rtg, xfs_rfsblock_t nrblocks) { struct xfs_mount *mp = rtg_mount(rtg); struct xfs_mount *nmp; struct xfs_trans *tp; xfs_rtbxlen_t freed_rtx; int error; /* * Calculate new sb and mount fields for this round. Also ensure the * rtg_extents value is uptodate as the rtbitmap code relies on it. */ nmp = xfs_growfs_rt_alloc_fake_mount(mp, nrblocks, mp->m_sb.sb_rextsize); if (!nmp) return -ENOMEM; freed_rtx = nmp->m_sb.sb_rextents - mp->m_sb.sb_rextents; xfs_rtgroup_calc_geometry(nmp, rtg, rtg_rgno(rtg), nmp->m_sb.sb_rgcount, nmp->m_sb.sb_rextents); error = xfs_trans_alloc(mp, &M_RES(nmp)->tr_growrtfree, 0, 0, 0, &tp); if (error) goto out_free; xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP); xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_RMAP); xfs_growfs_rt_sb_fields(tp, nmp); xfs_trans_mod_sb(tp, XFS_TRANS_SB_FREXTENTS, freed_rtx); error = xfs_trans_commit(tp); if (error) goto out_free; /* * Ensure the mount RT feature flag is now set, and compute new * maxlevels for rt btrees. */ mp->m_features |= XFS_FEAT_REALTIME; xfs_rtrmapbt_compute_maxlevels(mp); xfs_rtrefcountbt_compute_maxlevels(mp); xfs_zoned_add_available(mp, freed_rtx); out_free: kfree(nmp); return error; } static int xfs_growfs_rt_bmblock( struct xfs_rtgroup *rtg, xfs_rfsblock_t nrblocks, xfs_agblock_t rextsize, xfs_fileoff_t bmbno) { struct xfs_mount *mp = rtg_mount(rtg); struct xfs_inode *rbmip = rtg_bitmap(rtg); struct xfs_inode *rsumip = rtg_summary(rtg); struct xfs_rtalloc_args args = { .mp = mp, .rtg = rtg, }; struct xfs_rtalloc_args nargs = { .rtg = rtg, }; struct xfs_mount *nmp; xfs_rtbxlen_t freed_rtx; int error; /* * Calculate new sb and mount fields for this round. Also ensure the * rtg_extents value is uptodate as the rtbitmap code relies on it. */ nmp = nargs.mp = xfs_growfs_rt_alloc_fake_mount(mp, xfs_growfs_rt_nrblocks(rtg, nrblocks, rextsize, bmbno), rextsize); if (!nmp) return -ENOMEM; xfs_rtgroup_calc_geometry(nmp, rtg, rtg_rgno(rtg), nmp->m_sb.sb_rgcount, nmp->m_sb.sb_rextents); /* * Recompute the growfsrt reservation from the new rsumsize, so that the * transaction below use the new, potentially larger value. * */ xfs_trans_resv_calc(nmp, &nmp->m_resv); error = xfs_trans_alloc(mp, &M_RES(nmp)->tr_growrtfree, 0, 0, 0, &args.tp); if (error) goto out_free; nargs.tp = args.tp; xfs_rtgroup_lock(args.rtg, XFS_RTGLOCK_BITMAP | XFS_RTGLOCK_RMAP); xfs_rtgroup_trans_join(args.tp, args.rtg, XFS_RTGLOCK_BITMAP | XFS_RTGLOCK_RMAP); /* * Update the bitmap inode's size ondisk and incore. We need to update * the incore size so that inode inactivation won't punch what it thinks * are "posteof" blocks. */ rbmip->i_disk_size = nmp->m_sb.sb_rbmblocks * nmp->m_sb.sb_blocksize; i_size_write(VFS_I(rbmip), rbmip->i_disk_size); xfs_trans_log_inode(args.tp, rbmip, XFS_ILOG_CORE); /* * Update the summary inode's size. We need to update the incore size * so that inode inactivation won't punch what it thinks are "posteof" * blocks. */ rsumip->i_disk_size = nmp->m_rsumblocks * nmp->m_sb.sb_blocksize; i_size_write(VFS_I(rsumip), rsumip->i_disk_size); xfs_trans_log_inode(args.tp, rsumip, XFS_ILOG_CORE); /* * Copy summary data from old to new sizes when the real size (not * block-aligned) changes. */ if (mp->m_sb.sb_rbmblocks != nmp->m_sb.sb_rbmblocks || mp->m_rsumlevels != nmp->m_rsumlevels) { error = xfs_rtcopy_summary(&args, &nargs); if (error) goto out_cancel; } error = xfs_growfs_rt_init_rtsb(&nargs, rtg, &args); if (error) goto out_cancel; /* * Update superblock fields. */ xfs_growfs_rt_sb_fields(args.tp, nmp); /* * Free the new extent. */ error = xfs_growfs_rt_free_new(rtg, &nargs, &freed_rtx); xfs_rtbuf_cache_relse(&nargs); if (error) goto out_cancel; /* * Mark more blocks free in the superblock. */ xfs_trans_mod_sb(args.tp, XFS_TRANS_SB_FREXTENTS, freed_rtx); /* * Update the calculated values in the real mount structure. */ mp->m_rsumlevels = nmp->m_rsumlevels; mp->m_rsumblocks = nmp->m_rsumblocks; /* * Recompute the growfsrt reservation from the new rsumsize. */ xfs_trans_resv_calc(mp, &mp->m_resv); error = xfs_trans_commit(args.tp); if (error) goto out_free; /* * Ensure the mount RT feature flag is now set, and compute new * maxlevels for rt btrees. */ mp->m_features |= XFS_FEAT_REALTIME; xfs_rtrmapbt_compute_maxlevels(mp); xfs_rtrefcountbt_compute_maxlevels(mp); kfree(nmp); return 0; out_cancel: xfs_trans_cancel(args.tp); out_free: kfree(nmp); return error; } static xfs_rtxnum_t xfs_last_rtgroup_extents( struct xfs_mount *mp) { return mp->m_sb.sb_rextents - ((xfs_rtxnum_t)(mp->m_sb.sb_rgcount - 1) * mp->m_sb.sb_rgextents); } /* * Calculate the last rbmblock currently used. * * This also deals with the case where there were no rtextents before. */ static xfs_fileoff_t xfs_last_rt_bmblock( struct xfs_rtgroup *rtg) { struct xfs_mount *mp = rtg_mount(rtg); xfs_rgnumber_t rgno = rtg_rgno(rtg); xfs_fileoff_t bmbno = 0; ASSERT(!mp->m_sb.sb_rgcount || rgno >= mp->m_sb.sb_rgcount - 1); if (mp->m_sb.sb_rgcount && rgno == mp->m_sb.sb_rgcount - 1) { xfs_rtxnum_t nrext = xfs_last_rtgroup_extents(mp); /* Also fill up the previous block if not entirely full. */ bmbno = xfs_rtbitmap_blockcount_len(mp, nrext); if (xfs_rtx_to_rbmword(mp, nrext) != 0) bmbno--; } return bmbno; } /* * Allocate space to the bitmap and summary files, as necessary. */ static int xfs_growfs_rt_alloc_blocks( struct xfs_rtgroup *rtg, xfs_rfsblock_t nrblocks, xfs_agblock_t rextsize, xfs_extlen_t *nrbmblocks) { struct xfs_mount *mp = rtg_mount(rtg); struct xfs_inode *rbmip = rtg_bitmap(rtg); struct xfs_inode *rsumip = rtg_summary(rtg); xfs_extlen_t orbmblocks = 0; xfs_extlen_t orsumblocks = 0; struct xfs_mount *nmp; int error = 0; nmp = xfs_growfs_rt_alloc_fake_mount(mp, nrblocks, rextsize); if (!nmp) return -ENOMEM; *nrbmblocks = nmp->m_sb.sb_rbmblocks; if (xfs_has_rtgroups(mp)) { /* * For file systems with the rtgroups feature, the RT bitmap and * summary are always fully allocated, which means that we never * need to grow the existing files. * * But we have to be careful to only fill the bitmap until the * end of the actually used range. */ if (rtg_rgno(rtg) == nmp->m_sb.sb_rgcount - 1) *nrbmblocks = xfs_rtbitmap_blockcount_len(nmp, xfs_last_rtgroup_extents(nmp)); if (mp->m_sb.sb_rgcount && rtg_rgno(rtg) == mp->m_sb.sb_rgcount - 1) goto out_free; } else { /* * Get the old block counts for bitmap and summary inodes. * These can't change since other growfs callers are locked out. */ orbmblocks = XFS_B_TO_FSB(mp, rbmip->i_disk_size); orsumblocks = XFS_B_TO_FSB(mp, rsumip->i_disk_size); } error = xfs_rtfile_initialize_blocks(rtg, XFS_RTGI_BITMAP, orbmblocks, nmp->m_sb.sb_rbmblocks, NULL); if (error) goto out_free; error = xfs_rtfile_initialize_blocks(rtg, XFS_RTGI_SUMMARY, orsumblocks, nmp->m_rsumblocks, NULL); out_free: kfree(nmp); return error; } static int xfs_growfs_rtg( struct xfs_mount *mp, xfs_rgnumber_t rgno, xfs_rfsblock_t nrblocks, xfs_agblock_t rextsize) { uint8_t *old_rsum_cache = NULL; xfs_extlen_t bmblocks; xfs_fileoff_t bmbno; struct xfs_rtgroup *rtg; unsigned int i; int error; rtg = xfs_rtgroup_grab(mp, rgno); if (!rtg) return -EINVAL; for (i = 0; i < XFS_RTGI_MAX; i++) { error = xfs_rtginode_ensure(rtg, i); if (error) goto out_rele; } if (xfs_has_zoned(mp)) { error = xfs_growfs_rt_zoned(rtg, nrblocks); goto out_rele; } error = xfs_growfs_rt_alloc_blocks(rtg, nrblocks, rextsize, &bmblocks); if (error) goto out_rele; if (bmblocks != rtg_mount(rtg)->m_sb.sb_rbmblocks) { old_rsum_cache = rtg->rtg_rsum_cache; error = xfs_alloc_rsum_cache(rtg, bmblocks); if (error) goto out_rele; } for (bmbno = xfs_last_rt_bmblock(rtg); bmbno < bmblocks; bmbno++) { error = xfs_growfs_rt_bmblock(rtg, nrblocks, rextsize, bmbno); if (error) goto out_error; } kvfree(old_rsum_cache); goto out_rele; out_error: /* * Reset rtg_extents to the old value if adding more blocks failed. */ xfs_rtgroup_calc_geometry(mp, rtg, rtg_rgno(rtg), mp->m_sb.sb_rgcount, mp->m_sb.sb_rextents); if (old_rsum_cache) { kvfree(rtg->rtg_rsum_cache); rtg->rtg_rsum_cache = old_rsum_cache; } out_rele: xfs_rtgroup_rele(rtg); return error; } int xfs_growfs_check_rtgeom( const struct xfs_mount *mp, xfs_rfsblock_t dblocks, xfs_rfsblock_t rblocks, xfs_extlen_t rextsize) { xfs_extlen_t min_logfsbs; struct xfs_mount *nmp; nmp = xfs_growfs_rt_alloc_fake_mount(mp, rblocks, rextsize); if (!nmp) return -ENOMEM; nmp->m_sb.sb_dblocks = dblocks; xfs_rtrmapbt_compute_maxlevels(nmp); xfs_rtrefcountbt_compute_maxlevels(nmp); xfs_trans_resv_calc(nmp, M_RES(nmp)); /* * New summary size can't be more than half the size of the log. This * prevents us from getting a log overflow, since we'll log basically * the whole summary file at once. */ min_logfsbs = min_t(xfs_extlen_t, xfs_log_calc_minimum_size(nmp), nmp->m_rsumblocks * 2); kfree(nmp); if (min_logfsbs > mp->m_sb.sb_logblocks) return -EINVAL; if (xfs_has_zoned(mp)) { uint32_t gblocks = mp->m_groups[XG_TYPE_RTG].blocks; uint32_t rem; if (rextsize != 1) return -EINVAL; div_u64_rem(mp->m_sb.sb_rblocks, gblocks, &rem); if (rem) { xfs_warn(mp, "new RT volume size (%lld) not aligned to RT group size (%d)", mp->m_sb.sb_rblocks, gblocks); return -EINVAL; } } return 0; } /* * Compute the new number of rt groups and ensure that /rtgroups exists. * * Changing the rtgroup size is not allowed (even if the rt volume hasn't yet * been initialized) because the userspace ABI doesn't support it. */ static int xfs_growfs_rt_prep_groups( struct xfs_mount *mp, xfs_rfsblock_t rblocks, xfs_extlen_t rextsize, xfs_rgnumber_t *new_rgcount) { int error; *new_rgcount = howmany_64(rblocks, mp->m_sb.sb_rgextents * rextsize); if (*new_rgcount > XFS_MAX_RGNUMBER) return -EINVAL; /* Make sure the /rtgroups dir has been created */ if (!mp->m_rtdirip) { struct xfs_trans *tp; error = xfs_trans_alloc_empty(mp, &tp); if (error) return error; error = xfs_rtginode_load_parent(tp); xfs_trans_cancel(tp); if (error == -ENOENT) error = xfs_rtginode_mkdir_parent(mp); if (error) return error; } return 0; } static bool xfs_grow_last_rtg( struct xfs_mount *mp) { if (!xfs_has_rtgroups(mp)) return true; if (mp->m_sb.sb_rgcount == 0) return false; return xfs_rtgroup_extents(mp, mp->m_sb.sb_rgcount - 1) <= mp->m_sb.sb_rgextents; } /* * Read in the last block of the RT device to make sure it is accessible. */ static int xfs_rt_check_size( struct xfs_mount *mp, xfs_rfsblock_t last_block) { xfs_daddr_t daddr = XFS_FSB_TO_BB(mp, last_block); struct xfs_buf *bp; int error; if (XFS_BB_TO_FSB(mp, daddr) != last_block) { xfs_warn(mp, "RT device size overflow: %llu != %llu", XFS_BB_TO_FSB(mp, daddr), last_block); return -EFBIG; } error = xfs_buf_read_uncached(mp->m_rtdev_targp, XFS_FSB_TO_BB(mp, mp->m_sb.sb_rtstart) + daddr, XFS_FSB_TO_BB(mp, 1), &bp, NULL); if (error) xfs_warn(mp, "cannot read last RT device sector (%lld)", last_block); else xfs_buf_relse(bp); return error; } /* * Grow the realtime area of the filesystem. */ int xfs_growfs_rt( struct xfs_mount *mp, struct xfs_growfs_rt *in) { xfs_rgnumber_t old_rgcount = mp->m_sb.sb_rgcount; xfs_rgnumber_t new_rgcount = 1; xfs_rgnumber_t rgno; xfs_agblock_t old_rextsize = mp->m_sb.sb_rextsize; int error; if (!capable(CAP_SYS_ADMIN)) return -EPERM; /* Needs to have been mounted with an rt device. */ if (!XFS_IS_REALTIME_MOUNT(mp)) return -EINVAL; if (!mutex_trylock(&mp->m_growlock)) return -EWOULDBLOCK; /* Shrink not supported. */ error = -EINVAL; if (in->newblocks <= mp->m_sb.sb_rblocks) goto out_unlock; /* Can only change rt extent size when adding rt volume. */ if (mp->m_sb.sb_rblocks > 0 && in->extsize != mp->m_sb.sb_rextsize) goto out_unlock; /* Range check the extent size. */ if (XFS_FSB_TO_B(mp, in->extsize) > XFS_MAX_RTEXTSIZE || XFS_FSB_TO_B(mp, in->extsize) < XFS_MIN_RTEXTSIZE) goto out_unlock; /* Check for features supported only on rtgroups filesystems. */ error = -EOPNOTSUPP; if (!xfs_has_rtgroups(mp)) { if (xfs_has_rmapbt(mp)) goto out_unlock; if (xfs_has_quota(mp)) goto out_unlock; if (xfs_has_reflink(mp)) goto out_unlock; } else if (xfs_has_reflink(mp) && !xfs_reflink_supports_rextsize(mp, in->extsize)) goto out_unlock; error = xfs_sb_validate_fsb_count(&mp->m_sb, in->newblocks); if (error) goto out_unlock; error = xfs_rt_check_size(mp, in->newblocks - 1); if (error) goto out_unlock; /* * Calculate new parameters. These are the final values to be reached. */ error = -EINVAL; if (in->newblocks < in->extsize) goto out_unlock; /* Make sure the new fs size won't cause problems with the log. */ error = xfs_growfs_check_rtgeom(mp, mp->m_sb.sb_dblocks, in->newblocks, in->extsize); if (error) goto out_unlock; if (xfs_has_rtgroups(mp)) { error = xfs_growfs_rt_prep_groups(mp, in->newblocks, in->extsize, &new_rgcount); if (error) goto out_unlock; } if (xfs_grow_last_rtg(mp)) { error = xfs_growfs_rtg(mp, old_rgcount - 1, in->newblocks, in->extsize); if (error) goto out_unlock; } for (rgno = old_rgcount; rgno < new_rgcount; rgno++) { xfs_rtbxlen_t rextents = div_u64(in->newblocks, in->extsize); error = xfs_rtgroup_alloc(mp, rgno, new_rgcount, rextents); if (error) goto out_unlock; error = xfs_growfs_rtg(mp, rgno, in->newblocks, in->extsize); if (error) { struct xfs_rtgroup *rtg; rtg = xfs_rtgroup_grab(mp, rgno); if (!WARN_ON_ONCE(!rtg)) { xfs_rtunmount_rtg(rtg); xfs_rtgroup_rele(rtg); xfs_rtgroup_free(mp, rgno); } break; } } if (!error && old_rextsize != in->extsize) error = xfs_growfs_rt_fixup_extsize(mp); /* * Update secondary superblocks now the physical grow has completed. * * Also do this in case of an error as we might have already * successfully updated one or more RTGs and incremented sb_rgcount. */ if (!xfs_is_shutdown(mp)) { int error2 = xfs_update_secondary_sbs(mp); if (!error) error = error2; /* Reset the rt metadata btree space reservations. */ error2 = xfs_metafile_resv_init(mp); if (error2 && error2 != -ENOSPC) error = error2; } out_unlock: mutex_unlock(&mp->m_growlock); return error; } /* Read the realtime superblock and attach it to the mount. */ int xfs_rtmount_readsb( struct xfs_mount *mp) { struct xfs_buf *bp; int error; if (!xfs_has_rtsb(mp)) return 0; if (mp->m_sb.sb_rblocks == 0) return 0; if (mp->m_rtdev_targp == NULL) { xfs_warn(mp, "Filesystem has a realtime volume, use rtdev=device option"); return -ENODEV; } /* m_blkbb_log is not set up yet */ error = xfs_buf_read_uncached(mp->m_rtdev_targp, XFS_RTSB_DADDR, mp->m_sb.sb_blocksize >> BBSHIFT, &bp, &xfs_rtsb_buf_ops); if (error) { xfs_warn(mp, "rt sb validate failed with error %d.", error); /* bad CRC means corrupted metadata */ if (error == -EFSBADCRC) error = -EFSCORRUPTED; return error; } mp->m_rtsb_bp = bp; xfs_buf_unlock(bp); return 0; } /* Detach the realtime superblock from the mount and free it. */ void xfs_rtmount_freesb( struct xfs_mount *mp) { struct xfs_buf *bp = mp->m_rtsb_bp; if (!bp) return; xfs_buf_lock(bp); mp->m_rtsb_bp = NULL; xfs_buf_relse(bp); } /* * Initialize realtime fields in the mount structure. */ int /* error */ xfs_rtmount_init( struct xfs_mount *mp) /* file system mount structure */ { if (mp->m_sb.sb_rblocks == 0) return 0; if (mp->m_rtdev_targp == NULL) { xfs_warn(mp, "Filesystem has a realtime volume, use rtdev=device option"); return -ENODEV; } mp->m_rsumblocks = xfs_rtsummary_blockcount(mp, &mp->m_rsumlevels); return xfs_rt_check_size(mp, mp->m_sb.sb_rblocks - 1); } static int xfs_rtalloc_count_frextent( struct xfs_rtgroup *rtg, struct xfs_trans *tp, const struct xfs_rtalloc_rec *rec, void *priv) { uint64_t *valp = priv; *valp += rec->ar_extcount; return 0; } /* * Reinitialize the number of free realtime extents from the realtime bitmap. * Callers must ensure that there is no other activity in the filesystem. */ int xfs_rtalloc_reinit_frextents( struct xfs_mount *mp) { uint64_t val = 0; int error; struct xfs_rtgroup *rtg = NULL; while ((rtg = xfs_rtgroup_next(mp, rtg))) { xfs_rtgroup_lock(rtg, XFS_RTGLOCK_BITMAP_SHARED); error = xfs_rtalloc_query_all(rtg, NULL, xfs_rtalloc_count_frextent, &val); xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_BITMAP_SHARED); if (error) { xfs_rtgroup_rele(rtg); return error; } } spin_lock(&mp->m_sb_lock); mp->m_sb.sb_frextents = val; spin_unlock(&mp->m_sb_lock); xfs_set_freecounter(mp, XC_FREE_RTEXTENTS, mp->m_sb.sb_frextents); return 0; } /* * Read in the bmbt of an rt metadata inode so that we never have to load them * at runtime. This enables the use of shared ILOCKs for rtbitmap scans. Use * an empty transaction to avoid deadlocking on loops in the bmbt. */ static inline int xfs_rtmount_iread_extents( struct xfs_trans *tp, struct xfs_inode *ip) { int error; xfs_ilock(ip, XFS_ILOCK_EXCL); error = xfs_iread_extents(tp, ip, XFS_DATA_FORK); if (error) goto out_unlock; if (xfs_inode_has_attr_fork(ip)) { error = xfs_iread_extents(tp, ip, XFS_ATTR_FORK); if (error) goto out_unlock; } out_unlock: xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; } static int xfs_rtmount_rtg( struct xfs_mount *mp, struct xfs_trans *tp, struct xfs_rtgroup *rtg) { int error, i; for (i = 0; i < XFS_RTGI_MAX; i++) { error = xfs_rtginode_load(rtg, i, tp); if (error) return error; if (rtg->rtg_inodes[i]) { error = xfs_rtmount_iread_extents(tp, rtg->rtg_inodes[i]); if (error) return error; } } if (xfs_has_zoned(mp)) return 0; return xfs_alloc_rsum_cache(rtg, mp->m_sb.sb_rbmblocks); } /* * Get the bitmap and summary inodes and the summary cache into the mount * structure at mount time. */ int xfs_rtmount_inodes( struct xfs_mount *mp) { struct xfs_trans *tp; struct xfs_rtgroup *rtg = NULL; int error; error = xfs_trans_alloc_empty(mp, &tp); if (error) return error; if (xfs_has_rtgroups(mp) && mp->m_sb.sb_rgcount > 0) { error = xfs_rtginode_load_parent(tp); if (error) goto out_cancel; } while ((rtg = xfs_rtgroup_next(mp, rtg))) { error = xfs_rtmount_rtg(mp, tp, rtg); if (error) { xfs_rtgroup_rele(rtg); xfs_rtunmount_inodes(mp); break; } } out_cancel: xfs_trans_cancel(tp); return error; } void xfs_rtunmount_inodes( struct xfs_mount *mp) { struct xfs_rtgroup *rtg = NULL; while ((rtg = xfs_rtgroup_next(mp, rtg))) xfs_rtunmount_rtg(rtg); xfs_rtginode_irele(&mp->m_rtdirip); } /* * Pick an extent for allocation at the start of a new realtime file. * Use the sequence number stored in the atime field of the bitmap inode. * Translate this to a fraction of the rtextents, and return the product * of rtextents and the fraction. * The fraction sequence is 0, 1/2, 1/4, 3/4, 1/8, ..., 7/8, 1/16, ... */ static xfs_rtxnum_t xfs_rtpick_extent( struct xfs_rtgroup *rtg, struct xfs_trans *tp, xfs_rtxlen_t len) /* allocation length (rtextents) */ { struct xfs_mount *mp = rtg_mount(rtg); struct xfs_inode *rbmip = rtg_bitmap(rtg); xfs_rtxnum_t b = 0; /* result rtext */ int log2; /* log of sequence number */ uint64_t resid; /* residual after log removed */ uint64_t seq; /* sequence number of file creation */ struct timespec64 ts; /* timespec in inode */ xfs_assert_ilocked(rbmip, XFS_ILOCK_EXCL); ts = inode_get_atime(VFS_I(rbmip)); if (!(rbmip->i_diflags & XFS_DIFLAG_NEWRTBM)) { rbmip->i_diflags |= XFS_DIFLAG_NEWRTBM; seq = 0; } else { seq = ts.tv_sec; } log2 = xfs_highbit64(seq); if (log2 != -1) { resid = seq - (1ULL << log2); b = (mp->m_sb.sb_rextents * ((resid << 1) + 1ULL)) >> (log2 + 1); if (b >= mp->m_sb.sb_rextents) div64_u64_rem(b, mp->m_sb.sb_rextents, &b); if (b + len > mp->m_sb.sb_rextents) b = mp->m_sb.sb_rextents - len; } ts.tv_sec = seq + 1; inode_set_atime_to_ts(VFS_I(rbmip), ts); xfs_trans_log_inode(tp, rbmip, XFS_ILOG_CORE); return b; } static void xfs_rtalloc_align_minmax( xfs_rtxlen_t *raminlen, xfs_rtxlen_t *ramaxlen, xfs_rtxlen_t *prod) { xfs_rtxlen_t newmaxlen = *ramaxlen; xfs_rtxlen_t newminlen = *raminlen; xfs_rtxlen_t slack; slack = newmaxlen % *prod; if (slack) newmaxlen -= slack; slack = newminlen % *prod; if (slack) newminlen += *prod - slack; /* * If adjusting for extent size hint alignment produces an invalid * min/max len combination, go ahead without it. */ if (newmaxlen < newminlen) { *prod = 1; return; } *ramaxlen = newmaxlen; *raminlen = newminlen; } /* Given a free extent, find any part of it that isn't busy, if possible. */ STATIC bool xfs_rtalloc_check_busy( struct xfs_rtalloc_args *args, xfs_rtxnum_t start, xfs_rtxlen_t minlen_rtx, xfs_rtxlen_t maxlen_rtx, xfs_rtxlen_t len_rtx, xfs_rtxlen_t prod, xfs_rtxnum_t rtx, xfs_rtxlen_t *reslen, xfs_rtxnum_t *resrtx, unsigned *busy_gen) { struct xfs_rtgroup *rtg = args->rtg; struct xfs_mount *mp = rtg_mount(rtg); xfs_agblock_t rgbno = xfs_rtx_to_rgbno(rtg, rtx); xfs_rgblock_t min_rgbno = xfs_rtx_to_rgbno(rtg, start); xfs_extlen_t minlen = xfs_rtxlen_to_extlen(mp, minlen_rtx); xfs_extlen_t len = xfs_rtxlen_to_extlen(mp, len_rtx); xfs_extlen_t diff; bool busy; busy = xfs_extent_busy_trim(rtg_group(rtg), minlen, xfs_rtxlen_to_extlen(mp, maxlen_rtx), &rgbno, &len, busy_gen); /* * If we have a largish extent that happens to start before min_rgbno, * see if we can shift it into range... */ if (rgbno < min_rgbno && rgbno + len > min_rgbno) { diff = min_rgbno - rgbno; if (len > diff) { rgbno += diff; len -= diff; } } if (prod > 1 && len >= minlen) { xfs_rgblock_t aligned_rgbno = roundup(rgbno, prod); diff = aligned_rgbno - rgbno; *resrtx = xfs_rgbno_to_rtx(mp, aligned_rgbno); *reslen = xfs_extlen_to_rtxlen(mp, diff >= len ? 0 : len - diff); } else { *resrtx = xfs_rgbno_to_rtx(mp, rgbno); *reslen = xfs_extlen_to_rtxlen(mp, len); } return busy; } /* * Adjust the given free extent so that it isn't busy, or flush the log and * wait for the space to become unbusy. Only needed for rtgroups. */ STATIC int xfs_rtallocate_adjust_for_busy( struct xfs_rtalloc_args *args, xfs_rtxnum_t start, xfs_rtxlen_t minlen, xfs_rtxlen_t maxlen, xfs_rtxlen_t *len, xfs_rtxlen_t prod, xfs_rtxnum_t *rtx) { xfs_rtxnum_t resrtx; xfs_rtxlen_t reslen; unsigned busy_gen; bool busy; int error; again: busy = xfs_rtalloc_check_busy(args, start, minlen, maxlen, *len, prod, *rtx, &reslen, &resrtx, &busy_gen); if (!busy) return 0; if (reslen < minlen || (start != 0 && resrtx != *rtx)) { /* * Enough of the extent was busy that we cannot satisfy the * allocation, or this is a near allocation and the start of * the extent is busy. Flush the log and wait for the busy * situation to resolve. */ trace_xfs_rtalloc_extent_busy(args->rtg, start, minlen, maxlen, *len, prod, *rtx, busy_gen); error = xfs_extent_busy_flush(args->tp, rtg_group(args->rtg), busy_gen, 0); if (error) return error; goto again; } /* Some of the free space wasn't busy, hand that back to the caller. */ trace_xfs_rtalloc_extent_busy_trim(args->rtg, *rtx, *len, resrtx, reslen); *len = reslen; *rtx = resrtx; return 0; } static int xfs_rtallocate_rtg( struct xfs_trans *tp, xfs_rgnumber_t rgno, xfs_rtblock_t bno_hint, xfs_rtxlen_t minlen, xfs_rtxlen_t maxlen, xfs_rtxlen_t prod, bool wasdel, bool initial_user_data, bool *rtlocked, xfs_rtblock_t *bno, xfs_extlen_t *blen) { struct xfs_rtalloc_args args = { .mp = tp->t_mountp, .tp = tp, }; xfs_rtxnum_t start = 0; xfs_rtxnum_t rtx; xfs_rtxlen_t len = 0; int error = 0; args.rtg = xfs_rtgroup_grab(args.mp, rgno); if (!args.rtg) return -ENOSPC; /* * We need to lock out modifications to both the RT bitmap and summary * inodes for finding free space in xfs_rtallocate_extent_{near,size} * and join the bitmap and summary inodes for the actual allocation * down in xfs_rtallocate_range. * * For RTG-enabled file system we don't want to join the inodes to the * transaction until we are committed to allocate to allocate from this * RTG so that only one inode of each type is locked at a time. * * But for pre-RTG file systems we need to already to join the bitmap * inode to the transaction for xfs_rtpick_extent, which bumps the * sequence number in it, so we'll have to join the inode to the * transaction early here. * * This is all a bit messy, but at least the mess is contained in * this function. */ if (!*rtlocked) { xfs_rtgroup_lock(args.rtg, XFS_RTGLOCK_BITMAP); if (!xfs_has_rtgroups(args.mp)) xfs_rtgroup_trans_join(tp, args.rtg, XFS_RTGLOCK_BITMAP); *rtlocked = true; } /* * For an allocation to an empty file at offset 0, pick an extent that * will space things out in the rt area. */ if (bno_hint != NULLFSBLOCK) start = xfs_rtb_to_rtx(args.mp, bno_hint); else if (!xfs_has_rtgroups(args.mp) && initial_user_data) start = xfs_rtpick_extent(args.rtg, tp, maxlen); if (start) { error = xfs_rtallocate_extent_near(&args, start, minlen, maxlen, &len, prod, &rtx); /* * If we can't allocate near a specific rt extent, try again * without locality criteria. */ if (error == -ENOSPC) { xfs_rtbuf_cache_relse(&args); error = 0; } } if (!error) { error = xfs_rtallocate_extent_size(&args, minlen, maxlen, &len, prod, &rtx); } if (error) { if (xfs_has_rtgroups(args.mp)) goto out_unlock; goto out_release; } if (xfs_has_rtgroups(args.mp)) { error = xfs_rtallocate_adjust_for_busy(&args, start, minlen, maxlen, &len, prod, &rtx); if (error) goto out_unlock; xfs_rtgroup_trans_join(tp, args.rtg, XFS_RTGLOCK_BITMAP); } error = xfs_rtallocate_range(&args, rtx, len); if (error) goto out_release; xfs_trans_mod_sb(tp, wasdel ? XFS_TRANS_SB_RES_FREXTENTS : XFS_TRANS_SB_FREXTENTS, -(long)len); *bno = xfs_rtx_to_rtb(args.rtg, rtx); *blen = xfs_rtxlen_to_extlen(args.mp, len); out_release: xfs_rtgroup_rele(args.rtg); xfs_rtbuf_cache_relse(&args); return error; out_unlock: xfs_rtgroup_unlock(args.rtg, XFS_RTGLOCK_BITMAP); *rtlocked = false; goto out_release; } int xfs_rtallocate_rtgs( struct xfs_trans *tp, xfs_fsblock_t bno_hint, xfs_rtxlen_t minlen, xfs_rtxlen_t maxlen, xfs_rtxlen_t prod, bool wasdel, bool initial_user_data, xfs_rtblock_t *bno, xfs_extlen_t *blen) { struct xfs_mount *mp = tp->t_mountp; xfs_rgnumber_t start_rgno, rgno; int error; /* * For now this just blindly iterates over the RTGs for an initial * allocation. We could try to keep an in-memory rtg_longest member * to avoid the locking when just looking for big enough free space, * but for now this keeps things simple. */ if (bno_hint != NULLFSBLOCK) start_rgno = xfs_rtb_to_rgno(mp, bno_hint); else start_rgno = (atomic_inc_return(&mp->m_rtgrotor) - 1) % mp->m_sb.sb_rgcount; rgno = start_rgno; do { bool rtlocked = false; error = xfs_rtallocate_rtg(tp, rgno, bno_hint, minlen, maxlen, prod, wasdel, initial_user_data, &rtlocked, bno, blen); if (error != -ENOSPC) return error; ASSERT(!rtlocked); if (++rgno == mp->m_sb.sb_rgcount) rgno = 0; bno_hint = NULLFSBLOCK; } while (rgno != start_rgno); return -ENOSPC; } static int xfs_rtallocate_align( struct xfs_bmalloca *ap, xfs_rtxlen_t *ralen, xfs_rtxlen_t *raminlen, xfs_rtxlen_t *prod, bool *noalign) { struct xfs_mount *mp = ap->ip->i_mount; xfs_fileoff_t orig_offset = ap->offset; xfs_extlen_t minlen = mp->m_sb.sb_rextsize; xfs_extlen_t align; /* minimum allocation alignment */ xfs_extlen_t mod; /* product factor for allocators */ int error; if (*noalign) { align = mp->m_sb.sb_rextsize; } else { if (ap->flags & XFS_BMAPI_COWFORK) align = xfs_get_cowextsz_hint(ap->ip); else align = xfs_get_extsz_hint(ap->ip); if (!align) align = 1; if (align == mp->m_sb.sb_rextsize) *noalign = true; } error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev, align, 1, ap->eof, 0, ap->conv, &ap->offset, &ap->length); if (error) return error; ASSERT(ap->length); ASSERT(xfs_extlen_to_rtxmod(mp, ap->length) == 0); /* * If we shifted the file offset downward to satisfy an extent size * hint, increase minlen by that amount so that the allocator won't * give us an allocation that's too short to cover at least one of the * blocks that the caller asked for. */ if (ap->offset != orig_offset) minlen += orig_offset - ap->offset; /* * Set ralen to be the actual requested length in rtextents. * * If the old value was close enough to XFS_BMBT_MAX_EXTLEN that * we rounded up to it, cut it back so it's valid again. * Note that if it's a really large request (bigger than * XFS_BMBT_MAX_EXTLEN), we don't hear about that number, and can't * adjust the starting point to match it. */ *ralen = xfs_extlen_to_rtxlen(mp, min(ap->length, XFS_MAX_BMBT_EXTLEN)); *raminlen = max_t(xfs_rtxlen_t, 1, xfs_extlen_to_rtxlen(mp, minlen)); ASSERT(*raminlen > 0); ASSERT(*raminlen <= *ralen); /* * Only bother calculating a real prod factor if offset & length are * perfectly aligned, otherwise it will just get us in trouble. */ div_u64_rem(ap->offset, align, &mod); if (mod || ap->length % align) *prod = 1; else *prod = xfs_extlen_to_rtxlen(mp, align); if (*prod > 1) xfs_rtalloc_align_minmax(raminlen, ralen, prod); return 0; } int xfs_bmap_rtalloc( struct xfs_bmalloca *ap) { xfs_fileoff_t orig_offset = ap->offset; xfs_rtxlen_t prod = 0; /* product factor for allocators */ xfs_rtxlen_t ralen = 0; /* realtime allocation length */ xfs_rtblock_t bno_hint = NULLRTBLOCK; xfs_extlen_t orig_length = ap->length; xfs_rtxlen_t raminlen; bool rtlocked = false; bool noalign = false; bool initial_user_data = ap->datatype & XFS_ALLOC_INITIAL_USER_DATA; int error; ASSERT(!xfs_has_zoned(ap->tp->t_mountp)); retry: error = xfs_rtallocate_align(ap, &ralen, &raminlen, &prod, &noalign); if (error) return error; if (xfs_bmap_adjacent(ap)) bno_hint = ap->blkno; if (xfs_has_rtgroups(ap->ip->i_mount)) { error = xfs_rtallocate_rtgs(ap->tp, bno_hint, raminlen, ralen, prod, ap->wasdel, initial_user_data, &ap->blkno, &ap->length); } else { error = xfs_rtallocate_rtg(ap->tp, 0, bno_hint, raminlen, ralen, prod, ap->wasdel, initial_user_data, &rtlocked, &ap->blkno, &ap->length); } if (error == -ENOSPC) { if (!noalign) { /* * We previously enlarged the request length to try to * satisfy an extent size hint. The allocator didn't * return anything, so reset the parameters to the * original values and try again without alignment * criteria. */ ap->offset = orig_offset; ap->length = orig_length; noalign = true; goto retry; } ap->blkno = NULLFSBLOCK; ap->length = 0; return 0; } if (error) return error; xfs_bmap_alloc_account(ap); return 0; } |
| 24 24 25 25 25 25 25 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 | // SPDX-License-Identifier: GPL-2.0 /* * Implementation of HKDF ("HMAC-based Extract-and-Expand Key Derivation * Function"), aka RFC 5869. See also the original paper (Krawczyk 2010): * "Cryptographic Extraction and Key Derivation: The HKDF Scheme". * * Copyright 2019 Google LLC */ #include <crypto/internal/hash.h> #include <crypto/sha2.h> #include <crypto/hkdf.h> #include <linux/module.h> /* * HKDF consists of two steps: * * 1. HKDF-Extract: extract a pseudorandom key from the input keying material * and optional salt. * 2. HKDF-Expand: expand the pseudorandom key into output keying material of * any length, parameterized by an application-specific info string. * */ /** * hkdf_extract - HKDF-Extract (RFC 5869 section 2.2) * @hmac_tfm: an HMAC transform using the hash function desired for HKDF. The * caller is responsible for setting the @prk afterwards. * @ikm: input keying material * @ikmlen: length of @ikm * @salt: input salt value * @saltlen: length of @salt * @prk: resulting pseudorandom key * * Extracts a pseudorandom key @prk from the input keying material * @ikm with length @ikmlen and salt @salt with length @saltlen. * The length of @prk is given by the digest size of @hmac_tfm. * For an 'unsalted' version of HKDF-Extract @salt must be set * to all zeroes and @saltlen must be set to the length of @prk. * * Returns 0 on success with the pseudorandom key stored in @prk, * or a negative errno value otherwise. */ int hkdf_extract(struct crypto_shash *hmac_tfm, const u8 *ikm, unsigned int ikmlen, const u8 *salt, unsigned int saltlen, u8 *prk) { int err; err = crypto_shash_setkey(hmac_tfm, salt, saltlen); if (!err) err = crypto_shash_tfm_digest(hmac_tfm, ikm, ikmlen, prk); return err; } EXPORT_SYMBOL_GPL(hkdf_extract); /** * hkdf_expand - HKDF-Expand (RFC 5869 section 2.3) * @hmac_tfm: hash context keyed with pseudorandom key * @info: application-specific information * @infolen: length of @info * @okm: output keying material * @okmlen: length of @okm * * This expands the pseudorandom key, which was already keyed into @hmac_tfm, * into @okmlen bytes of output keying material parameterized by the * application-specific @info of length @infolen bytes. * This is thread-safe and may be called by multiple threads in parallel. * * Returns 0 on success with output keying material stored in @okm, * or a negative errno value otherwise. */ int hkdf_expand(struct crypto_shash *hmac_tfm, const u8 *info, unsigned int infolen, u8 *okm, unsigned int okmlen) { SHASH_DESC_ON_STACK(desc, hmac_tfm); unsigned int i, hashlen = crypto_shash_digestsize(hmac_tfm); int err; const u8 *prev = NULL; u8 counter = 1; u8 tmp[HASH_MAX_DIGESTSIZE] = {}; if (WARN_ON(okmlen > 255 * hashlen)) return -EINVAL; desc->tfm = hmac_tfm; for (i = 0; i < okmlen; i += hashlen) { err = crypto_shash_init(desc); if (err) goto out; if (prev) { err = crypto_shash_update(desc, prev, hashlen); if (err) goto out; } if (infolen) { err = crypto_shash_update(desc, info, infolen); if (err) goto out; } BUILD_BUG_ON(sizeof(counter) != 1); if (okmlen - i < hashlen) { err = crypto_shash_finup(desc, &counter, 1, tmp); if (err) goto out; memcpy(&okm[i], tmp, okmlen - i); memzero_explicit(tmp, sizeof(tmp)); } else { err = crypto_shash_finup(desc, &counter, 1, &okm[i]); if (err) goto out; } counter++; prev = &okm[i]; } err = 0; out: if (unlikely(err)) memzero_explicit(okm, okmlen); /* so caller doesn't need to */ shash_desc_zero(desc); memzero_explicit(tmp, HASH_MAX_DIGESTSIZE); return err; } EXPORT_SYMBOL_GPL(hkdf_expand); struct hkdf_testvec { const char *test; const u8 *ikm; const u8 *salt; const u8 *info; const u8 *prk; const u8 *okm; u16 ikm_size; u16 salt_size; u16 info_size; u16 prk_size; u16 okm_size; }; /* * HKDF test vectors from RFC5869 * * Additional HKDF test vectors from * https://github.com/brycx/Test-Vector-Generation/blob/master/HKDF/hkdf-hmac-sha2-test-vectors.md */ static const struct hkdf_testvec hkdf_sha256_tv[] = { { .test = "basic hdkf test", .ikm = "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b" "\x0b\x0b\x0b\x0b\x0b\x0b", .ikm_size = 22, .salt = "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c", .salt_size = 13, .info = "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9", .info_size = 10, .prk = "\x07\x77\x09\x36\x2c\x2e\x32\xdf\x0d\xdc\x3f\x0d\xc4\x7b\xba\x63" "\x90\xb6\xc7\x3b\xb5\x0f\x9c\x31\x22\xec\x84\x4a\xd7\xc2\xb3\xe5", .prk_size = 32, .okm = "\x3c\xb2\x5f\x25\xfa\xac\xd5\x7a\x90\x43\x4f\x64\xd0\x36\x2f\x2a" "\x2d\x2d\x0a\x90\xcf\x1a\x5a\x4c\x5d\xb0\x2d\x56\xec\xc4\xc5\xbf" "\x34\x00\x72\x08\xd5\xb8\x87\x18\x58\x65", .okm_size = 42, }, { .test = "hkdf test with long input", .ikm = "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f" "\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f" "\x20\x21\x22\x23\x24\x25\x26\x27\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f" "\x30\x31\x32\x33\x34\x35\x36\x37\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f" "\x40\x41\x42\x43\x44\x45\x46\x47\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f", .ikm_size = 80, .salt = "\x60\x61\x62\x63\x64\x65\x66\x67\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f" "\x70\x71\x72\x73\x74\x75\x76\x77\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f" "\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f" "\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f" "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf", .salt_size = 80, .info = "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf" "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf" "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf" "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef" "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff", .info_size = 80, .prk = "\x06\xa6\xb8\x8c\x58\x53\x36\x1a\x06\x10\x4c\x9c\xeb\x35\xb4\x5c" "\xef\x76\x00\x14\x90\x46\x71\x01\x4a\x19\x3f\x40\xc1\x5f\xc2\x44", .prk_size = 32, .okm = "\xb1\x1e\x39\x8d\xc8\x03\x27\xa1\xc8\xe7\xf7\x8c\x59\x6a\x49\x34" "\x4f\x01\x2e\xda\x2d\x4e\xfa\xd8\xa0\x50\xcc\x4c\x19\xaf\xa9\x7c" "\x59\x04\x5a\x99\xca\xc7\x82\x72\x71\xcb\x41\xc6\x5e\x59\x0e\x09" "\xda\x32\x75\x60\x0c\x2f\x09\xb8\x36\x77\x93\xa9\xac\xa3\xdb\x71" "\xcc\x30\xc5\x81\x79\xec\x3e\x87\xc1\x4c\x01\xd5\xc1\xf3\x43\x4f" "\x1d\x87", .okm_size = 82, }, { .test = "hkdf test with zero salt and info", .ikm = "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b" "\x0b\x0b\x0b\x0b\x0b\x0b", .ikm_size = 22, .salt = NULL, .salt_size = 0, .info = NULL, .info_size = 0, .prk = "\x19\xef\x24\xa3\x2c\x71\x7b\x16\x7f\x33\xa9\x1d\x6f\x64\x8b\xdf" "\x96\x59\x67\x76\xaf\xdb\x63\x77\xac\x43\x4c\x1c\x29\x3c\xcb\x04", .prk_size = 32, .okm = "\x8d\xa4\xe7\x75\xa5\x63\xc1\x8f\x71\x5f\x80\x2a\x06\x3c\x5a\x31" "\xb8\xa1\x1f\x5c\x5e\xe1\x87\x9e\xc3\x45\x4e\x5f\x3c\x73\x8d\x2d" "\x9d\x20\x13\x95\xfa\xa4\xb6\x1a\x96\xc8", .okm_size = 42, }, { .test = "hkdf test with short input", .ikm = "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b", .ikm_size = 11, .salt = "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c", .salt_size = 13, .info = "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9", .info_size = 10, .prk = "\x82\x65\xf6\x9d\x7f\xf7\xe5\x01\x37\x93\x01\x5c\xa0\xef\x92\x0c" "\xb1\x68\x21\x99\xc8\xbc\x3a\x00\xda\x0c\xab\x47\xb7\xb0\x0f\xdf", .prk_size = 32, .okm = "\x58\xdc\xe1\x0d\x58\x01\xcd\xfd\xa8\x31\x72\x6b\xfe\xbc\xb7\x43" "\xd1\x4a\x7e\xe8\x3a\xa0\x57\xa9\x3d\x59\xb0\xa1\x31\x7f\xf0\x9d" "\x10\x5c\xce\xcf\x53\x56\x92\xb1\x4d\xd5", .okm_size = 42, }, { .test = "unsalted hkdf test with zero info", .ikm = "\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c" "\x0c\x0c\x0c\x0c\x0c\x0c", .ikm_size = 22, .salt = "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", .salt_size = 32, .info = NULL, .info_size = 0, .prk = "\xaa\x84\x1e\x1f\x35\x74\xf3\x2d\x13\xfb\xa8\x00\x5f\xcd\x9b\x8d" "\x77\x67\x82\xa5\xdf\xa1\x92\x38\x92\xfd\x8b\x63\x5d\x3a\x89\xdf", .prk_size = 32, .okm = "\x59\x68\x99\x17\x9a\xb1\xbc\x00\xa7\xc0\x37\x86\xff\x43\xee\x53" "\x50\x04\xbe\x2b\xb9\xbe\x68\xbc\x14\x06\x63\x6f\x54\xbd\x33\x8a" "\x66\xa2\x37\xba\x2a\xcb\xce\xe3\xc9\xa7", .okm_size = 42, } }; static const struct hkdf_testvec hkdf_sha384_tv[] = { { .test = "basic hkdf test", .ikm = "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b" "\x0b\x0b\x0b\x0b\x0b\x0b", .ikm_size = 22, .salt = "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c", .salt_size = 13, .info = "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9", .info_size = 10, .prk = "\x70\x4b\x39\x99\x07\x79\xce\x1d\xc5\x48\x05\x2c\x7d\xc3\x9f\x30" "\x35\x70\xdd\x13\xfb\x39\xf7\xac\xc5\x64\x68\x0b\xef\x80\xe8\xde" "\xc7\x0e\xe9\xa7\xe1\xf3\xe2\x93\xef\x68\xec\xeb\x07\x2a\x5a\xde", .prk_size = 48, .okm = "\x9b\x50\x97\xa8\x60\x38\xb8\x05\x30\x90\x76\xa4\x4b\x3a\x9f\x38" "\x06\x3e\x25\xb5\x16\xdc\xbf\x36\x9f\x39\x4c\xfa\xb4\x36\x85\xf7" "\x48\xb6\x45\x77\x63\xe4\xf0\x20\x4f\xc5", .okm_size = 42, }, { .test = "hkdf test with long input", .ikm = "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f" "\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f" "\x20\x21\x22\x23\x24\x25\x26\x27\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f" "\x30\x31\x32\x33\x34\x35\x36\x37\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f" "\x40\x41\x42\x43\x44\x45\x46\x47\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f", .ikm_size = 80, .salt = "\x60\x61\x62\x63\x64\x65\x66\x67\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f" "\x70\x71\x72\x73\x74\x75\x76\x77\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f" "\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f" "\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f" "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf", .salt_size = 80, .info = "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf" "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf" "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf" "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef" "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff", .info_size = 80, .prk = "\xb3\x19\xf6\x83\x1d\xff\x93\x14\xef\xb6\x43\xba\xa2\x92\x63\xb3" "\x0e\x4a\x8d\x77\x9f\xe3\x1e\x9c\x90\x1e\xfd\x7d\xe7\x37\xc8\x5b" "\x62\xe6\x76\xd4\xdc\x87\xb0\x89\x5c\x6a\x7d\xc9\x7b\x52\xce\xbb", .prk_size = 48, .okm = "\x48\x4c\xa0\x52\xb8\xcc\x72\x4f\xd1\xc4\xec\x64\xd5\x7b\x4e\x81" "\x8c\x7e\x25\xa8\xe0\xf4\x56\x9e\xd7\x2a\x6a\x05\xfe\x06\x49\xee" "\xbf\x69\xf8\xd5\xc8\x32\x85\x6b\xf4\xe4\xfb\xc1\x79\x67\xd5\x49" "\x75\x32\x4a\x94\x98\x7f\x7f\x41\x83\x58\x17\xd8\x99\x4f\xdb\xd6" "\xf4\xc0\x9c\x55\x00\xdc\xa2\x4a\x56\x22\x2f\xea\x53\xd8\x96\x7a" "\x8b\x2e", .okm_size = 82, }, { .test = "hkdf test with zero salt and info", .ikm = "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b" "\x0b\x0b\x0b\x0b\x0b\x0b", .ikm_size = 22, .salt = NULL, .salt_size = 0, .info = NULL, .info_size = 0, .prk = "\x10\xe4\x0c\xf0\x72\xa4\xc5\x62\x6e\x43\xdd\x22\xc1\xcf\x72\x7d" "\x4b\xb1\x40\x97\x5c\x9a\xd0\xcb\xc8\xe4\x5b\x40\x06\x8f\x8f\x0b" "\xa5\x7c\xdb\x59\x8a\xf9\xdf\xa6\x96\x3a\x96\x89\x9a\xf0\x47\xe5", .prk_size = 48, .okm = "\xc8\xc9\x6e\x71\x0f\x89\xb0\xd7\x99\x0b\xca\x68\xbc\xde\xc8\xcf" "\x85\x40\x62\xe5\x4c\x73\xa7\xab\xc7\x43\xfa\xde\x9b\x24\x2d\xaa" "\xcc\x1c\xea\x56\x70\x41\x5b\x52\x84\x9c", .okm_size = 42, }, { .test = "hkdf test with short input", .ikm = "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b", .ikm_size = 11, .salt = "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c", .salt_size = 13, .info = "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9", .info_size = 10, .prk = "\x6d\x31\x69\x98\x28\x79\x80\x88\xb3\x59\xda\xd5\x0b\x8f\x01\xb0" "\x15\xf1\x7a\xa3\xbd\x4e\x27\xa6\xe9\xf8\x73\xb7\x15\x85\xca\x6a" "\x00\xd1\xf0\x82\x12\x8a\xdb\x3c\xf0\x53\x0b\x57\xc0\xf9\xac\x72", .prk_size = 48, .okm = "\xfb\x7e\x67\x43\xeb\x42\xcd\xe9\x6f\x1b\x70\x77\x89\x52\xab\x75" "\x48\xca\xfe\x53\x24\x9f\x7f\xfe\x14\x97\xa1\x63\x5b\x20\x1f\xf1" "\x85\xb9\x3e\x95\x19\x92\xd8\x58\xf1\x1a", .okm_size = 42, }, { .test = "unsalted hkdf test with zero info", .ikm = "\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c" "\x0c\x0c\x0c\x0c\x0c\x0c", .ikm_size = 22, .salt = "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", .salt_size = 48, .info = NULL, .info_size = 0, .prk = "\x9d\x2d\xa5\x06\x6f\x05\xd1\x6c\x59\xfe\xdf\x6c\x5f\x32\xc7\x5e" "\xda\x9a\x47\xa7\x9c\x93\x6a\xa4\x4c\xb7\x63\xa8\xe2\x2f\xfb\xfc" "\xd8\xfe\x55\x43\x58\x53\x47\x21\x90\x39\xd1\x68\x28\x36\x33\xf5", .prk_size = 48, .okm = "\x6a\xd7\xc7\x26\xc8\x40\x09\x54\x6a\x76\xe0\x54\x5d\xf2\x66\x78" "\x7e\x2b\x2c\xd6\xca\x43\x73\xa1\xf3\x14\x50\xa7\xbd\xf9\x48\x2b" "\xfa\xb8\x11\xf5\x54\x20\x0e\xad\x8f\x53", .okm_size = 42, } }; static const struct hkdf_testvec hkdf_sha512_tv[] = { { .test = "basic hkdf test", .ikm = "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b" "\x0b\x0b\x0b\x0b\x0b\x0b", .ikm_size = 22, .salt = "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c", .salt_size = 13, .info = "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9", .info_size = 10, .prk = "\x66\x57\x99\x82\x37\x37\xde\xd0\x4a\x88\xe4\x7e\x54\xa5\x89\x0b" "\xb2\xc3\xd2\x47\xc7\xa4\x25\x4a\x8e\x61\x35\x07\x23\x59\x0a\x26" "\xc3\x62\x38\x12\x7d\x86\x61\xb8\x8c\xf8\x0e\xf8\x02\xd5\x7e\x2f" "\x7c\xeb\xcf\x1e\x00\xe0\x83\x84\x8b\xe1\x99\x29\xc6\x1b\x42\x37", .prk_size = 64, .okm = "\x83\x23\x90\x08\x6c\xda\x71\xfb\x47\x62\x5b\xb5\xce\xb1\x68\xe4" "\xc8\xe2\x6a\x1a\x16\xed\x34\xd9\xfc\x7f\xe9\x2c\x14\x81\x57\x93" "\x38\xda\x36\x2c\xb8\xd9\xf9\x25\xd7\xcb", .okm_size = 42, }, { .test = "hkdf test with long input", .ikm = "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f" "\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f" "\x20\x21\x22\x23\x24\x25\x26\x27\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f" "\x30\x31\x32\x33\x34\x35\x36\x37\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f" "\x40\x41\x42\x43\x44\x45\x46\x47\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f", .ikm_size = 80, .salt = "\x60\x61\x62\x63\x64\x65\x66\x67\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f" "\x70\x71\x72\x73\x74\x75\x76\x77\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f" "\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f" "\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f" "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf", .salt_size = 80, .info = "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf" "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf" "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf" "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef" "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff", .info_size = 80, .prk = "\x35\x67\x25\x42\x90\x7d\x4e\x14\x2c\x00\xe8\x44\x99\xe7\x4e\x1d" "\xe0\x8b\xe8\x65\x35\xf9\x24\xe0\x22\x80\x4a\xd7\x75\xdd\xe2\x7e" "\xc8\x6c\xd1\xe5\xb7\xd1\x78\xc7\x44\x89\xbd\xbe\xb3\x07\x12\xbe" "\xb8\x2d\x4f\x97\x41\x6c\x5a\x94\xea\x81\xeb\xdf\x3e\x62\x9e\x4a", .prk_size = 64, .okm = "\xce\x6c\x97\x19\x28\x05\xb3\x46\xe6\x16\x1e\x82\x1e\xd1\x65\x67" "\x3b\x84\xf4\x00\xa2\xb5\x14\xb2\xfe\x23\xd8\x4c\xd1\x89\xdd\xf1" "\xb6\x95\xb4\x8c\xbd\x1c\x83\x88\x44\x11\x37\xb3\xce\x28\xf1\x6a" "\xa6\x4b\xa3\x3b\xa4\x66\xb2\x4d\xf6\xcf\xcb\x02\x1e\xcf\xf2\x35" "\xf6\xa2\x05\x6c\xe3\xaf\x1d\xe4\x4d\x57\x20\x97\xa8\x50\x5d\x9e" "\x7a\x93", .okm_size = 82, }, { .test = "hkdf test with zero salt and info", .ikm = "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b" "\x0b\x0b\x0b\x0b\x0b\x0b", .ikm_size = 22, .salt = NULL, .salt_size = 0, .info = NULL, .info_size = 0, .prk = "\xfd\x20\x0c\x49\x87\xac\x49\x13\x13\xbd\x4a\x2a\x13\x28\x71\x21" "\x24\x72\x39\xe1\x1c\x9e\xf8\x28\x02\x04\x4b\x66\xef\x35\x7e\x5b" "\x19\x44\x98\xd0\x68\x26\x11\x38\x23\x48\x57\x2a\x7b\x16\x11\xde" "\x54\x76\x40\x94\x28\x63\x20\x57\x8a\x86\x3f\x36\x56\x2b\x0d\xf6", .prk_size = 64, .okm = "\xf5\xfa\x02\xb1\x82\x98\xa7\x2a\x8c\x23\x89\x8a\x87\x03\x47\x2c" "\x6e\xb1\x79\xdc\x20\x4c\x03\x42\x5c\x97\x0e\x3b\x16\x4b\xf9\x0f" "\xff\x22\xd0\x48\x36\xd0\xe2\x34\x3b\xac", .okm_size = 42, }, { .test = "hkdf test with short input", .ikm = "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b", .ikm_size = 11, .salt = "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c", .salt_size = 13, .info = "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9", .info_size = 10, .prk = "\x67\x40\x9c\x9c\xac\x28\xb5\x2e\xe9\xfa\xd9\x1c\x2f\xda\x99\x9f" "\x7c\xa2\x2e\x34\x34\xf0\xae\x77\x28\x63\x83\x65\x68\xad\x6a\x7f" "\x10\xcf\x11\x3b\xfd\xdd\x56\x01\x29\xa5\x94\xa8\xf5\x23\x85\xc2" "\xd6\x61\xd7\x85\xd2\x9c\xe9\x3a\x11\x40\x0c\x92\x06\x83\x18\x1d", .prk_size = 64, .okm = "\x74\x13\xe8\x99\x7e\x02\x06\x10\xfb\xf6\x82\x3f\x2c\xe1\x4b\xff" "\x01\x87\x5d\xb1\xca\x55\xf6\x8c\xfc\xf3\x95\x4d\xc8\xaf\xf5\x35" "\x59\xbd\x5e\x30\x28\xb0\x80\xf7\xc0\x68", .okm_size = 42, }, { .test = "unsalted hkdf test with zero info", .ikm = "\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c" "\x0c\x0c\x0c\x0c\x0c\x0c", .ikm_size = 22, .salt = "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", .salt_size = 64, .info = NULL, .info_size = 0, .prk = "\x53\x46\xb3\x76\xbf\x3a\xa9\xf8\x4f\x8f\x6e\xd5\xb1\xc4\xf4\x89" "\x17\x2e\x24\x4d\xac\x30\x3d\x12\xf6\x8e\xcc\x76\x6e\xa6\x00\xaa" "\x88\x49\x5e\x7f\xb6\x05\x80\x31\x22\xfa\x13\x69\x24\xa8\x40\xb1" "\xf0\x71\x9d\x2d\x5f\x68\xe2\x9b\x24\x22\x99\xd7\x58\xed\x68\x0c", .prk_size = 64, .okm = "\x14\x07\xd4\x60\x13\xd9\x8b\xc6\xde\xce\xfc\xfe\xe5\x5f\x0f\x90" "\xb0\xc7\xf6\x3d\x68\xeb\x1a\x80\xea\xf0\x7e\x95\x3c\xfc\x0a\x3a" "\x52\x40\xa1\x55\xd6\xe4\xda\xa9\x65\xbb", .okm_size = 42, } }; static int hkdf_test(const char *shash, const struct hkdf_testvec *tv) { struct crypto_shash *tfm = NULL; u8 *prk = NULL, *okm = NULL; unsigned int prk_size; const char *driver; int err; tfm = crypto_alloc_shash(shash, 0, 0); if (IS_ERR(tfm)) { pr_err("%s(%s): failed to allocate transform: %ld\n", tv->test, shash, PTR_ERR(tfm)); return PTR_ERR(tfm); } driver = crypto_shash_driver_name(tfm); prk_size = crypto_shash_digestsize(tfm); prk = kzalloc(prk_size, GFP_KERNEL); if (!prk) { err = -ENOMEM; goto out_free; } if (tv->prk_size != prk_size) { pr_err("%s(%s): prk size mismatch (vec %u, digest %u\n", tv->test, driver, tv->prk_size, prk_size); err = -EINVAL; goto out_free; } err = hkdf_extract(tfm, tv->ikm, tv->ikm_size, tv->salt, tv->salt_size, prk); if (err) { pr_err("%s(%s): hkdf_extract failed with %d\n", tv->test, driver, err); goto out_free; } if (memcmp(prk, tv->prk, tv->prk_size)) { pr_err("%s(%s): hkdf_extract prk mismatch\n", tv->test, driver); print_hex_dump(KERN_ERR, "prk: ", DUMP_PREFIX_NONE, 16, 1, prk, tv->prk_size, false); err = -EINVAL; goto out_free; } okm = kzalloc(tv->okm_size, GFP_KERNEL); if (!okm) { err = -ENOMEM; goto out_free; } err = crypto_shash_setkey(tfm, tv->prk, tv->prk_size); if (err) { pr_err("%s(%s): failed to set prk, error %d\n", tv->test, driver, err); goto out_free; } err = hkdf_expand(tfm, tv->info, tv->info_size, okm, tv->okm_size); if (err) { pr_err("%s(%s): hkdf_expand() failed with %d\n", tv->test, driver, err); } else if (memcmp(okm, tv->okm, tv->okm_size)) { pr_err("%s(%s): hkdf_expand() okm mismatch\n", tv->test, driver); print_hex_dump(KERN_ERR, "okm: ", DUMP_PREFIX_NONE, 16, 1, okm, tv->okm_size, false); err = -EINVAL; } out_free: kfree(okm); kfree(prk); crypto_free_shash(tfm); return err; } static int __init crypto_hkdf_module_init(void) { int ret = 0, i; if (IS_ENABLED(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS)) return 0; for (i = 0; i < ARRAY_SIZE(hkdf_sha256_tv); i++) { ret = hkdf_test("hmac(sha256)", &hkdf_sha256_tv[i]); if (ret) return ret; } for (i = 0; i < ARRAY_SIZE(hkdf_sha384_tv); i++) { ret = hkdf_test("hmac(sha384)", &hkdf_sha384_tv[i]); if (ret) return ret; } for (i = 0; i < ARRAY_SIZE(hkdf_sha512_tv); i++) { ret = hkdf_test("hmac(sha512)", &hkdf_sha512_tv[i]); if (ret) return ret; } return 0; } static void __exit crypto_hkdf_module_exit(void) {} module_init(crypto_hkdf_module_init); module_exit(crypto_hkdf_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("HMAC-based Key Derivation Function (HKDF)"); |
| 1781 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * x86 KFENCE support. * * Copyright (C) 2020, Google LLC. */ #ifndef _ASM_X86_KFENCE_H #define _ASM_X86_KFENCE_H #ifndef MODULE #include <linux/bug.h> #include <linux/kfence.h> #include <asm/pgalloc.h> #include <asm/pgtable.h> #include <asm/set_memory.h> #include <asm/tlbflush.h> /* Force 4K pages for __kfence_pool. */ static inline bool arch_kfence_init_pool(void) { unsigned long addr; for (addr = (unsigned long)__kfence_pool; is_kfence_address((void *)addr); addr += PAGE_SIZE) { unsigned int level; if (!lookup_address(addr, &level)) return false; if (level != PG_LEVEL_4K) set_memory_4k(addr, 1); } return true; } /* Protect the given page and flush TLB. */ static inline bool kfence_protect_page(unsigned long addr, bool protect) { unsigned int level; pte_t *pte = lookup_address(addr, &level); if (WARN_ON(!pte || level != PG_LEVEL_4K)) return false; /* * We need to avoid IPIs, as we may get KFENCE allocations or faults * with interrupts disabled. Therefore, the below is best-effort, and * does not flush TLBs on all CPUs. We can tolerate some inaccuracy; * lazy fault handling takes care of faults after the page is PRESENT. */ if (protect) set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_PRESENT)); else set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT)); /* * Flush this CPU's TLB, assuming whoever did the allocation/free is * likely to continue running on this CPU. */ preempt_disable(); flush_tlb_one_kernel(addr); preempt_enable(); return true; } #endif /* !MODULE */ #endif /* _ASM_X86_KFENCE_H */ |
| 4 3 7 7 3 3 3 3 3 3 4 8 1 3 4 1 4 6 1 5 3 2 3 2 3 3 6 1 2 8 1 8 1 7 7 8 8 8 8 8 8 8 12 12 12 1 1 10 10 9 8 8 1 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2010, 2023 Red Hat, Inc. * All Rights Reserved. */ #include "xfs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_trans.h" #include "xfs_mount.h" #include "xfs_btree.h" #include "xfs_alloc_btree.h" #include "xfs_alloc.h" #include "xfs_discard.h" #include "xfs_error.h" #include "xfs_extent_busy.h" #include "xfs_trace.h" #include "xfs_log.h" #include "xfs_ag.h" #include "xfs_health.h" #include "xfs_rtbitmap.h" #include "xfs_rtgroup.h" /* * Notes on an efficient, low latency fstrim algorithm * * We need to walk the filesystem free space and issue discards on the free * space that meet the search criteria (size and location). We cannot issue * discards on extents that might be in use, or are so recently in use they are * still marked as busy. To serialise against extent state changes whilst we are * gathering extents to trim, we must hold the AGF lock to lock out other * allocations and extent free operations that might change extent state. * * However, we cannot just hold the AGF for the entire AG free space walk whilst * we issue discards on each free space that is found. Storage devices can have * extremely slow discard implementations (e.g. ceph RBD) and so walking a * couple of million free extents and issuing synchronous discards on each * extent can take a *long* time. Whilst we are doing this walk, nothing else * can access the AGF, and we can stall transactions and hence the log whilst * modifications wait for the AGF lock to be released. This can lead hung tasks * kicking the hung task timer and rebooting the system. This is bad. * * Hence we need to take a leaf from the bulkstat playbook. It takes the AGI * lock, gathers a range of inode cluster buffers that are allocated, drops the * AGI lock and then reads all the inode cluster buffers and processes them. It * loops doing this, using a cursor to keep track of where it is up to in the AG * for each iteration to restart the INOBT lookup from. * * We can't do this exactly with free space - once we drop the AGF lock, the * state of the free extent is out of our control and we cannot run a discard * safely on it in this situation. Unless, of course, we've marked the free * extent as busy and undergoing a discard operation whilst we held the AGF * locked. * * This is exactly how online discard works - free extents are marked busy when * they are freed, and once the extent free has been committed to the journal, * the busy extent record is marked as "undergoing discard" and the discard is * then issued on the free extent. Once the discard completes, the busy extent * record is removed and the extent is able to be allocated again. * * In the context of fstrim, if we find a free extent we need to discard, we * don't have to discard it immediately. All we need to do it record that free * extent as being busy and under discard, and all the allocation routines will * now avoid trying to allocate it. Hence if we mark the extent as busy under * the AGF lock, we can safely discard it without holding the AGF lock because * nothing will attempt to allocate that free space until the discard completes. * * This also allows us to issue discards asynchronously like we do with online * discard, and so for fast devices fstrim will run much faster as we can have * multiple discard operations in flight at once, as well as pipeline the free * extent search so that it overlaps in flight discard IO. */ #define XFS_DISCARD_MAX_EXAMINE (100) struct workqueue_struct *xfs_discard_wq; static void xfs_discard_endio_work( struct work_struct *work) { struct xfs_busy_extents *extents = container_of(work, struct xfs_busy_extents, endio_work); xfs_extent_busy_clear(&extents->extent_list, false); kfree(extents->owner); } /* * Queue up the actual completion to a thread to avoid IRQ-safe locking for * eb_lock. */ static void xfs_discard_endio( struct bio *bio) { struct xfs_busy_extents *extents = bio->bi_private; INIT_WORK(&extents->endio_work, xfs_discard_endio_work); queue_work(xfs_discard_wq, &extents->endio_work); bio_put(bio); } static inline struct block_device * xfs_group_bdev( const struct xfs_group *xg) { struct xfs_mount *mp = xg->xg_mount; switch (xg->xg_type) { case XG_TYPE_AG: return mp->m_ddev_targp->bt_bdev; case XG_TYPE_RTG: return mp->m_rtdev_targp->bt_bdev; default: ASSERT(0); break; } return NULL; } /* * Walk the discard list and issue discards on all the busy extents in the * list. We plug and chain the bios so that we only need a single completion * call to clear all the busy extents once the discards are complete. */ int xfs_discard_extents( struct xfs_mount *mp, struct xfs_busy_extents *extents) { struct xfs_extent_busy *busyp; struct bio *bio = NULL; struct blk_plug plug; int error = 0; blk_start_plug(&plug); list_for_each_entry(busyp, &extents->extent_list, list) { trace_xfs_discard_extent(busyp->group, busyp->bno, busyp->length); error = __blkdev_issue_discard(xfs_group_bdev(busyp->group), xfs_gbno_to_daddr(busyp->group, busyp->bno), XFS_FSB_TO_BB(mp, busyp->length), GFP_KERNEL, &bio); if (error && error != -EOPNOTSUPP) { xfs_info(mp, "discard failed for extent [0x%llx,%u], error %d", (unsigned long long)busyp->bno, busyp->length, error); break; } } if (bio) { bio->bi_private = extents; bio->bi_end_io = xfs_discard_endio; submit_bio(bio); } else { xfs_discard_endio_work(&extents->endio_work); } blk_finish_plug(&plug); return error; } struct xfs_trim_cur { xfs_agblock_t start; xfs_extlen_t count; xfs_agblock_t end; xfs_extlen_t minlen; bool by_bno; }; static int xfs_trim_gather_extents( struct xfs_perag *pag, struct xfs_trim_cur *tcur, struct xfs_busy_extents *extents) { struct xfs_mount *mp = pag_mount(pag); struct xfs_trans *tp; struct xfs_btree_cur *cur; struct xfs_buf *agbp; int error; int i; int batch = XFS_DISCARD_MAX_EXAMINE; /* * Force out the log. This means any transactions that might have freed * space before we take the AGF buffer lock are now on disk, and the * volatile disk cache is flushed. */ xfs_log_force(mp, XFS_LOG_SYNC); error = xfs_trans_alloc_empty(mp, &tp); if (error) return error; error = xfs_alloc_read_agf(pag, tp, 0, &agbp); if (error) goto out_trans_cancel; if (tcur->by_bno) { /* sub-AG discard request always starts at tcur->start */ cur = xfs_bnobt_init_cursor(mp, tp, agbp, pag); error = xfs_alloc_lookup_le(cur, tcur->start, 0, &i); if (!error && !i) error = xfs_alloc_lookup_ge(cur, tcur->start, 0, &i); } else if (tcur->start == 0) { /* first time through a by-len starts with max length */ cur = xfs_cntbt_init_cursor(mp, tp, agbp, pag); error = xfs_alloc_lookup_ge(cur, 0, tcur->count, &i); } else { /* nth time through a by-len starts where we left off */ cur = xfs_cntbt_init_cursor(mp, tp, agbp, pag); error = xfs_alloc_lookup_le(cur, tcur->start, tcur->count, &i); } if (error) goto out_del_cursor; if (i == 0) { /* nothing of that length left in the AG, we are done */ tcur->count = 0; goto out_del_cursor; } /* * Loop until we are done with all extents that are large * enough to be worth discarding or we hit batch limits. */ while (i) { xfs_agblock_t fbno; xfs_extlen_t flen; error = xfs_alloc_get_rec(cur, &fbno, &flen, &i); if (error) break; if (XFS_IS_CORRUPT(mp, i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; break; } if (--batch <= 0) { /* * Update the cursor to point at this extent so we * restart the next batch from this extent. */ tcur->start = fbno; tcur->count = flen; break; } /* * If the extent is entirely outside of the range we are * supposed to skip it. Do not bother to trim down partially * overlapping ranges for now. */ if (fbno + flen < tcur->start) { trace_xfs_discard_exclude(pag_group(pag), fbno, flen); goto next_extent; } if (fbno > tcur->end) { trace_xfs_discard_exclude(pag_group(pag), fbno, flen); if (tcur->by_bno) { tcur->count = 0; break; } goto next_extent; } /* Trim the extent returned to the range we want. */ if (fbno < tcur->start) { flen -= tcur->start - fbno; fbno = tcur->start; } if (fbno + flen > tcur->end + 1) flen = tcur->end - fbno + 1; /* Too small? Give up. */ if (flen < tcur->minlen) { trace_xfs_discard_toosmall(pag_group(pag), fbno, flen); if (tcur->by_bno) goto next_extent; tcur->count = 0; break; } /* * If any blocks in the range are still busy, skip the * discard and try again the next time. */ if (xfs_extent_busy_search(pag_group(pag), fbno, flen)) { trace_xfs_discard_busy(pag_group(pag), fbno, flen); goto next_extent; } xfs_extent_busy_insert_discard(pag_group(pag), fbno, flen, &extents->extent_list); next_extent: if (tcur->by_bno) error = xfs_btree_increment(cur, 0, &i); else error = xfs_btree_decrement(cur, 0, &i); if (error) break; /* * If there's no more records in the tree, we are done. Set the * cursor block count to 0 to indicate to the caller that there * is no more extents to search. */ if (i == 0) tcur->count = 0; } /* * If there was an error, release all the gathered busy extents because * we aren't going to issue a discard on them any more. */ if (error) xfs_extent_busy_clear(&extents->extent_list, false); out_del_cursor: xfs_btree_del_cursor(cur, error); out_trans_cancel: xfs_trans_cancel(tp); return error; } static bool xfs_trim_should_stop(void) { return fatal_signal_pending(current) || freezing(current); } /* * Iterate the free list gathering extents and discarding them. We need a cursor * for the repeated iteration of gather/discard loop, so use the longest extent * we found in the last batch as the key to start the next. */ static int xfs_trim_perag_extents( struct xfs_perag *pag, xfs_agblock_t start, xfs_agblock_t end, xfs_extlen_t minlen) { struct xfs_trim_cur tcur = { .start = start, .count = pag->pagf_longest, .end = end, .minlen = minlen, }; int error = 0; if (start != 0 || end != pag_group(pag)->xg_block_count) tcur.by_bno = true; do { struct xfs_busy_extents *extents; extents = kzalloc(sizeof(*extents), GFP_KERNEL); if (!extents) { error = -ENOMEM; break; } extents->owner = extents; INIT_LIST_HEAD(&extents->extent_list); error = xfs_trim_gather_extents(pag, &tcur, extents); if (error) { kfree(extents); break; } /* * We hand the extent list to the discard function here so the * discarded extents can be removed from the busy extent list. * This allows the discards to run asynchronously with gathering * the next round of extents to discard. * * However, we must ensure that we do not reference the extent * list after this function call, as it may have been freed by * the time control returns to us. */ error = xfs_discard_extents(pag_mount(pag), extents); if (error) break; if (xfs_trim_should_stop()) break; } while (tcur.count != 0); return error; } static int xfs_trim_datadev_extents( struct xfs_mount *mp, xfs_daddr_t start, xfs_daddr_t end, xfs_extlen_t minlen) { xfs_agnumber_t start_agno, end_agno; xfs_agblock_t start_agbno, end_agbno; struct xfs_perag *pag = NULL; xfs_daddr_t ddev_end; int last_error = 0, error; ddev_end = min_t(xfs_daddr_t, end, XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) - 1); start_agno = xfs_daddr_to_agno(mp, start); start_agbno = xfs_daddr_to_agbno(mp, start); end_agno = xfs_daddr_to_agno(mp, ddev_end); end_agbno = xfs_daddr_to_agbno(mp, ddev_end); while ((pag = xfs_perag_next_range(mp, pag, start_agno, end_agno))) { xfs_agblock_t agend = pag_group(pag)->xg_block_count; if (pag_agno(pag) == end_agno) agend = end_agbno; error = xfs_trim_perag_extents(pag, start_agbno, agend, minlen); if (error) last_error = error; if (xfs_trim_should_stop()) { xfs_perag_rele(pag); break; } start_agbno = 0; } return last_error; } #ifdef CONFIG_XFS_RT struct xfs_trim_rtdev { /* list of rt extents to free */ struct list_head extent_list; /* minimum length that caller allows us to trim */ xfs_rtblock_t minlen_fsb; /* restart point for the rtbitmap walk */ xfs_rtxnum_t restart_rtx; /* stopping point for the current rtbitmap walk */ xfs_rtxnum_t stop_rtx; }; struct xfs_rtx_busy { struct list_head list; xfs_rtblock_t bno; xfs_rtblock_t length; }; static void xfs_discard_free_rtdev_extents( struct xfs_trim_rtdev *tr) { struct xfs_rtx_busy *busyp, *n; list_for_each_entry_safe(busyp, n, &tr->extent_list, list) { list_del_init(&busyp->list); kfree(busyp); } } /* * Walk the discard list and issue discards on all the busy extents in the * list. We plug and chain the bios so that we only need a single completion * call to clear all the busy extents once the discards are complete. */ static int xfs_discard_rtdev_extents( struct xfs_mount *mp, struct xfs_trim_rtdev *tr) { struct block_device *bdev = mp->m_rtdev_targp->bt_bdev; struct xfs_rtx_busy *busyp; struct bio *bio = NULL; struct blk_plug plug; xfs_rtblock_t start = NULLRTBLOCK, length = 0; int error = 0; blk_start_plug(&plug); list_for_each_entry(busyp, &tr->extent_list, list) { if (start == NULLRTBLOCK) start = busyp->bno; length += busyp->length; trace_xfs_discard_rtextent(mp, busyp->bno, busyp->length); error = __blkdev_issue_discard(bdev, xfs_rtb_to_daddr(mp, busyp->bno), XFS_FSB_TO_BB(mp, busyp->length), GFP_NOFS, &bio); if (error) break; } xfs_discard_free_rtdev_extents(tr); if (bio) { error = submit_bio_wait(bio); if (error == -EOPNOTSUPP) error = 0; if (error) xfs_info(mp, "discard failed for rtextent [0x%llx,%llu], error %d", (unsigned long long)start, (unsigned long long)length, error); bio_put(bio); } blk_finish_plug(&plug); return error; } static int xfs_trim_gather_rtextent( struct xfs_rtgroup *rtg, struct xfs_trans *tp, const struct xfs_rtalloc_rec *rec, void *priv) { struct xfs_trim_rtdev *tr = priv; struct xfs_rtx_busy *busyp; xfs_rtblock_t rbno, rlen; if (rec->ar_startext > tr->stop_rtx) { /* * If we've scanned a large number of rtbitmap blocks, update * the cursor to point at this extent so we restart the next * batch from this extent. */ tr->restart_rtx = rec->ar_startext; return -ECANCELED; } rbno = xfs_rtx_to_rtb(rtg, rec->ar_startext); rlen = xfs_rtbxlen_to_blen(rtg_mount(rtg), rec->ar_extcount); /* Ignore too small. */ if (rlen < tr->minlen_fsb) { trace_xfs_discard_rttoosmall(rtg_mount(rtg), rbno, rlen); return 0; } busyp = kzalloc(sizeof(struct xfs_rtx_busy), GFP_KERNEL); if (!busyp) return -ENOMEM; busyp->bno = rbno; busyp->length = rlen; INIT_LIST_HEAD(&busyp->list); list_add_tail(&busyp->list, &tr->extent_list); tr->restart_rtx = rec->ar_startext + rec->ar_extcount; return 0; } /* Trim extents on an !rtgroups realtime device */ static int xfs_trim_rtextents( struct xfs_rtgroup *rtg, xfs_rtxnum_t low, xfs_rtxnum_t high, xfs_daddr_t minlen) { struct xfs_mount *mp = rtg_mount(rtg); struct xfs_trim_rtdev tr = { .minlen_fsb = XFS_BB_TO_FSB(mp, minlen), .extent_list = LIST_HEAD_INIT(tr.extent_list), }; struct xfs_trans *tp; int error; error = xfs_trans_alloc_empty(mp, &tp); if (error) return error; /* * Walk the free ranges between low and high. The query_range function * trims the extents returned. */ do { tr.stop_rtx = low + xfs_rtbitmap_rtx_per_rbmblock(mp); xfs_rtgroup_lock(rtg, XFS_RTGLOCK_BITMAP_SHARED); error = xfs_rtalloc_query_range(rtg, tp, low, high, xfs_trim_gather_rtextent, &tr); if (error == -ECANCELED) error = 0; if (error) { xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_BITMAP_SHARED); xfs_discard_free_rtdev_extents(&tr); break; } if (list_empty(&tr.extent_list)) { xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_BITMAP_SHARED); break; } error = xfs_discard_rtdev_extents(mp, &tr); xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_BITMAP_SHARED); if (error) break; low = tr.restart_rtx; } while (!xfs_trim_should_stop() && low <= high); xfs_trans_cancel(tp); return error; } struct xfs_trim_rtgroup { /* list of rtgroup extents to free */ struct xfs_busy_extents *extents; /* minimum length that caller allows us to trim */ xfs_rtblock_t minlen_fsb; /* restart point for the rtbitmap walk */ xfs_rtxnum_t restart_rtx; /* number of extents to examine before stopping to issue discard ios */ int batch; /* number of extents queued for discard */ int queued; }; static int xfs_trim_gather_rtgroup_extent( struct xfs_rtgroup *rtg, struct xfs_trans *tp, const struct xfs_rtalloc_rec *rec, void *priv) { struct xfs_trim_rtgroup *tr = priv; xfs_rgblock_t rgbno; xfs_extlen_t len; if (--tr->batch <= 0) { /* * If we've checked a large number of extents, update the * cursor to point at this extent so we restart the next batch * from this extent. */ tr->restart_rtx = rec->ar_startext; return -ECANCELED; } rgbno = xfs_rtx_to_rgbno(rtg, rec->ar_startext); len = xfs_rtxlen_to_extlen(rtg_mount(rtg), rec->ar_extcount); /* Ignore too small. */ if (len < tr->minlen_fsb) { trace_xfs_discard_toosmall(rtg_group(rtg), rgbno, len); return 0; } /* * If any blocks in the range are still busy, skip the discard and try * again the next time. */ if (xfs_extent_busy_search(rtg_group(rtg), rgbno, len)) { trace_xfs_discard_busy(rtg_group(rtg), rgbno, len); return 0; } xfs_extent_busy_insert_discard(rtg_group(rtg), rgbno, len, &tr->extents->extent_list); tr->queued++; tr->restart_rtx = rec->ar_startext + rec->ar_extcount; return 0; } /* Trim extents in this rtgroup using the busy extent machinery. */ static int xfs_trim_rtgroup_extents( struct xfs_rtgroup *rtg, xfs_rtxnum_t low, xfs_rtxnum_t high, xfs_daddr_t minlen) { struct xfs_mount *mp = rtg_mount(rtg); struct xfs_trim_rtgroup tr = { .minlen_fsb = XFS_BB_TO_FSB(mp, minlen), }; struct xfs_trans *tp; int error; error = xfs_trans_alloc_empty(mp, &tp); if (error) return error; /* * Walk the free ranges between low and high. The query_range function * trims the extents returned. */ do { tr.extents = kzalloc(sizeof(*tr.extents), GFP_KERNEL); if (!tr.extents) { error = -ENOMEM; break; } tr.queued = 0; tr.batch = XFS_DISCARD_MAX_EXAMINE; tr.extents->owner = tr.extents; INIT_LIST_HEAD(&tr.extents->extent_list); xfs_rtgroup_lock(rtg, XFS_RTGLOCK_BITMAP_SHARED); error = xfs_rtalloc_query_range(rtg, tp, low, high, xfs_trim_gather_rtgroup_extent, &tr); xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_BITMAP_SHARED); if (error == -ECANCELED) error = 0; if (error) { kfree(tr.extents); break; } if (!tr.queued) break; /* * We hand the extent list to the discard function here so the * discarded extents can be removed from the busy extent list. * This allows the discards to run asynchronously with * gathering the next round of extents to discard. * * However, we must ensure that we do not reference the extent * list after this function call, as it may have been freed by * the time control returns to us. */ error = xfs_discard_extents(rtg_mount(rtg), tr.extents); if (error) break; low = tr.restart_rtx; } while (!xfs_trim_should_stop() && low <= high); xfs_trans_cancel(tp); return error; } static int xfs_trim_rtdev_extents( struct xfs_mount *mp, xfs_daddr_t start, xfs_daddr_t end, xfs_daddr_t minlen) { xfs_rtblock_t start_rtbno, end_rtbno; xfs_rtxnum_t start_rtx, end_rtx; xfs_rgnumber_t start_rgno, end_rgno; xfs_daddr_t daddr_offset; int last_error = 0, error; struct xfs_rtgroup *rtg = NULL; /* Shift the start and end downwards to match the rt device. */ daddr_offset = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks); if (start > daddr_offset) start -= daddr_offset; else start = 0; start_rtbno = xfs_daddr_to_rtb(mp, start); start_rtx = xfs_rtb_to_rtx(mp, start_rtbno); start_rgno = xfs_rtb_to_rgno(mp, start_rtbno); if (end <= daddr_offset) return 0; else end -= daddr_offset; end_rtbno = xfs_daddr_to_rtb(mp, end); end_rtx = xfs_rtb_to_rtx(mp, end_rtbno + mp->m_sb.sb_rextsize - 1); end_rgno = xfs_rtb_to_rgno(mp, end_rtbno); while ((rtg = xfs_rtgroup_next_range(mp, rtg, start_rgno, end_rgno))) { xfs_rtxnum_t rtg_end = rtg->rtg_extents; if (rtg_rgno(rtg) == end_rgno) rtg_end = min(rtg_end, end_rtx); if (xfs_has_rtgroups(mp)) error = xfs_trim_rtgroup_extents(rtg, start_rtx, rtg_end, minlen); else error = xfs_trim_rtextents(rtg, start_rtx, rtg_end, minlen); if (error) last_error = error; if (xfs_trim_should_stop()) { xfs_rtgroup_rele(rtg); break; } start_rtx = 0; } return last_error; } #else # define xfs_trim_rtdev_extents(...) (-EOPNOTSUPP) #endif /* CONFIG_XFS_RT */ /* * trim a range of the filesystem. * * Note: the parameters passed from userspace are byte ranges into the * filesystem which does not match to the format we use for filesystem block * addressing. FSB addressing is sparse (AGNO|AGBNO), while the incoming format * is a linear address range. Hence we need to use DADDR based conversions and * comparisons for determining the correct offset and regions to trim. * * The realtime device is mapped into the FITRIM "address space" immediately * after the data device. */ int xfs_ioc_trim( struct xfs_mount *mp, struct fstrim_range __user *urange) { unsigned int granularity = bdev_discard_granularity(mp->m_ddev_targp->bt_bdev); struct block_device *rt_bdev = NULL; struct fstrim_range range; xfs_daddr_t start, end; xfs_extlen_t minlen; xfs_rfsblock_t max_blocks; int error, last_error = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (mp->m_rtdev_targp && !xfs_has_zoned(mp) && bdev_max_discard_sectors(mp->m_rtdev_targp->bt_bdev)) rt_bdev = mp->m_rtdev_targp->bt_bdev; if (!bdev_max_discard_sectors(mp->m_ddev_targp->bt_bdev) && !rt_bdev) return -EOPNOTSUPP; if (rt_bdev) granularity = max(granularity, bdev_discard_granularity(rt_bdev)); /* * We haven't recovered the log, so we cannot use our bnobt-guided * storage zapping commands. */ if (xfs_has_norecovery(mp)) return -EROFS; if (copy_from_user(&range, urange, sizeof(range))) return -EFAULT; range.minlen = max_t(u64, granularity, range.minlen); minlen = XFS_B_TO_FSB(mp, range.minlen); /* * Truncating down the len isn't actually quite correct, but using * BBTOB would mean we trivially get overflows for values * of ULLONG_MAX or slightly lower. And ULLONG_MAX is the default * used by the fstrim application. In the end it really doesn't * matter as trimming blocks is an advisory interface. */ max_blocks = mp->m_sb.sb_dblocks + mp->m_sb.sb_rblocks; if (range.start >= XFS_FSB_TO_B(mp, max_blocks) || range.minlen > XFS_FSB_TO_B(mp, mp->m_ag_max_usable) || range.len < mp->m_sb.sb_blocksize) return -EINVAL; start = BTOBB(range.start); end = start + BTOBBT(range.len) - 1; if (bdev_max_discard_sectors(mp->m_ddev_targp->bt_bdev)) { error = xfs_trim_datadev_extents(mp, start, end, minlen); if (error) last_error = error; } if (rt_bdev && !xfs_trim_should_stop()) { error = xfs_trim_rtdev_extents(mp, start, end, minlen); if (error) last_error = error; } if (last_error) return last_error; range.len = min_t(unsigned long long, range.len, XFS_FSB_TO_B(mp, max_blocks) - range.start); if (copy_to_user(urange, &range, sizeof(range))) return -EFAULT; return 0; } |
| 3 3 3 3 3 3 2 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Yama Linux Security Module * * Author: Kees Cook <keescook@chromium.org> * * Copyright (C) 2010 Canonical, Ltd. * Copyright (C) 2011 The Chromium OS Authors. */ #include <linux/lsm_hooks.h> #include <linux/sysctl.h> #include <linux/ptrace.h> #include <linux/prctl.h> #include <linux/ratelimit.h> #include <linux/workqueue.h> #include <linux/string_helpers.h> #include <linux/task_work.h> #include <linux/sched.h> #include <linux/spinlock.h> #include <uapi/linux/lsm.h> #define YAMA_SCOPE_DISABLED 0 #define YAMA_SCOPE_RELATIONAL 1 #define YAMA_SCOPE_CAPABILITY 2 #define YAMA_SCOPE_NO_ATTACH 3 static int ptrace_scope = YAMA_SCOPE_RELATIONAL; /* describe a ptrace relationship for potential exception */ struct ptrace_relation { struct task_struct *tracer; struct task_struct *tracee; bool invalid; struct list_head node; struct rcu_head rcu; }; static LIST_HEAD(ptracer_relations); static DEFINE_SPINLOCK(ptracer_relations_lock); static void yama_relation_cleanup(struct work_struct *work); static DECLARE_WORK(yama_relation_work, yama_relation_cleanup); struct access_report_info { struct callback_head work; const char *access; struct task_struct *target; struct task_struct *agent; }; static void __report_access(struct callback_head *work) { struct access_report_info *info = container_of(work, struct access_report_info, work); char *target_cmd, *agent_cmd; target_cmd = kstrdup_quotable_cmdline(info->target, GFP_KERNEL); agent_cmd = kstrdup_quotable_cmdline(info->agent, GFP_KERNEL); pr_notice_ratelimited( "ptrace %s of \"%s\"[%d] was attempted by \"%s\"[%d]\n", info->access, target_cmd, info->target->pid, agent_cmd, info->agent->pid); kfree(agent_cmd); kfree(target_cmd); put_task_struct(info->agent); put_task_struct(info->target); kfree(info); } /* defers execution because cmdline access can sleep */ static void report_access(const char *access, struct task_struct *target, struct task_struct *agent) { struct access_report_info *info; assert_spin_locked(&target->alloc_lock); /* for target->comm */ if (current->flags & PF_KTHREAD) { /* I don't think kthreads call task_work_run() before exiting. * Imagine angry ranting about procfs here. */ pr_notice_ratelimited( "ptrace %s of \"%s\"[%d] was attempted by \"%s\"[%d]\n", access, target->comm, target->pid, agent->comm, agent->pid); return; } info = kmalloc(sizeof(*info), GFP_ATOMIC); if (!info) return; init_task_work(&info->work, __report_access); get_task_struct(target); get_task_struct(agent); info->access = access; info->target = target; info->agent = agent; if (task_work_add(current, &info->work, TWA_RESUME) == 0) return; /* success */ WARN(1, "report_access called from exiting task"); put_task_struct(target); put_task_struct(agent); kfree(info); } /** * yama_relation_cleanup - remove invalid entries from the relation list * @work: unused * */ static void yama_relation_cleanup(struct work_struct *work) { struct ptrace_relation *relation; spin_lock(&ptracer_relations_lock); rcu_read_lock(); list_for_each_entry_rcu(relation, &ptracer_relations, node) { if (relation->invalid) { list_del_rcu(&relation->node); kfree_rcu(relation, rcu); } } rcu_read_unlock(); spin_unlock(&ptracer_relations_lock); } /** * yama_ptracer_add - add/replace an exception for this tracer/tracee pair * @tracer: the task_struct of the process doing the ptrace * @tracee: the task_struct of the process to be ptraced * * Each tracee can have, at most, one tracer registered. Each time this * is called, the prior registered tracer will be replaced for the tracee. * * Returns 0 if relationship was added, -ve on error. */ static int yama_ptracer_add(struct task_struct *tracer, struct task_struct *tracee) { struct ptrace_relation *relation, *added; added = kmalloc(sizeof(*added), GFP_KERNEL); if (!added) return -ENOMEM; added->tracee = tracee; added->tracer = tracer; added->invalid = false; spin_lock(&ptracer_relations_lock); rcu_read_lock(); list_for_each_entry_rcu(relation, &ptracer_relations, node) { if (relation->invalid) continue; if (relation->tracee == tracee) { list_replace_rcu(&relation->node, &added->node); kfree_rcu(relation, rcu); goto out; } } list_add_rcu(&added->node, &ptracer_relations); out: rcu_read_unlock(); spin_unlock(&ptracer_relations_lock); return 0; } /** * yama_ptracer_del - remove exceptions related to the given tasks * @tracer: remove any relation where tracer task matches * @tracee: remove any relation where tracee task matches */ static void yama_ptracer_del(struct task_struct *tracer, struct task_struct *tracee) { struct ptrace_relation *relation; bool marked = false; rcu_read_lock(); list_for_each_entry_rcu(relation, &ptracer_relations, node) { if (relation->invalid) continue; if (relation->tracee == tracee || (tracer && relation->tracer == tracer)) { relation->invalid = true; marked = true; } } rcu_read_unlock(); if (marked) schedule_work(&yama_relation_work); } /** * yama_task_free - check for task_pid to remove from exception list * @task: task being removed */ static void yama_task_free(struct task_struct *task) { yama_ptracer_del(task, task); } /** * yama_task_prctl - check for Yama-specific prctl operations * @option: operation * @arg2: argument * @arg3: argument * @arg4: argument * @arg5: argument * * Return 0 on success, -ve on error. -ENOSYS is returned when Yama * does not handle the given option. */ static int yama_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { int rc = -ENOSYS; struct task_struct *myself; switch (option) { case PR_SET_PTRACER: /* Since a thread can call prctl(), find the group leader * before calling _add() or _del() on it, since we want * process-level granularity of control. The tracer group * leader checking is handled later when walking the ancestry * at the time of PTRACE_ATTACH check. */ myself = current->group_leader; if (arg2 == 0) { yama_ptracer_del(NULL, myself); rc = 0; } else if (arg2 == PR_SET_PTRACER_ANY || (int)arg2 == -1) { rc = yama_ptracer_add(NULL, myself); } else { struct task_struct *tracer; tracer = find_get_task_by_vpid(arg2); if (!tracer) { rc = -EINVAL; } else { rc = yama_ptracer_add(tracer, myself); put_task_struct(tracer); } } break; } return rc; } /** * task_is_descendant - walk up a process family tree looking for a match * @parent: the process to compare against while walking up from child * @child: the process to start from while looking upwards for parent * * Returns 1 if child is a descendant of parent, 0 if not. */ static int task_is_descendant(struct task_struct *parent, struct task_struct *child) { int rc = 0; struct task_struct *walker = child; if (!parent || !child) return 0; rcu_read_lock(); if (!thread_group_leader(parent)) parent = rcu_dereference(parent->group_leader); while (walker->pid > 0) { if (!thread_group_leader(walker)) walker = rcu_dereference(walker->group_leader); if (walker == parent) { rc = 1; break; } walker = rcu_dereference(walker->real_parent); } rcu_read_unlock(); return rc; } /** * ptracer_exception_found - tracer registered as exception for this tracee * @tracer: the task_struct of the process attempting ptrace * @tracee: the task_struct of the process to be ptraced * * Returns 1 if tracer has a ptracer exception ancestor for tracee. */ static int ptracer_exception_found(struct task_struct *tracer, struct task_struct *tracee) { int rc = 0; struct ptrace_relation *relation; struct task_struct *parent = NULL; bool found = false; rcu_read_lock(); /* * If there's already an active tracing relationship, then make an * exception for the sake of other accesses, like process_vm_rw(). */ parent = ptrace_parent(tracee); if (parent != NULL && same_thread_group(parent, tracer)) { rc = 1; goto unlock; } /* Look for a PR_SET_PTRACER relationship. */ if (!thread_group_leader(tracee)) tracee = rcu_dereference(tracee->group_leader); list_for_each_entry_rcu(relation, &ptracer_relations, node) { if (relation->invalid) continue; if (relation->tracee == tracee) { parent = relation->tracer; found = true; break; } } if (found && (parent == NULL || task_is_descendant(parent, tracer))) rc = 1; unlock: rcu_read_unlock(); return rc; } /** * yama_ptrace_access_check - validate PTRACE_ATTACH calls * @child: task that current task is attempting to ptrace * @mode: ptrace attach mode * * Returns 0 if following the ptrace is allowed, -ve on error. */ static int yama_ptrace_access_check(struct task_struct *child, unsigned int mode) { int rc = 0; /* require ptrace target be a child of ptracer on attach */ if (mode & PTRACE_MODE_ATTACH) { switch (ptrace_scope) { case YAMA_SCOPE_DISABLED: /* No additional restrictions. */ break; case YAMA_SCOPE_RELATIONAL: rcu_read_lock(); if (!pid_alive(child)) rc = -EPERM; if (!rc && !task_is_descendant(current, child) && !ptracer_exception_found(current, child) && !ns_capable(__task_cred(child)->user_ns, CAP_SYS_PTRACE)) rc = -EPERM; rcu_read_unlock(); break; case YAMA_SCOPE_CAPABILITY: rcu_read_lock(); if (!ns_capable(__task_cred(child)->user_ns, CAP_SYS_PTRACE)) rc = -EPERM; rcu_read_unlock(); break; case YAMA_SCOPE_NO_ATTACH: default: rc = -EPERM; break; } } if (rc && (mode & PTRACE_MODE_NOAUDIT) == 0) report_access("attach", child, current); return rc; } /** * yama_ptrace_traceme - validate PTRACE_TRACEME calls * @parent: task that will become the ptracer of the current task * * Returns 0 if following the ptrace is allowed, -ve on error. */ static int yama_ptrace_traceme(struct task_struct *parent) { int rc = 0; /* Only disallow PTRACE_TRACEME on more aggressive settings. */ switch (ptrace_scope) { case YAMA_SCOPE_CAPABILITY: if (!has_ns_capability(parent, current_user_ns(), CAP_SYS_PTRACE)) rc = -EPERM; break; case YAMA_SCOPE_NO_ATTACH: rc = -EPERM; break; } if (rc) { task_lock(current); report_access("traceme", current, parent); task_unlock(current); } return rc; } static const struct lsm_id yama_lsmid = { .name = "yama", .id = LSM_ID_YAMA, }; static struct security_hook_list yama_hooks[] __ro_after_init = { LSM_HOOK_INIT(ptrace_access_check, yama_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, yama_ptrace_traceme), LSM_HOOK_INIT(task_prctl, yama_task_prctl), LSM_HOOK_INIT(task_free, yama_task_free), }; #ifdef CONFIG_SYSCTL static int yama_dointvec_minmax(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table table_copy; if (write && !capable(CAP_SYS_PTRACE)) return -EPERM; /* Lock the max value if it ever gets set. */ table_copy = *table; if (*(int *)table_copy.data == *(int *)table_copy.extra2) table_copy.extra1 = table_copy.extra2; return proc_dointvec_minmax(&table_copy, write, buffer, lenp, ppos); } static int max_scope = YAMA_SCOPE_NO_ATTACH; static const struct ctl_table yama_sysctl_table[] = { { .procname = "ptrace_scope", .data = &ptrace_scope, .maxlen = sizeof(int), .mode = 0644, .proc_handler = yama_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &max_scope, }, }; static void __init yama_init_sysctl(void) { if (!register_sysctl("kernel/yama", yama_sysctl_table)) panic("Yama: sysctl registration failed.\n"); } #else static inline void yama_init_sysctl(void) { } #endif /* CONFIG_SYSCTL */ static int __init yama_init(void) { pr_info("Yama: becoming mindful.\n"); security_add_hooks(yama_hooks, ARRAY_SIZE(yama_hooks), &yama_lsmid); yama_init_sysctl(); return 0; } DEFINE_LSM(yama) = { .name = "yama", .init = yama_init, }; |
| 397 27 584 102 85 20 35 27 27 14 428 429 13 46 8 1 1 33 33 13 7 139 140 128 2 41 583 28 584 47 581 469 561 52 53 47 4 7 52 21 2 59 59 57 53 53 429 429 1 32 61 14 397 13 13 403 28 100 282 21 75 37 43 69 242 209 429 7 7 6 1 2 7 4 4 2 2 3 3 3 2 238 338 3 219 222 222 108 108 24 24 108 380 2 112 46 108 108 108 52 101 3 22 106 107 107 63 61 113 381 6 377 378 2 379 3 216 1 377 5 2 378 1 12 375 4 378 380 28 244 317 319 33 2 12 314 14 12 20 7 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 | // SPDX-License-Identifier: GPL-2.0 /* * * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. * * TODO: try to use extents tree (instead of array) */ #include <linux/blkdev.h> #include <linux/fs.h> #include <linux/log2.h> #include "debug.h" #include "ntfs.h" #include "ntfs_fs.h" /* runs_tree is a continues memory. Try to avoid big size. */ #define NTFS3_RUN_MAX_BYTES 0x10000 struct ntfs_run { CLST vcn; /* Virtual cluster number. */ CLST len; /* Length in clusters. */ CLST lcn; /* Logical cluster number. */ }; /* * run_lookup - Lookup the index of a MCB entry that is first <= vcn. * * Case of success it will return non-zero value and set * @index parameter to index of entry been found. * Case of entry missing from list 'index' will be set to * point to insertion position for the entry question. */ static bool run_lookup(const struct runs_tree *run, CLST vcn, size_t *index) { size_t min_idx, max_idx, mid_idx; struct ntfs_run *r; if (!run->count) { *index = 0; return false; } min_idx = 0; max_idx = run->count - 1; /* Check boundary cases specially, 'cause they cover the often requests. */ r = run->runs; if (vcn < r->vcn) { *index = 0; return false; } if (vcn < r->vcn + r->len) { *index = 0; return true; } r += max_idx; if (vcn >= r->vcn + r->len) { *index = run->count; return false; } if (vcn >= r->vcn) { *index = max_idx; return true; } do { mid_idx = min_idx + ((max_idx - min_idx) >> 1); r = run->runs + mid_idx; if (vcn < r->vcn) { max_idx = mid_idx - 1; if (!mid_idx) break; } else if (vcn >= r->vcn + r->len) { min_idx = mid_idx + 1; } else { *index = mid_idx; return true; } } while (min_idx <= max_idx); *index = max_idx + 1; return false; } /* * run_consolidate - Consolidate runs starting from a given one. */ static void run_consolidate(struct runs_tree *run, size_t index) { size_t i; struct ntfs_run *r = run->runs + index; while (index + 1 < run->count) { /* * I should merge current run with next * if start of the next run lies inside one being tested. */ struct ntfs_run *n = r + 1; CLST end = r->vcn + r->len; CLST dl; /* Stop if runs are not aligned one to another. */ if (n->vcn > end) break; dl = end - n->vcn; /* * If range at index overlaps with next one * then I will either adjust it's start position * or (if completely matches) dust remove one from the list. */ if (dl > 0) { if (n->len <= dl) goto remove_next_range; n->len -= dl; n->vcn += dl; if (n->lcn != SPARSE_LCN) n->lcn += dl; dl = 0; } /* * Stop if sparse mode does not match * both current and next runs. */ if ((n->lcn == SPARSE_LCN) != (r->lcn == SPARSE_LCN)) { index += 1; r = n; continue; } /* * Check if volume block * of a next run lcn does not match * last volume block of the current run. */ if (n->lcn != SPARSE_LCN && n->lcn != r->lcn + r->len) break; /* * Next and current are siblings. * Eat/join. */ r->len += n->len - dl; remove_next_range: i = run->count - (index + 1); if (i > 1) memmove(n, n + 1, sizeof(*n) * (i - 1)); run->count -= 1; } } /* * run_is_mapped_full * * Return: True if range [svcn - evcn] is mapped. */ bool run_is_mapped_full(const struct runs_tree *run, CLST svcn, CLST evcn) { size_t i; const struct ntfs_run *r, *end; CLST next_vcn; if (!run_lookup(run, svcn, &i)) return false; end = run->runs + run->count; r = run->runs + i; for (;;) { next_vcn = r->vcn + r->len; if (next_vcn > evcn) return true; if (++r >= end) return false; if (r->vcn != next_vcn) return false; } } bool run_lookup_entry(const struct runs_tree *run, CLST vcn, CLST *lcn, CLST *len, size_t *index) { size_t idx; CLST gap; struct ntfs_run *r; /* Fail immediately if nrun was not touched yet. */ if (!run->runs) return false; if (!run_lookup(run, vcn, &idx)) return false; r = run->runs + idx; if (vcn >= r->vcn + r->len) return false; gap = vcn - r->vcn; if (r->len <= gap) return false; *lcn = r->lcn == SPARSE_LCN ? SPARSE_LCN : (r->lcn + gap); if (len) *len = r->len - gap; if (index) *index = idx; return true; } /* * run_truncate_head - Decommit the range before vcn. */ void run_truncate_head(struct runs_tree *run, CLST vcn) { size_t index; struct ntfs_run *r; if (run_lookup(run, vcn, &index)) { r = run->runs + index; if (vcn > r->vcn) { CLST dlen = vcn - r->vcn; r->vcn = vcn; r->len -= dlen; if (r->lcn != SPARSE_LCN) r->lcn += dlen; } if (!index) return; } r = run->runs; memmove(r, r + index, sizeof(*r) * (run->count - index)); run->count -= index; if (!run->count) { kvfree(run->runs); run->runs = NULL; run->allocated = 0; } } /* * run_truncate - Decommit the range after vcn. */ void run_truncate(struct runs_tree *run, CLST vcn) { size_t index; /* * If I hit the range then * I have to truncate one. * If range to be truncated is becoming empty * then it will entirely be removed. */ if (run_lookup(run, vcn, &index)) { struct ntfs_run *r = run->runs + index; r->len = vcn - r->vcn; if (r->len > 0) index += 1; } /* * At this point 'index' is set to position that * should be thrown away (including index itself) * Simple one - just set the limit. */ run->count = index; /* Do not reallocate array 'runs'. Only free if possible. */ if (!index) { kvfree(run->runs); run->runs = NULL; run->allocated = 0; } } /* * run_truncate_around - Trim head and tail if necessary. */ void run_truncate_around(struct runs_tree *run, CLST vcn) { run_truncate_head(run, vcn); if (run->count >= NTFS3_RUN_MAX_BYTES / sizeof(struct ntfs_run) / 2) run_truncate(run, (run->runs + (run->count >> 1))->vcn); } /* * run_add_entry * * Sets location to known state. * Run to be added may overlap with existing location. * * Return: false if of memory. */ bool run_add_entry(struct runs_tree *run, CLST vcn, CLST lcn, CLST len, bool is_mft) { size_t used, index; struct ntfs_run *r; bool inrange; CLST tail_vcn = 0, tail_len = 0, tail_lcn = 0; bool should_add_tail = false; /* * Lookup the insertion point. * * Execute bsearch for the entry containing * start position question. */ inrange = run_lookup(run, vcn, &index); /* * Shortcut here would be case of * range not been found but one been added * continues previous run. * This case I can directly make use of * existing range as my start point. */ if (!inrange && index > 0) { struct ntfs_run *t = run->runs + index - 1; if (t->vcn + t->len == vcn && (t->lcn == SPARSE_LCN) == (lcn == SPARSE_LCN) && (lcn == SPARSE_LCN || lcn == t->lcn + t->len)) { inrange = true; index -= 1; } } /* * At this point 'index' either points to the range * containing start position or to the insertion position * for a new range. * So first let's check if range I'm probing is here already. */ if (!inrange) { requires_new_range: /* * Range was not found. * Insert at position 'index' */ used = run->count * sizeof(struct ntfs_run); /* * Check allocated space. * If one is not enough to get one more entry * then it will be reallocated. */ if (run->allocated < used + sizeof(struct ntfs_run)) { size_t bytes; struct ntfs_run *new_ptr; /* Use power of 2 for 'bytes'. */ if (!used) { bytes = 64; } else if (used <= 16 * PAGE_SIZE) { if (is_power_of_2(run->allocated)) bytes = run->allocated << 1; else bytes = (size_t)1 << (2 + blksize_bits(used)); } else { bytes = run->allocated + (16 * PAGE_SIZE); } WARN_ON(!is_mft && bytes > NTFS3_RUN_MAX_BYTES); new_ptr = kvmalloc(bytes, GFP_KERNEL); if (!new_ptr) return false; r = new_ptr + index; memcpy(new_ptr, run->runs, index * sizeof(struct ntfs_run)); memcpy(r + 1, run->runs + index, sizeof(struct ntfs_run) * (run->count - index)); kvfree(run->runs); run->runs = new_ptr; run->allocated = bytes; } else { size_t i = run->count - index; r = run->runs + index; /* memmove appears to be a bottle neck here... */ if (i > 0) memmove(r + 1, r, sizeof(struct ntfs_run) * i); } r->vcn = vcn; r->lcn = lcn; r->len = len; run->count += 1; } else { r = run->runs + index; /* * If one of ranges was not allocated then we * have to split location we just matched and * insert current one. * A common case this requires tail to be reinserted * a recursive call. */ if (((lcn == SPARSE_LCN) != (r->lcn == SPARSE_LCN)) || (lcn != SPARSE_LCN && lcn != r->lcn + (vcn - r->vcn))) { CLST to_eat = vcn - r->vcn; CLST Tovcn = to_eat + len; should_add_tail = Tovcn < r->len; if (should_add_tail) { tail_lcn = r->lcn == SPARSE_LCN ? SPARSE_LCN : (r->lcn + Tovcn); tail_vcn = r->vcn + Tovcn; tail_len = r->len - Tovcn; } if (to_eat > 0) { r->len = to_eat; inrange = false; index += 1; goto requires_new_range; } /* lcn should match one were going to add. */ r->lcn = lcn; } /* * If existing range fits then were done. * Otherwise extend found one and fall back to range jocode. */ if (r->vcn + r->len < vcn + len) r->len += len - ((r->vcn + r->len) - vcn); } /* * And normalize it starting from insertion point. * It's possible that no insertion needed case if * start point lies within the range of an entry * that 'index' points to. */ if (inrange && index > 0) index -= 1; run_consolidate(run, index); run_consolidate(run, index + 1); /* * A special case. * We have to add extra range a tail. */ if (should_add_tail && !run_add_entry(run, tail_vcn, tail_lcn, tail_len, is_mft)) return false; return true; } /* run_collapse_range * * Helper for attr_collapse_range(), * which is helper for fallocate(collapse_range). */ bool run_collapse_range(struct runs_tree *run, CLST vcn, CLST len) { size_t index, eat; struct ntfs_run *r, *e, *eat_start, *eat_end; CLST end; if (WARN_ON(!run_lookup(run, vcn, &index))) return true; /* Should never be here. */ e = run->runs + run->count; r = run->runs + index; end = vcn + len; if (vcn > r->vcn) { if (r->vcn + r->len <= end) { /* Collapse tail of run .*/ r->len = vcn - r->vcn; } else if (r->lcn == SPARSE_LCN) { /* Collapse a middle part of sparsed run. */ r->len -= len; } else { /* Collapse a middle part of normal run, split. */ if (!run_add_entry(run, vcn, SPARSE_LCN, len, false)) return false; return run_collapse_range(run, vcn, len); } r += 1; } eat_start = r; eat_end = r; for (; r < e; r++) { CLST d; if (r->vcn >= end) { r->vcn -= len; continue; } if (r->vcn + r->len <= end) { /* Eat this run. */ eat_end = r + 1; continue; } d = end - r->vcn; if (r->lcn != SPARSE_LCN) r->lcn += d; r->len -= d; r->vcn -= len - d; } eat = eat_end - eat_start; memmove(eat_start, eat_end, (e - eat_end) * sizeof(*r)); run->count -= eat; return true; } /* run_insert_range * * Helper for attr_insert_range(), * which is helper for fallocate(insert_range). */ bool run_insert_range(struct runs_tree *run, CLST vcn, CLST len) { size_t index; struct ntfs_run *r, *e; if (WARN_ON(!run_lookup(run, vcn, &index))) return false; /* Should never be here. */ e = run->runs + run->count; r = run->runs + index; if (vcn > r->vcn) r += 1; for (; r < e; r++) r->vcn += len; r = run->runs + index; if (vcn > r->vcn) { /* split fragment. */ CLST len1 = vcn - r->vcn; CLST len2 = r->len - len1; CLST lcn2 = r->lcn == SPARSE_LCN ? SPARSE_LCN : (r->lcn + len1); r->len = len1; if (!run_add_entry(run, vcn + len, lcn2, len2, false)) return false; } if (!run_add_entry(run, vcn, SPARSE_LCN, len, false)) return false; return true; } /* * run_get_entry - Return index-th mapped region. */ bool run_get_entry(const struct runs_tree *run, size_t index, CLST *vcn, CLST *lcn, CLST *len) { const struct ntfs_run *r; if (index >= run->count) return false; r = run->runs + index; if (!r->len) return false; if (vcn) *vcn = r->vcn; if (lcn) *lcn = r->lcn; if (len) *len = r->len; return true; } /* * run_packed_size - Calculate the size of packed int64. */ #ifdef __BIG_ENDIAN static inline int run_packed_size(const s64 n) { const u8 *p = (const u8 *)&n + sizeof(n) - 1; if (n >= 0) { if (p[-7] || p[-6] || p[-5] || p[-4]) p -= 4; if (p[-3] || p[-2]) p -= 2; if (p[-1]) p -= 1; if (p[0] & 0x80) p -= 1; } else { if (p[-7] != 0xff || p[-6] != 0xff || p[-5] != 0xff || p[-4] != 0xff) p -= 4; if (p[-3] != 0xff || p[-2] != 0xff) p -= 2; if (p[-1] != 0xff) p -= 1; if (!(p[0] & 0x80)) p -= 1; } return (const u8 *)&n + sizeof(n) - p; } /* Full trusted function. It does not check 'size' for errors. */ static inline void run_pack_s64(u8 *run_buf, u8 size, s64 v) { const u8 *p = (u8 *)&v; switch (size) { case 8: run_buf[7] = p[0]; fallthrough; case 7: run_buf[6] = p[1]; fallthrough; case 6: run_buf[5] = p[2]; fallthrough; case 5: run_buf[4] = p[3]; fallthrough; case 4: run_buf[3] = p[4]; fallthrough; case 3: run_buf[2] = p[5]; fallthrough; case 2: run_buf[1] = p[6]; fallthrough; case 1: run_buf[0] = p[7]; } } /* Full trusted function. It does not check 'size' for errors. */ static inline s64 run_unpack_s64(const u8 *run_buf, u8 size, s64 v) { u8 *p = (u8 *)&v; switch (size) { case 8: p[0] = run_buf[7]; fallthrough; case 7: p[1] = run_buf[6]; fallthrough; case 6: p[2] = run_buf[5]; fallthrough; case 5: p[3] = run_buf[4]; fallthrough; case 4: p[4] = run_buf[3]; fallthrough; case 3: p[5] = run_buf[2]; fallthrough; case 2: p[6] = run_buf[1]; fallthrough; case 1: p[7] = run_buf[0]; } return v; } #else static inline int run_packed_size(const s64 n) { const u8 *p = (const u8 *)&n; if (n >= 0) { if (p[7] || p[6] || p[5] || p[4]) p += 4; if (p[3] || p[2]) p += 2; if (p[1]) p += 1; if (p[0] & 0x80) p += 1; } else { if (p[7] != 0xff || p[6] != 0xff || p[5] != 0xff || p[4] != 0xff) p += 4; if (p[3] != 0xff || p[2] != 0xff) p += 2; if (p[1] != 0xff) p += 1; if (!(p[0] & 0x80)) p += 1; } return 1 + p - (const u8 *)&n; } /* Full trusted function. It does not check 'size' for errors. */ static inline void run_pack_s64(u8 *run_buf, u8 size, s64 v) { const u8 *p = (u8 *)&v; /* memcpy( run_buf, &v, size); Is it faster? */ switch (size) { case 8: run_buf[7] = p[7]; fallthrough; case 7: run_buf[6] = p[6]; fallthrough; case 6: run_buf[5] = p[5]; fallthrough; case 5: run_buf[4] = p[4]; fallthrough; case 4: run_buf[3] = p[3]; fallthrough; case 3: run_buf[2] = p[2]; fallthrough; case 2: run_buf[1] = p[1]; fallthrough; case 1: run_buf[0] = p[0]; } } /* full trusted function. It does not check 'size' for errors */ static inline s64 run_unpack_s64(const u8 *run_buf, u8 size, s64 v) { u8 *p = (u8 *)&v; /* memcpy( &v, run_buf, size); Is it faster? */ switch (size) { case 8: p[7] = run_buf[7]; fallthrough; case 7: p[6] = run_buf[6]; fallthrough; case 6: p[5] = run_buf[5]; fallthrough; case 5: p[4] = run_buf[4]; fallthrough; case 4: p[3] = run_buf[3]; fallthrough; case 3: p[2] = run_buf[2]; fallthrough; case 2: p[1] = run_buf[1]; fallthrough; case 1: p[0] = run_buf[0]; } return v; } #endif /* * run_pack - Pack runs into buffer. * * packed_vcns - How much runs we have packed. * packed_size - How much bytes we have used run_buf. */ int run_pack(const struct runs_tree *run, CLST svcn, CLST len, u8 *run_buf, u32 run_buf_size, CLST *packed_vcns) { CLST next_vcn, vcn, lcn; CLST prev_lcn = 0; CLST evcn1 = svcn + len; const struct ntfs_run *r, *r_end; int packed_size = 0; size_t i; s64 dlcn; int offset_size, size_size, tmp; *packed_vcns = 0; if (!len) goto out; /* Check all required entries [svcn, encv1) available. */ if (!run_lookup(run, svcn, &i)) return -ENOENT; r_end = run->runs + run->count; r = run->runs + i; for (next_vcn = r->vcn + r->len; next_vcn < evcn1; next_vcn = r->vcn + r->len) { if (++r >= r_end || r->vcn != next_vcn) return -ENOENT; } /* Repeat cycle above and pack runs. Assume no errors. */ r = run->runs + i; len = svcn - r->vcn; vcn = svcn; lcn = r->lcn == SPARSE_LCN ? SPARSE_LCN : (r->lcn + len); len = r->len - len; for (;;) { next_vcn = vcn + len; if (next_vcn > evcn1) len = evcn1 - vcn; /* How much bytes required to pack len. */ size_size = run_packed_size(len); /* offset_size - How much bytes is packed dlcn. */ if (lcn == SPARSE_LCN) { offset_size = 0; dlcn = 0; } else { /* NOTE: lcn can be less than prev_lcn! */ dlcn = (s64)lcn - prev_lcn; offset_size = run_packed_size(dlcn); prev_lcn = lcn; } tmp = run_buf_size - packed_size - 2 - offset_size; if (tmp <= 0) goto out; /* Can we store this entire run. */ if (tmp < size_size) goto out; if (run_buf) { /* Pack run header. */ run_buf[0] = ((u8)(size_size | (offset_size << 4))); run_buf += 1; /* Pack the length of run. */ run_pack_s64(run_buf, size_size, len); run_buf += size_size; /* Pack the offset from previous LCN. */ run_pack_s64(run_buf, offset_size, dlcn); run_buf += offset_size; } packed_size += 1 + offset_size + size_size; *packed_vcns += len; if (packed_size + 1 >= run_buf_size || next_vcn >= evcn1) goto out; r += 1; vcn = r->vcn; lcn = r->lcn; len = r->len; } out: /* Store last zero. */ if (run_buf) run_buf[0] = 0; return packed_size + 1; } /* * run_unpack - Unpack packed runs from @run_buf. * * Return: Error if negative, or real used bytes. */ int run_unpack(struct runs_tree *run, struct ntfs_sb_info *sbi, CLST ino, CLST svcn, CLST evcn, CLST vcn, const u8 *run_buf, int run_buf_size) { u64 prev_lcn, vcn64, lcn, next_vcn; const u8 *run_last, *run_0; bool is_mft = ino == MFT_REC_MFT; if (run_buf_size < 0) return -EINVAL; /* Check for empty. */ if (evcn + 1 == svcn) return 0; if (evcn < svcn) return -EINVAL; run_0 = run_buf; run_last = run_buf + run_buf_size; prev_lcn = 0; vcn64 = svcn; /* Read all runs the chain. */ /* size_size - How much bytes is packed len. */ while (run_buf < run_last) { /* size_size - How much bytes is packed len. */ u8 size_size = *run_buf & 0xF; /* offset_size - How much bytes is packed dlcn. */ u8 offset_size = *run_buf++ >> 4; u64 len; if (!size_size) break; /* * Unpack runs. * NOTE: Runs are stored little endian order * "len" is unsigned value, "dlcn" is signed. * Large positive number requires to store 5 bytes * e.g.: 05 FF 7E FF FF 00 00 00 */ if (size_size > sizeof(len)) return -EINVAL; len = run_unpack_s64(run_buf, size_size, 0); /* Skip size_size. */ run_buf += size_size; if (!len) return -EINVAL; if (!offset_size) lcn = SPARSE_LCN64; else if (offset_size <= sizeof(s64)) { s64 dlcn; /* Initial value of dlcn is -1 or 0. */ dlcn = (run_buf[offset_size - 1] & 0x80) ? (s64)-1 : 0; dlcn = run_unpack_s64(run_buf, offset_size, dlcn); /* Skip offset_size. */ run_buf += offset_size; if (!dlcn) return -EINVAL; lcn = prev_lcn + dlcn; prev_lcn = lcn; } else { /* The size of 'dlcn' can't be > 8. */ return -EINVAL; } next_vcn = vcn64 + len; /* Check boundary. */ if (next_vcn > evcn + 1) return -EINVAL; #ifndef CONFIG_NTFS3_64BIT_CLUSTER if (next_vcn > 0x100000000ull || (lcn + len) > 0x100000000ull) { ntfs_err( sbi->sb, "This driver is compiled without CONFIG_NTFS3_64BIT_CLUSTER (like windows driver).\n" "Volume contains 64 bits run: vcn %llx, lcn %llx, len %llx.\n" "Activate CONFIG_NTFS3_64BIT_CLUSTER to process this case", vcn64, lcn, len); return -EOPNOTSUPP; } #endif if (lcn != SPARSE_LCN64 && lcn + len > sbi->used.bitmap.nbits) { /* LCN range is out of volume. */ return -EINVAL; } if (!run) ; /* Called from check_attr(fslog.c) to check run. */ else if (run == RUN_DEALLOCATE) { /* * Called from ni_delete_all to free clusters * without storing in run. */ if (lcn != SPARSE_LCN64) mark_as_free_ex(sbi, lcn, len, true); } else if (vcn64 >= vcn) { if (!run_add_entry(run, vcn64, lcn, len, is_mft)) return -ENOMEM; } else if (next_vcn > vcn) { u64 dlen = vcn - vcn64; if (!run_add_entry(run, vcn, lcn + dlen, len - dlen, is_mft)) return -ENOMEM; } vcn64 = next_vcn; } if (vcn64 != evcn + 1) { /* Not expected length of unpacked runs. */ return -EINVAL; } return run_buf - run_0; } #ifdef NTFS3_CHECK_FREE_CLST /* * run_unpack_ex - Unpack packed runs from "run_buf". * * Checks unpacked runs to be used in bitmap. * * Return: Error if negative, or real used bytes. */ int run_unpack_ex(struct runs_tree *run, struct ntfs_sb_info *sbi, CLST ino, CLST svcn, CLST evcn, CLST vcn, const u8 *run_buf, int run_buf_size) { int ret, err; CLST next_vcn, lcn, len; size_t index, done; bool ok, zone; struct wnd_bitmap *wnd; ret = run_unpack(run, sbi, ino, svcn, evcn, vcn, run_buf, run_buf_size); if (ret <= 0) return ret; if (!sbi->used.bitmap.sb || !run || run == RUN_DEALLOCATE) return ret; if (ino == MFT_REC_BADCLUST) return ret; next_vcn = vcn = svcn; wnd = &sbi->used.bitmap; for (ok = run_lookup_entry(run, vcn, &lcn, &len, &index); next_vcn <= evcn; ok = run_get_entry(run, ++index, &vcn, &lcn, &len)) { if (!ok || next_vcn != vcn) return -EINVAL; next_vcn = vcn + len; if (lcn == SPARSE_LCN) continue; if (sbi->flags & NTFS_FLAGS_NEED_REPLAY) continue; down_read_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS); zone = max(wnd->zone_bit, lcn) < min(wnd->zone_end, lcn + len); /* Check for free blocks. */ ok = !zone && wnd_is_used(wnd, lcn, len); up_read(&wnd->rw_lock); if (ok) continue; /* Looks like volume is corrupted. */ ntfs_set_state(sbi, NTFS_DIRTY_ERROR); if (!down_write_trylock(&wnd->rw_lock)) continue; if (zone) { /* * Range [lcn, lcn + len) intersects with zone. * To avoid complex with zone just turn it off. */ wnd_zone_set(wnd, 0, 0); } /* Mark all zero bits as used in range [lcn, lcn+len). */ err = wnd_set_used_safe(wnd, lcn, len, &done); if (zone) { /* Restore zone. Lock mft run. */ struct rw_semaphore *lock = is_mounted(sbi) ? &sbi->mft.ni->file.run_lock : NULL; if (lock) down_read(lock); ntfs_refresh_zone(sbi); if (lock) up_read(lock); } up_write(&wnd->rw_lock); if (err) return err; } return ret; } #endif /* * run_get_highest_vcn * * Return the highest vcn from a mapping pairs array * it used while replaying log file. */ int run_get_highest_vcn(CLST vcn, const u8 *run_buf, u64 *highest_vcn) { u64 vcn64 = vcn; u8 size_size; while ((size_size = *run_buf & 0xF)) { u8 offset_size = *run_buf++ >> 4; u64 len; if (size_size > 8 || offset_size > 8) return -EINVAL; len = run_unpack_s64(run_buf, size_size, 0); if (!len) return -EINVAL; run_buf += size_size + offset_size; vcn64 += len; #ifndef CONFIG_NTFS3_64BIT_CLUSTER if (vcn64 > 0x100000000ull) return -EINVAL; #endif } *highest_vcn = vcn64 - 1; return 0; } /* * run_clone * * Make a copy of run */ int run_clone(const struct runs_tree *run, struct runs_tree *new_run) { size_t bytes = run->count * sizeof(struct ntfs_run); if (bytes > new_run->allocated) { struct ntfs_run *new_ptr = kvmalloc(bytes, GFP_KERNEL); if (!new_ptr) return -ENOMEM; kvfree(new_run->runs); new_run->runs = new_ptr; new_run->allocated = bytes; } memcpy(new_run->runs, run->runs, bytes); new_run->count = run->count; return 0; } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright 2011-2014 Autronica Fire and Security AS * * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * * include file for HSR and PRP. */ #ifndef __HSR_SLAVE_H #define __HSR_SLAVE_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include "hsr_main.h" int hsr_add_port(struct hsr_priv *hsr, struct net_device *dev, enum hsr_port_type pt, struct netlink_ext_ack *extack); void hsr_del_port(struct hsr_port *port); bool hsr_port_exists(const struct net_device *dev); static inline struct hsr_port *hsr_port_get_rtnl(const struct net_device *dev) { ASSERT_RTNL(); return hsr_port_exists(dev) ? rtnl_dereference(dev->rx_handler_data) : NULL; } static inline struct hsr_port *hsr_port_get_rcu(const struct net_device *dev) { return hsr_port_exists(dev) ? rcu_dereference(dev->rx_handler_data) : NULL; } bool hsr_invalid_dan_ingress_frame(__be16 protocol); #endif /* __HSR_SLAVE_H */ |
| 64 65 67 67 2 65 65 | 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 | /* * kmod - the kernel module loader * * Copyright (C) 2023 Luis Chamberlain <mcgrof@kernel.org> */ #include <linux/module.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/binfmts.h> #include <linux/syscalls.h> #include <linux/unistd.h> #include <linux/kmod.h> #include <linux/slab.h> #include <linux/completion.h> #include <linux/cred.h> #include <linux/file.h> #include <linux/workqueue.h> #include <linux/security.h> #include <linux/mount.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/resource.h> #include <linux/notifier.h> #include <linux/suspend.h> #include <linux/rwsem.h> #include <linux/ptrace.h> #include <linux/async.h> #include <linux/uaccess.h> #include <trace/events/module.h> #include "internal.h" /* * Assuming: * * threads = div64_u64((u64) totalram_pages * (u64) PAGE_SIZE, * (u64) THREAD_SIZE * 8UL); * * If you need less than 50 threads would mean we're dealing with systems * smaller than 3200 pages. This assumes you are capable of having ~13M memory, * and this would only be an upper limit, after which the OOM killer would take * effect. Systems like these are very unlikely if modules are enabled. */ #define MAX_KMOD_CONCURRENT 50 static DEFINE_SEMAPHORE(kmod_concurrent_max, MAX_KMOD_CONCURRENT); /* * This is a restriction on having *all* MAX_KMOD_CONCURRENT threads * running at the same time without returning. When this happens we * believe you've somehow ended up with a recursive module dependency * creating a loop. * * We have no option but to fail. * * Userspace should proactively try to detect and prevent these. */ #define MAX_KMOD_ALL_BUSY_TIMEOUT 5 /* modprobe_path is set via /proc/sys. */ char modprobe_path[KMOD_PATH_LEN] = CONFIG_MODPROBE_PATH; static void free_modprobe_argv(struct subprocess_info *info) { kfree(info->argv[3]); /* check call_modprobe() */ kfree(info->argv); } static int call_modprobe(char *orig_module_name, int wait) { struct subprocess_info *info; static char *envp[] = { "HOME=/", "TERM=linux", "PATH=/sbin:/usr/sbin:/bin:/usr/bin", NULL }; char *module_name; int ret; char **argv = kmalloc(sizeof(char *[5]), GFP_KERNEL); if (!argv) goto out; module_name = kstrdup(orig_module_name, GFP_KERNEL); if (!module_name) goto free_argv; argv[0] = modprobe_path; argv[1] = "-q"; argv[2] = "--"; argv[3] = module_name; /* check free_modprobe_argv() */ argv[4] = NULL; info = call_usermodehelper_setup(modprobe_path, argv, envp, GFP_KERNEL, NULL, free_modprobe_argv, NULL); if (!info) goto free_module_name; ret = call_usermodehelper_exec(info, wait | UMH_KILLABLE); kmod_dup_request_announce(orig_module_name, ret); return ret; free_module_name: kfree(module_name); free_argv: kfree(argv); out: kmod_dup_request_announce(orig_module_name, -ENOMEM); return -ENOMEM; } /** * __request_module - try to load a kernel module * @wait: wait (or not) for the operation to complete * @fmt: printf style format string for the name of the module * @...: arguments as specified in the format string * * Load a module using the user mode module loader. The function returns * zero on success or a negative errno code or positive exit code from * "modprobe" on failure. Note that a successful module load does not mean * the module did not then unload and exit on an error of its own. Callers * must check that the service they requested is now available not blindly * invoke it. * * If module auto-loading support is disabled then this function * simply returns -ENOENT. */ int __request_module(bool wait, const char *fmt, ...) { va_list args; char module_name[MODULE_NAME_LEN]; int ret, dup_ret; /* * We don't allow synchronous module loading from async. Module * init may invoke async_synchronize_full() which will end up * waiting for this task which already is waiting for the module * loading to complete, leading to a deadlock. */ WARN_ON_ONCE(wait && current_is_async()); if (!modprobe_path[0]) return -ENOENT; va_start(args, fmt); ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args); va_end(args); if (ret >= MODULE_NAME_LEN) return -ENAMETOOLONG; ret = security_kernel_module_request(module_name); if (ret) return ret; ret = down_timeout(&kmod_concurrent_max, MAX_KMOD_ALL_BUSY_TIMEOUT * HZ); if (ret) { pr_warn_ratelimited("request_module: modprobe %s cannot be processed, kmod busy with %d threads for more than %d seconds now", module_name, MAX_KMOD_CONCURRENT, MAX_KMOD_ALL_BUSY_TIMEOUT); return ret; } trace_module_request(module_name, wait, _RET_IP_); if (kmod_dup_request_exists_wait(module_name, wait, &dup_ret)) { ret = dup_ret; goto out; } ret = call_modprobe(module_name, wait ? UMH_WAIT_PROC : UMH_WAIT_EXEC); out: up(&kmod_concurrent_max); return ret; } EXPORT_SYMBOL(__request_module); |
| 7 1 6 7 7 7 7 7 7 1 1 1 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * * Modified by Fred N. van Kempen, 01/29/93, to add line disciplines * which can be dynamically activated and de-activated by the line * discipline handling modules (like SLIP). */ #include <linux/bits.h> #include <linux/types.h> #include <linux/termios.h> #include <linux/errno.h> #include <linux/sched/signal.h> #include <linux/kernel.h> #include <linux/major.h> #include <linux/tty.h> #include <linux/fcntl.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/bitops.h> #include <linux/mutex.h> #include <linux/compat.h> #include <linux/termios_internal.h> #include "tty.h" #include <asm/io.h> #include <linux/uaccess.h> #undef DEBUG /* * Internal flag options for termios setting behavior */ #define TERMIOS_FLUSH BIT(0) #define TERMIOS_WAIT BIT(1) #define TERMIOS_TERMIO BIT(2) #define TERMIOS_OLD BIT(3) /** * tty_chars_in_buffer - characters pending * @tty: terminal * * Returns: the number of bytes of data in the device private output queue. If * no private method is supplied there is assumed to be no queue on the device. */ unsigned int tty_chars_in_buffer(struct tty_struct *tty) { if (tty->ops->chars_in_buffer) return tty->ops->chars_in_buffer(tty); return 0; } EXPORT_SYMBOL(tty_chars_in_buffer); /** * tty_write_room - write queue space * @tty: terminal * * Returns: the number of bytes that can be queued to this device at the present * time. The result should be treated as a guarantee and the driver cannot * offer a value it later shrinks by more than the number of bytes written. If * no method is provided, 2K is always returned and data may be lost as there * will be no flow control. */ unsigned int tty_write_room(struct tty_struct *tty) { if (tty->ops->write_room) return tty->ops->write_room(tty); return 2048; } EXPORT_SYMBOL(tty_write_room); /** * tty_driver_flush_buffer - discard internal buffer * @tty: terminal * * Discard the internal output buffer for this device. If no method is provided, * then either the buffer cannot be hardware flushed or there is no buffer * driver side. */ void tty_driver_flush_buffer(struct tty_struct *tty) { if (tty->ops->flush_buffer) tty->ops->flush_buffer(tty); } EXPORT_SYMBOL(tty_driver_flush_buffer); /** * tty_unthrottle - flow control * @tty: terminal * * Indicate that a @tty may continue transmitting data down the stack. Takes * the &tty_struct->termios_rwsem to protect against parallel * throttle/unthrottle and also to ensure the driver can consistently reference * its own termios data at this point when implementing software flow control. * * Drivers should however remember that the stack can issue a throttle, then * change flow control method, then unthrottle. */ void tty_unthrottle(struct tty_struct *tty) { down_write(&tty->termios_rwsem); if (test_and_clear_bit(TTY_THROTTLED, &tty->flags) && tty->ops->unthrottle) tty->ops->unthrottle(tty); tty->flow_change = TTY_FLOW_NO_CHANGE; up_write(&tty->termios_rwsem); } EXPORT_SYMBOL(tty_unthrottle); /** * tty_throttle_safe - flow control * @tty: terminal * * Indicate that a @tty should stop transmitting data down the stack. * tty_throttle_safe() will only attempt throttle if @tty->flow_change is * %TTY_THROTTLE_SAFE. Prevents an accidental throttle due to race conditions * when throttling is conditional on factors evaluated prior to throttling. * * Returns: %true if @tty is throttled (or was already throttled) */ bool tty_throttle_safe(struct tty_struct *tty) { bool ret = true; mutex_lock(&tty->throttle_mutex); if (!tty_throttled(tty)) { if (tty->flow_change != TTY_THROTTLE_SAFE) ret = false; else { set_bit(TTY_THROTTLED, &tty->flags); if (tty->ops->throttle) tty->ops->throttle(tty); } } mutex_unlock(&tty->throttle_mutex); return ret; } /** * tty_unthrottle_safe - flow control * @tty: terminal * * Similar to tty_unthrottle() but will only attempt unthrottle if * @tty->flow_change is %TTY_UNTHROTTLE_SAFE. Prevents an accidental unthrottle * due to race conditions when unthrottling is conditional on factors evaluated * prior to unthrottling. * * Returns: %true if @tty is unthrottled (or was already unthrottled) */ bool tty_unthrottle_safe(struct tty_struct *tty) { bool ret = true; mutex_lock(&tty->throttle_mutex); if (tty_throttled(tty)) { if (tty->flow_change != TTY_UNTHROTTLE_SAFE) ret = false; else { clear_bit(TTY_THROTTLED, &tty->flags); if (tty->ops->unthrottle) tty->ops->unthrottle(tty); } } mutex_unlock(&tty->throttle_mutex); return ret; } /** * tty_wait_until_sent - wait for I/O to finish * @tty: tty we are waiting for * @timeout: how long we will wait * * Wait for characters pending in a tty driver to hit the wire, or for a * timeout to occur (eg due to flow control). * * Locking: none */ void tty_wait_until_sent(struct tty_struct *tty, long timeout) { if (!timeout) timeout = MAX_SCHEDULE_TIMEOUT; timeout = wait_event_interruptible_timeout(tty->write_wait, !tty_chars_in_buffer(tty), timeout); if (timeout <= 0) return; if (timeout == MAX_SCHEDULE_TIMEOUT) timeout = 0; if (tty->ops->wait_until_sent) tty->ops->wait_until_sent(tty, timeout); } EXPORT_SYMBOL(tty_wait_until_sent); /* * Termios Helper Methods */ static void unset_locked_termios(struct tty_struct *tty, const struct ktermios *old) { struct ktermios *termios = &tty->termios; struct ktermios *locked = &tty->termios_locked; int i; #define NOSET_MASK(x, y, z) (x = ((x) & ~(z)) | ((y) & (z))) NOSET_MASK(termios->c_iflag, old->c_iflag, locked->c_iflag); NOSET_MASK(termios->c_oflag, old->c_oflag, locked->c_oflag); NOSET_MASK(termios->c_cflag, old->c_cflag, locked->c_cflag); NOSET_MASK(termios->c_lflag, old->c_lflag, locked->c_lflag); termios->c_line = locked->c_line ? old->c_line : termios->c_line; for (i = 0; i < NCCS; i++) termios->c_cc[i] = locked->c_cc[i] ? old->c_cc[i] : termios->c_cc[i]; /* FIXME: What should we do for i/ospeed */ } /** * tty_termios_copy_hw - copy hardware settings * @new: new termios * @old: old termios * * Propagate the hardware specific terminal setting bits from the @old termios * structure to the @new one. This is used in cases where the hardware does not * support reconfiguration or as a helper in some cases where only minimal * reconfiguration is supported. */ void tty_termios_copy_hw(struct ktermios *new, const struct ktermios *old) { /* The bits a dumb device handles in software. Smart devices need to always provide a set_termios method */ new->c_cflag &= HUPCL | CREAD | CLOCAL; new->c_cflag |= old->c_cflag & ~(HUPCL | CREAD | CLOCAL); new->c_ispeed = old->c_ispeed; new->c_ospeed = old->c_ospeed; } EXPORT_SYMBOL(tty_termios_copy_hw); /** * tty_termios_hw_change - check for setting change * @a: termios * @b: termios to compare * * Check if any of the bits that affect a dumb device have changed between the * two termios structures, or a speed change is needed. * * Returns: %true if change is needed */ bool tty_termios_hw_change(const struct ktermios *a, const struct ktermios *b) { if (a->c_ispeed != b->c_ispeed || a->c_ospeed != b->c_ospeed) return true; if ((a->c_cflag ^ b->c_cflag) & ~(HUPCL | CREAD | CLOCAL)) return true; return false; } EXPORT_SYMBOL(tty_termios_hw_change); /** * tty_get_char_size - get size of a character * @cflag: termios cflag value * * Returns: size (in bits) of a character depending on @cflag's %CSIZE setting */ unsigned char tty_get_char_size(unsigned int cflag) { switch (cflag & CSIZE) { case CS5: return 5; case CS6: return 6; case CS7: return 7; case CS8: default: return 8; } } EXPORT_SYMBOL_GPL(tty_get_char_size); /** * tty_get_frame_size - get size of a frame * @cflag: termios cflag value * * Get the size (in bits) of a frame depending on @cflag's %CSIZE, %CSTOPB, and * %PARENB setting. The result is a sum of character size, start and stop bits * -- one bit each -- second stop bit (if set), and parity bit (if set). * * Returns: size (in bits) of a frame depending on @cflag's setting. */ unsigned char tty_get_frame_size(unsigned int cflag) { unsigned char bits = 2 + tty_get_char_size(cflag); if (cflag & CSTOPB) bits++; if (cflag & PARENB) bits++; if (cflag & ADDRB) bits++; return bits; } EXPORT_SYMBOL_GPL(tty_get_frame_size); /** * tty_set_termios - update termios values * @tty: tty to update * @new_termios: desired new value * * Perform updates to the termios values set on this @tty. A master pty's * termios should never be set. * * Locking: &tty_struct->termios_rwsem */ int tty_set_termios(struct tty_struct *tty, struct ktermios *new_termios) { struct ktermios old_termios; struct tty_ldisc *ld; WARN_ON(tty->driver->type == TTY_DRIVER_TYPE_PTY && tty->driver->subtype == PTY_TYPE_MASTER); /* * Perform the actual termios internal changes under lock. */ /* FIXME: we need to decide on some locking/ordering semantics for the set_termios notification eventually */ down_write(&tty->termios_rwsem); old_termios = tty->termios; tty->termios = *new_termios; unset_locked_termios(tty, &old_termios); /* Reset any ADDRB changes, ADDRB is changed through ->rs485_config() */ tty->termios.c_cflag ^= (tty->termios.c_cflag ^ old_termios.c_cflag) & ADDRB; if (tty->ops->set_termios) tty->ops->set_termios(tty, &old_termios); else tty_termios_copy_hw(&tty->termios, &old_termios); ld = tty_ldisc_ref(tty); if (ld != NULL) { if (ld->ops->set_termios) ld->ops->set_termios(tty, &old_termios); tty_ldisc_deref(ld); } up_write(&tty->termios_rwsem); return 0; } EXPORT_SYMBOL_GPL(tty_set_termios); /* * Translate a "termio" structure into a "termios". Ugh. */ __weak int user_termio_to_kernel_termios(struct ktermios *termios, struct termio __user *termio) { struct termio v; if (copy_from_user(&v, termio, sizeof(struct termio))) return -EFAULT; termios->c_iflag = (0xffff0000 & termios->c_iflag) | v.c_iflag; termios->c_oflag = (0xffff0000 & termios->c_oflag) | v.c_oflag; termios->c_cflag = (0xffff0000 & termios->c_cflag) | v.c_cflag; termios->c_lflag = (0xffff0000 & termios->c_lflag) | v.c_lflag; termios->c_line = (0xffff0000 & termios->c_lflag) | v.c_line; memcpy(termios->c_cc, v.c_cc, NCC); return 0; } /* * Translate a "termios" structure into a "termio". Ugh. */ __weak int kernel_termios_to_user_termio(struct termio __user *termio, struct ktermios *termios) { struct termio v; memset(&v, 0, sizeof(struct termio)); v.c_iflag = termios->c_iflag; v.c_oflag = termios->c_oflag; v.c_cflag = termios->c_cflag; v.c_lflag = termios->c_lflag; v.c_line = termios->c_line; memcpy(v.c_cc, termios->c_cc, NCC); return copy_to_user(termio, &v, sizeof(struct termio)); } #ifdef TCGETS2 __weak int user_termios_to_kernel_termios(struct ktermios *k, struct termios2 __user *u) { return copy_from_user(k, u, sizeof(struct termios2)); } __weak int kernel_termios_to_user_termios(struct termios2 __user *u, struct ktermios *k) { return copy_to_user(u, k, sizeof(struct termios2)); } __weak int user_termios_to_kernel_termios_1(struct ktermios *k, struct termios __user *u) { return copy_from_user(k, u, sizeof(struct termios)); } __weak int kernel_termios_to_user_termios_1(struct termios __user *u, struct ktermios *k) { return copy_to_user(u, k, sizeof(struct termios)); } #else __weak int user_termios_to_kernel_termios(struct ktermios *k, struct termios __user *u) { return copy_from_user(k, u, sizeof(struct termios)); } __weak int kernel_termios_to_user_termios(struct termios __user *u, struct ktermios *k) { return copy_to_user(u, k, sizeof(struct termios)); } #endif /* TCGETS2 */ /** * set_termios - set termios values for a tty * @tty: terminal device * @arg: user data * @opt: option information * * Helper function to prepare termios data and run necessary other functions * before using tty_set_termios() to do the actual changes. * * Locking: called functions take &tty_struct->ldisc_sem and * &tty_struct->termios_rwsem locks * * Returns: 0 on success, an error otherwise */ static int set_termios(struct tty_struct *tty, void __user *arg, int opt) { struct ktermios tmp_termios; struct tty_ldisc *ld; int retval = tty_check_change(tty); if (retval) return retval; down_read(&tty->termios_rwsem); tmp_termios = tty->termios; up_read(&tty->termios_rwsem); if (opt & TERMIOS_TERMIO) { if (user_termio_to_kernel_termios(&tmp_termios, (struct termio __user *)arg)) return -EFAULT; #ifdef TCGETS2 } else if (opt & TERMIOS_OLD) { if (user_termios_to_kernel_termios_1(&tmp_termios, (struct termios __user *)arg)) return -EFAULT; } else { if (user_termios_to_kernel_termios(&tmp_termios, (struct termios2 __user *)arg)) return -EFAULT; } #else } else if (user_termios_to_kernel_termios(&tmp_termios, (struct termios __user *)arg)) return -EFAULT; #endif /* If old style Bfoo values are used then load c_ispeed/c_ospeed * with the real speed so its unconditionally usable */ tmp_termios.c_ispeed = tty_termios_input_baud_rate(&tmp_termios); tmp_termios.c_ospeed = tty_termios_baud_rate(&tmp_termios); if (opt & (TERMIOS_FLUSH|TERMIOS_WAIT)) { retry_write_wait: retval = wait_event_interruptible(tty->write_wait, !tty_chars_in_buffer(tty)); if (retval < 0) return retval; if (tty_write_lock(tty, false) < 0) goto retry_write_wait; /* Racing writer? */ if (tty_chars_in_buffer(tty)) { tty_write_unlock(tty); goto retry_write_wait; } ld = tty_ldisc_ref(tty); if (ld != NULL) { if ((opt & TERMIOS_FLUSH) && ld->ops->flush_buffer) ld->ops->flush_buffer(tty); tty_ldisc_deref(ld); } if ((opt & TERMIOS_WAIT) && tty->ops->wait_until_sent) { tty->ops->wait_until_sent(tty, 0); if (signal_pending(current)) { tty_write_unlock(tty); return -ERESTARTSYS; } } tty_set_termios(tty, &tmp_termios); tty_write_unlock(tty); } else { tty_set_termios(tty, &tmp_termios); } /* FIXME: Arguably if tmp_termios == tty->termios AND the actual requested termios was not tmp_termios then we may want to return an error as no user requested change has succeeded */ return 0; } static void copy_termios(struct tty_struct *tty, struct ktermios *kterm) { down_read(&tty->termios_rwsem); *kterm = tty->termios; up_read(&tty->termios_rwsem); } static void copy_termios_locked(struct tty_struct *tty, struct ktermios *kterm) { down_read(&tty->termios_rwsem); *kterm = tty->termios_locked; up_read(&tty->termios_rwsem); } static int get_termio(struct tty_struct *tty, struct termio __user *termio) { struct ktermios kterm; copy_termios(tty, &kterm); if (kernel_termios_to_user_termio(termio, &kterm)) return -EFAULT; return 0; } #ifdef TIOCGETP /* * These are deprecated, but there is limited support.. * * The "sg_flags" translation is a joke.. */ static int get_sgflags(struct tty_struct *tty) { int flags = 0; if (!L_ICANON(tty)) { if (L_ISIG(tty)) flags |= 0x02; /* cbreak */ else flags |= 0x20; /* raw */ } if (L_ECHO(tty)) flags |= 0x08; /* echo */ if (O_OPOST(tty)) if (O_ONLCR(tty)) flags |= 0x10; /* crmod */ return flags; } static int get_sgttyb(struct tty_struct *tty, struct sgttyb __user *sgttyb) { struct sgttyb tmp; down_read(&tty->termios_rwsem); tmp.sg_ispeed = tty->termios.c_ispeed; tmp.sg_ospeed = tty->termios.c_ospeed; tmp.sg_erase = tty->termios.c_cc[VERASE]; tmp.sg_kill = tty->termios.c_cc[VKILL]; tmp.sg_flags = get_sgflags(tty); up_read(&tty->termios_rwsem); return copy_to_user(sgttyb, &tmp, sizeof(tmp)) ? -EFAULT : 0; } static void set_sgflags(struct ktermios *termios, int flags) { termios->c_iflag = ICRNL | IXON; termios->c_oflag = 0; termios->c_lflag = ISIG | ICANON; if (flags & 0x02) { /* cbreak */ termios->c_iflag = 0; termios->c_lflag &= ~ICANON; } if (flags & 0x08) { /* echo */ termios->c_lflag |= ECHO | ECHOE | ECHOK | ECHOCTL | ECHOKE | IEXTEN; } if (flags & 0x10) { /* crmod */ termios->c_oflag |= OPOST | ONLCR; } if (flags & 0x20) { /* raw */ termios->c_iflag = 0; termios->c_lflag &= ~(ISIG | ICANON); } if (!(termios->c_lflag & ICANON)) { termios->c_cc[VMIN] = 1; termios->c_cc[VTIME] = 0; } } /** * set_sgttyb - set legacy terminal values * @tty: tty structure * @sgttyb: pointer to old style terminal structure * * Updates a terminal from the legacy BSD style terminal information structure. * * Locking: &tty_struct->termios_rwsem * * Returns: 0 on success, an error otherwise */ static int set_sgttyb(struct tty_struct *tty, struct sgttyb __user *sgttyb) { int retval; struct sgttyb tmp; struct ktermios termios; retval = tty_check_change(tty); if (retval) return retval; if (copy_from_user(&tmp, sgttyb, sizeof(tmp))) return -EFAULT; down_write(&tty->termios_rwsem); termios = tty->termios; termios.c_cc[VERASE] = tmp.sg_erase; termios.c_cc[VKILL] = tmp.sg_kill; set_sgflags(&termios, tmp.sg_flags); /* Try and encode into Bfoo format */ tty_termios_encode_baud_rate(&termios, termios.c_ispeed, termios.c_ospeed); up_write(&tty->termios_rwsem); tty_set_termios(tty, &termios); return 0; } #endif #ifdef TIOCGETC static int get_tchars(struct tty_struct *tty, struct tchars __user *tchars) { struct tchars tmp; down_read(&tty->termios_rwsem); tmp.t_intrc = tty->termios.c_cc[VINTR]; tmp.t_quitc = tty->termios.c_cc[VQUIT]; tmp.t_startc = tty->termios.c_cc[VSTART]; tmp.t_stopc = tty->termios.c_cc[VSTOP]; tmp.t_eofc = tty->termios.c_cc[VEOF]; tmp.t_brkc = tty->termios.c_cc[VEOL2]; /* what is brkc anyway? */ up_read(&tty->termios_rwsem); return copy_to_user(tchars, &tmp, sizeof(tmp)) ? -EFAULT : 0; } static int set_tchars(struct tty_struct *tty, struct tchars __user *tchars) { struct tchars tmp; if (copy_from_user(&tmp, tchars, sizeof(tmp))) return -EFAULT; down_write(&tty->termios_rwsem); tty->termios.c_cc[VINTR] = tmp.t_intrc; tty->termios.c_cc[VQUIT] = tmp.t_quitc; tty->termios.c_cc[VSTART] = tmp.t_startc; tty->termios.c_cc[VSTOP] = tmp.t_stopc; tty->termios.c_cc[VEOF] = tmp.t_eofc; tty->termios.c_cc[VEOL2] = tmp.t_brkc; /* what is brkc anyway? */ up_write(&tty->termios_rwsem); return 0; } #endif #ifdef TIOCGLTC static int get_ltchars(struct tty_struct *tty, struct ltchars __user *ltchars) { struct ltchars tmp; down_read(&tty->termios_rwsem); tmp.t_suspc = tty->termios.c_cc[VSUSP]; /* what is dsuspc anyway? */ tmp.t_dsuspc = tty->termios.c_cc[VSUSP]; tmp.t_rprntc = tty->termios.c_cc[VREPRINT]; /* what is flushc anyway? */ tmp.t_flushc = tty->termios.c_cc[VEOL2]; tmp.t_werasc = tty->termios.c_cc[VWERASE]; tmp.t_lnextc = tty->termios.c_cc[VLNEXT]; up_read(&tty->termios_rwsem); return copy_to_user(ltchars, &tmp, sizeof(tmp)) ? -EFAULT : 0; } static int set_ltchars(struct tty_struct *tty, struct ltchars __user *ltchars) { struct ltchars tmp; if (copy_from_user(&tmp, ltchars, sizeof(tmp))) return -EFAULT; down_write(&tty->termios_rwsem); tty->termios.c_cc[VSUSP] = tmp.t_suspc; /* what is dsuspc anyway? */ tty->termios.c_cc[VEOL2] = tmp.t_dsuspc; tty->termios.c_cc[VREPRINT] = tmp.t_rprntc; /* what is flushc anyway? */ tty->termios.c_cc[VEOL2] = tmp.t_flushc; tty->termios.c_cc[VWERASE] = tmp.t_werasc; tty->termios.c_cc[VLNEXT] = tmp.t_lnextc; up_write(&tty->termios_rwsem); return 0; } #endif /** * tty_change_softcar - carrier change ioctl helper * @tty: tty to update * @enable: enable/disable %CLOCAL * * Perform a change to the %CLOCAL state and call into the driver layer to make * it visible. * * Locking: &tty_struct->termios_rwsem. * * Returns: 0 on success, an error otherwise */ static int tty_change_softcar(struct tty_struct *tty, bool enable) { int ret = 0; struct ktermios old; tcflag_t bit = enable ? CLOCAL : 0; down_write(&tty->termios_rwsem); old = tty->termios; tty->termios.c_cflag &= ~CLOCAL; tty->termios.c_cflag |= bit; if (tty->ops->set_termios) tty->ops->set_termios(tty, &old); if (C_CLOCAL(tty) != bit) ret = -EINVAL; up_write(&tty->termios_rwsem); return ret; } /** * tty_mode_ioctl - mode related ioctls * @tty: tty for the ioctl * @cmd: command * @arg: ioctl argument * * Perform non-line discipline specific mode control ioctls. This is designed * to be called by line disciplines to ensure they provide consistent mode * setting. */ int tty_mode_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { struct tty_struct *real_tty; void __user *p = (void __user *)arg; int ret = 0; struct ktermios kterm; if (tty->driver->type == TTY_DRIVER_TYPE_PTY && tty->driver->subtype == PTY_TYPE_MASTER) real_tty = tty->link; else real_tty = tty; switch (cmd) { #ifdef TIOCGETP case TIOCGETP: return get_sgttyb(real_tty, (struct sgttyb __user *) arg); case TIOCSETP: case TIOCSETN: return set_sgttyb(real_tty, (struct sgttyb __user *) arg); #endif #ifdef TIOCGETC case TIOCGETC: return get_tchars(real_tty, p); case TIOCSETC: return set_tchars(real_tty, p); #endif #ifdef TIOCGLTC case TIOCGLTC: return get_ltchars(real_tty, p); case TIOCSLTC: return set_ltchars(real_tty, p); #endif case TCSETSF: return set_termios(real_tty, p, TERMIOS_FLUSH | TERMIOS_WAIT | TERMIOS_OLD); case TCSETSW: return set_termios(real_tty, p, TERMIOS_WAIT | TERMIOS_OLD); case TCSETS: return set_termios(real_tty, p, TERMIOS_OLD); #ifndef TCGETS2 case TCGETS: copy_termios(real_tty, &kterm); if (kernel_termios_to_user_termios((struct termios __user *)arg, &kterm)) ret = -EFAULT; return ret; #else case TCGETS: copy_termios(real_tty, &kterm); if (kernel_termios_to_user_termios_1((struct termios __user *)arg, &kterm)) ret = -EFAULT; return ret; case TCGETS2: copy_termios(real_tty, &kterm); if (kernel_termios_to_user_termios((struct termios2 __user *)arg, &kterm)) ret = -EFAULT; return ret; case TCSETSF2: return set_termios(real_tty, p, TERMIOS_FLUSH | TERMIOS_WAIT); case TCSETSW2: return set_termios(real_tty, p, TERMIOS_WAIT); case TCSETS2: return set_termios(real_tty, p, 0); #endif case TCGETA: return get_termio(real_tty, p); case TCSETAF: return set_termios(real_tty, p, TERMIOS_FLUSH | TERMIOS_WAIT | TERMIOS_TERMIO); case TCSETAW: return set_termios(real_tty, p, TERMIOS_WAIT | TERMIOS_TERMIO); case TCSETA: return set_termios(real_tty, p, TERMIOS_TERMIO); #ifndef TCGETS2 case TIOCGLCKTRMIOS: copy_termios_locked(real_tty, &kterm); if (kernel_termios_to_user_termios((struct termios __user *)arg, &kterm)) ret = -EFAULT; return ret; case TIOCSLCKTRMIOS: if (!checkpoint_restore_ns_capable(&init_user_ns)) return -EPERM; copy_termios_locked(real_tty, &kterm); if (user_termios_to_kernel_termios(&kterm, (struct termios __user *) arg)) return -EFAULT; down_write(&real_tty->termios_rwsem); real_tty->termios_locked = kterm; up_write(&real_tty->termios_rwsem); return 0; #else case TIOCGLCKTRMIOS: copy_termios_locked(real_tty, &kterm); if (kernel_termios_to_user_termios_1((struct termios __user *)arg, &kterm)) ret = -EFAULT; return ret; case TIOCSLCKTRMIOS: if (!checkpoint_restore_ns_capable(&init_user_ns)) return -EPERM; copy_termios_locked(real_tty, &kterm); if (user_termios_to_kernel_termios_1(&kterm, (struct termios __user *) arg)) return -EFAULT; down_write(&real_tty->termios_rwsem); real_tty->termios_locked = kterm; up_write(&real_tty->termios_rwsem); return ret; #endif #ifdef TCGETX case TCGETX: case TCSETX: case TCSETXW: case TCSETXF: return -ENOTTY; #endif case TIOCGSOFTCAR: copy_termios(real_tty, &kterm); ret = put_user((kterm.c_cflag & CLOCAL) ? 1 : 0, (int __user *)arg); return ret; case TIOCSSOFTCAR: if (get_user(arg, (unsigned int __user *) arg)) return -EFAULT; return tty_change_softcar(real_tty, arg); default: return -ENOIOCTLCMD; } } EXPORT_SYMBOL_GPL(tty_mode_ioctl); /* Caller guarantees ldisc reference is held */ static int __tty_perform_flush(struct tty_struct *tty, unsigned long arg) { struct tty_ldisc *ld = tty->ldisc; switch (arg) { case TCIFLUSH: if (ld && ld->ops->flush_buffer) { ld->ops->flush_buffer(tty); tty_unthrottle(tty); } break; case TCIOFLUSH: if (ld && ld->ops->flush_buffer) { ld->ops->flush_buffer(tty); tty_unthrottle(tty); } fallthrough; case TCOFLUSH: tty_driver_flush_buffer(tty); break; default: return -EINVAL; } return 0; } int tty_perform_flush(struct tty_struct *tty, unsigned long arg) { struct tty_ldisc *ld; int retval = tty_check_change(tty); if (retval) return retval; ld = tty_ldisc_ref_wait(tty); retval = __tty_perform_flush(tty, arg); if (ld) tty_ldisc_deref(ld); return retval; } EXPORT_SYMBOL_GPL(tty_perform_flush); int n_tty_ioctl_helper(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { int retval; switch (cmd) { case TCXONC: retval = tty_check_change(tty); if (retval) return retval; switch (arg) { case TCOOFF: spin_lock_irq(&tty->flow.lock); if (!tty->flow.tco_stopped) { tty->flow.tco_stopped = true; __stop_tty(tty); } spin_unlock_irq(&tty->flow.lock); break; case TCOON: spin_lock_irq(&tty->flow.lock); if (tty->flow.tco_stopped) { tty->flow.tco_stopped = false; __start_tty(tty); } spin_unlock_irq(&tty->flow.lock); break; case TCIOFF: if (STOP_CHAR(tty) != __DISABLED_CHAR) retval = tty_send_xchar(tty, STOP_CHAR(tty)); break; case TCION: if (START_CHAR(tty) != __DISABLED_CHAR) retval = tty_send_xchar(tty, START_CHAR(tty)); break; default: return -EINVAL; } return retval; case TCFLSH: retval = tty_check_change(tty); if (retval) return retval; return __tty_perform_flush(tty, arg); default: /* Try the mode commands */ return tty_mode_ioctl(tty, cmd, arg); } } EXPORT_SYMBOL(n_tty_ioctl_helper); |
| 64 8 204 204 204 205 204 139 1 64 64 204 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * umh - the kernel usermode helper */ #include <linux/module.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/binfmts.h> #include <linux/syscalls.h> #include <linux/unistd.h> #include <linux/kmod.h> #include <linux/slab.h> #include <linux/completion.h> #include <linux/cred.h> #include <linux/file.h> #include <linux/fs_struct.h> #include <linux/workqueue.h> #include <linux/security.h> #include <linux/mount.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/resource.h> #include <linux/notifier.h> #include <linux/suspend.h> #include <linux/rwsem.h> #include <linux/ptrace.h> #include <linux/async.h> #include <linux/uaccess.h> #include <linux/initrd.h> #include <linux/freezer.h> #include <trace/events/module.h> static kernel_cap_t usermodehelper_bset = CAP_FULL_SET; static kernel_cap_t usermodehelper_inheritable = CAP_FULL_SET; static DEFINE_SPINLOCK(umh_sysctl_lock); static DECLARE_RWSEM(umhelper_sem); static void call_usermodehelper_freeinfo(struct subprocess_info *info) { if (info->cleanup) (*info->cleanup)(info); kfree(info); } static void umh_complete(struct subprocess_info *sub_info) { struct completion *comp = xchg(&sub_info->complete, NULL); /* * See call_usermodehelper_exec(). If xchg() returns NULL * we own sub_info, the UMH_KILLABLE caller has gone away * or the caller used UMH_NO_WAIT. */ if (comp) complete(comp); else call_usermodehelper_freeinfo(sub_info); } /* * This is the task which runs the usermode application */ static int call_usermodehelper_exec_async(void *data) { struct subprocess_info *sub_info = data; struct cred *new; int retval; spin_lock_irq(¤t->sighand->siglock); flush_signal_handlers(current, 1); spin_unlock_irq(¤t->sighand->siglock); /* * Initial kernel threads share ther FS with init, in order to * get the init root directory. But we've now created a new * thread that is going to execve a user process and has its own * 'struct fs_struct'. Reset umask to the default. */ current->fs->umask = 0022; /* * Our parent (unbound workqueue) runs with elevated scheduling * priority. Avoid propagating that into the userspace child. */ set_user_nice(current, 0); retval = -ENOMEM; new = prepare_kernel_cred(current); if (!new) goto out; spin_lock(&umh_sysctl_lock); new->cap_bset = cap_intersect(usermodehelper_bset, new->cap_bset); new->cap_inheritable = cap_intersect(usermodehelper_inheritable, new->cap_inheritable); spin_unlock(&umh_sysctl_lock); if (sub_info->init) { retval = sub_info->init(sub_info, new); if (retval) { abort_creds(new); goto out; } } commit_creds(new); wait_for_initramfs(); retval = kernel_execve(sub_info->path, (const char *const *)sub_info->argv, (const char *const *)sub_info->envp); out: sub_info->retval = retval; /* * call_usermodehelper_exec_sync() will call umh_complete * if UHM_WAIT_PROC. */ if (!(sub_info->wait & UMH_WAIT_PROC)) umh_complete(sub_info); if (!retval) return 0; do_exit(0); } /* Handles UMH_WAIT_PROC. */ static void call_usermodehelper_exec_sync(struct subprocess_info *sub_info) { pid_t pid; /* If SIGCLD is ignored do_wait won't populate the status. */ kernel_sigaction(SIGCHLD, SIG_DFL); pid = user_mode_thread(call_usermodehelper_exec_async, sub_info, SIGCHLD); if (pid < 0) sub_info->retval = pid; else kernel_wait(pid, &sub_info->retval); /* Restore default kernel sig handler */ kernel_sigaction(SIGCHLD, SIG_IGN); umh_complete(sub_info); } /* * We need to create the usermodehelper kernel thread from a task that is affine * to an optimized set of CPUs (or nohz housekeeping ones) such that they * inherit a widest affinity irrespective of call_usermodehelper() callers with * possibly reduced affinity (eg: per-cpu workqueues). We don't want * usermodehelper targets to contend a busy CPU. * * Unbound workqueues provide such wide affinity and allow to block on * UMH_WAIT_PROC requests without blocking pending request (up to some limit). * * Besides, workqueues provide the privilege level that caller might not have * to perform the usermodehelper request. * */ static void call_usermodehelper_exec_work(struct work_struct *work) { struct subprocess_info *sub_info = container_of(work, struct subprocess_info, work); if (sub_info->wait & UMH_WAIT_PROC) { call_usermodehelper_exec_sync(sub_info); } else { pid_t pid; /* * Use CLONE_PARENT to reparent it to kthreadd; we do not * want to pollute current->children, and we need a parent * that always ignores SIGCHLD to ensure auto-reaping. */ pid = user_mode_thread(call_usermodehelper_exec_async, sub_info, CLONE_PARENT | SIGCHLD); if (pid < 0) { sub_info->retval = pid; umh_complete(sub_info); } } } /* * If set, call_usermodehelper_exec() will exit immediately returning -EBUSY * (used for preventing user land processes from being created after the user * land has been frozen during a system-wide hibernation or suspend operation). * Should always be manipulated under umhelper_sem acquired for write. */ static enum umh_disable_depth usermodehelper_disabled = UMH_DISABLED; /* Number of helpers running */ static atomic_t running_helpers = ATOMIC_INIT(0); /* * Wait queue head used by usermodehelper_disable() to wait for all running * helpers to finish. */ static DECLARE_WAIT_QUEUE_HEAD(running_helpers_waitq); /* * Used by usermodehelper_read_lock_wait() to wait for usermodehelper_disabled * to become 'false'. */ static DECLARE_WAIT_QUEUE_HEAD(usermodehelper_disabled_waitq); /* * Time to wait for running_helpers to become zero before the setting of * usermodehelper_disabled in usermodehelper_disable() fails */ #define RUNNING_HELPERS_TIMEOUT (5 * HZ) int usermodehelper_read_trylock(void) { DEFINE_WAIT(wait); int ret = 0; down_read(&umhelper_sem); for (;;) { prepare_to_wait(&usermodehelper_disabled_waitq, &wait, TASK_INTERRUPTIBLE); if (!usermodehelper_disabled) break; if (usermodehelper_disabled == UMH_DISABLED) ret = -EAGAIN; up_read(&umhelper_sem); if (ret) break; schedule(); try_to_freeze(); down_read(&umhelper_sem); } finish_wait(&usermodehelper_disabled_waitq, &wait); return ret; } EXPORT_SYMBOL_GPL(usermodehelper_read_trylock); long usermodehelper_read_lock_wait(long timeout) { DEFINE_WAIT(wait); if (timeout < 0) return -EINVAL; down_read(&umhelper_sem); for (;;) { prepare_to_wait(&usermodehelper_disabled_waitq, &wait, TASK_UNINTERRUPTIBLE); if (!usermodehelper_disabled) break; up_read(&umhelper_sem); timeout = schedule_timeout(timeout); if (!timeout) break; down_read(&umhelper_sem); } finish_wait(&usermodehelper_disabled_waitq, &wait); return timeout; } EXPORT_SYMBOL_GPL(usermodehelper_read_lock_wait); void usermodehelper_read_unlock(void) { up_read(&umhelper_sem); } EXPORT_SYMBOL_GPL(usermodehelper_read_unlock); /** * __usermodehelper_set_disable_depth - Modify usermodehelper_disabled. * @depth: New value to assign to usermodehelper_disabled. * * Change the value of usermodehelper_disabled (under umhelper_sem locked for * writing) and wakeup tasks waiting for it to change. */ void __usermodehelper_set_disable_depth(enum umh_disable_depth depth) { down_write(&umhelper_sem); usermodehelper_disabled = depth; wake_up(&usermodehelper_disabled_waitq); up_write(&umhelper_sem); } /** * __usermodehelper_disable - Prevent new helpers from being started. * @depth: New value to assign to usermodehelper_disabled. * * Set usermodehelper_disabled to @depth and wait for running helpers to exit. */ int __usermodehelper_disable(enum umh_disable_depth depth) { long retval; if (!depth) return -EINVAL; down_write(&umhelper_sem); usermodehelper_disabled = depth; up_write(&umhelper_sem); /* * From now on call_usermodehelper_exec() won't start any new * helpers, so it is sufficient if running_helpers turns out to * be zero at one point (it may be increased later, but that * doesn't matter). */ retval = wait_event_timeout(running_helpers_waitq, atomic_read(&running_helpers) == 0, RUNNING_HELPERS_TIMEOUT); if (retval) return 0; __usermodehelper_set_disable_depth(UMH_ENABLED); return -EAGAIN; } static void helper_lock(void) { atomic_inc(&running_helpers); smp_mb__after_atomic(); } static void helper_unlock(void) { if (atomic_dec_and_test(&running_helpers)) wake_up(&running_helpers_waitq); } /** * call_usermodehelper_setup - prepare to call a usermode helper * @path: path to usermode executable * @argv: arg vector for process * @envp: environment for process * @gfp_mask: gfp mask for memory allocation * @init: an init function * @cleanup: a cleanup function * @data: arbitrary context sensitive data * * Returns either %NULL on allocation failure, or a subprocess_info * structure. This should be passed to call_usermodehelper_exec to * exec the process and free the structure. * * The init function is used to customize the helper process prior to * exec. A non-zero return code causes the process to error out, exit, * and return the failure to the calling process * * The cleanup function is just before the subprocess_info is about to * be freed. This can be used for freeing the argv and envp. The * Function must be runnable in either a process context or the * context in which call_usermodehelper_exec is called. */ struct subprocess_info *call_usermodehelper_setup(const char *path, char **argv, char **envp, gfp_t gfp_mask, int (*init)(struct subprocess_info *info, struct cred *new), void (*cleanup)(struct subprocess_info *info), void *data) { struct subprocess_info *sub_info; sub_info = kzalloc(sizeof(struct subprocess_info), gfp_mask); if (!sub_info) goto out; INIT_WORK(&sub_info->work, call_usermodehelper_exec_work); #ifdef CONFIG_STATIC_USERMODEHELPER sub_info->path = CONFIG_STATIC_USERMODEHELPER_PATH; #else sub_info->path = path; #endif sub_info->argv = argv; sub_info->envp = envp; sub_info->cleanup = cleanup; sub_info->init = init; sub_info->data = data; out: return sub_info; } EXPORT_SYMBOL(call_usermodehelper_setup); /** * call_usermodehelper_exec - start a usermode application * @sub_info: information about the subprocess * @wait: wait for the application to finish and return status. * when UMH_NO_WAIT don't wait at all, but you get no useful error back * when the program couldn't be exec'ed. This makes it safe to call * from interrupt context. * * Runs a user-space application. The application is started * asynchronously if wait is not set, and runs as a child of system workqueues. * (ie. it runs with full root capabilities and optimized affinity). * * Note: successful return value does not guarantee the helper was called at * all. You can't rely on sub_info->{init,cleanup} being called even for * UMH_WAIT_* wait modes as STATIC_USERMODEHELPER_PATH="" turns all helpers * into a successful no-op. */ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait) { unsigned int state = TASK_UNINTERRUPTIBLE; DECLARE_COMPLETION_ONSTACK(done); int retval = 0; if (!sub_info->path) { call_usermodehelper_freeinfo(sub_info); return -EINVAL; } helper_lock(); if (usermodehelper_disabled) { retval = -EBUSY; goto out; } /* * If there is no binary for us to call, then just return and get out of * here. This allows us to set STATIC_USERMODEHELPER_PATH to "" and * disable all call_usermodehelper() calls. */ if (strlen(sub_info->path) == 0) goto out; /* * Set the completion pointer only if there is a waiter. * This makes it possible to use umh_complete to free * the data structure in case of UMH_NO_WAIT. */ sub_info->complete = (wait == UMH_NO_WAIT) ? NULL : &done; sub_info->wait = wait; queue_work(system_unbound_wq, &sub_info->work); if (wait == UMH_NO_WAIT) /* task has freed sub_info */ goto unlock; if (wait & UMH_FREEZABLE) state |= TASK_FREEZABLE; if (wait & UMH_KILLABLE) { retval = wait_for_completion_state(&done, state | TASK_KILLABLE); if (!retval) goto wait_done; /* umh_complete() will see NULL and free sub_info */ if (xchg(&sub_info->complete, NULL)) goto unlock; /* * fallthrough; in case of -ERESTARTSYS now do uninterruptible * wait_for_completion_state(). Since umh_complete() shall call * complete() in a moment if xchg() above returned NULL, this * uninterruptible wait_for_completion_state() will not block * SIGKILL'ed processes for long. */ } wait_for_completion_state(&done, state); wait_done: retval = sub_info->retval; out: call_usermodehelper_freeinfo(sub_info); unlock: helper_unlock(); return retval; } EXPORT_SYMBOL(call_usermodehelper_exec); /** * call_usermodehelper() - prepare and start a usermode application * @path: path to usermode executable * @argv: arg vector for process * @envp: environment for process * @wait: wait for the application to finish and return status. * when UMH_NO_WAIT don't wait at all, but you get no useful error back * when the program couldn't be exec'ed. This makes it safe to call * from interrupt context. * * This function is the equivalent to use call_usermodehelper_setup() and * call_usermodehelper_exec(). */ int call_usermodehelper(const char *path, char **argv, char **envp, int wait) { struct subprocess_info *info; gfp_t gfp_mask = (wait == UMH_NO_WAIT) ? GFP_ATOMIC : GFP_KERNEL; info = call_usermodehelper_setup(path, argv, envp, gfp_mask, NULL, NULL, NULL); if (info == NULL) return -ENOMEM; return call_usermodehelper_exec(info, wait); } EXPORT_SYMBOL(call_usermodehelper); #if defined(CONFIG_SYSCTL) static int proc_cap_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; unsigned long cap_array[2]; kernel_cap_t new_cap, *cap; int err; if (write && (!capable(CAP_SETPCAP) || !capable(CAP_SYS_MODULE))) return -EPERM; /* * convert from the global kernel_cap_t to the ulong array to print to * userspace if this is a read. * * Legacy format: capabilities are exposed as two 32-bit values */ cap = table->data; spin_lock(&umh_sysctl_lock); cap_array[0] = (u32) cap->val; cap_array[1] = cap->val >> 32; spin_unlock(&umh_sysctl_lock); t = *table; t.data = &cap_array; /* * actually read or write and array of ulongs from userspace. Remember * these are least significant 32 bits first */ err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos); if (err < 0) return err; new_cap.val = (u32)cap_array[0]; new_cap.val += (u64)cap_array[1] << 32; /* * Drop everything not in the new_cap (but don't add things) */ if (write) { spin_lock(&umh_sysctl_lock); *cap = cap_intersect(*cap, new_cap); spin_unlock(&umh_sysctl_lock); } return 0; } static const struct ctl_table usermodehelper_table[] = { { .procname = "bset", .data = &usermodehelper_bset, .maxlen = 2 * sizeof(unsigned long), .mode = 0600, .proc_handler = proc_cap_handler, }, { .procname = "inheritable", .data = &usermodehelper_inheritable, .maxlen = 2 * sizeof(unsigned long), .mode = 0600, .proc_handler = proc_cap_handler, }, }; static int __init init_umh_sysctls(void) { register_sysctl_init("kernel/usermodehelper", usermodehelper_table); return 0; } early_initcall(init_umh_sysctls); #endif /* CONFIG_SYSCTL */ |
| 188 114 113 114 189 190 188 290 290 291 93 93 292 177 177 174 30 10 10 7 7 7 10 10 10 2 8 10 10 66 57 10 10 10 10 10 10 10 2 8 2 5 82 82 82 82 2 2 82 39 37 37 37 37 37 37 37 37 40 39 41 41 40 41 41 41 41 176 177 41 174 174 177 16 160 177 177 177 176 173 174 173 174 173 174 28 146 146 174 173 174 174 174 96 78 57 4 61 176 176 41 10 41 41 41 41 41 41 41 176 177 174 174 174 177 177 176 177 176 177 177 173 174 174 174 174 174 174 173 290 292 178 112 178 177 177 177 176 177 37 174 174 290 37 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * bcachefs setup/teardown code, and some metadata io - read a superblock and * figure out what to do with it. * * Copyright 2010, 2011 Kent Overstreet <kent.overstreet@gmail.com> * Copyright 2012 Google, Inc. */ #include "bcachefs.h" #include "alloc_background.h" #include "alloc_foreground.h" #include "bkey_sort.h" #include "btree_cache.h" #include "btree_gc.h" #include "btree_journal_iter.h" #include "btree_key_cache.h" #include "btree_node_scan.h" #include "btree_update_interior.h" #include "btree_io.h" #include "btree_write_buffer.h" #include "buckets_waiting_for_journal.h" #include "chardev.h" #include "checksum.h" #include "clock.h" #include "compress.h" #include "debug.h" #include "disk_accounting.h" #include "disk_groups.h" #include "ec.h" #include "errcode.h" #include "error.h" #include "fs.h" #include "fs-io.h" #include "fs-io-buffered.h" #include "fs-io-direct.h" #include "fsck.h" #include "inode.h" #include "io_read.h" #include "io_write.h" #include "journal.h" #include "journal_reclaim.h" #include "journal_seq_blacklist.h" #include "move.h" #include "migrate.h" #include "movinggc.h" #include "nocow_locking.h" #include "quota.h" #include "rebalance.h" #include "recovery.h" #include "replicas.h" #include "sb-clean.h" #include "sb-counters.h" #include "sb-errors.h" #include "sb-members.h" #include "snapshot.h" #include "subvolume.h" #include "super.h" #include "super-io.h" #include "sysfs.h" #include "thread_with_file.h" #include "trace.h" #include <linux/backing-dev.h> #include <linux/blkdev.h> #include <linux/debugfs.h> #include <linux/device.h> #include <linux/idr.h> #include <linux/module.h> #include <linux/percpu.h> #include <linux/random.h> #include <linux/sysfs.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Kent Overstreet <kent.overstreet@gmail.com>"); MODULE_DESCRIPTION("bcachefs filesystem"); const char * const bch2_fs_flag_strs[] = { #define x(n) #n, BCH_FS_FLAGS() #undef x NULL }; void bch2_print_str(struct bch_fs *c, const char *str) { #ifdef __KERNEL__ struct stdio_redirect *stdio = bch2_fs_stdio_redirect(c); if (unlikely(stdio)) { bch2_stdio_redirect_printf(stdio, true, "%s", str); return; } #endif bch2_print_string_as_lines(KERN_ERR, str); } __printf(2, 0) static void bch2_print_maybe_redirect(struct stdio_redirect *stdio, const char *fmt, va_list args) { #ifdef __KERNEL__ if (unlikely(stdio)) { if (fmt[0] == KERN_SOH[0]) fmt += 2; bch2_stdio_redirect_vprintf(stdio, true, fmt, args); return; } #endif vprintk(fmt, args); } void bch2_print_opts(struct bch_opts *opts, const char *fmt, ...) { struct stdio_redirect *stdio = (void *)(unsigned long)opts->stdio; va_list args; va_start(args, fmt); bch2_print_maybe_redirect(stdio, fmt, args); va_end(args); } void __bch2_print(struct bch_fs *c, const char *fmt, ...) { struct stdio_redirect *stdio = bch2_fs_stdio_redirect(c); va_list args; va_start(args, fmt); bch2_print_maybe_redirect(stdio, fmt, args); va_end(args); } #define KTYPE(type) \ static const struct attribute_group type ## _group = { \ .attrs = type ## _files \ }; \ \ static const struct attribute_group *type ## _groups[] = { \ &type ## _group, \ NULL \ }; \ \ static const struct kobj_type type ## _ktype = { \ .release = type ## _release, \ .sysfs_ops = &type ## _sysfs_ops, \ .default_groups = type ## _groups \ } static void bch2_fs_release(struct kobject *); static void bch2_dev_release(struct kobject *); static void bch2_fs_counters_release(struct kobject *k) { } static void bch2_fs_internal_release(struct kobject *k) { } static void bch2_fs_opts_dir_release(struct kobject *k) { } static void bch2_fs_time_stats_release(struct kobject *k) { } KTYPE(bch2_fs); KTYPE(bch2_fs_counters); KTYPE(bch2_fs_internal); KTYPE(bch2_fs_opts_dir); KTYPE(bch2_fs_time_stats); KTYPE(bch2_dev); static struct kset *bcachefs_kset; static LIST_HEAD(bch_fs_list); static DEFINE_MUTEX(bch_fs_list_lock); DECLARE_WAIT_QUEUE_HEAD(bch2_read_only_wait); static void bch2_dev_unlink(struct bch_dev *); static void bch2_dev_free(struct bch_dev *); static int bch2_dev_alloc(struct bch_fs *, unsigned); static int bch2_dev_sysfs_online(struct bch_fs *, struct bch_dev *); static void bch2_dev_io_ref_stop(struct bch_dev *, int); static void __bch2_dev_read_only(struct bch_fs *, struct bch_dev *); struct bch_fs *bch2_dev_to_fs(dev_t dev) { struct bch_fs *c; mutex_lock(&bch_fs_list_lock); rcu_read_lock(); list_for_each_entry(c, &bch_fs_list, list) for_each_member_device_rcu(c, ca, NULL) if (ca->disk_sb.bdev && ca->disk_sb.bdev->bd_dev == dev) { closure_get(&c->cl); goto found; } c = NULL; found: rcu_read_unlock(); mutex_unlock(&bch_fs_list_lock); return c; } static struct bch_fs *__bch2_uuid_to_fs(__uuid_t uuid) { struct bch_fs *c; lockdep_assert_held(&bch_fs_list_lock); list_for_each_entry(c, &bch_fs_list, list) if (!memcmp(&c->disk_sb.sb->uuid, &uuid, sizeof(uuid))) return c; return NULL; } struct bch_fs *bch2_uuid_to_fs(__uuid_t uuid) { struct bch_fs *c; mutex_lock(&bch_fs_list_lock); c = __bch2_uuid_to_fs(uuid); if (c) closure_get(&c->cl); mutex_unlock(&bch_fs_list_lock); return c; } /* Filesystem RO/RW: */ /* * For startup/shutdown of RW stuff, the dependencies are: * * - foreground writes depend on copygc and rebalance (to free up space) * * - copygc and rebalance depend on mark and sweep gc (they actually probably * don't because they either reserve ahead of time or don't block if * allocations fail, but allocations can require mark and sweep gc to run * because of generation number wraparound) * * - all of the above depends on the allocator threads * * - allocator depends on the journal (when it rewrites prios and gens) */ static void __bch2_fs_read_only(struct bch_fs *c) { unsigned clean_passes = 0; u64 seq = 0; bch2_fs_ec_stop(c); bch2_open_buckets_stop(c, NULL, true); bch2_rebalance_stop(c); bch2_copygc_stop(c); bch2_fs_ec_flush(c); bch_verbose(c, "flushing journal and stopping allocators, journal seq %llu", journal_cur_seq(&c->journal)); do { clean_passes++; if (bch2_btree_interior_updates_flush(c) || bch2_btree_write_buffer_flush_going_ro(c) || bch2_journal_flush_all_pins(&c->journal) || bch2_btree_flush_all_writes(c) || seq != atomic64_read(&c->journal.seq)) { seq = atomic64_read(&c->journal.seq); clean_passes = 0; } } while (clean_passes < 2); bch_verbose(c, "flushing journal and stopping allocators complete, journal seq %llu", journal_cur_seq(&c->journal)); if (test_bit(JOURNAL_replay_done, &c->journal.flags) && !test_bit(BCH_FS_emergency_ro, &c->flags)) set_bit(BCH_FS_clean_shutdown, &c->flags); bch2_fs_journal_stop(&c->journal); bch_info(c, "%sclean shutdown complete, journal seq %llu", test_bit(BCH_FS_clean_shutdown, &c->flags) ? "" : "un", c->journal.seq_ondisk); /* * After stopping journal: */ for_each_member_device(c, ca) { bch2_dev_io_ref_stop(ca, WRITE); bch2_dev_allocator_remove(c, ca); } } #ifndef BCH_WRITE_REF_DEBUG static void bch2_writes_disabled(struct percpu_ref *writes) { struct bch_fs *c = container_of(writes, struct bch_fs, writes); set_bit(BCH_FS_write_disable_complete, &c->flags); wake_up(&bch2_read_only_wait); } #endif void bch2_fs_read_only(struct bch_fs *c) { if (!test_bit(BCH_FS_rw, &c->flags)) { bch2_journal_reclaim_stop(&c->journal); return; } BUG_ON(test_bit(BCH_FS_write_disable_complete, &c->flags)); bch_verbose(c, "going read-only"); /* * Block new foreground-end write operations from starting - any new * writes will return -EROFS: */ set_bit(BCH_FS_going_ro, &c->flags); #ifndef BCH_WRITE_REF_DEBUG percpu_ref_kill(&c->writes); #else for (unsigned i = 0; i < BCH_WRITE_REF_NR; i++) bch2_write_ref_put(c, i); #endif /* * If we're not doing an emergency shutdown, we want to wait on * outstanding writes to complete so they don't see spurious errors due * to shutting down the allocator: * * If we are doing an emergency shutdown outstanding writes may * hang until we shutdown the allocator so we don't want to wait * on outstanding writes before shutting everything down - but * we do need to wait on them before returning and signalling * that going RO is complete: */ wait_event(bch2_read_only_wait, test_bit(BCH_FS_write_disable_complete, &c->flags) || test_bit(BCH_FS_emergency_ro, &c->flags)); bool writes_disabled = test_bit(BCH_FS_write_disable_complete, &c->flags); if (writes_disabled) bch_verbose(c, "finished waiting for writes to stop"); __bch2_fs_read_only(c); wait_event(bch2_read_only_wait, test_bit(BCH_FS_write_disable_complete, &c->flags)); if (!writes_disabled) bch_verbose(c, "finished waiting for writes to stop"); clear_bit(BCH_FS_write_disable_complete, &c->flags); clear_bit(BCH_FS_going_ro, &c->flags); clear_bit(BCH_FS_rw, &c->flags); if (!bch2_journal_error(&c->journal) && !test_bit(BCH_FS_error, &c->flags) && !test_bit(BCH_FS_emergency_ro, &c->flags) && test_bit(BCH_FS_started, &c->flags) && test_bit(BCH_FS_clean_shutdown, &c->flags) && c->recovery_pass_done >= BCH_RECOVERY_PASS_journal_replay) { BUG_ON(c->journal.last_empty_seq != journal_cur_seq(&c->journal)); BUG_ON(atomic_long_read(&c->btree_cache.nr_dirty)); BUG_ON(atomic_long_read(&c->btree_key_cache.nr_dirty)); BUG_ON(c->btree_write_buffer.inc.keys.nr); BUG_ON(c->btree_write_buffer.flushing.keys.nr); bch2_verify_accounting_clean(c); bch_verbose(c, "marking filesystem clean"); bch2_fs_mark_clean(c); } else { /* Make sure error counts/counters are persisted */ mutex_lock(&c->sb_lock); bch2_write_super(c); mutex_unlock(&c->sb_lock); bch_verbose(c, "done going read-only, filesystem not clean"); } } static void bch2_fs_read_only_work(struct work_struct *work) { struct bch_fs *c = container_of(work, struct bch_fs, read_only_work); down_write(&c->state_lock); bch2_fs_read_only(c); up_write(&c->state_lock); } static void bch2_fs_read_only_async(struct bch_fs *c) { queue_work(system_long_wq, &c->read_only_work); } bool bch2_fs_emergency_read_only(struct bch_fs *c) { bool ret = !test_and_set_bit(BCH_FS_emergency_ro, &c->flags); bch2_journal_halt(&c->journal); bch2_fs_read_only_async(c); wake_up(&bch2_read_only_wait); return ret; } bool bch2_fs_emergency_read_only_locked(struct bch_fs *c) { bool ret = !test_and_set_bit(BCH_FS_emergency_ro, &c->flags); bch2_journal_halt_locked(&c->journal); bch2_fs_read_only_async(c); wake_up(&bch2_read_only_wait); return ret; } static int __bch2_fs_read_write(struct bch_fs *c, bool early) { int ret; BUG_ON(!test_bit(BCH_FS_may_go_rw, &c->flags)); if (test_bit(BCH_FS_initial_gc_unfixed, &c->flags)) { bch_err(c, "cannot go rw, unfixed btree errors"); return -BCH_ERR_erofs_unfixed_errors; } if (test_bit(BCH_FS_rw, &c->flags)) return 0; bch_info(c, "going read-write"); ret = bch2_sb_members_v2_init(c); if (ret) goto err; clear_bit(BCH_FS_clean_shutdown, &c->flags); __for_each_online_member(c, ca, BIT(BCH_MEMBER_STATE_rw), READ) { bch2_dev_allocator_add(c, ca); percpu_ref_reinit(&ca->io_ref[WRITE]); } bch2_recalc_capacity(c); /* * First journal write must be a flush write: after a clean shutdown we * don't read the journal, so the first journal write may end up * overwriting whatever was there previously, and there must always be * at least one non-flush write in the journal or recovery will fail: */ spin_lock(&c->journal.lock); set_bit(JOURNAL_need_flush_write, &c->journal.flags); set_bit(JOURNAL_running, &c->journal.flags); bch2_journal_space_available(&c->journal); spin_unlock(&c->journal.lock); ret = bch2_fs_mark_dirty(c); if (ret) goto err; ret = bch2_journal_reclaim_start(&c->journal); if (ret) goto err; set_bit(BCH_FS_rw, &c->flags); set_bit(BCH_FS_was_rw, &c->flags); #ifndef BCH_WRITE_REF_DEBUG percpu_ref_reinit(&c->writes); #else for (unsigned i = 0; i < BCH_WRITE_REF_NR; i++) { BUG_ON(atomic_long_read(&c->writes[i])); atomic_long_inc(&c->writes[i]); } #endif ret = bch2_copygc_start(c); if (ret) { bch_err_msg(c, ret, "error starting copygc thread"); goto err; } ret = bch2_rebalance_start(c); if (ret) { bch_err_msg(c, ret, "error starting rebalance thread"); goto err; } bch2_do_discards(c); bch2_do_invalidates(c); bch2_do_stripe_deletes(c); bch2_do_pending_node_rewrites(c); return 0; err: if (test_bit(BCH_FS_rw, &c->flags)) bch2_fs_read_only(c); else __bch2_fs_read_only(c); return ret; } int bch2_fs_read_write(struct bch_fs *c) { if (c->opts.recovery_pass_last && c->opts.recovery_pass_last < BCH_RECOVERY_PASS_journal_replay) return -BCH_ERR_erofs_norecovery; if (c->opts.nochanges) return -BCH_ERR_erofs_nochanges; return __bch2_fs_read_write(c, false); } int bch2_fs_read_write_early(struct bch_fs *c) { down_write(&c->state_lock); int ret = __bch2_fs_read_write(c, true); up_write(&c->state_lock); return ret; } /* Filesystem startup/shutdown: */ static void __bch2_fs_free(struct bch_fs *c) { for (unsigned i = 0; i < BCH_TIME_STAT_NR; i++) bch2_time_stats_exit(&c->times[i]); #ifdef CONFIG_UNICODE utf8_unload(c->cf_encoding); #endif bch2_find_btree_nodes_exit(&c->found_btree_nodes); bch2_free_pending_node_rewrites(c); bch2_free_fsck_errs(c); bch2_fs_accounting_exit(c); bch2_fs_sb_errors_exit(c); bch2_fs_counters_exit(c); bch2_fs_snapshots_exit(c); bch2_fs_quota_exit(c); bch2_fs_fs_io_direct_exit(c); bch2_fs_fs_io_buffered_exit(c); bch2_fs_fsio_exit(c); bch2_fs_vfs_exit(c); bch2_fs_ec_exit(c); bch2_fs_encryption_exit(c); bch2_fs_nocow_locking_exit(c); bch2_fs_io_write_exit(c); bch2_fs_io_read_exit(c); bch2_fs_buckets_waiting_for_journal_exit(c); bch2_fs_btree_interior_update_exit(c); bch2_fs_btree_key_cache_exit(&c->btree_key_cache); bch2_fs_btree_cache_exit(c); bch2_fs_btree_iter_exit(c); bch2_fs_replicas_exit(c); bch2_fs_journal_exit(&c->journal); bch2_io_clock_exit(&c->io_clock[WRITE]); bch2_io_clock_exit(&c->io_clock[READ]); bch2_fs_compress_exit(c); bch2_fs_btree_gc_exit(c); bch2_journal_keys_put_initial(c); bch2_find_btree_nodes_exit(&c->found_btree_nodes); BUG_ON(atomic_read(&c->journal_keys.ref)); bch2_fs_btree_write_buffer_exit(c); percpu_free_rwsem(&c->mark_lock); if (c->online_reserved) { u64 v = percpu_u64_get(c->online_reserved); WARN(v, "online_reserved not 0 at shutdown: %lli", v); free_percpu(c->online_reserved); } darray_exit(&c->incompat_versions_requested); darray_exit(&c->btree_roots_extra); free_percpu(c->pcpu); free_percpu(c->usage); mempool_exit(&c->large_bkey_pool); mempool_exit(&c->btree_bounce_pool); bioset_exit(&c->btree_bio); mempool_exit(&c->fill_iter); #ifndef BCH_WRITE_REF_DEBUG percpu_ref_exit(&c->writes); #endif kfree(rcu_dereference_protected(c->disk_groups, 1)); kfree(c->journal_seq_blacklist_table); if (c->write_ref_wq) destroy_workqueue(c->write_ref_wq); if (c->btree_write_submit_wq) destroy_workqueue(c->btree_write_submit_wq); if (c->btree_read_complete_wq) destroy_workqueue(c->btree_read_complete_wq); if (c->copygc_wq) destroy_workqueue(c->copygc_wq); if (c->btree_io_complete_wq) destroy_workqueue(c->btree_io_complete_wq); if (c->btree_update_wq) destroy_workqueue(c->btree_update_wq); bch2_free_super(&c->disk_sb); kvfree(c); module_put(THIS_MODULE); } static void bch2_fs_release(struct kobject *kobj) { struct bch_fs *c = container_of(kobj, struct bch_fs, kobj); __bch2_fs_free(c); } void __bch2_fs_stop(struct bch_fs *c) { bch_verbose(c, "shutting down"); set_bit(BCH_FS_stopping, &c->flags); down_write(&c->state_lock); bch2_fs_read_only(c); up_write(&c->state_lock); for_each_member_device(c, ca) bch2_dev_unlink(ca); if (c->kobj.state_in_sysfs) kobject_del(&c->kobj); bch2_fs_debug_exit(c); bch2_fs_chardev_exit(c); bch2_ro_ref_put(c); wait_event(c->ro_ref_wait, !refcount_read(&c->ro_ref)); kobject_put(&c->counters_kobj); kobject_put(&c->time_stats); kobject_put(&c->opts_dir); kobject_put(&c->internal); /* btree prefetch might have kicked off reads in the background: */ bch2_btree_flush_all_reads(c); for_each_member_device(c, ca) cancel_work_sync(&ca->io_error_work); cancel_work_sync(&c->read_only_work); } void bch2_fs_free(struct bch_fs *c) { unsigned i; mutex_lock(&bch_fs_list_lock); list_del(&c->list); mutex_unlock(&bch_fs_list_lock); closure_sync(&c->cl); closure_debug_destroy(&c->cl); for (i = 0; i < c->sb.nr_devices; i++) { struct bch_dev *ca = rcu_dereference_protected(c->devs[i], true); if (ca) { EBUG_ON(atomic_long_read(&ca->ref) != 1); bch2_dev_io_ref_stop(ca, READ); bch2_free_super(&ca->disk_sb); bch2_dev_free(ca); } } bch_verbose(c, "shutdown complete"); kobject_put(&c->kobj); } void bch2_fs_stop(struct bch_fs *c) { __bch2_fs_stop(c); bch2_fs_free(c); } static int bch2_fs_online(struct bch_fs *c) { int ret = 0; lockdep_assert_held(&bch_fs_list_lock); if (__bch2_uuid_to_fs(c->sb.uuid)) { bch_err(c, "filesystem UUID already open"); return -EINVAL; } ret = bch2_fs_chardev_init(c); if (ret) { bch_err(c, "error creating character device"); return ret; } bch2_fs_debug_init(c); ret = kobject_add(&c->kobj, NULL, "%pU", c->sb.user_uuid.b) ?: kobject_add(&c->internal, &c->kobj, "internal") ?: kobject_add(&c->opts_dir, &c->kobj, "options") ?: #ifndef CONFIG_BCACHEFS_NO_LATENCY_ACCT kobject_add(&c->time_stats, &c->kobj, "time_stats") ?: #endif kobject_add(&c->counters_kobj, &c->kobj, "counters") ?: bch2_opts_create_sysfs_files(&c->opts_dir, OPT_FS); if (ret) { bch_err(c, "error creating sysfs objects"); return ret; } down_write(&c->state_lock); for_each_member_device(c, ca) { ret = bch2_dev_sysfs_online(c, ca); if (ret) { bch_err(c, "error creating sysfs objects"); bch2_dev_put(ca); goto err; } } BUG_ON(!list_empty(&c->list)); list_add(&c->list, &bch_fs_list); err: up_write(&c->state_lock); return ret; } static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts) { struct bch_fs *c; struct printbuf name = PRINTBUF; unsigned i, iter_size; int ret = 0; c = kvmalloc(sizeof(struct bch_fs), GFP_KERNEL|__GFP_ZERO); if (!c) { c = ERR_PTR(-BCH_ERR_ENOMEM_fs_alloc); goto out; } c->stdio = (void *)(unsigned long) opts.stdio; __module_get(THIS_MODULE); closure_init(&c->cl, NULL); c->kobj.kset = bcachefs_kset; kobject_init(&c->kobj, &bch2_fs_ktype); kobject_init(&c->internal, &bch2_fs_internal_ktype); kobject_init(&c->opts_dir, &bch2_fs_opts_dir_ktype); kobject_init(&c->time_stats, &bch2_fs_time_stats_ktype); kobject_init(&c->counters_kobj, &bch2_fs_counters_ktype); c->minor = -1; c->disk_sb.fs_sb = true; init_rwsem(&c->state_lock); mutex_init(&c->sb_lock); mutex_init(&c->replicas_gc_lock); mutex_init(&c->btree_root_lock); INIT_WORK(&c->read_only_work, bch2_fs_read_only_work); refcount_set(&c->ro_ref, 1); init_waitqueue_head(&c->ro_ref_wait); spin_lock_init(&c->recovery_pass_lock); sema_init(&c->online_fsck_mutex, 1); for (i = 0; i < BCH_TIME_STAT_NR; i++) bch2_time_stats_init(&c->times[i]); bch2_fs_copygc_init(c); bch2_fs_btree_key_cache_init_early(&c->btree_key_cache); bch2_fs_btree_iter_init_early(c); bch2_fs_btree_interior_update_init_early(c); bch2_fs_journal_keys_init(c); bch2_fs_allocator_background_init(c); bch2_fs_allocator_foreground_init(c); bch2_fs_rebalance_init(c); bch2_fs_quota_init(c); bch2_fs_ec_init_early(c); bch2_fs_move_init(c); bch2_fs_sb_errors_init_early(c); INIT_LIST_HEAD(&c->list); mutex_init(&c->bio_bounce_pages_lock); mutex_init(&c->snapshot_table_lock); init_rwsem(&c->snapshot_create_lock); spin_lock_init(&c->btree_write_error_lock); INIT_LIST_HEAD(&c->journal_iters); INIT_LIST_HEAD(&c->fsck_error_msgs); mutex_init(&c->fsck_error_msgs_lock); seqcount_init(&c->usage_lock); sema_init(&c->io_in_flight, 128); INIT_LIST_HEAD(&c->vfs_inodes_list); mutex_init(&c->vfs_inodes_lock); c->journal.flush_write_time = &c->times[BCH_TIME_journal_flush_write]; c->journal.noflush_write_time = &c->times[BCH_TIME_journal_noflush_write]; c->journal.flush_seq_time = &c->times[BCH_TIME_journal_flush_seq]; bch2_fs_btree_cache_init_early(&c->btree_cache); mutex_init(&c->sectors_available_lock); ret = percpu_init_rwsem(&c->mark_lock); if (ret) goto err; mutex_lock(&c->sb_lock); ret = bch2_sb_to_fs(c, sb); mutex_unlock(&c->sb_lock); if (ret) goto err; pr_uuid(&name, c->sb.user_uuid.b); ret = name.allocation_failure ? -BCH_ERR_ENOMEM_fs_name_alloc : 0; if (ret) goto err; strscpy(c->name, name.buf, sizeof(c->name)); printbuf_exit(&name); /* Compat: */ if (le16_to_cpu(sb->version) <= bcachefs_metadata_version_inode_v2 && !BCH_SB_JOURNAL_FLUSH_DELAY(sb)) SET_BCH_SB_JOURNAL_FLUSH_DELAY(sb, 1000); if (le16_to_cpu(sb->version) <= bcachefs_metadata_version_inode_v2 && !BCH_SB_JOURNAL_RECLAIM_DELAY(sb)) SET_BCH_SB_JOURNAL_RECLAIM_DELAY(sb, 100); c->opts = bch2_opts_default; ret = bch2_opts_from_sb(&c->opts, sb); if (ret) goto err; bch2_opts_apply(&c->opts, opts); c->btree_key_cache_btrees |= 1U << BTREE_ID_alloc; if (c->opts.inodes_use_key_cache) c->btree_key_cache_btrees |= 1U << BTREE_ID_inodes; c->btree_key_cache_btrees |= 1U << BTREE_ID_logged_ops; c->block_bits = ilog2(block_sectors(c)); c->btree_foreground_merge_threshold = BTREE_FOREGROUND_MERGE_THRESHOLD(c); if (bch2_fs_init_fault("fs_alloc")) { bch_err(c, "fs_alloc fault injected"); ret = -EFAULT; goto err; } iter_size = sizeof(struct sort_iter) + (btree_blocks(c) + 1) * 2 * sizeof(struct sort_iter_set); if (!(c->btree_update_wq = alloc_workqueue("bcachefs", WQ_HIGHPRI|WQ_FREEZABLE|WQ_MEM_RECLAIM|WQ_UNBOUND, 512)) || !(c->btree_io_complete_wq = alloc_workqueue("bcachefs_btree_io", WQ_HIGHPRI|WQ_FREEZABLE|WQ_MEM_RECLAIM, 1)) || !(c->copygc_wq = alloc_workqueue("bcachefs_copygc", WQ_HIGHPRI|WQ_FREEZABLE|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE, 1)) || !(c->btree_read_complete_wq = alloc_workqueue("bcachefs_btree_read_complete", WQ_HIGHPRI|WQ_FREEZABLE|WQ_MEM_RECLAIM, 512)) || !(c->btree_write_submit_wq = alloc_workqueue("bcachefs_btree_write_sumit", WQ_HIGHPRI|WQ_FREEZABLE|WQ_MEM_RECLAIM, 1)) || !(c->write_ref_wq = alloc_workqueue("bcachefs_write_ref", WQ_FREEZABLE, 0)) || #ifndef BCH_WRITE_REF_DEBUG percpu_ref_init(&c->writes, bch2_writes_disabled, PERCPU_REF_INIT_DEAD, GFP_KERNEL) || #endif mempool_init_kmalloc_pool(&c->fill_iter, 1, iter_size) || bioset_init(&c->btree_bio, 1, max(offsetof(struct btree_read_bio, bio), offsetof(struct btree_write_bio, wbio.bio)), BIOSET_NEED_BVECS) || !(c->pcpu = alloc_percpu(struct bch_fs_pcpu)) || !(c->usage = alloc_percpu(struct bch_fs_usage_base)) || !(c->online_reserved = alloc_percpu(u64)) || mempool_init_kvmalloc_pool(&c->btree_bounce_pool, 1, c->opts.btree_node_size) || mempool_init_kmalloc_pool(&c->large_bkey_pool, 1, 2048)) { ret = -BCH_ERR_ENOMEM_fs_other_alloc; goto err; } ret = bch2_fs_counters_init(c) ?: bch2_fs_sb_errors_init(c) ?: bch2_io_clock_init(&c->io_clock[READ]) ?: bch2_io_clock_init(&c->io_clock[WRITE]) ?: bch2_fs_journal_init(&c->journal) ?: bch2_fs_btree_iter_init(c) ?: bch2_fs_btree_cache_init(c) ?: bch2_fs_btree_key_cache_init(&c->btree_key_cache) ?: bch2_fs_btree_interior_update_init(c) ?: bch2_fs_btree_gc_init(c) ?: bch2_fs_buckets_waiting_for_journal_init(c) ?: bch2_fs_btree_write_buffer_init(c) ?: bch2_fs_subvolumes_init(c) ?: bch2_fs_io_read_init(c) ?: bch2_fs_io_write_init(c) ?: bch2_fs_nocow_locking_init(c) ?: bch2_fs_encryption_init(c) ?: bch2_fs_compress_init(c) ?: bch2_fs_ec_init(c) ?: bch2_fs_vfs_init(c) ?: bch2_fs_fsio_init(c) ?: bch2_fs_fs_io_buffered_init(c) ?: bch2_fs_fs_io_direct_init(c); if (ret) goto err; #ifdef CONFIG_UNICODE /* Default encoding until we can potentially have more as an option. */ c->cf_encoding = utf8_load(BCH_FS_DEFAULT_UTF8_ENCODING); if (IS_ERR(c->cf_encoding)) { printk(KERN_ERR "Cannot load UTF-8 encoding for filesystem. Version: %u.%u.%u", unicode_major(BCH_FS_DEFAULT_UTF8_ENCODING), unicode_minor(BCH_FS_DEFAULT_UTF8_ENCODING), unicode_rev(BCH_FS_DEFAULT_UTF8_ENCODING)); ret = -EINVAL; goto err; } bch_info(c, "Using encoding defined by superblock: utf8-%u.%u.%u", unicode_major(BCH_FS_DEFAULT_UTF8_ENCODING), unicode_minor(BCH_FS_DEFAULT_UTF8_ENCODING), unicode_rev(BCH_FS_DEFAULT_UTF8_ENCODING)); #else if (c->sb.features & BIT_ULL(BCH_FEATURE_casefolding)) { printk(KERN_ERR "Cannot mount a filesystem with casefolding on a kernel without CONFIG_UNICODE\n"); ret = -EINVAL; goto err; } #endif for (i = 0; i < c->sb.nr_devices; i++) { if (!bch2_member_exists(c->disk_sb.sb, i)) continue; ret = bch2_dev_alloc(c, i); if (ret) goto err; } bch2_journal_entry_res_resize(&c->journal, &c->btree_root_journal_res, BTREE_ID_NR * (JSET_KEYS_U64s + BKEY_BTREE_PTR_U64s_MAX)); bch2_journal_entry_res_resize(&c->journal, &c->clock_journal_res, (sizeof(struct jset_entry_clock) / sizeof(u64)) * 2); mutex_lock(&bch_fs_list_lock); ret = bch2_fs_online(c); mutex_unlock(&bch_fs_list_lock); if (ret) goto err; out: return c; err: bch2_fs_free(c); c = ERR_PTR(ret); goto out; } noinline_for_stack static void print_mount_opts(struct bch_fs *c) { enum bch_opt_id i; struct printbuf p = PRINTBUF; bool first = true; prt_str(&p, "starting version "); bch2_version_to_text(&p, c->sb.version); for (i = 0; i < bch2_opts_nr; i++) { const struct bch_option *opt = &bch2_opt_table[i]; u64 v = bch2_opt_get_by_id(&c->opts, i); if (!(opt->flags & OPT_MOUNT)) continue; if (v == bch2_opt_get_by_id(&bch2_opts_default, i)) continue; prt_str(&p, first ? " opts=" : ","); first = false; bch2_opt_to_text(&p, c, c->disk_sb.sb, opt, v, OPT_SHOW_MOUNT_STYLE); } if (c->sb.version_incompat_allowed != c->sb.version) { prt_printf(&p, "\n allowing incompatible features above "); bch2_version_to_text(&p, c->sb.version_incompat_allowed); } bch_info(c, "%s", p.buf); printbuf_exit(&p); } static bool bch2_fs_may_start(struct bch_fs *c) { struct bch_dev *ca; unsigned i, flags = 0; if (c->opts.very_degraded) flags |= BCH_FORCE_IF_DEGRADED|BCH_FORCE_IF_LOST; if (c->opts.degraded) flags |= BCH_FORCE_IF_DEGRADED; if (!c->opts.degraded && !c->opts.very_degraded) { mutex_lock(&c->sb_lock); for (i = 0; i < c->disk_sb.sb->nr_devices; i++) { if (!bch2_member_exists(c->disk_sb.sb, i)) continue; ca = bch2_dev_locked(c, i); if (!bch2_dev_is_online(ca) && (ca->mi.state == BCH_MEMBER_STATE_rw || ca->mi.state == BCH_MEMBER_STATE_ro)) { mutex_unlock(&c->sb_lock); return false; } } mutex_unlock(&c->sb_lock); } return bch2_have_enough_devs(c, bch2_online_devs(c), flags, true); } int bch2_fs_start(struct bch_fs *c) { time64_t now = ktime_get_real_seconds(); int ret = 0; print_mount_opts(c); if (!bch2_fs_may_start(c)) return -BCH_ERR_insufficient_devices_to_start; down_write(&c->state_lock); mutex_lock(&c->sb_lock); BUG_ON(test_bit(BCH_FS_started, &c->flags)); if (!bch2_sb_field_get_minsize(&c->disk_sb, ext, sizeof(struct bch_sb_field_ext) / sizeof(u64))) { mutex_unlock(&c->sb_lock); up_write(&c->state_lock); ret = -BCH_ERR_ENOSPC_sb; goto err; } ret = bch2_sb_members_v2_init(c); if (ret) { mutex_unlock(&c->sb_lock); up_write(&c->state_lock); goto err; } for_each_online_member(c, ca) bch2_members_v2_get_mut(c->disk_sb.sb, ca->dev_idx)->last_mount = cpu_to_le64(now); mutex_unlock(&c->sb_lock); for_each_rw_member(c, ca) bch2_dev_allocator_add(c, ca); bch2_recalc_capacity(c); up_write(&c->state_lock); c->recovery_task = current; ret = BCH_SB_INITIALIZED(c->disk_sb.sb) ? bch2_fs_recovery(c) : bch2_fs_initialize(c); c->recovery_task = NULL; if (ret) goto err; ret = bch2_opts_check_may_set(c); if (ret) goto err; if (bch2_fs_init_fault("fs_start")) { ret = -BCH_ERR_injected_fs_start; goto err; } set_bit(BCH_FS_started, &c->flags); wake_up(&c->ro_ref_wait); down_write(&c->state_lock); if (c->opts.read_only) bch2_fs_read_only(c); else if (!test_bit(BCH_FS_rw, &c->flags)) ret = bch2_fs_read_write(c); up_write(&c->state_lock); err: if (ret) bch_err_msg(c, ret, "starting filesystem"); else bch_verbose(c, "done starting filesystem"); return ret; } static int bch2_dev_may_add(struct bch_sb *sb, struct bch_fs *c) { struct bch_member m = bch2_sb_member_get(sb, sb->dev_idx); if (le16_to_cpu(sb->block_size) != block_sectors(c)) return -BCH_ERR_mismatched_block_size; if (le16_to_cpu(m.bucket_size) < BCH_SB_BTREE_NODE_SIZE(c->disk_sb.sb)) return -BCH_ERR_bucket_size_too_small; return 0; } static int bch2_dev_in_fs(struct bch_sb_handle *fs, struct bch_sb_handle *sb, struct bch_opts *opts) { if (fs == sb) return 0; if (!uuid_equal(&fs->sb->uuid, &sb->sb->uuid)) return -BCH_ERR_device_not_a_member_of_filesystem; if (!bch2_member_exists(fs->sb, sb->sb->dev_idx)) return -BCH_ERR_device_has_been_removed; if (fs->sb->block_size != sb->sb->block_size) return -BCH_ERR_mismatched_block_size; if (le16_to_cpu(fs->sb->version) < bcachefs_metadata_version_member_seq || le16_to_cpu(sb->sb->version) < bcachefs_metadata_version_member_seq) return 0; if (fs->sb->seq == sb->sb->seq && fs->sb->write_time != sb->sb->write_time) { struct printbuf buf = PRINTBUF; prt_str(&buf, "Split brain detected between "); prt_bdevname(&buf, sb->bdev); prt_str(&buf, " and "); prt_bdevname(&buf, fs->bdev); prt_char(&buf, ':'); prt_newline(&buf); prt_printf(&buf, "seq=%llu but write_time different, got", le64_to_cpu(sb->sb->seq)); prt_newline(&buf); prt_bdevname(&buf, fs->bdev); prt_char(&buf, ' '); bch2_prt_datetime(&buf, le64_to_cpu(fs->sb->write_time)); prt_newline(&buf); prt_bdevname(&buf, sb->bdev); prt_char(&buf, ' '); bch2_prt_datetime(&buf, le64_to_cpu(sb->sb->write_time)); prt_newline(&buf); if (!opts->no_splitbrain_check) prt_printf(&buf, "Not using older sb"); pr_err("%s", buf.buf); printbuf_exit(&buf); if (!opts->no_splitbrain_check) return -BCH_ERR_device_splitbrain; } struct bch_member m = bch2_sb_member_get(fs->sb, sb->sb->dev_idx); u64 seq_from_fs = le64_to_cpu(m.seq); u64 seq_from_member = le64_to_cpu(sb->sb->seq); if (seq_from_fs && seq_from_fs < seq_from_member) { struct printbuf buf = PRINTBUF; prt_str(&buf, "Split brain detected between "); prt_bdevname(&buf, sb->bdev); prt_str(&buf, " and "); prt_bdevname(&buf, fs->bdev); prt_char(&buf, ':'); prt_newline(&buf); prt_bdevname(&buf, fs->bdev); prt_str(&buf, " believes seq of "); prt_bdevname(&buf, sb->bdev); prt_printf(&buf, " to be %llu, but ", seq_from_fs); prt_bdevname(&buf, sb->bdev); prt_printf(&buf, " has %llu\n", seq_from_member); if (!opts->no_splitbrain_check) { prt_str(&buf, "Not using "); prt_bdevname(&buf, sb->bdev); } pr_err("%s", buf.buf); printbuf_exit(&buf); if (!opts->no_splitbrain_check) return -BCH_ERR_device_splitbrain; } return 0; } /* Device startup/shutdown: */ static void bch2_dev_io_ref_stop(struct bch_dev *ca, int rw) { if (!percpu_ref_is_zero(&ca->io_ref[rw])) { reinit_completion(&ca->io_ref_completion[rw]); percpu_ref_kill(&ca->io_ref[rw]); wait_for_completion(&ca->io_ref_completion[rw]); } } static void bch2_dev_release(struct kobject *kobj) { struct bch_dev *ca = container_of(kobj, struct bch_dev, kobj); kfree(ca); } static void bch2_dev_free(struct bch_dev *ca) { WARN_ON(!percpu_ref_is_zero(&ca->io_ref[WRITE])); WARN_ON(!percpu_ref_is_zero(&ca->io_ref[READ])); cancel_work_sync(&ca->io_error_work); bch2_dev_unlink(ca); if (ca->kobj.state_in_sysfs) kobject_del(&ca->kobj); bch2_free_super(&ca->disk_sb); bch2_dev_allocator_background_exit(ca); bch2_dev_journal_exit(ca); free_percpu(ca->io_done); bch2_dev_buckets_free(ca); kfree(ca->sb_read_scratch); bch2_time_stats_quantiles_exit(&ca->io_latency[WRITE]); bch2_time_stats_quantiles_exit(&ca->io_latency[READ]); percpu_ref_exit(&ca->io_ref[WRITE]); percpu_ref_exit(&ca->io_ref[READ]); #ifndef CONFIG_BCACHEFS_DEBUG percpu_ref_exit(&ca->ref); #endif kobject_put(&ca->kobj); } static void __bch2_dev_offline(struct bch_fs *c, struct bch_dev *ca) { lockdep_assert_held(&c->state_lock); if (percpu_ref_is_zero(&ca->io_ref[READ])) return; __bch2_dev_read_only(c, ca); bch2_dev_io_ref_stop(ca, READ); bch2_dev_unlink(ca); bch2_free_super(&ca->disk_sb); bch2_dev_journal_exit(ca); } #ifndef CONFIG_BCACHEFS_DEBUG static void bch2_dev_ref_complete(struct percpu_ref *ref) { struct bch_dev *ca = container_of(ref, struct bch_dev, ref); complete(&ca->ref_completion); } #endif static void bch2_dev_io_ref_read_complete(struct percpu_ref *ref) { struct bch_dev *ca = container_of(ref, struct bch_dev, io_ref[READ]); complete(&ca->io_ref_completion[READ]); } static void bch2_dev_io_ref_write_complete(struct percpu_ref *ref) { struct bch_dev *ca = container_of(ref, struct bch_dev, io_ref[WRITE]); complete(&ca->io_ref_completion[WRITE]); } static void bch2_dev_unlink(struct bch_dev *ca) { struct kobject *b; /* * This is racy w.r.t. the underlying block device being hot-removed, * which removes it from sysfs. * * It'd be lovely if we had a way to handle this race, but the sysfs * code doesn't appear to provide a good method and block/holder.c is * susceptible as well: */ if (ca->kobj.state_in_sysfs && ca->disk_sb.bdev && (b = bdev_kobj(ca->disk_sb.bdev))->state_in_sysfs) { sysfs_remove_link(b, "bcachefs"); sysfs_remove_link(&ca->kobj, "block"); } } static int bch2_dev_sysfs_online(struct bch_fs *c, struct bch_dev *ca) { int ret; if (!c->kobj.state_in_sysfs) return 0; if (!ca->kobj.state_in_sysfs) { ret = kobject_add(&ca->kobj, &c->kobj, "dev-%u", ca->dev_idx) ?: bch2_opts_create_sysfs_files(&ca->kobj, OPT_DEVICE); if (ret) return ret; } if (ca->disk_sb.bdev) { struct kobject *block = bdev_kobj(ca->disk_sb.bdev); ret = sysfs_create_link(block, &ca->kobj, "bcachefs"); if (ret) return ret; ret = sysfs_create_link(&ca->kobj, block, "block"); if (ret) return ret; } return 0; } static struct bch_dev *__bch2_dev_alloc(struct bch_fs *c, struct bch_member *member) { struct bch_dev *ca; unsigned i; ca = kzalloc(sizeof(*ca), GFP_KERNEL); if (!ca) return NULL; kobject_init(&ca->kobj, &bch2_dev_ktype); init_completion(&ca->ref_completion); init_completion(&ca->io_ref_completion[READ]); init_completion(&ca->io_ref_completion[WRITE]); INIT_WORK(&ca->io_error_work, bch2_io_error_work); bch2_time_stats_quantiles_init(&ca->io_latency[READ]); bch2_time_stats_quantiles_init(&ca->io_latency[WRITE]); ca->mi = bch2_mi_to_cpu(member); for (i = 0; i < ARRAY_SIZE(member->errors); i++) atomic64_set(&ca->errors[i], le64_to_cpu(member->errors[i])); ca->uuid = member->uuid; ca->nr_btree_reserve = DIV_ROUND_UP(BTREE_NODE_RESERVE, ca->mi.bucket_size / btree_sectors(c)); #ifndef CONFIG_BCACHEFS_DEBUG if (percpu_ref_init(&ca->ref, bch2_dev_ref_complete, 0, GFP_KERNEL)) goto err; #else atomic_long_set(&ca->ref, 1); #endif bch2_dev_allocator_background_init(ca); if (percpu_ref_init(&ca->io_ref[READ], bch2_dev_io_ref_read_complete, PERCPU_REF_INIT_DEAD, GFP_KERNEL) || percpu_ref_init(&ca->io_ref[WRITE], bch2_dev_io_ref_write_complete, PERCPU_REF_INIT_DEAD, GFP_KERNEL) || !(ca->sb_read_scratch = kmalloc(BCH_SB_READ_SCRATCH_BUF_SIZE, GFP_KERNEL)) || bch2_dev_buckets_alloc(c, ca) || !(ca->io_done = alloc_percpu(*ca->io_done))) goto err; return ca; err: bch2_dev_free(ca); return NULL; } static void bch2_dev_attach(struct bch_fs *c, struct bch_dev *ca, unsigned dev_idx) { ca->dev_idx = dev_idx; __set_bit(ca->dev_idx, ca->self.d); scnprintf(ca->name, sizeof(ca->name), "dev-%u", dev_idx); ca->fs = c; rcu_assign_pointer(c->devs[ca->dev_idx], ca); if (bch2_dev_sysfs_online(c, ca)) pr_warn("error creating sysfs objects"); } static int bch2_dev_alloc(struct bch_fs *c, unsigned dev_idx) { struct bch_member member = bch2_sb_member_get(c->disk_sb.sb, dev_idx); struct bch_dev *ca = NULL; if (bch2_fs_init_fault("dev_alloc")) goto err; ca = __bch2_dev_alloc(c, &member); if (!ca) goto err; ca->fs = c; bch2_dev_attach(c, ca, dev_idx); return 0; err: return -BCH_ERR_ENOMEM_dev_alloc; } static int __bch2_dev_attach_bdev(struct bch_dev *ca, struct bch_sb_handle *sb) { unsigned ret; if (bch2_dev_is_online(ca)) { bch_err(ca, "already have device online in slot %u", sb->sb->dev_idx); return -BCH_ERR_device_already_online; } if (get_capacity(sb->bdev->bd_disk) < ca->mi.bucket_size * ca->mi.nbuckets) { bch_err(ca, "cannot online: device too small"); return -BCH_ERR_device_size_too_small; } BUG_ON(!percpu_ref_is_zero(&ca->io_ref[READ])); BUG_ON(!percpu_ref_is_zero(&ca->io_ref[WRITE])); ret = bch2_dev_journal_init(ca, sb->sb); if (ret) return ret; /* Commit: */ ca->disk_sb = *sb; memset(sb, 0, sizeof(*sb)); /* * Stash pointer to the filesystem for blk_holder_ops - note that once * attached to a filesystem, we will always close the block device * before tearing down the filesystem object. */ ca->disk_sb.holder->c = ca->fs; ca->dev = ca->disk_sb.bdev->bd_dev; percpu_ref_reinit(&ca->io_ref[READ]); return 0; } static int bch2_dev_attach_bdev(struct bch_fs *c, struct bch_sb_handle *sb) { struct bch_dev *ca; int ret; lockdep_assert_held(&c->state_lock); if (le64_to_cpu(sb->sb->seq) > le64_to_cpu(c->disk_sb.sb->seq)) bch2_sb_to_fs(c, sb->sb); BUG_ON(!bch2_dev_exists(c, sb->sb->dev_idx)); ca = bch2_dev_locked(c, sb->sb->dev_idx); ret = __bch2_dev_attach_bdev(ca, sb); if (ret) return ret; bch2_dev_sysfs_online(c, ca); struct printbuf name = PRINTBUF; prt_bdevname(&name, ca->disk_sb.bdev); if (c->sb.nr_devices == 1) strscpy(c->name, name.buf, sizeof(c->name)); strscpy(ca->name, name.buf, sizeof(ca->name)); printbuf_exit(&name); bch2_rebalance_wakeup(c); return 0; } /* Device management: */ /* * Note: this function is also used by the error paths - when a particular * device sees an error, we call it to determine whether we can just set the * device RO, or - if this function returns false - we'll set the whole * filesystem RO: * * XXX: maybe we should be more explicit about whether we're changing state * because we got an error or what have you? */ bool bch2_dev_state_allowed(struct bch_fs *c, struct bch_dev *ca, enum bch_member_state new_state, int flags) { struct bch_devs_mask new_online_devs; int nr_rw = 0, required; lockdep_assert_held(&c->state_lock); switch (new_state) { case BCH_MEMBER_STATE_rw: return true; case BCH_MEMBER_STATE_ro: if (ca->mi.state != BCH_MEMBER_STATE_rw) return true; /* do we have enough devices to write to? */ for_each_member_device(c, ca2) if (ca2 != ca) nr_rw += ca2->mi.state == BCH_MEMBER_STATE_rw; required = max(!(flags & BCH_FORCE_IF_METADATA_DEGRADED) ? c->opts.metadata_replicas : metadata_replicas_required(c), !(flags & BCH_FORCE_IF_DATA_DEGRADED) ? c->opts.data_replicas : data_replicas_required(c)); return nr_rw >= required; case BCH_MEMBER_STATE_failed: case BCH_MEMBER_STATE_spare: if (ca->mi.state != BCH_MEMBER_STATE_rw && ca->mi.state != BCH_MEMBER_STATE_ro) return true; /* do we have enough devices to read from? */ new_online_devs = bch2_online_devs(c); __clear_bit(ca->dev_idx, new_online_devs.d); return bch2_have_enough_devs(c, new_online_devs, flags, false); default: BUG(); } } static void __bch2_dev_read_only(struct bch_fs *c, struct bch_dev *ca) { bch2_dev_io_ref_stop(ca, WRITE); /* * The allocator thread itself allocates btree nodes, so stop it first: */ bch2_dev_allocator_remove(c, ca); bch2_recalc_capacity(c); bch2_dev_journal_stop(&c->journal, ca); } static void __bch2_dev_read_write(struct bch_fs *c, struct bch_dev *ca) { lockdep_assert_held(&c->state_lock); BUG_ON(ca->mi.state != BCH_MEMBER_STATE_rw); bch2_dev_allocator_add(c, ca); bch2_recalc_capacity(c); if (percpu_ref_is_zero(&ca->io_ref[WRITE])) percpu_ref_reinit(&ca->io_ref[WRITE]); bch2_dev_do_discards(ca); } int __bch2_dev_set_state(struct bch_fs *c, struct bch_dev *ca, enum bch_member_state new_state, int flags) { struct bch_member *m; int ret = 0; if (ca->mi.state == new_state) return 0; if (!bch2_dev_state_allowed(c, ca, new_state, flags)) return -BCH_ERR_device_state_not_allowed; if (new_state != BCH_MEMBER_STATE_rw) __bch2_dev_read_only(c, ca); bch_notice(ca, "%s", bch2_member_states[new_state]); mutex_lock(&c->sb_lock); m = bch2_members_v2_get_mut(c->disk_sb.sb, ca->dev_idx); SET_BCH_MEMBER_STATE(m, new_state); bch2_write_super(c); mutex_unlock(&c->sb_lock); if (new_state == BCH_MEMBER_STATE_rw) __bch2_dev_read_write(c, ca); bch2_rebalance_wakeup(c); return ret; } int bch2_dev_set_state(struct bch_fs *c, struct bch_dev *ca, enum bch_member_state new_state, int flags) { int ret; down_write(&c->state_lock); ret = __bch2_dev_set_state(c, ca, new_state, flags); up_write(&c->state_lock); return ret; } /* Device add/removal: */ int bch2_dev_remove(struct bch_fs *c, struct bch_dev *ca, int flags) { struct bch_member *m; unsigned dev_idx = ca->dev_idx, data; int ret; down_write(&c->state_lock); /* * We consume a reference to ca->ref, regardless of whether we succeed * or fail: */ bch2_dev_put(ca); if (!bch2_dev_state_allowed(c, ca, BCH_MEMBER_STATE_failed, flags)) { bch_err(ca, "Cannot remove without losing data"); ret = -BCH_ERR_device_state_not_allowed; goto err; } __bch2_dev_read_only(c, ca); ret = bch2_dev_data_drop(c, ca->dev_idx, flags); bch_err_msg(ca, ret, "bch2_dev_data_drop()"); if (ret) goto err; ret = bch2_dev_remove_alloc(c, ca); bch_err_msg(ca, ret, "bch2_dev_remove_alloc()"); if (ret) goto err; /* * We need to flush the entire journal to get rid of keys that reference * the device being removed before removing the superblock entry */ bch2_journal_flush_all_pins(&c->journal); /* * this is really just needed for the bch2_replicas_gc_(start|end) * calls, and could be cleaned up: */ ret = bch2_journal_flush_device_pins(&c->journal, ca->dev_idx); bch_err_msg(ca, ret, "bch2_journal_flush_device_pins()"); if (ret) goto err; ret = bch2_journal_flush(&c->journal); bch_err_msg(ca, ret, "bch2_journal_flush()"); if (ret) goto err; ret = bch2_replicas_gc2(c); bch_err_msg(ca, ret, "bch2_replicas_gc2()"); if (ret) goto err; data = bch2_dev_has_data(c, ca); if (data) { struct printbuf data_has = PRINTBUF; prt_bitflags(&data_has, __bch2_data_types, data); bch_err(ca, "Remove failed, still has data (%s)", data_has.buf); printbuf_exit(&data_has); ret = -EBUSY; goto err; } __bch2_dev_offline(c, ca); mutex_lock(&c->sb_lock); rcu_assign_pointer(c->devs[ca->dev_idx], NULL); mutex_unlock(&c->sb_lock); #ifndef CONFIG_BCACHEFS_DEBUG percpu_ref_kill(&ca->ref); #else ca->dying = true; bch2_dev_put(ca); #endif wait_for_completion(&ca->ref_completion); bch2_dev_free(ca); /* * Free this device's slot in the bch_member array - all pointers to * this device must be gone: */ mutex_lock(&c->sb_lock); m = bch2_members_v2_get_mut(c->disk_sb.sb, dev_idx); memset(&m->uuid, 0, sizeof(m->uuid)); bch2_write_super(c); mutex_unlock(&c->sb_lock); up_write(&c->state_lock); return 0; err: if (test_bit(BCH_FS_rw, &c->flags) && ca->mi.state == BCH_MEMBER_STATE_rw && !percpu_ref_is_zero(&ca->io_ref[READ])) __bch2_dev_read_write(c, ca); up_write(&c->state_lock); return ret; } /* Add new device to running filesystem: */ int bch2_dev_add(struct bch_fs *c, const char *path) { struct bch_opts opts = bch2_opts_empty(); struct bch_sb_handle sb; struct bch_dev *ca = NULL; struct printbuf errbuf = PRINTBUF; struct printbuf label = PRINTBUF; int ret; ret = bch2_read_super(path, &opts, &sb); bch_err_msg(c, ret, "reading super"); if (ret) goto err; struct bch_member dev_mi = bch2_sb_member_get(sb.sb, sb.sb->dev_idx); if (BCH_MEMBER_GROUP(&dev_mi)) { bch2_disk_path_to_text_sb(&label, sb.sb, BCH_MEMBER_GROUP(&dev_mi) - 1); if (label.allocation_failure) { ret = -ENOMEM; goto err; } } ret = bch2_dev_may_add(sb.sb, c); if (ret) goto err; ca = __bch2_dev_alloc(c, &dev_mi); if (!ca) { ret = -ENOMEM; goto err; } ret = __bch2_dev_attach_bdev(ca, &sb); if (ret) goto err; down_write(&c->state_lock); mutex_lock(&c->sb_lock); ret = bch2_sb_from_fs(c, ca); bch_err_msg(c, ret, "setting up new superblock"); if (ret) goto err_unlock; if (dynamic_fault("bcachefs:add:no_slot")) goto err_unlock; ret = bch2_sb_member_alloc(c); if (ret < 0) { bch_err_msg(c, ret, "setting up new superblock"); goto err_unlock; } unsigned dev_idx = ret; /* success: */ dev_mi.last_mount = cpu_to_le64(ktime_get_real_seconds()); *bch2_members_v2_get_mut(c->disk_sb.sb, dev_idx) = dev_mi; ca->disk_sb.sb->dev_idx = dev_idx; bch2_dev_attach(c, ca, dev_idx); if (BCH_MEMBER_GROUP(&dev_mi)) { ret = __bch2_dev_group_set(c, ca, label.buf); bch_err_msg(c, ret, "creating new label"); if (ret) goto err_unlock; } bch2_write_super(c); mutex_unlock(&c->sb_lock); ret = bch2_dev_usage_init(ca, false); if (ret) goto err_late; ret = bch2_trans_mark_dev_sb(c, ca, BTREE_TRIGGER_transactional); bch_err_msg(ca, ret, "marking new superblock"); if (ret) goto err_late; ret = bch2_fs_freespace_init(c); bch_err_msg(ca, ret, "initializing free space"); if (ret) goto err_late; if (ca->mi.state == BCH_MEMBER_STATE_rw) __bch2_dev_read_write(c, ca); ret = bch2_dev_journal_alloc(ca, false); bch_err_msg(c, ret, "allocating journal"); if (ret) goto err_late; up_write(&c->state_lock); out: printbuf_exit(&label); printbuf_exit(&errbuf); bch_err_fn(c, ret); return ret; err_unlock: mutex_unlock(&c->sb_lock); up_write(&c->state_lock); err: if (ca) bch2_dev_free(ca); bch2_free_super(&sb); goto out; err_late: up_write(&c->state_lock); ca = NULL; goto err; } /* Hot add existing device to running filesystem: */ int bch2_dev_online(struct bch_fs *c, const char *path) { struct bch_opts opts = bch2_opts_empty(); struct bch_sb_handle sb = { NULL }; struct bch_dev *ca; unsigned dev_idx; int ret; down_write(&c->state_lock); ret = bch2_read_super(path, &opts, &sb); if (ret) { up_write(&c->state_lock); return ret; } dev_idx = sb.sb->dev_idx; ret = bch2_dev_in_fs(&c->disk_sb, &sb, &c->opts); bch_err_msg(c, ret, "bringing %s online", path); if (ret) goto err; ret = bch2_dev_attach_bdev(c, &sb); if (ret) goto err; ca = bch2_dev_locked(c, dev_idx); ret = bch2_trans_mark_dev_sb(c, ca, BTREE_TRIGGER_transactional); bch_err_msg(c, ret, "bringing %s online: error from bch2_trans_mark_dev_sb", path); if (ret) goto err; if (ca->mi.state == BCH_MEMBER_STATE_rw) __bch2_dev_read_write(c, ca); if (!ca->mi.freespace_initialized) { ret = bch2_dev_freespace_init(c, ca, 0, ca->mi.nbuckets); bch_err_msg(ca, ret, "initializing free space"); if (ret) goto err; } if (!ca->journal.nr) { ret = bch2_dev_journal_alloc(ca, false); bch_err_msg(ca, ret, "allocating journal"); if (ret) goto err; } mutex_lock(&c->sb_lock); bch2_members_v2_get_mut(c->disk_sb.sb, ca->dev_idx)->last_mount = cpu_to_le64(ktime_get_real_seconds()); bch2_write_super(c); mutex_unlock(&c->sb_lock); up_write(&c->state_lock); return 0; err: up_write(&c->state_lock); bch2_free_super(&sb); return ret; } int bch2_dev_offline(struct bch_fs *c, struct bch_dev *ca, int flags) { down_write(&c->state_lock); if (!bch2_dev_is_online(ca)) { bch_err(ca, "Already offline"); up_write(&c->state_lock); return 0; } if (!bch2_dev_state_allowed(c, ca, BCH_MEMBER_STATE_failed, flags)) { bch_err(ca, "Cannot offline required disk"); up_write(&c->state_lock); return -BCH_ERR_device_state_not_allowed; } __bch2_dev_offline(c, ca); up_write(&c->state_lock); return 0; } int bch2_dev_resize(struct bch_fs *c, struct bch_dev *ca, u64 nbuckets) { struct bch_member *m; u64 old_nbuckets; int ret = 0; down_write(&c->state_lock); old_nbuckets = ca->mi.nbuckets; if (nbuckets < ca->mi.nbuckets) { bch_err(ca, "Cannot shrink yet"); ret = -EINVAL; goto err; } if (nbuckets > BCH_MEMBER_NBUCKETS_MAX) { bch_err(ca, "New device size too big (%llu greater than max %u)", nbuckets, BCH_MEMBER_NBUCKETS_MAX); ret = -BCH_ERR_device_size_too_big; goto err; } if (bch2_dev_is_online(ca) && get_capacity(ca->disk_sb.bdev->bd_disk) < ca->mi.bucket_size * nbuckets) { bch_err(ca, "New size larger than device"); ret = -BCH_ERR_device_size_too_small; goto err; } ret = bch2_dev_buckets_resize(c, ca, nbuckets); bch_err_msg(ca, ret, "resizing buckets"); if (ret) goto err; ret = bch2_trans_mark_dev_sb(c, ca, BTREE_TRIGGER_transactional); if (ret) goto err; mutex_lock(&c->sb_lock); m = bch2_members_v2_get_mut(c->disk_sb.sb, ca->dev_idx); m->nbuckets = cpu_to_le64(nbuckets); bch2_write_super(c); mutex_unlock(&c->sb_lock); if (ca->mi.freespace_initialized) { u64 v[3] = { nbuckets - old_nbuckets, 0, 0 }; ret = bch2_trans_commit_do(ca->fs, NULL, NULL, 0, bch2_disk_accounting_mod2(trans, false, v, dev_data_type, .dev = ca->dev_idx, .data_type = BCH_DATA_free)) ?: bch2_dev_freespace_init(c, ca, old_nbuckets, nbuckets); if (ret) goto err; } bch2_recalc_capacity(c); err: up_write(&c->state_lock); return ret; } /* return with ref on ca->ref: */ struct bch_dev *bch2_dev_lookup(struct bch_fs *c, const char *name) { if (!strncmp(name, "/dev/", strlen("/dev/"))) name += strlen("/dev/"); for_each_member_device(c, ca) if (!strcmp(name, ca->name)) return ca; return ERR_PTR(-BCH_ERR_ENOENT_dev_not_found); } /* blk_holder_ops: */ static struct bch_fs *bdev_get_fs(struct block_device *bdev) __releases(&bdev->bd_holder_lock) { struct bch_sb_handle_holder *holder = bdev->bd_holder; struct bch_fs *c = holder->c; if (c && !bch2_ro_ref_tryget(c)) c = NULL; mutex_unlock(&bdev->bd_holder_lock); if (c) wait_event(c->ro_ref_wait, test_bit(BCH_FS_started, &c->flags)); return c; } /* returns with ref on ca->ref */ static struct bch_dev *bdev_to_bch_dev(struct bch_fs *c, struct block_device *bdev) { for_each_member_device(c, ca) if (ca->disk_sb.bdev == bdev) return ca; return NULL; } static void bch2_fs_bdev_mark_dead(struct block_device *bdev, bool surprise) { struct bch_fs *c = bdev_get_fs(bdev); if (!c) return; struct super_block *sb = c->vfs_sb; if (sb) { /* * Not necessary, c->ro_ref guards against the filesystem being * unmounted - we only take this to avoid a warning in * sync_filesystem: */ down_read(&sb->s_umount); } down_write(&c->state_lock); struct bch_dev *ca = bdev_to_bch_dev(c, bdev); if (!ca) goto unlock; if (bch2_dev_state_allowed(c, ca, BCH_MEMBER_STATE_failed, BCH_FORCE_IF_DEGRADED)) { __bch2_dev_offline(c, ca); } else { if (sb) { if (!surprise) sync_filesystem(sb); shrink_dcache_sb(sb); evict_inodes(sb); } bch2_journal_flush(&c->journal); bch2_fs_emergency_read_only(c); } bch2_dev_put(ca); unlock: if (sb) up_read(&sb->s_umount); up_write(&c->state_lock); bch2_ro_ref_put(c); } static void bch2_fs_bdev_sync(struct block_device *bdev) { struct bch_fs *c = bdev_get_fs(bdev); if (!c) return; struct super_block *sb = c->vfs_sb; if (sb) { /* * Not necessary, c->ro_ref guards against the filesystem being * unmounted - we only take this to avoid a warning in * sync_filesystem: */ down_read(&sb->s_umount); sync_filesystem(sb); up_read(&sb->s_umount); } bch2_ro_ref_put(c); } const struct blk_holder_ops bch2_sb_handle_bdev_ops = { .mark_dead = bch2_fs_bdev_mark_dead, .sync = bch2_fs_bdev_sync, }; /* Filesystem open: */ static inline int sb_cmp(struct bch_sb *l, struct bch_sb *r) { return cmp_int(le64_to_cpu(l->seq), le64_to_cpu(r->seq)) ?: cmp_int(le64_to_cpu(l->write_time), le64_to_cpu(r->write_time)); } struct bch_fs *bch2_fs_open(char * const *devices, unsigned nr_devices, struct bch_opts opts) { DARRAY(struct bch_sb_handle) sbs = { 0 }; struct bch_fs *c = NULL; struct bch_sb_handle *best = NULL; struct printbuf errbuf = PRINTBUF; int ret = 0; if (!try_module_get(THIS_MODULE)) return ERR_PTR(-ENODEV); if (!nr_devices) { ret = -EINVAL; goto err; } ret = darray_make_room(&sbs, nr_devices); if (ret) goto err; for (unsigned i = 0; i < nr_devices; i++) { struct bch_sb_handle sb = { NULL }; ret = bch2_read_super(devices[i], &opts, &sb); if (ret) goto err; BUG_ON(darray_push(&sbs, sb)); } if (opts.nochanges && !opts.read_only) { ret = -BCH_ERR_erofs_nochanges; goto err_print; } darray_for_each(sbs, sb) if (!best || sb_cmp(sb->sb, best->sb) > 0) best = sb; darray_for_each_reverse(sbs, sb) { ret = bch2_dev_in_fs(best, sb, &opts); if (ret == -BCH_ERR_device_has_been_removed || ret == -BCH_ERR_device_splitbrain) { bch2_free_super(sb); darray_remove_item(&sbs, sb); best -= best > sb; ret = 0; continue; } if (ret) goto err_print; } c = bch2_fs_alloc(best->sb, opts); ret = PTR_ERR_OR_ZERO(c); if (ret) goto err; down_write(&c->state_lock); darray_for_each(sbs, sb) { ret = bch2_dev_attach_bdev(c, sb); if (ret) { up_write(&c->state_lock); goto err; } } up_write(&c->state_lock); if (!c->opts.nostart) { ret = bch2_fs_start(c); if (ret) goto err; } out: darray_for_each(sbs, sb) bch2_free_super(sb); darray_exit(&sbs); printbuf_exit(&errbuf); module_put(THIS_MODULE); return c; err_print: pr_err("bch_fs_open err opening %s: %s", devices[0], bch2_err_str(ret)); err: if (!IS_ERR_OR_NULL(c)) bch2_fs_stop(c); c = ERR_PTR(ret); goto out; } /* Global interfaces/init */ static void bcachefs_exit(void) { bch2_debug_exit(); bch2_vfs_exit(); bch2_chardev_exit(); bch2_btree_key_cache_exit(); if (bcachefs_kset) kset_unregister(bcachefs_kset); } static int __init bcachefs_init(void) { bch2_bkey_pack_test(); if (!(bcachefs_kset = kset_create_and_add("bcachefs", NULL, fs_kobj)) || bch2_btree_key_cache_init() || bch2_chardev_init() || bch2_vfs_init() || bch2_debug_init()) goto err; return 0; err: bcachefs_exit(); return -ENOMEM; } #define BCH_DEBUG_PARAM(name, description) \ bool bch2_##name; \ module_param_named(name, bch2_##name, bool, 0644); \ MODULE_PARM_DESC(name, description); BCH_DEBUG_PARAMS() #undef BCH_DEBUG_PARAM __maybe_unused static unsigned bch2_metadata_version = bcachefs_metadata_version_current; module_param_named(version, bch2_metadata_version, uint, 0444); module_exit(bcachefs_exit); module_init(bcachefs_init); |
| 38 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef DECOMPRESSOR_H #define DECOMPRESSOR_H /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009 * Phillip Lougher <phillip@squashfs.org.uk> * * decompressor.h */ #include <linux/bio.h> struct squashfs_decompressor { void *(*init)(struct squashfs_sb_info *, void *); void *(*comp_opts)(struct squashfs_sb_info *, void *, int); void (*free)(void *); int (*decompress)(struct squashfs_sb_info *, void *, struct bio *, int, int, struct squashfs_page_actor *); int id; char *name; int alloc_buffer; int supported; }; static inline void *squashfs_comp_opts(struct squashfs_sb_info *msblk, void *buff, int length) { return msblk->decompressor->comp_opts ? msblk->decompressor->comp_opts(msblk, buff, length) : NULL; } #ifdef CONFIG_SQUASHFS_XZ extern const struct squashfs_decompressor squashfs_xz_comp_ops; #endif #ifdef CONFIG_SQUASHFS_LZ4 extern const struct squashfs_decompressor squashfs_lz4_comp_ops; #endif #ifdef CONFIG_SQUASHFS_LZO extern const struct squashfs_decompressor squashfs_lzo_comp_ops; #endif #ifdef CONFIG_SQUASHFS_ZLIB extern const struct squashfs_decompressor squashfs_zlib_comp_ops; #endif #ifdef CONFIG_SQUASHFS_ZSTD extern const struct squashfs_decompressor squashfs_zstd_comp_ops; #endif #endif |
| 3 1 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 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 | // SPDX-License-Identifier: GPL-2.0 /* * sysctl_net_ipv4.c: sysctl interface to net IPV4 subsystem. * * Begun April 1, 1996, Mike Shaver. * Added /proc/sys/net/ipv4 directory entry (empty =) ). [MS] */ #include <linux/sysctl.h> #include <linux/seqlock.h> #include <linux/init.h> #include <linux/slab.h> #include <net/icmp.h> #include <net/ip.h> #include <net/ip_fib.h> #include <net/tcp.h> #include <net/udp.h> #include <net/cipso_ipv4.h> #include <net/ping.h> #include <net/protocol.h> #include <net/netevent.h> static int tcp_retr1_max = 255; static int ip_local_port_range_min[] = { 1, 1 }; static int ip_local_port_range_max[] = { 65535, 65535 }; static int tcp_adv_win_scale_min = -31; static int tcp_adv_win_scale_max = 31; static int tcp_app_win_max = 31; static int tcp_min_snd_mss_min = TCP_MIN_SND_MSS; static int tcp_min_snd_mss_max = 65535; static int tcp_rto_max_max = TCP_RTO_MAX_SEC * MSEC_PER_SEC; static int ip_privileged_port_min; static int ip_privileged_port_max = 65535; static int ip_ttl_min = 1; static int ip_ttl_max = 255; static int tcp_syn_retries_min = 1; static int tcp_syn_retries_max = MAX_TCP_SYNCNT; static int tcp_syn_linear_timeouts_max = MAX_TCP_SYNCNT; static unsigned long ip_ping_group_range_min[] = { 0, 0 }; static unsigned long ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; static u32 u32_max_div_HZ = UINT_MAX / HZ; static int one_day_secs = 24 * 3600; static u32 fib_multipath_hash_fields_all_mask __maybe_unused = FIB_MULTIPATH_HASH_FIELD_ALL_MASK; static unsigned int tcp_child_ehash_entries_max = 16 * 1024 * 1024; static unsigned int udp_child_hash_entries_max = UDP_HTABLE_SIZE_MAX; static int tcp_plb_max_rounds = 31; static int tcp_plb_max_cong_thresh = 256; static unsigned int tcp_tw_reuse_delay_max = TCP_PAWS_MSL * MSEC_PER_SEC; /* obsolete */ static int sysctl_tcp_low_latency __read_mostly; /* Update system visible IP port range */ static void set_local_port_range(struct net *net, unsigned int low, unsigned int high) { bool same_parity = !((low ^ high) & 1); if (same_parity && !net->ipv4.ip_local_ports.warned) { net->ipv4.ip_local_ports.warned = true; pr_err_ratelimited("ip_local_port_range: prefer different parity for start/end values.\n"); } WRITE_ONCE(net->ipv4.ip_local_ports.range, high << 16 | low); } /* Validate changes from /proc interface. */ static int ipv4_local_port_range(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = table->data; int ret; int range[2]; struct ctl_table tmp = { .data = &range, .maxlen = sizeof(range), .mode = table->mode, .extra1 = &ip_local_port_range_min, .extra2 = &ip_local_port_range_max, }; inet_get_local_port_range(net, &range[0], &range[1]); ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) { /* Ensure that the upper limit is not smaller than the lower, * and that the lower does not encroach upon the privileged * port limit. */ if ((range[1] < range[0]) || (range[0] < READ_ONCE(net->ipv4.sysctl_ip_prot_sock))) ret = -EINVAL; else set_local_port_range(net, range[0], range[1]); } return ret; } /* Validate changes from /proc interface. */ static int ipv4_privileged_ports(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(table->data, struct net, ipv4.sysctl_ip_prot_sock); int ret; int pports; int range[2]; struct ctl_table tmp = { .data = &pports, .maxlen = sizeof(pports), .mode = table->mode, .extra1 = &ip_privileged_port_min, .extra2 = &ip_privileged_port_max, }; pports = READ_ONCE(net->ipv4.sysctl_ip_prot_sock); ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) { inet_get_local_port_range(net, &range[0], &range[1]); /* Ensure that the local port range doesn't overlap with the * privileged port range. */ if (range[0] < pports) ret = -EINVAL; else WRITE_ONCE(net->ipv4.sysctl_ip_prot_sock, pports); } return ret; } static void inet_get_ping_group_range_table(const struct ctl_table *table, kgid_t *low, kgid_t *high) { kgid_t *data = table->data; struct net *net = container_of(table->data, struct net, ipv4.ping_group_range.range); unsigned int seq; do { seq = read_seqbegin(&net->ipv4.ping_group_range.lock); *low = data[0]; *high = data[1]; } while (read_seqretry(&net->ipv4.ping_group_range.lock, seq)); } /* Update system visible IP port range */ static void set_ping_group_range(const struct ctl_table *table, kgid_t low, kgid_t high) { kgid_t *data = table->data; struct net *net = container_of(table->data, struct net, ipv4.ping_group_range.range); write_seqlock(&net->ipv4.ping_group_range.lock); data[0] = low; data[1] = high; write_sequnlock(&net->ipv4.ping_group_range.lock); } /* Validate changes from /proc interface. */ static int ipv4_ping_group_range(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct user_namespace *user_ns = current_user_ns(); int ret; unsigned long urange[2]; kgid_t low, high; struct ctl_table tmp = { .data = &urange, .maxlen = sizeof(urange), .mode = table->mode, .extra1 = &ip_ping_group_range_min, .extra2 = &ip_ping_group_range_max, }; inet_get_ping_group_range_table(table, &low, &high); urange[0] = from_kgid_munged(user_ns, low); urange[1] = from_kgid_munged(user_ns, high); ret = proc_doulongvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) { low = make_kgid(user_ns, urange[0]); high = make_kgid(user_ns, urange[1]); if (!gid_valid(low) || !gid_valid(high)) return -EINVAL; if (urange[1] < urange[0] || gid_lt(high, low)) { low = make_kgid(&init_user_ns, 1); high = make_kgid(&init_user_ns, 0); } set_ping_group_range(table, low, high); } return ret; } static int ipv4_fwd_update_priority(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net; int ret; net = container_of(table->data, struct net, ipv4.sysctl_ip_fwd_update_priority); ret = proc_dou8vec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) call_netevent_notifiers(NETEVENT_IPV4_FWD_UPDATE_PRIORITY_UPDATE, net); return ret; } static int proc_tcp_congestion_control(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(ctl->data, struct net, ipv4.tcp_congestion_control); char val[TCP_CA_NAME_MAX]; struct ctl_table tbl = { .data = val, .maxlen = TCP_CA_NAME_MAX, }; int ret; tcp_get_default_congestion_control(net, val); ret = proc_dostring(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) ret = tcp_set_default_congestion_control(net, val); return ret; } static int proc_tcp_available_congestion_control(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table tbl = { .maxlen = TCP_CA_BUF_MAX, }; int ret; tbl.data = kmalloc(tbl.maxlen, GFP_USER); if (!tbl.data) return -ENOMEM; tcp_get_available_congestion_control(tbl.data, TCP_CA_BUF_MAX); ret = proc_dostring(&tbl, write, buffer, lenp, ppos); kfree(tbl.data); return ret; } static int proc_allowed_congestion_control(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table tbl = { .maxlen = TCP_CA_BUF_MAX }; int ret; tbl.data = kmalloc(tbl.maxlen, GFP_USER); if (!tbl.data) return -ENOMEM; tcp_get_allowed_congestion_control(tbl.data, tbl.maxlen); ret = proc_dostring(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) ret = tcp_set_allowed_congestion_control(tbl.data); kfree(tbl.data); return ret; } static int sscanf_key(char *buf, __le32 *key) { u32 user_key[4]; int i, ret = 0; if (sscanf(buf, "%x-%x-%x-%x", user_key, user_key + 1, user_key + 2, user_key + 3) != 4) { ret = -EINVAL; } else { for (i = 0; i < ARRAY_SIZE(user_key); i++) key[i] = cpu_to_le32(user_key[i]); } pr_debug("proc TFO key set 0x%x-%x-%x-%x <- 0x%s: %u\n", user_key[0], user_key[1], user_key[2], user_key[3], buf, ret); return ret; } static int proc_tcp_fastopen_key(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(table->data, struct net, ipv4.sysctl_tcp_fastopen); /* maxlen to print the list of keys in hex (*2), with dashes * separating doublewords and a comma in between keys. */ struct ctl_table tbl = { .maxlen = ((TCP_FASTOPEN_KEY_LENGTH * 2 * TCP_FASTOPEN_KEY_MAX) + (TCP_FASTOPEN_KEY_MAX * 5)) }; u32 user_key[TCP_FASTOPEN_KEY_BUF_LENGTH / sizeof(u32)]; __le32 key[TCP_FASTOPEN_KEY_BUF_LENGTH / sizeof(__le32)]; char *backup_data; int ret, i = 0, off = 0, n_keys; tbl.data = kmalloc(tbl.maxlen, GFP_KERNEL); if (!tbl.data) return -ENOMEM; n_keys = tcp_fastopen_get_cipher(net, NULL, (u64 *)key); if (!n_keys) { memset(&key[0], 0, TCP_FASTOPEN_KEY_LENGTH); n_keys = 1; } for (i = 0; i < n_keys * 4; i++) user_key[i] = le32_to_cpu(key[i]); for (i = 0; i < n_keys; i++) { off += snprintf(tbl.data + off, tbl.maxlen - off, "%08x-%08x-%08x-%08x", user_key[i * 4], user_key[i * 4 + 1], user_key[i * 4 + 2], user_key[i * 4 + 3]); if (WARN_ON_ONCE(off >= tbl.maxlen - 1)) break; if (i + 1 < n_keys) off += snprintf(tbl.data + off, tbl.maxlen - off, ","); } ret = proc_dostring(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) { backup_data = strchr(tbl.data, ','); if (backup_data) { *backup_data = '\0'; backup_data++; } if (sscanf_key(tbl.data, key)) { ret = -EINVAL; goto bad_key; } if (backup_data) { if (sscanf_key(backup_data, key + 4)) { ret = -EINVAL; goto bad_key; } } tcp_fastopen_reset_cipher(net, NULL, key, backup_data ? key + 4 : NULL); } bad_key: kfree(tbl.data); return ret; } static int proc_tfo_blackhole_detect_timeout(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(table->data, struct net, ipv4.sysctl_tcp_fastopen_blackhole_timeout); int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) atomic_set(&net->ipv4.tfo_active_disable_times, 0); return ret; } static int proc_tcp_available_ulp(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table tbl = { .maxlen = TCP_ULP_BUF_MAX, }; int ret; tbl.data = kmalloc(tbl.maxlen, GFP_USER); if (!tbl.data) return -ENOMEM; tcp_get_available_ulp(tbl.data, TCP_ULP_BUF_MAX); ret = proc_dostring(&tbl, write, buffer, lenp, ppos); kfree(tbl.data); return ret; } static int proc_tcp_ehash_entries(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(table->data, struct net, ipv4.sysctl_tcp_child_ehash_entries); struct inet_hashinfo *hinfo = net->ipv4.tcp_death_row.hashinfo; int tcp_ehash_entries; struct ctl_table tbl; tcp_ehash_entries = hinfo->ehash_mask + 1; /* A negative number indicates that the child netns * shares the global ehash. */ if (!net_eq(net, &init_net) && !hinfo->pernet) tcp_ehash_entries *= -1; memset(&tbl, 0, sizeof(tbl)); tbl.data = &tcp_ehash_entries; tbl.maxlen = sizeof(int); return proc_dointvec(&tbl, write, buffer, lenp, ppos); } static int proc_udp_hash_entries(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(table->data, struct net, ipv4.sysctl_udp_child_hash_entries); int udp_hash_entries; struct ctl_table tbl; udp_hash_entries = net->ipv4.udp_table->mask + 1; /* A negative number indicates that the child netns * shares the global udp_table. */ if (!net_eq(net, &init_net) && net->ipv4.udp_table == &udp_table) udp_hash_entries *= -1; memset(&tbl, 0, sizeof(tbl)); tbl.data = &udp_hash_entries; tbl.maxlen = sizeof(int); return proc_dointvec(&tbl, write, buffer, lenp, ppos); } #ifdef CONFIG_IP_ROUTE_MULTIPATH static int proc_fib_multipath_hash_policy(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(table->data, struct net, ipv4.sysctl_fib_multipath_hash_policy); int ret; ret = proc_dou8vec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) call_netevent_notifiers(NETEVENT_IPV4_MPATH_HASH_UPDATE, net); return ret; } static int proc_fib_multipath_hash_fields(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net; int ret; net = container_of(table->data, struct net, ipv4.sysctl_fib_multipath_hash_fields); ret = proc_douintvec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) call_netevent_notifiers(NETEVENT_IPV4_MPATH_HASH_UPDATE, net); return ret; } static u32 proc_fib_multipath_hash_rand_seed __ro_after_init; static void proc_fib_multipath_hash_init_rand_seed(void) { get_random_bytes(&proc_fib_multipath_hash_rand_seed, sizeof(proc_fib_multipath_hash_rand_seed)); } static void proc_fib_multipath_hash_set_seed(struct net *net, u32 user_seed) { struct sysctl_fib_multipath_hash_seed new = { .user_seed = user_seed, .mp_seed = (user_seed ? user_seed : proc_fib_multipath_hash_rand_seed), }; WRITE_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed, new); } static int proc_fib_multipath_hash_seed(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct sysctl_fib_multipath_hash_seed *mphs; struct net *net = table->data; struct ctl_table tmp; u32 user_seed; int ret; mphs = &net->ipv4.sysctl_fib_multipath_hash_seed; user_seed = mphs->user_seed; tmp = *table; tmp.data = &user_seed; ret = proc_douintvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) { proc_fib_multipath_hash_set_seed(net, user_seed); call_netevent_notifiers(NETEVENT_IPV4_MPATH_HASH_UPDATE, net); } return ret; } #else static void proc_fib_multipath_hash_init_rand_seed(void) { } static void proc_fib_multipath_hash_set_seed(struct net *net, u32 user_seed) { } #endif static struct ctl_table ipv4_table[] = { { .procname = "tcp_max_orphans", .data = &sysctl_tcp_max_orphans, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "inet_peer_threshold", .data = &inet_peer_threshold, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "inet_peer_minttl", .data = &inet_peer_minttl, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "inet_peer_maxttl", .data = &inet_peer_maxttl, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "tcp_mem", .maxlen = sizeof(sysctl_tcp_mem), .data = &sysctl_tcp_mem, .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "tcp_low_latency", .data = &sysctl_tcp_low_latency, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, #ifdef CONFIG_NETLABEL { .procname = "cipso_cache_enable", .data = &cipso_v4_cache_enabled, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "cipso_cache_bucket_size", .data = &cipso_v4_cache_bucketsize, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "cipso_rbm_optfmt", .data = &cipso_v4_rbm_optfmt, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "cipso_rbm_strictvalid", .data = &cipso_v4_rbm_strictvalid, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #endif /* CONFIG_NETLABEL */ { .procname = "tcp_available_ulp", .maxlen = TCP_ULP_BUF_MAX, .mode = 0444, .proc_handler = proc_tcp_available_ulp, }, { .procname = "udp_mem", .data = &sysctl_udp_mem, .maxlen = sizeof(sysctl_udp_mem), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "fib_sync_mem", .data = &sysctl_fib_sync_mem, .maxlen = sizeof(sysctl_fib_sync_mem), .mode = 0644, .proc_handler = proc_douintvec_minmax, .extra1 = &sysctl_fib_sync_mem_min, .extra2 = &sysctl_fib_sync_mem_max, }, }; static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_max_tw_buckets", .data = &init_net.ipv4.tcp_death_row.sysctl_max_tw_buckets, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "icmp_echo_ignore_all", .data = &init_net.ipv4.sysctl_icmp_echo_ignore_all, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE }, { .procname = "icmp_echo_enable_probe", .data = &init_net.ipv4.sysctl_icmp_echo_enable_probe, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE }, { .procname = "icmp_echo_ignore_broadcasts", .data = &init_net.ipv4.sysctl_icmp_echo_ignore_broadcasts, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE }, { .procname = "icmp_ignore_bogus_error_responses", .data = &init_net.ipv4.sysctl_icmp_ignore_bogus_error_responses, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE }, { .procname = "icmp_errors_use_inbound_ifaddr", .data = &init_net.ipv4.sysctl_icmp_errors_use_inbound_ifaddr, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE }, { .procname = "icmp_ratelimit", .data = &init_net.ipv4.sysctl_icmp_ratelimit, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, { .procname = "icmp_ratemask", .data = &init_net.ipv4.sysctl_icmp_ratemask, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "icmp_msgs_per_sec", .data = &init_net.ipv4.sysctl_icmp_msgs_per_sec, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, { .procname = "icmp_msgs_burst", .data = &init_net.ipv4.sysctl_icmp_msgs_burst, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, { .procname = "ping_group_range", .data = &init_net.ipv4.ping_group_range.range, .maxlen = sizeof(gid_t)*2, .mode = 0644, .proc_handler = ipv4_ping_group_range, }, #ifdef CONFIG_NET_L3_MASTER_DEV { .procname = "raw_l3mdev_accept", .data = &init_net.ipv4.sysctl_raw_l3mdev_accept, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #endif { .procname = "tcp_ecn", .data = &init_net.ipv4.sysctl_tcp_ecn, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { .procname = "tcp_ecn_fallback", .data = &init_net.ipv4.sysctl_tcp_ecn_fallback, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "ip_dynaddr", .data = &init_net.ipv4.sysctl_ip_dynaddr, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "ip_early_demux", .data = &init_net.ipv4.sysctl_ip_early_demux, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "udp_early_demux", .data = &init_net.ipv4.sysctl_udp_early_demux, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_early_demux", .data = &init_net.ipv4.sysctl_tcp_early_demux, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "nexthop_compat_mode", .data = &init_net.ipv4.sysctl_nexthop_compat_mode, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "ip_default_ttl", .data = &init_net.ipv4.sysctl_ip_default_ttl, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = &ip_ttl_min, .extra2 = &ip_ttl_max, }, { .procname = "ip_local_port_range", .maxlen = 0, .data = &init_net, .mode = 0644, .proc_handler = ipv4_local_port_range, }, { .procname = "ip_local_reserved_ports", .data = &init_net.ipv4.sysctl_local_reserved_ports, .maxlen = 65536, .mode = 0644, .proc_handler = proc_do_large_bitmap, }, { .procname = "ip_no_pmtu_disc", .data = &init_net.ipv4.sysctl_ip_no_pmtu_disc, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "ip_forward_use_pmtu", .data = &init_net.ipv4.sysctl_ip_fwd_use_pmtu, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "ip_forward_update_priority", .data = &init_net.ipv4.sysctl_ip_fwd_update_priority, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = ipv4_fwd_update_priority, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "ip_nonlocal_bind", .data = &init_net.ipv4.sysctl_ip_nonlocal_bind, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "ip_autobind_reuse", .data = &init_net.ipv4.sysctl_ip_autobind_reuse, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "fwmark_reflect", .data = &init_net.ipv4.sysctl_fwmark_reflect, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_fwmark_accept", .data = &init_net.ipv4.sysctl_tcp_fwmark_accept, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, #ifdef CONFIG_NET_L3_MASTER_DEV { .procname = "tcp_l3mdev_accept", .data = &init_net.ipv4.sysctl_tcp_l3mdev_accept, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #endif { .procname = "tcp_mtu_probing", .data = &init_net.ipv4.sysctl_tcp_mtu_probing, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_base_mss", .data = &init_net.ipv4.sysctl_tcp_base_mss, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "tcp_min_snd_mss", .data = &init_net.ipv4.sysctl_tcp_min_snd_mss, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &tcp_min_snd_mss_min, .extra2 = &tcp_min_snd_mss_max, }, { .procname = "tcp_mtu_probe_floor", .data = &init_net.ipv4.sysctl_tcp_mtu_probe_floor, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &tcp_min_snd_mss_min, .extra2 = &tcp_min_snd_mss_max, }, { .procname = "tcp_probe_threshold", .data = &init_net.ipv4.sysctl_tcp_probe_threshold, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "tcp_probe_interval", .data = &init_net.ipv4.sysctl_tcp_probe_interval, .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_douintvec_minmax, .extra2 = &u32_max_div_HZ, }, { .procname = "igmp_link_local_mcast_reports", .data = &init_net.ipv4.sysctl_igmp_llm_reports, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "igmp_max_memberships", .data = &init_net.ipv4.sysctl_igmp_max_memberships, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "igmp_max_msf", .data = &init_net.ipv4.sysctl_igmp_max_msf, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, #ifdef CONFIG_IP_MULTICAST { .procname = "igmp_qrv", .data = &init_net.ipv4.sysctl_igmp_qrv, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE }, #endif { .procname = "tcp_congestion_control", .data = &init_net.ipv4.tcp_congestion_control, .mode = 0644, .maxlen = TCP_CA_NAME_MAX, .proc_handler = proc_tcp_congestion_control, }, { .procname = "tcp_available_congestion_control", .maxlen = TCP_CA_BUF_MAX, .mode = 0444, .proc_handler = proc_tcp_available_congestion_control, }, { .procname = "tcp_allowed_congestion_control", .maxlen = TCP_CA_BUF_MAX, .mode = 0644, .proc_handler = proc_allowed_congestion_control, }, { .procname = "tcp_keepalive_time", .data = &init_net.ipv4.sysctl_tcp_keepalive_time, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "tcp_keepalive_probes", .data = &init_net.ipv4.sysctl_tcp_keepalive_probes, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_keepalive_intvl", .data = &init_net.ipv4.sysctl_tcp_keepalive_intvl, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "tcp_syn_retries", .data = &init_net.ipv4.sysctl_tcp_syn_retries, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = &tcp_syn_retries_min, .extra2 = &tcp_syn_retries_max }, { .procname = "tcp_synack_retries", .data = &init_net.ipv4.sysctl_tcp_synack_retries, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, #ifdef CONFIG_SYN_COOKIES { .procname = "tcp_syncookies", .data = &init_net.ipv4.sysctl_tcp_syncookies, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, #endif { .procname = "tcp_migrate_req", .data = &init_net.ipv4.sysctl_tcp_migrate_req, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE }, { .procname = "tcp_reordering", .data = &init_net.ipv4.sysctl_tcp_reordering, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "tcp_retries1", .data = &init_net.ipv4.sysctl_tcp_retries1, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra2 = &tcp_retr1_max }, { .procname = "tcp_retries2", .data = &init_net.ipv4.sysctl_tcp_retries2, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_orphan_retries", .data = &init_net.ipv4.sysctl_tcp_orphan_retries, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_fin_timeout", .data = &init_net.ipv4.sysctl_tcp_fin_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "tcp_notsent_lowat", .data = &init_net.ipv4.sysctl_tcp_notsent_lowat, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_douintvec, }, { .procname = "tcp_tw_reuse", .data = &init_net.ipv4.sysctl_tcp_tw_reuse, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { .procname = "tcp_tw_reuse_delay", .data = &init_net.ipv4.sysctl_tcp_tw_reuse_delay, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_douintvec_minmax, .extra1 = SYSCTL_ONE, .extra2 = &tcp_tw_reuse_delay_max, }, { .procname = "tcp_max_syn_backlog", .data = &init_net.ipv4.sysctl_max_syn_backlog, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "tcp_fastopen", .data = &init_net.ipv4.sysctl_tcp_fastopen, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "tcp_fastopen_key", .mode = 0600, .data = &init_net.ipv4.sysctl_tcp_fastopen, /* maxlen to print the list of keys in hex (*2), with dashes * separating doublewords and a comma in between keys. */ .maxlen = ((TCP_FASTOPEN_KEY_LENGTH * 2 * TCP_FASTOPEN_KEY_MAX) + (TCP_FASTOPEN_KEY_MAX * 5)), .proc_handler = proc_tcp_fastopen_key, }, { .procname = "tcp_fastopen_blackhole_timeout_sec", .data = &init_net.ipv4.sysctl_tcp_fastopen_blackhole_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_tfo_blackhole_detect_timeout, .extra1 = SYSCTL_ZERO, }, #ifdef CONFIG_IP_ROUTE_MULTIPATH { .procname = "fib_multipath_use_neigh", .data = &init_net.ipv4.sysctl_fib_multipath_use_neigh, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "fib_multipath_hash_policy", .data = &init_net.ipv4.sysctl_fib_multipath_hash_policy, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_fib_multipath_hash_policy, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_THREE, }, { .procname = "fib_multipath_hash_fields", .data = &init_net.ipv4.sysctl_fib_multipath_hash_fields, .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_fib_multipath_hash_fields, .extra1 = SYSCTL_ONE, .extra2 = &fib_multipath_hash_fields_all_mask, }, { .procname = "fib_multipath_hash_seed", .data = &init_net, .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_fib_multipath_hash_seed, }, #endif { .procname = "ip_unprivileged_port_start", .maxlen = sizeof(int), .data = &init_net.ipv4.sysctl_ip_prot_sock, .mode = 0644, .proc_handler = ipv4_privileged_ports, }, #ifdef CONFIG_NET_L3_MASTER_DEV { .procname = "udp_l3mdev_accept", .data = &init_net.ipv4.sysctl_udp_l3mdev_accept, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #endif { .procname = "tcp_sack", .data = &init_net.ipv4.sysctl_tcp_sack, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_window_scaling", .data = &init_net.ipv4.sysctl_tcp_window_scaling, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_timestamps", .data = &init_net.ipv4.sysctl_tcp_timestamps, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_early_retrans", .data = &init_net.ipv4.sysctl_tcp_early_retrans, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_FOUR, }, { .procname = "tcp_recovery", .data = &init_net.ipv4.sysctl_tcp_recovery, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_thin_linear_timeouts", .data = &init_net.ipv4.sysctl_tcp_thin_linear_timeouts, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_slow_start_after_idle", .data = &init_net.ipv4.sysctl_tcp_slow_start_after_idle, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_retrans_collapse", .data = &init_net.ipv4.sysctl_tcp_retrans_collapse, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_stdurg", .data = &init_net.ipv4.sysctl_tcp_stdurg, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_rfc1337", .data = &init_net.ipv4.sysctl_tcp_rfc1337, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_abort_on_overflow", .data = &init_net.ipv4.sysctl_tcp_abort_on_overflow, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_fack", .data = &init_net.ipv4.sysctl_tcp_fack, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_max_reordering", .data = &init_net.ipv4.sysctl_tcp_max_reordering, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "tcp_dsack", .data = &init_net.ipv4.sysctl_tcp_dsack, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_app_win", .data = &init_net.ipv4.sysctl_tcp_app_win, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &tcp_app_win_max, }, { .procname = "tcp_adv_win_scale", .data = &init_net.ipv4.sysctl_tcp_adv_win_scale, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &tcp_adv_win_scale_min, .extra2 = &tcp_adv_win_scale_max, }, { .procname = "tcp_frto", .data = &init_net.ipv4.sysctl_tcp_frto, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_no_metrics_save", .data = &init_net.ipv4.sysctl_tcp_nometrics_save, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_no_ssthresh_metrics_save", .data = &init_net.ipv4.sysctl_tcp_no_ssthresh_metrics_save, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "tcp_moderate_rcvbuf", .data = &init_net.ipv4.sysctl_tcp_moderate_rcvbuf, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_tso_win_divisor", .data = &init_net.ipv4.sysctl_tcp_tso_win_divisor, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_workaround_signed_windows", .data = &init_net.ipv4.sysctl_tcp_workaround_signed_windows, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_limit_output_bytes", .data = &init_net.ipv4.sysctl_tcp_limit_output_bytes, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "tcp_challenge_ack_limit", .data = &init_net.ipv4.sysctl_tcp_challenge_ack_limit, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "tcp_min_tso_segs", .data = &init_net.ipv4.sysctl_tcp_min_tso_segs, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ONE, }, { .procname = "tcp_tso_rtt_log", .data = &init_net.ipv4.sysctl_tcp_tso_rtt_log, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_min_rtt_wlen", .data = &init_net.ipv4.sysctl_tcp_min_rtt_wlen, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &one_day_secs }, { .procname = "tcp_autocorking", .data = &init_net.ipv4.sysctl_tcp_autocorking, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "tcp_invalid_ratelimit", .data = &init_net.ipv4.sysctl_tcp_invalid_ratelimit, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, { .procname = "tcp_pacing_ss_ratio", .data = &init_net.ipv4.sysctl_tcp_pacing_ss_ratio, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE_THOUSAND, }, { .procname = "tcp_pacing_ca_ratio", .data = &init_net.ipv4.sysctl_tcp_pacing_ca_ratio, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE_THOUSAND, }, { .procname = "tcp_wmem", .data = &init_net.ipv4.sysctl_tcp_wmem, .maxlen = sizeof(init_net.ipv4.sysctl_tcp_wmem), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, }, { .procname = "tcp_rmem", .data = &init_net.ipv4.sysctl_tcp_rmem, .maxlen = sizeof(init_net.ipv4.sysctl_tcp_rmem), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, }, { .procname = "tcp_comp_sack_delay_ns", .data = &init_net.ipv4.sysctl_tcp_comp_sack_delay_ns, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "tcp_comp_sack_slack_ns", .data = &init_net.ipv4.sysctl_tcp_comp_sack_slack_ns, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "tcp_comp_sack_nr", .data = &init_net.ipv4.sysctl_tcp_comp_sack_nr, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, }, { .procname = "tcp_backlog_ack_defer", .data = &init_net.ipv4.sysctl_tcp_backlog_ack_defer, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "tcp_reflect_tos", .data = &init_net.ipv4.sysctl_tcp_reflect_tos, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "tcp_ehash_entries", .data = &init_net.ipv4.sysctl_tcp_child_ehash_entries, .mode = 0444, .proc_handler = proc_tcp_ehash_entries, }, { .procname = "tcp_child_ehash_entries", .data = &init_net.ipv4.sysctl_tcp_child_ehash_entries, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_douintvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &tcp_child_ehash_entries_max, }, { .procname = "udp_hash_entries", .data = &init_net.ipv4.sysctl_udp_child_hash_entries, .mode = 0444, .proc_handler = proc_udp_hash_entries, }, { .procname = "udp_child_hash_entries", .data = &init_net.ipv4.sysctl_udp_child_hash_entries, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_douintvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &udp_child_hash_entries_max, }, { .procname = "udp_rmem_min", .data = &init_net.ipv4.sysctl_udp_rmem_min, .maxlen = sizeof(init_net.ipv4.sysctl_udp_rmem_min), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE }, { .procname = "udp_wmem_min", .data = &init_net.ipv4.sysctl_udp_wmem_min, .maxlen = sizeof(init_net.ipv4.sysctl_udp_wmem_min), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE }, { .procname = "fib_notify_on_flag_change", .data = &init_net.ipv4.sysctl_fib_notify_on_flag_change, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { .procname = "tcp_plb_enabled", .data = &init_net.ipv4.sysctl_tcp_plb_enabled, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "tcp_plb_idle_rehash_rounds", .data = &init_net.ipv4.sysctl_tcp_plb_idle_rehash_rounds, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra2 = &tcp_plb_max_rounds, }, { .procname = "tcp_plb_rehash_rounds", .data = &init_net.ipv4.sysctl_tcp_plb_rehash_rounds, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra2 = &tcp_plb_max_rounds, }, { .procname = "tcp_plb_suspend_rto_sec", .data = &init_net.ipv4.sysctl_tcp_plb_suspend_rto_sec, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_plb_cong_thresh", .data = &init_net.ipv4.sysctl_tcp_plb_cong_thresh, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &tcp_plb_max_cong_thresh, }, { .procname = "tcp_syn_linear_timeouts", .data = &init_net.ipv4.sysctl_tcp_syn_linear_timeouts, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &tcp_syn_linear_timeouts_max, }, { .procname = "tcp_shrink_window", .data = &init_net.ipv4.sysctl_tcp_shrink_window, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "tcp_pingpong_thresh", .data = &init_net.ipv4.sysctl_tcp_pingpong_thresh, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ONE, }, { .procname = "tcp_rto_min_us", .data = &init_net.ipv4.sysctl_tcp_rto_min_us, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, }, { .procname = "tcp_rto_max_ms", .data = &init_net.ipv4.sysctl_tcp_rto_max_ms, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE_THOUSAND, .extra2 = &tcp_rto_max_max, }, }; static __net_init int ipv4_sysctl_init_net(struct net *net) { size_t table_size = ARRAY_SIZE(ipv4_net_table); struct ctl_table *table; table = ipv4_net_table; if (!net_eq(net, &init_net)) { int i; table = kmemdup(table, sizeof(ipv4_net_table), GFP_KERNEL); if (!table) goto err_alloc; for (i = 0; i < table_size; i++) { if (table[i].data) { /* Update the variables to point into * the current struct net */ table[i].data += (void *)net - (void *)&init_net; } else { /* Entries without data pointer are global; * Make them read-only in non-init_net ns */ table[i].mode &= ~0222; } } } net->ipv4.ipv4_hdr = register_net_sysctl_sz(net, "net/ipv4", table, table_size); if (!net->ipv4.ipv4_hdr) goto err_reg; net->ipv4.sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL); if (!net->ipv4.sysctl_local_reserved_ports) goto err_ports; proc_fib_multipath_hash_set_seed(net, 0); return 0; err_ports: unregister_net_sysctl_table(net->ipv4.ipv4_hdr); err_reg: if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; } static __net_exit void ipv4_sysctl_exit_net(struct net *net) { const struct ctl_table *table; kfree(net->ipv4.sysctl_local_reserved_ports); table = net->ipv4.ipv4_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.ipv4_hdr); kfree(table); } static __net_initdata struct pernet_operations ipv4_sysctl_ops = { .init = ipv4_sysctl_init_net, .exit = ipv4_sysctl_exit_net, }; static __init int sysctl_ipv4_init(void) { struct ctl_table_header *hdr; hdr = register_net_sysctl(&init_net, "net/ipv4", ipv4_table); if (!hdr) return -ENOMEM; proc_fib_multipath_hash_init_rand_seed(); if (register_pernet_subsys(&ipv4_sysctl_ops)) { unregister_net_sysctl_table(hdr); return -ENOMEM; } return 0; } __initcall(sysctl_ipv4_init); |
| 3 2 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * eCryptfs: Linux filesystem encryption layer * * Copyright (C) 1997-2004 Erez Zadok * Copyright (C) 2001-2004 Stony Brook University * Copyright (C) 2004-2007 International Business Machines Corp. * Author(s): Michael A. Halcrow <mahalcro@us.ibm.com> * Michael C. Thompson <mcthomps@us.ibm.com> */ #include <crypto/hash.h> #include <crypto/skcipher.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/pagemap.h> #include <linux/random.h> #include <linux/compiler.h> #include <linux/key.h> #include <linux/namei.h> #include <linux/file.h> #include <linux/scatterlist.h> #include <linux/slab.h> #include <linux/unaligned.h> #include <linux/kernel.h> #include <linux/xattr.h> #include "ecryptfs_kernel.h" #define DECRYPT 0 #define ENCRYPT 1 /** * ecryptfs_from_hex * @dst: Buffer to take the bytes from src hex; must be at least of * size (src_size / 2) * @src: Buffer to be converted from a hex string representation to raw value * @dst_size: size of dst buffer, or number of hex characters pairs to convert */ void ecryptfs_from_hex(char *dst, char *src, int dst_size) { int x; char tmp[3] = { 0, }; for (x = 0; x < dst_size; x++) { tmp[0] = src[x * 2]; tmp[1] = src[x * 2 + 1]; dst[x] = (unsigned char)simple_strtol(tmp, NULL, 16); } } /** * ecryptfs_calculate_md5 - calculates the md5 of @src * @dst: Pointer to 16 bytes of allocated memory * @crypt_stat: Pointer to crypt_stat struct for the current inode * @src: Data to be md5'd * @len: Length of @src * * Uses the allocated crypto context that crypt_stat references to * generate the MD5 sum of the contents of src. */ static int ecryptfs_calculate_md5(char *dst, struct ecryptfs_crypt_stat *crypt_stat, char *src, int len) { int rc = crypto_shash_tfm_digest(crypt_stat->hash_tfm, src, len, dst); if (rc) { printk(KERN_ERR "%s: Error computing crypto hash; rc = [%d]\n", __func__, rc); goto out; } out: return rc; } static int ecryptfs_crypto_api_algify_cipher_name(char **algified_name, char *cipher_name, char *chaining_modifier) { int cipher_name_len = strlen(cipher_name); int chaining_modifier_len = strlen(chaining_modifier); int algified_name_len; int rc; algified_name_len = (chaining_modifier_len + cipher_name_len + 3); (*algified_name) = kmalloc(algified_name_len, GFP_KERNEL); if (!(*algified_name)) { rc = -ENOMEM; goto out; } snprintf((*algified_name), algified_name_len, "%s(%s)", chaining_modifier, cipher_name); rc = 0; out: return rc; } /** * ecryptfs_derive_iv * @iv: destination for the derived iv vale * @crypt_stat: Pointer to crypt_stat struct for the current inode * @offset: Offset of the extent whose IV we are to derive * * Generate the initialization vector from the given root IV and page * offset. * * Returns zero on success; non-zero on error. */ int ecryptfs_derive_iv(char *iv, struct ecryptfs_crypt_stat *crypt_stat, loff_t offset) { int rc = 0; char dst[MD5_DIGEST_SIZE]; char src[ECRYPTFS_MAX_IV_BYTES + 16]; if (unlikely(ecryptfs_verbosity > 0)) { ecryptfs_printk(KERN_DEBUG, "root iv:\n"); ecryptfs_dump_hex(crypt_stat->root_iv, crypt_stat->iv_bytes); } /* TODO: It is probably secure to just cast the least * significant bits of the root IV into an unsigned long and * add the offset to that rather than go through all this * hashing business. -Halcrow */ memcpy(src, crypt_stat->root_iv, crypt_stat->iv_bytes); memset((src + crypt_stat->iv_bytes), 0, 16); snprintf((src + crypt_stat->iv_bytes), 16, "%lld", offset); if (unlikely(ecryptfs_verbosity > 0)) { ecryptfs_printk(KERN_DEBUG, "source:\n"); ecryptfs_dump_hex(src, (crypt_stat->iv_bytes + 16)); } rc = ecryptfs_calculate_md5(dst, crypt_stat, src, (crypt_stat->iv_bytes + 16)); if (rc) { ecryptfs_printk(KERN_WARNING, "Error attempting to compute " "MD5 while generating IV for a page\n"); goto out; } memcpy(iv, dst, crypt_stat->iv_bytes); if (unlikely(ecryptfs_verbosity > 0)) { ecryptfs_printk(KERN_DEBUG, "derived iv:\n"); ecryptfs_dump_hex(iv, crypt_stat->iv_bytes); } out: return rc; } /** * ecryptfs_init_crypt_stat * @crypt_stat: Pointer to the crypt_stat struct to initialize. * * Initialize the crypt_stat structure. */ int ecryptfs_init_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat) { struct crypto_shash *tfm; int rc; tfm = crypto_alloc_shash(ECRYPTFS_DEFAULT_HASH, 0, 0); if (IS_ERR(tfm)) { rc = PTR_ERR(tfm); ecryptfs_printk(KERN_ERR, "Error attempting to " "allocate crypto context; rc = [%d]\n", rc); return rc; } memset((void *)crypt_stat, 0, sizeof(struct ecryptfs_crypt_stat)); INIT_LIST_HEAD(&crypt_stat->keysig_list); mutex_init(&crypt_stat->keysig_list_mutex); mutex_init(&crypt_stat->cs_mutex); mutex_init(&crypt_stat->cs_tfm_mutex); crypt_stat->hash_tfm = tfm; crypt_stat->flags |= ECRYPTFS_STRUCT_INITIALIZED; return 0; } /** * ecryptfs_destroy_crypt_stat * @crypt_stat: Pointer to the crypt_stat struct to initialize. * * Releases all memory associated with a crypt_stat struct. */ void ecryptfs_destroy_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat) { struct ecryptfs_key_sig *key_sig, *key_sig_tmp; crypto_free_skcipher(crypt_stat->tfm); crypto_free_shash(crypt_stat->hash_tfm); list_for_each_entry_safe(key_sig, key_sig_tmp, &crypt_stat->keysig_list, crypt_stat_list) { list_del(&key_sig->crypt_stat_list); kmem_cache_free(ecryptfs_key_sig_cache, key_sig); } memset(crypt_stat, 0, sizeof(struct ecryptfs_crypt_stat)); } void ecryptfs_destroy_mount_crypt_stat( struct ecryptfs_mount_crypt_stat *mount_crypt_stat) { struct ecryptfs_global_auth_tok *auth_tok, *auth_tok_tmp; if (!(mount_crypt_stat->flags & ECRYPTFS_MOUNT_CRYPT_STAT_INITIALIZED)) return; mutex_lock(&mount_crypt_stat->global_auth_tok_list_mutex); list_for_each_entry_safe(auth_tok, auth_tok_tmp, &mount_crypt_stat->global_auth_tok_list, mount_crypt_stat_list) { list_del(&auth_tok->mount_crypt_stat_list); if (!(auth_tok->flags & ECRYPTFS_AUTH_TOK_INVALID)) key_put(auth_tok->global_auth_tok_key); kmem_cache_free(ecryptfs_global_auth_tok_cache, auth_tok); } mutex_unlock(&mount_crypt_stat->global_auth_tok_list_mutex); memset(mount_crypt_stat, 0, sizeof(struct ecryptfs_mount_crypt_stat)); } /** * virt_to_scatterlist * @addr: Virtual address * @size: Size of data; should be an even multiple of the block size * @sg: Pointer to scatterlist array; set to NULL to obtain only * the number of scatterlist structs required in array * @sg_size: Max array size * * Fills in a scatterlist array with page references for a passed * virtual address. * * Returns the number of scatterlist structs in array used */ int virt_to_scatterlist(const void *addr, int size, struct scatterlist *sg, int sg_size) { int i = 0; struct page *pg; int offset; int remainder_of_page; sg_init_table(sg, sg_size); while (size > 0 && i < sg_size) { pg = virt_to_page(addr); offset = offset_in_page(addr); sg_set_page(&sg[i], pg, 0, offset); remainder_of_page = PAGE_SIZE - offset; if (size >= remainder_of_page) { sg[i].length = remainder_of_page; addr += remainder_of_page; size -= remainder_of_page; } else { sg[i].length = size; addr += size; size = 0; } i++; } if (size > 0) return -ENOMEM; return i; } /** * crypt_scatterlist * @crypt_stat: Pointer to the crypt_stat struct to initialize. * @dst_sg: Destination of the data after performing the crypto operation * @src_sg: Data to be encrypted or decrypted * @size: Length of data * @iv: IV to use * @op: ENCRYPT or DECRYPT to indicate the desired operation * * Returns the number of bytes encrypted or decrypted; negative value on error */ static int crypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat, struct scatterlist *dst_sg, struct scatterlist *src_sg, int size, unsigned char *iv, int op) { struct skcipher_request *req = NULL; DECLARE_CRYPTO_WAIT(ecr); int rc = 0; if (unlikely(ecryptfs_verbosity > 0)) { ecryptfs_printk(KERN_DEBUG, "Key size [%zd]; key:\n", crypt_stat->key_size); ecryptfs_dump_hex(crypt_stat->key, crypt_stat->key_size); } mutex_lock(&crypt_stat->cs_tfm_mutex); req = skcipher_request_alloc(crypt_stat->tfm, GFP_NOFS); if (!req) { mutex_unlock(&crypt_stat->cs_tfm_mutex); rc = -ENOMEM; goto out; } skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, crypto_req_done, &ecr); /* Consider doing this once, when the file is opened */ if (!(crypt_stat->flags & ECRYPTFS_KEY_SET)) { rc = crypto_skcipher_setkey(crypt_stat->tfm, crypt_stat->key, crypt_stat->key_size); if (rc) { ecryptfs_printk(KERN_ERR, "Error setting key; rc = [%d]\n", rc); mutex_unlock(&crypt_stat->cs_tfm_mutex); rc = -EINVAL; goto out; } crypt_stat->flags |= ECRYPTFS_KEY_SET; } mutex_unlock(&crypt_stat->cs_tfm_mutex); skcipher_request_set_crypt(req, src_sg, dst_sg, size, iv); rc = op == ENCRYPT ? crypto_skcipher_encrypt(req) : crypto_skcipher_decrypt(req); rc = crypto_wait_req(rc, &ecr); out: skcipher_request_free(req); return rc; } /* * lower_offset_for_page * * Convert an eCryptfs page index into a lower byte offset */ static loff_t lower_offset_for_page(struct ecryptfs_crypt_stat *crypt_stat, struct folio *folio) { return ecryptfs_lower_header_size(crypt_stat) + (loff_t)folio->index * PAGE_SIZE; } /** * crypt_extent * @crypt_stat: crypt_stat containing cryptographic context for the * encryption operation * @dst_page: The page to write the result into * @src_page: The page to read from * @page_index: The offset in the file (in units of PAGE_SIZE) * @extent_offset: Page extent offset for use in generating IV * @op: ENCRYPT or DECRYPT to indicate the desired operation * * Encrypts or decrypts one extent of data. * * Return zero on success; non-zero otherwise */ static int crypt_extent(struct ecryptfs_crypt_stat *crypt_stat, struct page *dst_page, struct page *src_page, pgoff_t page_index, unsigned long extent_offset, int op) { loff_t extent_base; char extent_iv[ECRYPTFS_MAX_IV_BYTES]; struct scatterlist src_sg, dst_sg; size_t extent_size = crypt_stat->extent_size; int rc; extent_base = (((loff_t)page_index) * (PAGE_SIZE / extent_size)); rc = ecryptfs_derive_iv(extent_iv, crypt_stat, (extent_base + extent_offset)); if (rc) { ecryptfs_printk(KERN_ERR, "Error attempting to derive IV for " "extent [0x%.16llx]; rc = [%d]\n", (unsigned long long)(extent_base + extent_offset), rc); goto out; } sg_init_table(&src_sg, 1); sg_init_table(&dst_sg, 1); sg_set_page(&src_sg, src_page, extent_size, extent_offset * extent_size); sg_set_page(&dst_sg, dst_page, extent_size, extent_offset * extent_size); rc = crypt_scatterlist(crypt_stat, &dst_sg, &src_sg, extent_size, extent_iv, op); if (rc < 0) { printk(KERN_ERR "%s: Error attempting to crypt page with " "page_index = [%ld], extent_offset = [%ld]; " "rc = [%d]\n", __func__, page_index, extent_offset, rc); goto out; } rc = 0; out: return rc; } /** * ecryptfs_encrypt_page * @folio: Folio mapped from the eCryptfs inode for the file; contains * decrypted content that needs to be encrypted (to a temporary * page; not in place) and written out to the lower file * * Encrypt an eCryptfs page. This is done on a per-extent basis. Note * that eCryptfs pages may straddle the lower pages -- for instance, * if the file was created on a machine with an 8K page size * (resulting in an 8K header), and then the file is copied onto a * host with a 32K page size, then when reading page 0 of the eCryptfs * file, 24K of page 0 of the lower file will be read and decrypted, * and then 8K of page 1 of the lower file will be read and decrypted. * * Returns zero on success; negative on error */ int ecryptfs_encrypt_page(struct folio *folio) { struct inode *ecryptfs_inode; struct ecryptfs_crypt_stat *crypt_stat; char *enc_extent_virt; struct page *enc_extent_page = NULL; loff_t extent_offset; loff_t lower_offset; int rc = 0; ecryptfs_inode = folio->mapping->host; crypt_stat = &(ecryptfs_inode_to_private(ecryptfs_inode)->crypt_stat); BUG_ON(!(crypt_stat->flags & ECRYPTFS_ENCRYPTED)); enc_extent_page = alloc_page(GFP_USER); if (!enc_extent_page) { rc = -ENOMEM; ecryptfs_printk(KERN_ERR, "Error allocating memory for " "encrypted extent\n"); goto out; } for (extent_offset = 0; extent_offset < (PAGE_SIZE / crypt_stat->extent_size); extent_offset++) { rc = crypt_extent(crypt_stat, enc_extent_page, folio_page(folio, 0), folio->index, extent_offset, ENCRYPT); if (rc) { printk(KERN_ERR "%s: Error encrypting extent; " "rc = [%d]\n", __func__, rc); goto out; } } lower_offset = lower_offset_for_page(crypt_stat, folio); enc_extent_virt = kmap_local_page(enc_extent_page); rc = ecryptfs_write_lower(ecryptfs_inode, enc_extent_virt, lower_offset, PAGE_SIZE); kunmap_local(enc_extent_virt); if (rc < 0) { ecryptfs_printk(KERN_ERR, "Error attempting to write lower page; rc = [%d]\n", rc); goto out; } rc = 0; out: if (enc_extent_page) { __free_page(enc_extent_page); } return rc; } /** * ecryptfs_decrypt_page * @folio: Folio mapped from the eCryptfs inode for the file; data read * and decrypted from the lower file will be written into this * page * * Decrypt an eCryptfs page. This is done on a per-extent basis. Note * that eCryptfs pages may straddle the lower pages -- for instance, * if the file was created on a machine with an 8K page size * (resulting in an 8K header), and then the file is copied onto a * host with a 32K page size, then when reading page 0 of the eCryptfs * file, 24K of page 0 of the lower file will be read and decrypted, * and then 8K of page 1 of the lower file will be read and decrypted. * * Returns zero on success; negative on error */ int ecryptfs_decrypt_page(struct folio *folio) { struct inode *ecryptfs_inode; struct ecryptfs_crypt_stat *crypt_stat; char *page_virt; unsigned long extent_offset; loff_t lower_offset; int rc = 0; ecryptfs_inode = folio->mapping->host; crypt_stat = &(ecryptfs_inode_to_private(ecryptfs_inode)->crypt_stat); BUG_ON(!(crypt_stat->flags & ECRYPTFS_ENCRYPTED)); lower_offset = lower_offset_for_page(crypt_stat, folio); page_virt = kmap_local_folio(folio, 0); rc = ecryptfs_read_lower(page_virt, lower_offset, PAGE_SIZE, ecryptfs_inode); kunmap_local(page_virt); if (rc < 0) { ecryptfs_printk(KERN_ERR, "Error attempting to read lower page; rc = [%d]\n", rc); goto out; } for (extent_offset = 0; extent_offset < (PAGE_SIZE / crypt_stat->extent_size); extent_offset++) { struct page *page = folio_page(folio, 0); rc = crypt_extent(crypt_stat, page, page, folio->index, extent_offset, DECRYPT); if (rc) { printk(KERN_ERR "%s: Error decrypting extent; " "rc = [%d]\n", __func__, rc); goto out; } } out: return rc; } #define ECRYPTFS_MAX_SCATTERLIST_LEN 4 /** * ecryptfs_init_crypt_ctx * @crypt_stat: Uninitialized crypt stats structure * * Initialize the crypto context. * * TODO: Performance: Keep a cache of initialized cipher contexts; * only init if needed */ int ecryptfs_init_crypt_ctx(struct ecryptfs_crypt_stat *crypt_stat) { char *full_alg_name; int rc = -EINVAL; ecryptfs_printk(KERN_DEBUG, "Initializing cipher [%s]; strlen = [%d]; " "key_size_bits = [%zd]\n", crypt_stat->cipher, (int)strlen(crypt_stat->cipher), crypt_stat->key_size << 3); mutex_lock(&crypt_stat->cs_tfm_mutex); if (crypt_stat->tfm) { rc = 0; goto out_unlock; } rc = ecryptfs_crypto_api_algify_cipher_name(&full_alg_name, crypt_stat->cipher, "cbc"); if (rc) goto out_unlock; crypt_stat->tfm = crypto_alloc_skcipher(full_alg_name, 0, 0); if (IS_ERR(crypt_stat->tfm)) { rc = PTR_ERR(crypt_stat->tfm); crypt_stat->tfm = NULL; ecryptfs_printk(KERN_ERR, "cryptfs: init_crypt_ctx(): " "Error initializing cipher [%s]\n", full_alg_name); goto out_free; } crypto_skcipher_set_flags(crypt_stat->tfm, CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); rc = 0; out_free: kfree(full_alg_name); out_unlock: mutex_unlock(&crypt_stat->cs_tfm_mutex); return rc; } static void set_extent_mask_and_shift(struct ecryptfs_crypt_stat *crypt_stat) { int extent_size_tmp; crypt_stat->extent_mask = 0xFFFFFFFF; crypt_stat->extent_shift = 0; if (crypt_stat->extent_size == 0) return; extent_size_tmp = crypt_stat->extent_size; while ((extent_size_tmp & 0x01) == 0) { extent_size_tmp >>= 1; crypt_stat->extent_mask <<= 1; crypt_stat->extent_shift++; } } void ecryptfs_set_default_sizes(struct ecryptfs_crypt_stat *crypt_stat) { /* Default values; may be overwritten as we are parsing the * packets. */ crypt_stat->extent_size = ECRYPTFS_DEFAULT_EXTENT_SIZE; set_extent_mask_and_shift(crypt_stat); crypt_stat->iv_bytes = ECRYPTFS_DEFAULT_IV_BYTES; if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR) crypt_stat->metadata_size = ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE; else { if (PAGE_SIZE <= ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE) crypt_stat->metadata_size = ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE; else crypt_stat->metadata_size = PAGE_SIZE; } } /* * ecryptfs_compute_root_iv * * On error, sets the root IV to all 0's. */ int ecryptfs_compute_root_iv(struct ecryptfs_crypt_stat *crypt_stat) { int rc = 0; char dst[MD5_DIGEST_SIZE]; BUG_ON(crypt_stat->iv_bytes > MD5_DIGEST_SIZE); BUG_ON(crypt_stat->iv_bytes <= 0); if (!(crypt_stat->flags & ECRYPTFS_KEY_VALID)) { rc = -EINVAL; ecryptfs_printk(KERN_WARNING, "Session key not valid; " "cannot generate root IV\n"); goto out; } rc = ecryptfs_calculate_md5(dst, crypt_stat, crypt_stat->key, crypt_stat->key_size); if (rc) { ecryptfs_printk(KERN_WARNING, "Error attempting to compute " "MD5 while generating root IV\n"); goto out; } memcpy(crypt_stat->root_iv, dst, crypt_stat->iv_bytes); out: if (rc) { memset(crypt_stat->root_iv, 0, crypt_stat->iv_bytes); crypt_stat->flags |= ECRYPTFS_SECURITY_WARNING; } return rc; } static void ecryptfs_generate_new_key(struct ecryptfs_crypt_stat *crypt_stat) { get_random_bytes(crypt_stat->key, crypt_stat->key_size); crypt_stat->flags |= ECRYPTFS_KEY_VALID; ecryptfs_compute_root_iv(crypt_stat); if (unlikely(ecryptfs_verbosity > 0)) { ecryptfs_printk(KERN_DEBUG, "Generated new session key:\n"); ecryptfs_dump_hex(crypt_stat->key, crypt_stat->key_size); } } /** * ecryptfs_copy_mount_wide_flags_to_inode_flags * @crypt_stat: The inode's cryptographic context * @mount_crypt_stat: The mount point's cryptographic context * * This function propagates the mount-wide flags to individual inode * flags. */ static void ecryptfs_copy_mount_wide_flags_to_inode_flags( struct ecryptfs_crypt_stat *crypt_stat, struct ecryptfs_mount_crypt_stat *mount_crypt_stat) { if (mount_crypt_stat->flags & ECRYPTFS_XATTR_METADATA_ENABLED) crypt_stat->flags |= ECRYPTFS_METADATA_IN_XATTR; if (mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED) crypt_stat->flags |= ECRYPTFS_VIEW_AS_ENCRYPTED; if (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES) { crypt_stat->flags |= ECRYPTFS_ENCRYPT_FILENAMES; if (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK) crypt_stat->flags |= ECRYPTFS_ENCFN_USE_MOUNT_FNEK; else if (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCFN_USE_FEK) crypt_stat->flags |= ECRYPTFS_ENCFN_USE_FEK; } } static int ecryptfs_copy_mount_wide_sigs_to_inode_sigs( struct ecryptfs_crypt_stat *crypt_stat, struct ecryptfs_mount_crypt_stat *mount_crypt_stat) { struct ecryptfs_global_auth_tok *global_auth_tok; int rc = 0; mutex_lock(&crypt_stat->keysig_list_mutex); mutex_lock(&mount_crypt_stat->global_auth_tok_list_mutex); list_for_each_entry(global_auth_tok, &mount_crypt_stat->global_auth_tok_list, mount_crypt_stat_list) { if (global_auth_tok->flags & ECRYPTFS_AUTH_TOK_FNEK) continue; rc = ecryptfs_add_keysig(crypt_stat, global_auth_tok->sig); if (rc) { printk(KERN_ERR "Error adding keysig; rc = [%d]\n", rc); goto out; } } out: mutex_unlock(&mount_crypt_stat->global_auth_tok_list_mutex); mutex_unlock(&crypt_stat->keysig_list_mutex); return rc; } /** * ecryptfs_set_default_crypt_stat_vals * @crypt_stat: The inode's cryptographic context * @mount_crypt_stat: The mount point's cryptographic context * * Default values in the event that policy does not override them. */ static void ecryptfs_set_default_crypt_stat_vals( struct ecryptfs_crypt_stat *crypt_stat, struct ecryptfs_mount_crypt_stat *mount_crypt_stat) { ecryptfs_copy_mount_wide_flags_to_inode_flags(crypt_stat, mount_crypt_stat); ecryptfs_set_default_sizes(crypt_stat); strcpy(crypt_stat->cipher, ECRYPTFS_DEFAULT_CIPHER); crypt_stat->key_size = ECRYPTFS_DEFAULT_KEY_BYTES; crypt_stat->flags &= ~(ECRYPTFS_KEY_VALID); crypt_stat->file_version = ECRYPTFS_FILE_VERSION; crypt_stat->mount_crypt_stat = mount_crypt_stat; } /** * ecryptfs_new_file_context * @ecryptfs_inode: The eCryptfs inode * * If the crypto context for the file has not yet been established, * this is where we do that. Establishing a new crypto context * involves the following decisions: * - What cipher to use? * - What set of authentication tokens to use? * Here we just worry about getting enough information into the * authentication tokens so that we know that they are available. * We associate the available authentication tokens with the new file * via the set of signatures in the crypt_stat struct. Later, when * the headers are actually written out, we may again defer to * userspace to perform the encryption of the session key; for the * foreseeable future, this will be the case with public key packets. * * Returns zero on success; non-zero otherwise */ int ecryptfs_new_file_context(struct inode *ecryptfs_inode) { struct ecryptfs_crypt_stat *crypt_stat = &ecryptfs_inode_to_private(ecryptfs_inode)->crypt_stat; struct ecryptfs_mount_crypt_stat *mount_crypt_stat = &ecryptfs_superblock_to_private( ecryptfs_inode->i_sb)->mount_crypt_stat; int cipher_name_len; int rc = 0; ecryptfs_set_default_crypt_stat_vals(crypt_stat, mount_crypt_stat); crypt_stat->flags |= (ECRYPTFS_ENCRYPTED | ECRYPTFS_KEY_VALID); ecryptfs_copy_mount_wide_flags_to_inode_flags(crypt_stat, mount_crypt_stat); rc = ecryptfs_copy_mount_wide_sigs_to_inode_sigs(crypt_stat, mount_crypt_stat); if (rc) { printk(KERN_ERR "Error attempting to copy mount-wide key sigs " "to the inode key sigs; rc = [%d]\n", rc); goto out; } cipher_name_len = strlen(mount_crypt_stat->global_default_cipher_name); memcpy(crypt_stat->cipher, mount_crypt_stat->global_default_cipher_name, cipher_name_len); crypt_stat->cipher[cipher_name_len] = '\0'; crypt_stat->key_size = mount_crypt_stat->global_default_cipher_key_size; ecryptfs_generate_new_key(crypt_stat); rc = ecryptfs_init_crypt_ctx(crypt_stat); if (rc) ecryptfs_printk(KERN_ERR, "Error initializing cryptographic " "context for cipher [%s]: rc = [%d]\n", crypt_stat->cipher, rc); out: return rc; } /** * ecryptfs_validate_marker - check for the ecryptfs marker * @data: The data block in which to check * * Returns zero if marker found; -EINVAL if not found */ static int ecryptfs_validate_marker(char *data) { u32 m_1, m_2; m_1 = get_unaligned_be32(data); m_2 = get_unaligned_be32(data + 4); if ((m_1 ^ MAGIC_ECRYPTFS_MARKER) == m_2) return 0; ecryptfs_printk(KERN_DEBUG, "m_1 = [0x%.8x]; m_2 = [0x%.8x]; " "MAGIC_ECRYPTFS_MARKER = [0x%.8x]\n", m_1, m_2, MAGIC_ECRYPTFS_MARKER); ecryptfs_printk(KERN_DEBUG, "(m_1 ^ MAGIC_ECRYPTFS_MARKER) = " "[0x%.8x]\n", (m_1 ^ MAGIC_ECRYPTFS_MARKER)); return -EINVAL; } struct ecryptfs_flag_map_elem { u32 file_flag; u32 local_flag; }; /* Add support for additional flags by adding elements here. */ static struct ecryptfs_flag_map_elem ecryptfs_flag_map[] = { {0x00000001, ECRYPTFS_ENABLE_HMAC}, {0x00000002, ECRYPTFS_ENCRYPTED}, {0x00000004, ECRYPTFS_METADATA_IN_XATTR}, {0x00000008, ECRYPTFS_ENCRYPT_FILENAMES} }; /** * ecryptfs_process_flags * @crypt_stat: The cryptographic context * @page_virt: Source data to be parsed * @bytes_read: Updated with the number of bytes read */ static void ecryptfs_process_flags(struct ecryptfs_crypt_stat *crypt_stat, char *page_virt, int *bytes_read) { int i; u32 flags; flags = get_unaligned_be32(page_virt); for (i = 0; i < ARRAY_SIZE(ecryptfs_flag_map); i++) if (flags & ecryptfs_flag_map[i].file_flag) { crypt_stat->flags |= ecryptfs_flag_map[i].local_flag; } else crypt_stat->flags &= ~(ecryptfs_flag_map[i].local_flag); /* Version is in top 8 bits of the 32-bit flag vector */ crypt_stat->file_version = ((flags >> 24) & 0xFF); (*bytes_read) = 4; } /** * write_ecryptfs_marker * @page_virt: The pointer to in a page to begin writing the marker * @written: Number of bytes written * * Marker = 0x3c81b7f5 */ static void write_ecryptfs_marker(char *page_virt, size_t *written) { u32 m_1, m_2; get_random_bytes(&m_1, (MAGIC_ECRYPTFS_MARKER_SIZE_BYTES / 2)); m_2 = (m_1 ^ MAGIC_ECRYPTFS_MARKER); put_unaligned_be32(m_1, page_virt); page_virt += (MAGIC_ECRYPTFS_MARKER_SIZE_BYTES / 2); put_unaligned_be32(m_2, page_virt); (*written) = MAGIC_ECRYPTFS_MARKER_SIZE_BYTES; } void ecryptfs_write_crypt_stat_flags(char *page_virt, struct ecryptfs_crypt_stat *crypt_stat, size_t *written) { u32 flags = 0; int i; for (i = 0; i < ARRAY_SIZE(ecryptfs_flag_map); i++) if (crypt_stat->flags & ecryptfs_flag_map[i].local_flag) flags |= ecryptfs_flag_map[i].file_flag; /* Version is in top 8 bits of the 32-bit flag vector */ flags |= ((((u8)crypt_stat->file_version) << 24) & 0xFF000000); put_unaligned_be32(flags, page_virt); (*written) = 4; } struct ecryptfs_cipher_code_str_map_elem { char cipher_str[16]; u8 cipher_code; }; /* Add support for additional ciphers by adding elements here. The * cipher_code is whatever OpenPGP applications use to identify the * ciphers. List in order of probability. */ static struct ecryptfs_cipher_code_str_map_elem ecryptfs_cipher_code_str_map[] = { {"aes",RFC2440_CIPHER_AES_128 }, {"blowfish", RFC2440_CIPHER_BLOWFISH}, {"des3_ede", RFC2440_CIPHER_DES3_EDE}, {"cast5", RFC2440_CIPHER_CAST_5}, {"twofish", RFC2440_CIPHER_TWOFISH}, {"cast6", RFC2440_CIPHER_CAST_6}, {"aes", RFC2440_CIPHER_AES_192}, {"aes", RFC2440_CIPHER_AES_256} }; /** * ecryptfs_code_for_cipher_string * @cipher_name: The string alias for the cipher * @key_bytes: Length of key in bytes; used for AES code selection * * Returns zero on no match, or the cipher code on match */ u8 ecryptfs_code_for_cipher_string(char *cipher_name, size_t key_bytes) { int i; u8 code = 0; struct ecryptfs_cipher_code_str_map_elem *map = ecryptfs_cipher_code_str_map; if (strcmp(cipher_name, "aes") == 0) { switch (key_bytes) { case 16: code = RFC2440_CIPHER_AES_128; break; case 24: code = RFC2440_CIPHER_AES_192; break; case 32: code = RFC2440_CIPHER_AES_256; } } else { for (i = 0; i < ARRAY_SIZE(ecryptfs_cipher_code_str_map); i++) if (strcmp(cipher_name, map[i].cipher_str) == 0) { code = map[i].cipher_code; break; } } return code; } /** * ecryptfs_cipher_code_to_string * @str: Destination to write out the cipher name * @cipher_code: The code to convert to cipher name string * * Returns zero on success */ int ecryptfs_cipher_code_to_string(char *str, u8 cipher_code) { int rc = 0; int i; str[0] = '\0'; for (i = 0; i < ARRAY_SIZE(ecryptfs_cipher_code_str_map); i++) if (cipher_code == ecryptfs_cipher_code_str_map[i].cipher_code) strcpy(str, ecryptfs_cipher_code_str_map[i].cipher_str); if (str[0] == '\0') { ecryptfs_printk(KERN_WARNING, "Cipher code not recognized: " "[%d]\n", cipher_code); rc = -EINVAL; } return rc; } int ecryptfs_read_and_validate_header_region(struct inode *inode) { u8 file_size[ECRYPTFS_SIZE_AND_MARKER_BYTES]; u8 *marker = file_size + ECRYPTFS_FILE_SIZE_BYTES; int rc; rc = ecryptfs_read_lower(file_size, 0, ECRYPTFS_SIZE_AND_MARKER_BYTES, inode); if (rc < 0) return rc; else if (rc < ECRYPTFS_SIZE_AND_MARKER_BYTES) return -EINVAL; rc = ecryptfs_validate_marker(marker); if (!rc) ecryptfs_i_size_init(file_size, inode); return rc; } void ecryptfs_write_header_metadata(char *virt, struct ecryptfs_crypt_stat *crypt_stat, size_t *written) { u32 header_extent_size; u16 num_header_extents_at_front; header_extent_size = (u32)crypt_stat->extent_size; num_header_extents_at_front = (u16)(crypt_stat->metadata_size / crypt_stat->extent_size); put_unaligned_be32(header_extent_size, virt); virt += 4; put_unaligned_be16(num_header_extents_at_front, virt); (*written) = 6; } struct kmem_cache *ecryptfs_header_cache; /** * ecryptfs_write_headers_virt * @page_virt: The virtual address to write the headers to * @max: The size of memory allocated at page_virt * @size: Set to the number of bytes written by this function * @crypt_stat: The cryptographic context * @ecryptfs_dentry: The eCryptfs dentry * * Format version: 1 * * Header Extent: * Octets 0-7: Unencrypted file size (big-endian) * Octets 8-15: eCryptfs special marker * Octets 16-19: Flags * Octet 16: File format version number (between 0 and 255) * Octets 17-18: Reserved * Octet 19: Bit 1 (lsb): Reserved * Bit 2: Encrypted? * Bits 3-8: Reserved * Octets 20-23: Header extent size (big-endian) * Octets 24-25: Number of header extents at front of file * (big-endian) * Octet 26: Begin RFC 2440 authentication token packet set * Data Extent 0: * Lower data (CBC encrypted) * Data Extent 1: * Lower data (CBC encrypted) * ... * * Returns zero on success */ static int ecryptfs_write_headers_virt(char *page_virt, size_t max, size_t *size, struct ecryptfs_crypt_stat *crypt_stat, struct dentry *ecryptfs_dentry) { int rc; size_t written; size_t offset; offset = ECRYPTFS_FILE_SIZE_BYTES; write_ecryptfs_marker((page_virt + offset), &written); offset += written; ecryptfs_write_crypt_stat_flags((page_virt + offset), crypt_stat, &written); offset += written; ecryptfs_write_header_metadata((page_virt + offset), crypt_stat, &written); offset += written; rc = ecryptfs_generate_key_packet_set((page_virt + offset), crypt_stat, ecryptfs_dentry, &written, max - offset); if (rc) ecryptfs_printk(KERN_WARNING, "Error generating key packet " "set; rc = [%d]\n", rc); if (size) { offset += written; *size = offset; } return rc; } static int ecryptfs_write_metadata_to_contents(struct inode *ecryptfs_inode, char *virt, size_t virt_len) { int rc; rc = ecryptfs_write_lower(ecryptfs_inode, virt, 0, virt_len); if (rc < 0) printk(KERN_ERR "%s: Error attempting to write header " "information to lower file; rc = [%d]\n", __func__, rc); else rc = 0; return rc; } static int ecryptfs_write_metadata_to_xattr(struct dentry *ecryptfs_dentry, struct inode *ecryptfs_inode, char *page_virt, size_t size) { int rc; struct dentry *lower_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry); struct inode *lower_inode = d_inode(lower_dentry); if (!(lower_inode->i_opflags & IOP_XATTR)) { rc = -EOPNOTSUPP; goto out; } inode_lock(lower_inode); rc = __vfs_setxattr(&nop_mnt_idmap, lower_dentry, lower_inode, ECRYPTFS_XATTR_NAME, page_virt, size, 0); if (!rc && ecryptfs_inode) fsstack_copy_attr_all(ecryptfs_inode, lower_inode); inode_unlock(lower_inode); out: return rc; } static unsigned long ecryptfs_get_zeroed_pages(gfp_t gfp_mask, unsigned int order) { struct page *page; page = alloc_pages(gfp_mask | __GFP_ZERO, order); if (page) return (unsigned long) page_address(page); return 0; } /** * ecryptfs_write_metadata * @ecryptfs_dentry: The eCryptfs dentry, which should be negative * @ecryptfs_inode: The newly created eCryptfs inode * * Write the file headers out. This will likely involve a userspace * callout, in which the session key is encrypted with one or more * public keys and/or the passphrase necessary to do the encryption is * retrieved via a prompt. Exactly what happens at this point should * be policy-dependent. * * Returns zero on success; non-zero on error */ int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry, struct inode *ecryptfs_inode) { struct ecryptfs_crypt_stat *crypt_stat = &ecryptfs_inode_to_private(ecryptfs_inode)->crypt_stat; unsigned int order; char *virt; size_t virt_len; size_t size = 0; int rc = 0; if (likely(crypt_stat->flags & ECRYPTFS_ENCRYPTED)) { if (!(crypt_stat->flags & ECRYPTFS_KEY_VALID)) { printk(KERN_ERR "Key is invalid; bailing out\n"); rc = -EINVAL; goto out; } } else { printk(KERN_WARNING "%s: Encrypted flag not set\n", __func__); rc = -EINVAL; goto out; } virt_len = crypt_stat->metadata_size; order = get_order(virt_len); /* Released in this function */ virt = (char *)ecryptfs_get_zeroed_pages(GFP_KERNEL, order); if (!virt) { printk(KERN_ERR "%s: Out of memory\n", __func__); rc = -ENOMEM; goto out; } /* Zeroed page ensures the in-header unencrypted i_size is set to 0 */ rc = ecryptfs_write_headers_virt(virt, virt_len, &size, crypt_stat, ecryptfs_dentry); if (unlikely(rc)) { printk(KERN_ERR "%s: Error whilst writing headers; rc = [%d]\n", __func__, rc); goto out_free; } if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR) rc = ecryptfs_write_metadata_to_xattr(ecryptfs_dentry, ecryptfs_inode, virt, size); else rc = ecryptfs_write_metadata_to_contents(ecryptfs_inode, virt, virt_len); if (rc) { printk(KERN_ERR "%s: Error writing metadata out to lower file; " "rc = [%d]\n", __func__, rc); goto out_free; } out_free: free_pages((unsigned long)virt, order); out: return rc; } #define ECRYPTFS_DONT_VALIDATE_HEADER_SIZE 0 #define ECRYPTFS_VALIDATE_HEADER_SIZE 1 static int parse_header_metadata(struct ecryptfs_crypt_stat *crypt_stat, char *virt, int *bytes_read, int validate_header_size) { int rc = 0; u32 header_extent_size; u16 num_header_extents_at_front; header_extent_size = get_unaligned_be32(virt); virt += sizeof(__be32); num_header_extents_at_front = get_unaligned_be16(virt); crypt_stat->metadata_size = (((size_t)num_header_extents_at_front * (size_t)header_extent_size)); (*bytes_read) = (sizeof(__be32) + sizeof(__be16)); if ((validate_header_size == ECRYPTFS_VALIDATE_HEADER_SIZE) && (crypt_stat->metadata_size < ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE)) { rc = -EINVAL; printk(KERN_WARNING "Invalid header size: [%zd]\n", crypt_stat->metadata_size); } return rc; } /** * set_default_header_data * @crypt_stat: The cryptographic context * * For version 0 file format; this function is only for backwards * compatibility for files created with the prior versions of * eCryptfs. */ static void set_default_header_data(struct ecryptfs_crypt_stat *crypt_stat) { crypt_stat->metadata_size = ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE; } void ecryptfs_i_size_init(const char *page_virt, struct inode *inode) { struct ecryptfs_mount_crypt_stat *mount_crypt_stat; struct ecryptfs_crypt_stat *crypt_stat; u64 file_size; crypt_stat = &ecryptfs_inode_to_private(inode)->crypt_stat; mount_crypt_stat = &ecryptfs_superblock_to_private(inode->i_sb)->mount_crypt_stat; if (mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED) { file_size = i_size_read(ecryptfs_inode_to_lower(inode)); if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR) file_size += crypt_stat->metadata_size; } else file_size = get_unaligned_be64(page_virt); i_size_write(inode, (loff_t)file_size); crypt_stat->flags |= ECRYPTFS_I_SIZE_INITIALIZED; } /** * ecryptfs_read_headers_virt * @page_virt: The virtual address into which to read the headers * @crypt_stat: The cryptographic context * @ecryptfs_dentry: The eCryptfs dentry * @validate_header_size: Whether to validate the header size while reading * * Read/parse the header data. The header format is detailed in the * comment block for the ecryptfs_write_headers_virt() function. * * Returns zero on success */ static int ecryptfs_read_headers_virt(char *page_virt, struct ecryptfs_crypt_stat *crypt_stat, struct dentry *ecryptfs_dentry, int validate_header_size) { int rc = 0; int offset; int bytes_read; ecryptfs_set_default_sizes(crypt_stat); crypt_stat->mount_crypt_stat = &ecryptfs_superblock_to_private( ecryptfs_dentry->d_sb)->mount_crypt_stat; offset = ECRYPTFS_FILE_SIZE_BYTES; rc = ecryptfs_validate_marker(page_virt + offset); if (rc) goto out; if (!(crypt_stat->flags & ECRYPTFS_I_SIZE_INITIALIZED)) ecryptfs_i_size_init(page_virt, d_inode(ecryptfs_dentry)); offset += MAGIC_ECRYPTFS_MARKER_SIZE_BYTES; ecryptfs_process_flags(crypt_stat, (page_virt + offset), &bytes_read); if (crypt_stat->file_version > ECRYPTFS_SUPPORTED_FILE_VERSION) { ecryptfs_printk(KERN_WARNING, "File version is [%d]; only " "file version [%d] is supported by this " "version of eCryptfs\n", crypt_stat->file_version, ECRYPTFS_SUPPORTED_FILE_VERSION); rc = -EINVAL; goto out; } offset += bytes_read; if (crypt_stat->file_version >= 1) { rc = parse_header_metadata(crypt_stat, (page_virt + offset), &bytes_read, validate_header_size); if (rc) { ecryptfs_printk(KERN_WARNING, "Error reading header " "metadata; rc = [%d]\n", rc); } offset += bytes_read; } else set_default_header_data(crypt_stat); rc = ecryptfs_parse_packet_set(crypt_stat, (page_virt + offset), ecryptfs_dentry); out: return rc; } /** * ecryptfs_read_xattr_region * @page_virt: The vitual address into which to read the xattr data * @ecryptfs_inode: The eCryptfs inode * * Attempts to read the crypto metadata from the extended attribute * region of the lower file. * * Returns zero on success; non-zero on error */ int ecryptfs_read_xattr_region(char *page_virt, struct inode *ecryptfs_inode) { struct dentry *lower_dentry = ecryptfs_inode_to_private(ecryptfs_inode)->lower_file->f_path.dentry; ssize_t size; int rc = 0; size = ecryptfs_getxattr_lower(lower_dentry, ecryptfs_inode_to_lower(ecryptfs_inode), ECRYPTFS_XATTR_NAME, page_virt, ECRYPTFS_DEFAULT_EXTENT_SIZE); if (size < 0) { if (unlikely(ecryptfs_verbosity > 0)) printk(KERN_INFO "Error attempting to read the [%s] " "xattr from the lower file; return value = " "[%zd]\n", ECRYPTFS_XATTR_NAME, size); rc = -EINVAL; goto out; } out: return rc; } int ecryptfs_read_and_validate_xattr_region(struct dentry *dentry, struct inode *inode) { u8 file_size[ECRYPTFS_SIZE_AND_MARKER_BYTES]; u8 *marker = file_size + ECRYPTFS_FILE_SIZE_BYTES; int rc; rc = ecryptfs_getxattr_lower(ecryptfs_dentry_to_lower(dentry), ecryptfs_inode_to_lower(inode), ECRYPTFS_XATTR_NAME, file_size, ECRYPTFS_SIZE_AND_MARKER_BYTES); if (rc < 0) return rc; else if (rc < ECRYPTFS_SIZE_AND_MARKER_BYTES) return -EINVAL; rc = ecryptfs_validate_marker(marker); if (!rc) ecryptfs_i_size_init(file_size, inode); return rc; } /* * ecryptfs_read_metadata * * Common entry point for reading file metadata. From here, we could * retrieve the header information from the header region of the file, * the xattr region of the file, or some other repository that is * stored separately from the file itself. The current implementation * supports retrieving the metadata information from the file contents * and from the xattr region. * * Returns zero if valid headers found and parsed; non-zero otherwise */ int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry) { int rc; char *page_virt; struct inode *ecryptfs_inode = d_inode(ecryptfs_dentry); struct ecryptfs_crypt_stat *crypt_stat = &ecryptfs_inode_to_private(ecryptfs_inode)->crypt_stat; struct ecryptfs_mount_crypt_stat *mount_crypt_stat = &ecryptfs_superblock_to_private( ecryptfs_dentry->d_sb)->mount_crypt_stat; ecryptfs_copy_mount_wide_flags_to_inode_flags(crypt_stat, mount_crypt_stat); /* Read the first page from the underlying file */ page_virt = kmem_cache_alloc(ecryptfs_header_cache, GFP_USER); if (!page_virt) { rc = -ENOMEM; goto out; } rc = ecryptfs_read_lower(page_virt, 0, crypt_stat->extent_size, ecryptfs_inode); if (rc >= 0) rc = ecryptfs_read_headers_virt(page_virt, crypt_stat, ecryptfs_dentry, ECRYPTFS_VALIDATE_HEADER_SIZE); if (rc) { /* metadata is not in the file header, so try xattrs */ memset(page_virt, 0, PAGE_SIZE); rc = ecryptfs_read_xattr_region(page_virt, ecryptfs_inode); if (rc) { printk(KERN_DEBUG "Valid eCryptfs headers not found in " "file header region or xattr region, inode %lu\n", ecryptfs_inode->i_ino); rc = -EINVAL; goto out; } rc = ecryptfs_read_headers_virt(page_virt, crypt_stat, ecryptfs_dentry, ECRYPTFS_DONT_VALIDATE_HEADER_SIZE); if (rc) { printk(KERN_DEBUG "Valid eCryptfs headers not found in " "file xattr region either, inode %lu\n", ecryptfs_inode->i_ino); rc = -EINVAL; } if (crypt_stat->mount_crypt_stat->flags & ECRYPTFS_XATTR_METADATA_ENABLED) { crypt_stat->flags |= ECRYPTFS_METADATA_IN_XATTR; } else { printk(KERN_WARNING "Attempt to access file with " "crypto metadata only in the extended attribute " "region, but eCryptfs was mounted without " "xattr support enabled. eCryptfs will not treat " "this like an encrypted file, inode %lu\n", ecryptfs_inode->i_ino); rc = -EINVAL; } } out: if (page_virt) { memset(page_virt, 0, PAGE_SIZE); kmem_cache_free(ecryptfs_header_cache, page_virt); } return rc; } /* * ecryptfs_encrypt_filename - encrypt filename * * CBC-encrypts the filename. We do not want to encrypt the same * filename with the same key and IV, which may happen with hard * links, so we prepend random bits to each filename. * * Returns zero on success; non-zero otherwise */ static int ecryptfs_encrypt_filename(struct ecryptfs_filename *filename, struct ecryptfs_mount_crypt_stat *mount_crypt_stat) { int rc = 0; filename->encrypted_filename = NULL; filename->encrypted_filename_size = 0; if (mount_crypt_stat && (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK)) { size_t packet_size; size_t remaining_bytes; rc = ecryptfs_write_tag_70_packet( NULL, NULL, &filename->encrypted_filename_size, mount_crypt_stat, NULL, filename->filename_size); if (rc) { printk(KERN_ERR "%s: Error attempting to get packet " "size for tag 72; rc = [%d]\n", __func__, rc); filename->encrypted_filename_size = 0; goto out; } filename->encrypted_filename = kmalloc(filename->encrypted_filename_size, GFP_KERNEL); if (!filename->encrypted_filename) { rc = -ENOMEM; goto out; } remaining_bytes = filename->encrypted_filename_size; rc = ecryptfs_write_tag_70_packet(filename->encrypted_filename, &remaining_bytes, &packet_size, mount_crypt_stat, filename->filename, filename->filename_size); if (rc) { printk(KERN_ERR "%s: Error attempting to generate " "tag 70 packet; rc = [%d]\n", __func__, rc); kfree(filename->encrypted_filename); filename->encrypted_filename = NULL; filename->encrypted_filename_size = 0; goto out; } filename->encrypted_filename_size = packet_size; } else { printk(KERN_ERR "%s: No support for requested filename " "encryption method in this release\n", __func__); rc = -EOPNOTSUPP; goto out; } out: return rc; } static int ecryptfs_copy_filename(char **copied_name, size_t *copied_name_size, const char *name, size_t name_size) { int rc = 0; (*copied_name) = kmalloc((name_size + 1), GFP_KERNEL); if (!(*copied_name)) { rc = -ENOMEM; goto out; } memcpy((void *)(*copied_name), (void *)name, name_size); (*copied_name)[(name_size)] = '\0'; /* Only for convenience * in printing out the * string in debug * messages */ (*copied_name_size) = name_size; out: return rc; } /** * ecryptfs_process_key_cipher - Perform key cipher initialization. * @key_tfm: Crypto context for key material, set by this function * @cipher_name: Name of the cipher * @key_size: Size of the key in bytes * * Returns zero on success. Any crypto_tfm structs allocated here * should be released by other functions, such as on a superblock put * event, regardless of whether this function succeeds for fails. */ static int ecryptfs_process_key_cipher(struct crypto_skcipher **key_tfm, char *cipher_name, size_t *key_size) { char dummy_key[ECRYPTFS_MAX_KEY_BYTES]; char *full_alg_name = NULL; int rc; *key_tfm = NULL; if (*key_size > ECRYPTFS_MAX_KEY_BYTES) { rc = -EINVAL; printk(KERN_ERR "Requested key size is [%zd] bytes; maximum " "allowable is [%d]\n", *key_size, ECRYPTFS_MAX_KEY_BYTES); goto out; } rc = ecryptfs_crypto_api_algify_cipher_name(&full_alg_name, cipher_name, "ecb"); if (rc) goto out; *key_tfm = crypto_alloc_skcipher(full_alg_name, 0, CRYPTO_ALG_ASYNC); if (IS_ERR(*key_tfm)) { rc = PTR_ERR(*key_tfm); printk(KERN_ERR "Unable to allocate crypto cipher with name " "[%s]; rc = [%d]\n", full_alg_name, rc); goto out; } crypto_skcipher_set_flags(*key_tfm, CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); if (*key_size == 0) *key_size = crypto_skcipher_max_keysize(*key_tfm); get_random_bytes(dummy_key, *key_size); rc = crypto_skcipher_setkey(*key_tfm, dummy_key, *key_size); if (rc) { printk(KERN_ERR "Error attempting to set key of size [%zd] for " "cipher [%s]; rc = [%d]\n", *key_size, full_alg_name, rc); rc = -EINVAL; goto out; } out: kfree(full_alg_name); return rc; } struct kmem_cache *ecryptfs_key_tfm_cache; static struct list_head key_tfm_list; DEFINE_MUTEX(key_tfm_list_mutex); int __init ecryptfs_init_crypto(void) { INIT_LIST_HEAD(&key_tfm_list); return 0; } /** * ecryptfs_destroy_crypto - free all cached key_tfms on key_tfm_list * * Called only at module unload time */ int ecryptfs_destroy_crypto(void) { struct ecryptfs_key_tfm *key_tfm, *key_tfm_tmp; mutex_lock(&key_tfm_list_mutex); list_for_each_entry_safe(key_tfm, key_tfm_tmp, &key_tfm_list, key_tfm_list) { list_del(&key_tfm->key_tfm_list); crypto_free_skcipher(key_tfm->key_tfm); kmem_cache_free(ecryptfs_key_tfm_cache, key_tfm); } mutex_unlock(&key_tfm_list_mutex); return 0; } int ecryptfs_add_new_key_tfm(struct ecryptfs_key_tfm **key_tfm, char *cipher_name, size_t key_size) { struct ecryptfs_key_tfm *tmp_tfm; int rc = 0; BUG_ON(!mutex_is_locked(&key_tfm_list_mutex)); tmp_tfm = kmem_cache_alloc(ecryptfs_key_tfm_cache, GFP_KERNEL); if (key_tfm) (*key_tfm) = tmp_tfm; if (!tmp_tfm) { rc = -ENOMEM; goto out; } mutex_init(&tmp_tfm->key_tfm_mutex); strscpy(tmp_tfm->cipher_name, cipher_name); tmp_tfm->key_size = key_size; rc = ecryptfs_process_key_cipher(&tmp_tfm->key_tfm, tmp_tfm->cipher_name, &tmp_tfm->key_size); if (rc) { printk(KERN_ERR "Error attempting to initialize key TFM " "cipher with name = [%s]; rc = [%d]\n", tmp_tfm->cipher_name, rc); kmem_cache_free(ecryptfs_key_tfm_cache, tmp_tfm); if (key_tfm) (*key_tfm) = NULL; goto out; } list_add(&tmp_tfm->key_tfm_list, &key_tfm_list); out: return rc; } /** * ecryptfs_tfm_exists - Search for existing tfm for cipher_name. * @cipher_name: the name of the cipher to search for * @key_tfm: set to corresponding tfm if found * * Searches for cached key_tfm matching @cipher_name * Must be called with &key_tfm_list_mutex held * Returns 1 if found, with @key_tfm set * Returns 0 if not found, with @key_tfm set to NULL */ int ecryptfs_tfm_exists(char *cipher_name, struct ecryptfs_key_tfm **key_tfm) { struct ecryptfs_key_tfm *tmp_key_tfm; BUG_ON(!mutex_is_locked(&key_tfm_list_mutex)); list_for_each_entry(tmp_key_tfm, &key_tfm_list, key_tfm_list) { if (strcmp(tmp_key_tfm->cipher_name, cipher_name) == 0) { if (key_tfm) (*key_tfm) = tmp_key_tfm; return 1; } } if (key_tfm) (*key_tfm) = NULL; return 0; } /** * ecryptfs_get_tfm_and_mutex_for_cipher_name * * @tfm: set to cached tfm found, or new tfm created * @tfm_mutex: set to mutex for cached tfm found, or new tfm created * @cipher_name: the name of the cipher to search for and/or add * * Sets pointers to @tfm & @tfm_mutex matching @cipher_name. * Searches for cached item first, and creates new if not found. * Returns 0 on success, non-zero if adding new cipher failed */ int ecryptfs_get_tfm_and_mutex_for_cipher_name(struct crypto_skcipher **tfm, struct mutex **tfm_mutex, char *cipher_name) { struct ecryptfs_key_tfm *key_tfm; int rc = 0; (*tfm) = NULL; (*tfm_mutex) = NULL; mutex_lock(&key_tfm_list_mutex); if (!ecryptfs_tfm_exists(cipher_name, &key_tfm)) { rc = ecryptfs_add_new_key_tfm(&key_tfm, cipher_name, 0); if (rc) { printk(KERN_ERR "Error adding new key_tfm to list; " "rc = [%d]\n", rc); goto out; } } (*tfm) = key_tfm->key_tfm; (*tfm_mutex) = &key_tfm->key_tfm_mutex; out: mutex_unlock(&key_tfm_list_mutex); return rc; } /* 64 characters forming a 6-bit target field */ static unsigned char *portable_filename_chars = ("-.0123456789ABCD" "EFGHIJKLMNOPQRST" "UVWXYZabcdefghij" "klmnopqrstuvwxyz"); /* We could either offset on every reverse map or just pad some 0x00's * at the front here */ static const unsigned char filename_rev_map[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 15 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 23 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 31 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 39 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x00, /* 47 */ 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, /* 55 */ 0x0A, 0x0B, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 63 */ 0x00, 0x0C, 0x0D, 0x0E, 0x0F, 0x10, 0x11, 0x12, /* 71 */ 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1A, /* 79 */ 0x1B, 0x1C, 0x1D, 0x1E, 0x1F, 0x20, 0x21, 0x22, /* 87 */ 0x23, 0x24, 0x25, 0x00, 0x00, 0x00, 0x00, 0x00, /* 95 */ 0x00, 0x26, 0x27, 0x28, 0x29, 0x2A, 0x2B, 0x2C, /* 103 */ 0x2D, 0x2E, 0x2F, 0x30, 0x31, 0x32, 0x33, 0x34, /* 111 */ 0x35, 0x36, 0x37, 0x38, 0x39, 0x3A, 0x3B, 0x3C, /* 119 */ 0x3D, 0x3E, 0x3F /* 123 - 255 initialized to 0x00 */ }; /** * ecryptfs_encode_for_filename * @dst: Destination location for encoded filename * @dst_size: Size of the encoded filename in bytes * @src: Source location for the filename to encode * @src_size: Size of the source in bytes */ static void ecryptfs_encode_for_filename(unsigned char *dst, size_t *dst_size, unsigned char *src, size_t src_size) { size_t num_blocks; size_t block_num = 0; size_t dst_offset = 0; unsigned char last_block[3]; if (src_size == 0) { (*dst_size) = 0; goto out; } num_blocks = (src_size / 3); if ((src_size % 3) == 0) { memcpy(last_block, (&src[src_size - 3]), 3); } else { num_blocks++; last_block[2] = 0x00; switch (src_size % 3) { case 1: last_block[0] = src[src_size - 1]; last_block[1] = 0x00; break; case 2: last_block[0] = src[src_size - 2]; last_block[1] = src[src_size - 1]; } } (*dst_size) = (num_blocks * 4); if (!dst) goto out; while (block_num < num_blocks) { unsigned char *src_block; unsigned char dst_block[4]; if (block_num == (num_blocks - 1)) src_block = last_block; else src_block = &src[block_num * 3]; dst_block[0] = ((src_block[0] >> 2) & 0x3F); dst_block[1] = (((src_block[0] << 4) & 0x30) | ((src_block[1] >> 4) & 0x0F)); dst_block[2] = (((src_block[1] << 2) & 0x3C) | ((src_block[2] >> 6) & 0x03)); dst_block[3] = (src_block[2] & 0x3F); dst[dst_offset++] = portable_filename_chars[dst_block[0]]; dst[dst_offset++] = portable_filename_chars[dst_block[1]]; dst[dst_offset++] = portable_filename_chars[dst_block[2]]; dst[dst_offset++] = portable_filename_chars[dst_block[3]]; block_num++; } out: return; } static size_t ecryptfs_max_decoded_size(size_t encoded_size) { /* Not exact; conservatively long. Every block of 4 * encoded characters decodes into a block of 3 * decoded characters. This segment of code provides * the caller with the maximum amount of allocated * space that @dst will need to point to in a * subsequent call. */ return ((encoded_size + 1) * 3) / 4; } /** * ecryptfs_decode_from_filename * @dst: If NULL, this function only sets @dst_size and returns. If * non-NULL, this function decodes the encoded octets in @src * into the memory that @dst points to. * @dst_size: Set to the size of the decoded string. * @src: The encoded set of octets to decode. * @src_size: The size of the encoded set of octets to decode. */ static void ecryptfs_decode_from_filename(unsigned char *dst, size_t *dst_size, const unsigned char *src, size_t src_size) { u8 current_bit_offset = 0; size_t src_byte_offset = 0; size_t dst_byte_offset = 0; if (!dst) { (*dst_size) = ecryptfs_max_decoded_size(src_size); goto out; } while (src_byte_offset < src_size) { unsigned char src_byte = filename_rev_map[(int)src[src_byte_offset]]; switch (current_bit_offset) { case 0: dst[dst_byte_offset] = (src_byte << 2); current_bit_offset = 6; break; case 6: dst[dst_byte_offset++] |= (src_byte >> 4); dst[dst_byte_offset] = ((src_byte & 0xF) << 4); current_bit_offset = 4; break; case 4: dst[dst_byte_offset++] |= (src_byte >> 2); dst[dst_byte_offset] = (src_byte << 6); current_bit_offset = 2; break; case 2: dst[dst_byte_offset++] |= (src_byte); current_bit_offset = 0; break; } src_byte_offset++; } (*dst_size) = dst_byte_offset; out: return; } /** * ecryptfs_encrypt_and_encode_filename - converts a plaintext file name to cipher text * @encoded_name: The encrypted name * @encoded_name_size: Length of the encrypted name * @mount_crypt_stat: The crypt_stat struct associated with the file name to encode * @name: The plaintext name * @name_size: The length of the plaintext name * * Encrypts and encodes a filename into something that constitutes a * valid filename for a filesystem, with printable characters. * * We assume that we have a properly initialized crypto context, * pointed to by crypt_stat->tfm. * * Returns zero on success; non-zero on otherwise */ int ecryptfs_encrypt_and_encode_filename( char **encoded_name, size_t *encoded_name_size, struct ecryptfs_mount_crypt_stat *mount_crypt_stat, const char *name, size_t name_size) { size_t encoded_name_no_prefix_size; int rc = 0; (*encoded_name) = NULL; (*encoded_name_size) = 0; if (mount_crypt_stat && (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)) { struct ecryptfs_filename *filename; filename = kzalloc(sizeof(*filename), GFP_KERNEL); if (!filename) { rc = -ENOMEM; goto out; } filename->filename = (char *)name; filename->filename_size = name_size; rc = ecryptfs_encrypt_filename(filename, mount_crypt_stat); if (rc) { printk(KERN_ERR "%s: Error attempting to encrypt " "filename; rc = [%d]\n", __func__, rc); kfree(filename); goto out; } ecryptfs_encode_for_filename( NULL, &encoded_name_no_prefix_size, filename->encrypted_filename, filename->encrypted_filename_size); if (mount_crypt_stat && (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK)) (*encoded_name_size) = (ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE + encoded_name_no_prefix_size); else (*encoded_name_size) = (ECRYPTFS_FEK_ENCRYPTED_FILENAME_PREFIX_SIZE + encoded_name_no_prefix_size); (*encoded_name) = kmalloc((*encoded_name_size) + 1, GFP_KERNEL); if (!(*encoded_name)) { rc = -ENOMEM; kfree(filename->encrypted_filename); kfree(filename); goto out; } if (mount_crypt_stat && (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK)) { memcpy((*encoded_name), ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX, ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE); ecryptfs_encode_for_filename( ((*encoded_name) + ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE), &encoded_name_no_prefix_size, filename->encrypted_filename, filename->encrypted_filename_size); (*encoded_name_size) = (ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE + encoded_name_no_prefix_size); (*encoded_name)[(*encoded_name_size)] = '\0'; } else { rc = -EOPNOTSUPP; } if (rc) { printk(KERN_ERR "%s: Error attempting to encode " "encrypted filename; rc = [%d]\n", __func__, rc); kfree((*encoded_name)); (*encoded_name) = NULL; (*encoded_name_size) = 0; } kfree(filename->encrypted_filename); kfree(filename); } else { rc = ecryptfs_copy_filename(encoded_name, encoded_name_size, name, name_size); } out: return rc; } /** * ecryptfs_decode_and_decrypt_filename - converts the encoded cipher text name to decoded plaintext * @plaintext_name: The plaintext name * @plaintext_name_size: The plaintext name size * @sb: Ecryptfs's super_block * @name: The filename in cipher text * @name_size: The cipher text name size * * Decrypts and decodes the filename. * * Returns zero on error; non-zero otherwise */ int ecryptfs_decode_and_decrypt_filename(char **plaintext_name, size_t *plaintext_name_size, struct super_block *sb, const char *name, size_t name_size) { struct ecryptfs_mount_crypt_stat *mount_crypt_stat = &ecryptfs_superblock_to_private(sb)->mount_crypt_stat; char *decoded_name; size_t decoded_name_size; size_t packet_size; int rc = 0; if ((mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES) && !(mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED)) { if (is_dot_dotdot(name, name_size)) { rc = ecryptfs_copy_filename(plaintext_name, plaintext_name_size, name, name_size); goto out; } if (name_size <= ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE || strncmp(name, ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX, ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE)) { rc = -EINVAL; goto out; } name += ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE; name_size -= ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE; ecryptfs_decode_from_filename(NULL, &decoded_name_size, name, name_size); decoded_name = kmalloc(decoded_name_size, GFP_KERNEL); if (!decoded_name) { rc = -ENOMEM; goto out; } ecryptfs_decode_from_filename(decoded_name, &decoded_name_size, name, name_size); rc = ecryptfs_parse_tag_70_packet(plaintext_name, plaintext_name_size, &packet_size, mount_crypt_stat, decoded_name, decoded_name_size); if (rc) { ecryptfs_printk(KERN_DEBUG, "%s: Could not parse tag 70 packet from filename\n", __func__); goto out_free; } } else { rc = ecryptfs_copy_filename(plaintext_name, plaintext_name_size, name, name_size); goto out; } out_free: kfree(decoded_name); out: return rc; } #define ENC_NAME_MAX_BLOCKLEN_8_OR_16 143 int ecryptfs_set_f_namelen(long *namelen, long lower_namelen, struct ecryptfs_mount_crypt_stat *mount_crypt_stat) { struct crypto_skcipher *tfm; struct mutex *tfm_mutex; size_t cipher_blocksize; int rc; if (!(mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)) { (*namelen) = lower_namelen; return 0; } rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&tfm, &tfm_mutex, mount_crypt_stat->global_default_fn_cipher_name); if (unlikely(rc)) { (*namelen) = 0; return rc; } mutex_lock(tfm_mutex); cipher_blocksize = crypto_skcipher_blocksize(tfm); mutex_unlock(tfm_mutex); /* Return an exact amount for the common cases */ if (lower_namelen == NAME_MAX && (cipher_blocksize == 8 || cipher_blocksize == 16)) { (*namelen) = ENC_NAME_MAX_BLOCKLEN_8_OR_16; return 0; } /* Return a safe estimate for the uncommon cases */ (*namelen) = lower_namelen; (*namelen) -= ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE; /* Since this is the max decoded size, subtract 1 "decoded block" len */ (*namelen) = ecryptfs_max_decoded_size(*namelen) - 3; (*namelen) -= ECRYPTFS_TAG_70_MAX_METADATA_SIZE; (*namelen) -= ECRYPTFS_FILENAME_MIN_RANDOM_PREPEND_BYTES; /* Worst case is that the filename is padded nearly a full block size */ (*namelen) -= cipher_blocksize - 1; if ((*namelen) < 0) (*namelen) = 0; return 0; } |
| 22 | 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 | /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_IOPRIO_H #define _UAPI_LINUX_IOPRIO_H #include <linux/stddef.h> #include <linux/types.h> /* * Gives us 8 prio classes with 13-bits of data for each class */ #define IOPRIO_CLASS_SHIFT 13 #define IOPRIO_NR_CLASSES 8 #define IOPRIO_CLASS_MASK (IOPRIO_NR_CLASSES - 1) #define IOPRIO_PRIO_MASK ((1UL << IOPRIO_CLASS_SHIFT) - 1) #define IOPRIO_PRIO_CLASS(ioprio) \ (((ioprio) >> IOPRIO_CLASS_SHIFT) & IOPRIO_CLASS_MASK) #define IOPRIO_PRIO_DATA(ioprio) ((ioprio) & IOPRIO_PRIO_MASK) /* * These are the io priority classes as implemented by the BFQ and mq-deadline * schedulers. RT is the realtime class, it always gets premium service. For * ATA disks supporting NCQ IO priority, RT class IOs will be processed using * high priority NCQ commands. BE is the best-effort scheduling class, the * default for any process. IDLE is the idle scheduling class, it is only * served when no one else is using the disk. */ enum { IOPRIO_CLASS_NONE = 0, IOPRIO_CLASS_RT = 1, IOPRIO_CLASS_BE = 2, IOPRIO_CLASS_IDLE = 3, /* Special class to indicate an invalid ioprio value */ IOPRIO_CLASS_INVALID = 7, }; /* * The RT and BE priority classes both support up to 8 priority levels that * can be specified using the lower 3-bits of the priority data. */ #define IOPRIO_LEVEL_NR_BITS 3 #define IOPRIO_NR_LEVELS (1 << IOPRIO_LEVEL_NR_BITS) #define IOPRIO_LEVEL_MASK (IOPRIO_NR_LEVELS - 1) #define IOPRIO_PRIO_LEVEL(ioprio) ((ioprio) & IOPRIO_LEVEL_MASK) #define IOPRIO_BE_NR IOPRIO_NR_LEVELS /* * Possible values for the "which" argument of the ioprio_get() and * ioprio_set() system calls (see "man ioprio_set"). */ enum { IOPRIO_WHO_PROCESS = 1, IOPRIO_WHO_PGRP, IOPRIO_WHO_USER, }; /* * Fallback BE class priority level. */ #define IOPRIO_NORM 4 #define IOPRIO_BE_NORM IOPRIO_NORM /* * The 10 bits between the priority class and the priority level are used to * optionally define I/O hints for any combination of I/O priority class and * level. Depending on the kernel configuration, I/O scheduler being used and * the target I/O device being used, hints can influence how I/Os are processed * without affecting the I/O scheduling ordering defined by the I/O priority * class and level. */ #define IOPRIO_HINT_SHIFT IOPRIO_LEVEL_NR_BITS #define IOPRIO_HINT_NR_BITS 10 #define IOPRIO_NR_HINTS (1 << IOPRIO_HINT_NR_BITS) #define IOPRIO_HINT_MASK (IOPRIO_NR_HINTS - 1) #define IOPRIO_PRIO_HINT(ioprio) \ (((ioprio) >> IOPRIO_HINT_SHIFT) & IOPRIO_HINT_MASK) /* * I/O hints. */ enum { /* No hint */ IOPRIO_HINT_NONE = 0, /* * Device command duration limits: indicate to the device a desired * duration limit for the commands that will be used to process an I/O. * These will currently only be effective for SCSI and ATA devices that * support the command duration limits feature. If this feature is * enabled, then the commands issued to the device to process an I/O with * one of these hints set will have the duration limit index (dld field) * set to the value of the hint. */ IOPRIO_HINT_DEV_DURATION_LIMIT_1 = 1, IOPRIO_HINT_DEV_DURATION_LIMIT_2 = 2, IOPRIO_HINT_DEV_DURATION_LIMIT_3 = 3, IOPRIO_HINT_DEV_DURATION_LIMIT_4 = 4, IOPRIO_HINT_DEV_DURATION_LIMIT_5 = 5, IOPRIO_HINT_DEV_DURATION_LIMIT_6 = 6, IOPRIO_HINT_DEV_DURATION_LIMIT_7 = 7, }; #define IOPRIO_BAD_VALUE(val, max) ((val) < 0 || (val) >= (max)) /* * Return an I/O priority value based on a class, a level and a hint. */ static __always_inline __u16 ioprio_value(int prioclass, int priolevel, int priohint) { if (IOPRIO_BAD_VALUE(prioclass, IOPRIO_NR_CLASSES) || IOPRIO_BAD_VALUE(priolevel, IOPRIO_NR_LEVELS) || IOPRIO_BAD_VALUE(priohint, IOPRIO_NR_HINTS)) return IOPRIO_CLASS_INVALID << IOPRIO_CLASS_SHIFT; return (prioclass << IOPRIO_CLASS_SHIFT) | (priohint << IOPRIO_HINT_SHIFT) | priolevel; } #define IOPRIO_PRIO_VALUE(prioclass, priolevel) \ ioprio_value(prioclass, priolevel, IOPRIO_HINT_NONE) #define IOPRIO_PRIO_VALUE_HINT(prioclass, priolevel, priohint) \ ioprio_value(prioclass, priolevel, priohint) #endif /* _UAPI_LINUX_IOPRIO_H */ |
| 2 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 | // SPDX-License-Identifier: GPL-2.0 OR MIT /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #include <crypto/internal/blake2s.h> #include <linux/types.h> #include <linux/jump_label.h> #include <linux/kernel.h> #include <linux/sizes.h> #include <asm/cpufeature.h> #include <asm/fpu/api.h> #include <asm/processor.h> #include <asm/simd.h> asmlinkage void blake2s_compress_ssse3(struct blake2s_state *state, const u8 *block, const size_t nblocks, const u32 inc); asmlinkage void blake2s_compress_avx512(struct blake2s_state *state, const u8 *block, const size_t nblocks, const u32 inc); static __ro_after_init DEFINE_STATIC_KEY_FALSE(blake2s_use_ssse3); static __ro_after_init DEFINE_STATIC_KEY_FALSE(blake2s_use_avx512); void blake2s_compress(struct blake2s_state *state, const u8 *block, size_t nblocks, const u32 inc) { /* SIMD disables preemption, so relax after processing each page. */ BUILD_BUG_ON(SZ_4K / BLAKE2S_BLOCK_SIZE < 8); if (!static_branch_likely(&blake2s_use_ssse3) || !may_use_simd()) { blake2s_compress_generic(state, block, nblocks, inc); return; } do { const size_t blocks = min_t(size_t, nblocks, SZ_4K / BLAKE2S_BLOCK_SIZE); kernel_fpu_begin(); if (IS_ENABLED(CONFIG_AS_AVX512) && static_branch_likely(&blake2s_use_avx512)) blake2s_compress_avx512(state, block, blocks, inc); else blake2s_compress_ssse3(state, block, blocks, inc); kernel_fpu_end(); nblocks -= blocks; block += blocks * BLAKE2S_BLOCK_SIZE; } while (nblocks); } EXPORT_SYMBOL(blake2s_compress); static int __init blake2s_mod_init(void) { if (boot_cpu_has(X86_FEATURE_SSSE3)) static_branch_enable(&blake2s_use_ssse3); if (IS_ENABLED(CONFIG_AS_AVX512) && boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_AVX512F) && boot_cpu_has(X86_FEATURE_AVX512VL) && cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM | XFEATURE_MASK_AVX512, NULL)) static_branch_enable(&blake2s_use_avx512); return 0; } subsys_initcall(blake2s_mod_init); |
| 2 2 2 2 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET 802.1Q VLAN * Ethernet-type device handling. * * Authors: Ben Greear <greearb@candelatech.com> * Please send support related email to: netdev@vger.kernel.org * VLAN Home Page: http://www.candelatech.com/~greear/vlan.html * * Fixes: * Fix for packet capture - Nick Eggleston <nick@dccinc.com>; * Add HW acceleration hooks - David S. Miller <davem@redhat.com>; * Correct all the locking - David S. Miller <davem@redhat.com>; * Use hash table for VLAN groups - David S. Miller <davem@redhat.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/capability.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/rculist.h> #include <net/p8022.h> #include <net/arp.h> #include <linux/rtnetlink.h> #include <linux/notifier.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/uaccess.h> #include <linux/if_vlan.h> #include "vlan.h" #include "vlanproc.h" #define DRV_VERSION "1.8" /* Global VLAN variables */ unsigned int vlan_net_id __read_mostly; const char vlan_fullname[] = "802.1Q VLAN Support"; const char vlan_version[] = DRV_VERSION; /* End of global variables definitions. */ static int vlan_group_prealloc_vid(struct vlan_group *vg, __be16 vlan_proto, u16 vlan_id) { struct net_device **array; unsigned int vidx; unsigned int size; int pidx; ASSERT_RTNL(); pidx = vlan_proto_idx(vlan_proto); if (pidx < 0) return -EINVAL; vidx = vlan_id / VLAN_GROUP_ARRAY_PART_LEN; array = vg->vlan_devices_arrays[pidx][vidx]; if (array != NULL) return 0; size = sizeof(struct net_device *) * VLAN_GROUP_ARRAY_PART_LEN; array = kzalloc(size, GFP_KERNEL_ACCOUNT); if (array == NULL) return -ENOBUFS; /* paired with smp_rmb() in __vlan_group_get_device() */ smp_wmb(); vg->vlan_devices_arrays[pidx][vidx] = array; return 0; } static void vlan_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev, struct vlan_dev_priv *vlan) { if (!(vlan->flags & VLAN_FLAG_BRIDGE_BINDING)) netif_stacked_transfer_operstate(rootdev, dev); } void unregister_vlan_dev(struct net_device *dev, struct list_head *head) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; struct vlan_info *vlan_info; struct vlan_group *grp; u16 vlan_id = vlan->vlan_id; ASSERT_RTNL(); vlan_info = rtnl_dereference(real_dev->vlan_info); BUG_ON(!vlan_info); grp = &vlan_info->grp; grp->nr_vlan_devs--; if (vlan->flags & VLAN_FLAG_MVRP) vlan_mvrp_request_leave(dev); if (vlan->flags & VLAN_FLAG_GVRP) vlan_gvrp_request_leave(dev); vlan_group_set_device(grp, vlan->vlan_proto, vlan_id, NULL); netdev_upper_dev_unlink(real_dev, dev); /* Because unregister_netdevice_queue() makes sure at least one rcu * grace period is respected before device freeing, * we dont need to call synchronize_net() here. */ unregister_netdevice_queue(dev, head); if (grp->nr_vlan_devs == 0) { vlan_mvrp_uninit_applicant(real_dev); vlan_gvrp_uninit_applicant(real_dev); } vlan_vid_del(real_dev, vlan->vlan_proto, vlan_id); } int vlan_check_real_dev(struct net_device *real_dev, __be16 protocol, u16 vlan_id, struct netlink_ext_ack *extack) { const char *name = real_dev->name; if (real_dev->features & NETIF_F_VLAN_CHALLENGED || real_dev->type != ARPHRD_ETHER) { pr_info("VLANs not supported on %s\n", name); NL_SET_ERR_MSG_MOD(extack, "VLANs not supported on device"); return -EOPNOTSUPP; } if (vlan_find_dev(real_dev, protocol, vlan_id) != NULL) { NL_SET_ERR_MSG_MOD(extack, "VLAN device already exists"); return -EEXIST; } return 0; } int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; u16 vlan_id = vlan->vlan_id; struct vlan_info *vlan_info; struct vlan_group *grp; int err; err = vlan_vid_add(real_dev, vlan->vlan_proto, vlan_id); if (err) return err; vlan_info = rtnl_dereference(real_dev->vlan_info); /* vlan_info should be there now. vlan_vid_add took care of it */ BUG_ON(!vlan_info); grp = &vlan_info->grp; if (grp->nr_vlan_devs == 0) { err = vlan_gvrp_init_applicant(real_dev); if (err < 0) goto out_vid_del; err = vlan_mvrp_init_applicant(real_dev); if (err < 0) goto out_uninit_gvrp; } err = vlan_group_prealloc_vid(grp, vlan->vlan_proto, vlan_id); if (err < 0) goto out_uninit_mvrp; err = register_netdevice(dev); if (err < 0) goto out_uninit_mvrp; err = netdev_upper_dev_link(real_dev, dev, extack); if (err) goto out_unregister_netdev; vlan_stacked_transfer_operstate(real_dev, dev, vlan); linkwatch_fire_event(dev); /* _MUST_ call rfc2863_policy() */ /* So, got the sucker initialized, now lets place * it into our local structure. */ vlan_group_set_device(grp, vlan->vlan_proto, vlan_id, dev); grp->nr_vlan_devs++; return 0; out_unregister_netdev: unregister_netdevice(dev); out_uninit_mvrp: if (grp->nr_vlan_devs == 0) vlan_mvrp_uninit_applicant(real_dev); out_uninit_gvrp: if (grp->nr_vlan_devs == 0) vlan_gvrp_uninit_applicant(real_dev); out_vid_del: vlan_vid_del(real_dev, vlan->vlan_proto, vlan_id); return err; } /* Attach a VLAN device to a mac address (ie Ethernet Card). * Returns 0 if the device was created or a negative error code otherwise. */ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id) { struct net_device *new_dev; struct vlan_dev_priv *vlan; struct net *net = dev_net(real_dev); struct vlan_net *vn = net_generic(net, vlan_net_id); char name[IFNAMSIZ]; int err; if (vlan_id >= VLAN_VID_MASK) return -ERANGE; err = vlan_check_real_dev(real_dev, htons(ETH_P_8021Q), vlan_id, NULL); if (err < 0) return err; /* Gotta set up the fields for the device. */ switch (vn->name_type) { case VLAN_NAME_TYPE_RAW_PLUS_VID: /* name will look like: eth1.0005 */ snprintf(name, IFNAMSIZ, "%s.%.4i", real_dev->name, vlan_id); break; case VLAN_NAME_TYPE_PLUS_VID_NO_PAD: /* Put our vlan.VID in the name. * Name will look like: vlan5 */ snprintf(name, IFNAMSIZ, "vlan%i", vlan_id); break; case VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD: /* Put our vlan.VID in the name. * Name will look like: eth0.5 */ snprintf(name, IFNAMSIZ, "%s.%i", real_dev->name, vlan_id); break; case VLAN_NAME_TYPE_PLUS_VID: /* Put our vlan.VID in the name. * Name will look like: vlan0005 */ default: snprintf(name, IFNAMSIZ, "vlan%.4i", vlan_id); } new_dev = alloc_netdev(sizeof(struct vlan_dev_priv), name, NET_NAME_UNKNOWN, vlan_setup); if (new_dev == NULL) return -ENOBUFS; dev_net_set(new_dev, net); /* need 4 bytes for extra VLAN header info, * hope the underlying device can handle it. */ new_dev->mtu = real_dev->mtu; vlan = vlan_dev_priv(new_dev); vlan->vlan_proto = htons(ETH_P_8021Q); vlan->vlan_id = vlan_id; vlan->real_dev = real_dev; vlan->dent = NULL; vlan->flags = VLAN_FLAG_REORDER_HDR; new_dev->rtnl_link_ops = &vlan_link_ops; err = register_vlan_dev(new_dev, NULL); if (err < 0) goto out_free_newdev; return 0; out_free_newdev: free_netdev(new_dev); return err; } static void vlan_sync_address(struct net_device *dev, struct net_device *vlandev) { struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev); /* May be called without an actual change */ if (ether_addr_equal(vlan->real_dev_addr, dev->dev_addr)) return; /* vlan continues to inherit address of lower device */ if (vlan_dev_inherit_address(vlandev, dev)) goto out; /* vlan address was different from the old address and is equal to * the new address */ if (!ether_addr_equal(vlandev->dev_addr, vlan->real_dev_addr) && ether_addr_equal(vlandev->dev_addr, dev->dev_addr)) dev_uc_del(dev, vlandev->dev_addr); /* vlan address was equal to the old address and is different from * the new address */ if (ether_addr_equal(vlandev->dev_addr, vlan->real_dev_addr) && !ether_addr_equal(vlandev->dev_addr, dev->dev_addr)) dev_uc_add(dev, vlandev->dev_addr); out: ether_addr_copy(vlan->real_dev_addr, dev->dev_addr); } static void vlan_transfer_features(struct net_device *dev, struct net_device *vlandev) { struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev); netif_inherit_tso_max(vlandev, dev); if (vlan_hw_offload_capable(dev->features, vlan->vlan_proto)) vlandev->hard_header_len = dev->hard_header_len; else vlandev->hard_header_len = dev->hard_header_len + VLAN_HLEN; #if IS_ENABLED(CONFIG_FCOE) vlandev->fcoe_ddp_xid = dev->fcoe_ddp_xid; #endif vlandev->priv_flags &= ~IFF_XMIT_DST_RELEASE; vlandev->priv_flags |= (vlan->real_dev->priv_flags & IFF_XMIT_DST_RELEASE); vlandev->hw_enc_features = vlan_tnl_features(vlan->real_dev); netdev_update_features(vlandev); } static int __vlan_device_event(struct net_device *dev, unsigned long event) { int err = 0; switch (event) { case NETDEV_CHANGENAME: vlan_proc_rem_dev(dev); err = vlan_proc_add_dev(dev); break; case NETDEV_REGISTER: err = vlan_proc_add_dev(dev); break; case NETDEV_UNREGISTER: vlan_proc_rem_dev(dev); break; } return err; } static int vlan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr); struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct vlan_group *grp; struct vlan_info *vlan_info; int i, flgs; struct net_device *vlandev; struct vlan_dev_priv *vlan; bool last = false; LIST_HEAD(list); int err; if (is_vlan_dev(dev)) { int err = __vlan_device_event(dev, event); if (err) return notifier_from_errno(err); } if ((event == NETDEV_UP) && (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) { pr_info("adding VLAN 0 to HW filter on device %s\n", dev->name); vlan_vid_add(dev, htons(ETH_P_8021Q), 0); } if (event == NETDEV_DOWN && (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) vlan_vid_del(dev, htons(ETH_P_8021Q), 0); vlan_info = rtnl_dereference(dev->vlan_info); if (!vlan_info) goto out; grp = &vlan_info->grp; /* It is OK that we do not hold the group lock right now, * as we run under the RTNL lock. */ switch (event) { case NETDEV_CHANGE: /* Propagate real device state to vlan devices */ vlan_group_for_each_dev(grp, i, vlandev) vlan_stacked_transfer_operstate(dev, vlandev, vlan_dev_priv(vlandev)); break; case NETDEV_CHANGEADDR: /* Adjust unicast filters on underlying device */ vlan_group_for_each_dev(grp, i, vlandev) { flgs = vlandev->flags; if (!(flgs & IFF_UP)) continue; vlan_sync_address(dev, vlandev); } break; case NETDEV_CHANGEMTU: vlan_group_for_each_dev(grp, i, vlandev) { if (vlandev->mtu <= dev->mtu) continue; dev_set_mtu(vlandev, dev->mtu); } break; case NETDEV_FEAT_CHANGE: /* Propagate device features to underlying device */ vlan_group_for_each_dev(grp, i, vlandev) vlan_transfer_features(dev, vlandev); break; case NETDEV_DOWN: { struct net_device *tmp; LIST_HEAD(close_list); /* Put all VLANs for this dev in the down state too. */ vlan_group_for_each_dev(grp, i, vlandev) { flgs = vlandev->flags; if (!(flgs & IFF_UP)) continue; vlan = vlan_dev_priv(vlandev); if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) list_add(&vlandev->close_list, &close_list); } dev_close_many(&close_list, false); list_for_each_entry_safe(vlandev, tmp, &close_list, close_list) { vlan_stacked_transfer_operstate(dev, vlandev, vlan_dev_priv(vlandev)); list_del_init(&vlandev->close_list); } list_del(&close_list); break; } case NETDEV_UP: /* Put all VLANs for this dev in the up state too. */ vlan_group_for_each_dev(grp, i, vlandev) { flgs = dev_get_flags(vlandev); if (flgs & IFF_UP) continue; vlan = vlan_dev_priv(vlandev); if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) dev_change_flags(vlandev, flgs | IFF_UP, extack); vlan_stacked_transfer_operstate(dev, vlandev, vlan); } break; case NETDEV_UNREGISTER: /* twiddle thumbs on netns device moves */ if (dev->reg_state != NETREG_UNREGISTERING) break; vlan_group_for_each_dev(grp, i, vlandev) { /* removal of last vid destroys vlan_info, abort * afterwards */ if (vlan_info->nr_vids == 1) last = true; unregister_vlan_dev(vlandev, &list); if (last) break; } unregister_netdevice_many(&list); break; case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlaying device to change its type. */ if (vlan_uses_dev(dev)) return NOTIFY_BAD; break; case NETDEV_NOTIFY_PEERS: case NETDEV_BONDING_FAILOVER: case NETDEV_RESEND_IGMP: /* Propagate to vlan devices */ vlan_group_for_each_dev(grp, i, vlandev) call_netdevice_notifiers(event, vlandev); break; case NETDEV_CVLAN_FILTER_PUSH_INFO: err = vlan_filter_push_vids(vlan_info, htons(ETH_P_8021Q)); if (err) return notifier_from_errno(err); break; case NETDEV_CVLAN_FILTER_DROP_INFO: vlan_filter_drop_vids(vlan_info, htons(ETH_P_8021Q)); break; case NETDEV_SVLAN_FILTER_PUSH_INFO: err = vlan_filter_push_vids(vlan_info, htons(ETH_P_8021AD)); if (err) return notifier_from_errno(err); break; case NETDEV_SVLAN_FILTER_DROP_INFO: vlan_filter_drop_vids(vlan_info, htons(ETH_P_8021AD)); break; } out: return NOTIFY_DONE; } static struct notifier_block vlan_notifier_block __read_mostly = { .notifier_call = vlan_device_event, }; /* * VLAN IOCTL handler. * o execute requested action or pass command to the device driver * arg is really a struct vlan_ioctl_args __user *. */ static int vlan_ioctl_handler(struct net *net, void __user *arg) { int err; struct vlan_ioctl_args args; struct net_device *dev = NULL; if (copy_from_user(&args, arg, sizeof(struct vlan_ioctl_args))) return -EFAULT; /* Null terminate this sucker, just in case. */ args.device1[sizeof(args.device1) - 1] = 0; args.u.device2[sizeof(args.u.device2) - 1] = 0; rtnl_lock(); switch (args.cmd) { case SET_VLAN_INGRESS_PRIORITY_CMD: case SET_VLAN_EGRESS_PRIORITY_CMD: case SET_VLAN_FLAG_CMD: case ADD_VLAN_CMD: case DEL_VLAN_CMD: case GET_VLAN_REALDEV_NAME_CMD: case GET_VLAN_VID_CMD: err = -ENODEV; dev = __dev_get_by_name(net, args.device1); if (!dev) goto out; err = -EINVAL; if (args.cmd != ADD_VLAN_CMD && !is_vlan_dev(dev)) goto out; } switch (args.cmd) { case SET_VLAN_INGRESS_PRIORITY_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; vlan_dev_set_ingress_priority(dev, args.u.skb_priority, args.vlan_qos); err = 0; break; case SET_VLAN_EGRESS_PRIORITY_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = vlan_dev_set_egress_priority(dev, args.u.skb_priority, args.vlan_qos); break; case SET_VLAN_FLAG_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = vlan_dev_change_flags(dev, args.vlan_qos ? args.u.flag : 0, args.u.flag); break; case SET_VLAN_NAME_TYPE_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; if (args.u.name_type < VLAN_NAME_TYPE_HIGHEST) { struct vlan_net *vn; vn = net_generic(net, vlan_net_id); vn->name_type = args.u.name_type; err = 0; } else { err = -EINVAL; } break; case ADD_VLAN_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = register_vlan_device(dev, args.u.VID); break; case DEL_VLAN_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; unregister_vlan_dev(dev, NULL); err = 0; break; case GET_VLAN_REALDEV_NAME_CMD: err = 0; vlan_dev_get_realdev_name(dev, args.u.device2, sizeof(args.u.device2)); if (copy_to_user(arg, &args, sizeof(struct vlan_ioctl_args))) err = -EFAULT; break; case GET_VLAN_VID_CMD: err = 0; args.u.VID = vlan_dev_vlan_id(dev); if (copy_to_user(arg, &args, sizeof(struct vlan_ioctl_args))) err = -EFAULT; break; default: err = -EOPNOTSUPP; break; } out: rtnl_unlock(); return err; } static int __net_init vlan_init_net(struct net *net) { struct vlan_net *vn = net_generic(net, vlan_net_id); int err; vn->name_type = VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD; err = vlan_proc_init(net); return err; } static void __net_exit vlan_exit_net(struct net *net) { vlan_proc_cleanup(net); } static struct pernet_operations vlan_net_ops = { .init = vlan_init_net, .exit = vlan_exit_net, .id = &vlan_net_id, .size = sizeof(struct vlan_net), }; static int __init vlan_proto_init(void) { int err; pr_info("%s v%s\n", vlan_fullname, vlan_version); err = register_pernet_subsys(&vlan_net_ops); if (err < 0) goto err0; err = register_netdevice_notifier(&vlan_notifier_block); if (err < 0) goto err2; err = vlan_gvrp_init(); if (err < 0) goto err3; err = vlan_mvrp_init(); if (err < 0) goto err4; err = vlan_netlink_init(); if (err < 0) goto err5; vlan_ioctl_set(vlan_ioctl_handler); return 0; err5: vlan_mvrp_uninit(); err4: vlan_gvrp_uninit(); err3: unregister_netdevice_notifier(&vlan_notifier_block); err2: unregister_pernet_subsys(&vlan_net_ops); err0: return err; } static void __exit vlan_cleanup_module(void) { vlan_ioctl_set(NULL); vlan_netlink_fini(); unregister_netdevice_notifier(&vlan_notifier_block); unregister_pernet_subsys(&vlan_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ vlan_mvrp_uninit(); vlan_gvrp_uninit(); } module_init(vlan_proto_init); module_exit(vlan_cleanup_module); MODULE_DESCRIPTION("802.1Q/802.1ad VLAN Protocol"); MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_VERSION); |
| 17 14 | 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 | #ifndef INTERNAL_IO_SLIST_H #define INTERNAL_IO_SLIST_H #include <linux/io_uring_types.h> #define __wq_list_for_each(pos, head) \ for (pos = (head)->first; pos; pos = (pos)->next) #define wq_list_for_each(pos, prv, head) \ for (pos = (head)->first, prv = NULL; pos; prv = pos, pos = (pos)->next) #define wq_list_for_each_resume(pos, prv) \ for (; pos; prv = pos, pos = (pos)->next) #define wq_list_empty(list) (READ_ONCE((list)->first) == NULL) #define INIT_WQ_LIST(list) do { \ (list)->first = NULL; \ } while (0) static inline void wq_list_add_after(struct io_wq_work_node *node, struct io_wq_work_node *pos, struct io_wq_work_list *list) { struct io_wq_work_node *next = pos->next; pos->next = node; node->next = next; if (!next) list->last = node; } static inline void wq_list_add_tail(struct io_wq_work_node *node, struct io_wq_work_list *list) { node->next = NULL; if (!list->first) { list->last = node; WRITE_ONCE(list->first, node); } else { list->last->next = node; list->last = node; } } static inline void wq_list_add_head(struct io_wq_work_node *node, struct io_wq_work_list *list) { node->next = list->first; if (!node->next) list->last = node; WRITE_ONCE(list->first, node); } static inline void wq_list_cut(struct io_wq_work_list *list, struct io_wq_work_node *last, struct io_wq_work_node *prev) { /* first in the list, if prev==NULL */ if (!prev) WRITE_ONCE(list->first, last->next); else prev->next = last->next; if (last == list->last) list->last = prev; last->next = NULL; } static inline void __wq_list_splice(struct io_wq_work_list *list, struct io_wq_work_node *to) { list->last->next = to->next; to->next = list->first; INIT_WQ_LIST(list); } static inline bool wq_list_splice(struct io_wq_work_list *list, struct io_wq_work_node *to) { if (!wq_list_empty(list)) { __wq_list_splice(list, to); return true; } return false; } static inline void wq_stack_add_head(struct io_wq_work_node *node, struct io_wq_work_node *stack) { node->next = stack->next; stack->next = node; } static inline void wq_list_del(struct io_wq_work_list *list, struct io_wq_work_node *node, struct io_wq_work_node *prev) { wq_list_cut(list, node, prev); } static inline struct io_wq_work_node *wq_stack_extract(struct io_wq_work_node *stack) { struct io_wq_work_node *node = stack->next; stack->next = node->next; return node; } static inline struct io_wq_work *wq_next_work(struct io_wq_work *work) { if (!work->list.next) return NULL; return container_of(work->list.next, struct io_wq_work, list); } #endif // INTERNAL_IO_SLIST_H |
| 3 6536 6542 270 5446 5477 271 271 272 272 272 271 270 272 11 267 11 268 272 271 269 272 5861 5873 269 269 4 4 4 4 4 4 4 4 4 4 2 2 2 2 2 2 2 2 2 2 2 3 3 3 3 3 3 3 3 3 11 11 11 4 4 5800 5782 5860 5873 269 5864 5864 5860 5857 713 5873 5865 5860 348 5859 5860 372 371 5687 5694 2139 2132 2142 2138 | 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 | // 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; pr_info_once("blkio.%s is deprecated\n", cftype->name); 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), false); 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; } /* * Similar to blkg_conf_open_bdev, but additionally freezes the queue, * acquires q->elevator_lock, and ensures the correct locking order * between q->elevator_lock and q->rq_qos_mutex. * * This function returns negative error on failure. On success it returns * memflags which must be saved and later passed to blkg_conf_exit_frozen * for restoring the memalloc scope. */ unsigned long __must_check blkg_conf_open_bdev_frozen(struct blkg_conf_ctx *ctx) { int ret; unsigned long memflags; if (ctx->bdev) return -EINVAL; ret = blkg_conf_open_bdev(ctx); if (ret < 0) return ret; /* * At this point, we haven’t started protecting anything related to QoS, * so we release q->rq_qos_mutex here, which was first acquired in blkg_ * conf_open_bdev. Later, we re-acquire q->rq_qos_mutex after freezing * the queue and acquiring q->elevator_lock to maintain the correct * locking order. */ mutex_unlock(&ctx->bdev->bd_queue->rq_qos_mutex); memflags = blk_mq_freeze_queue(ctx->bdev->bd_queue); mutex_lock(&ctx->bdev->bd_queue->elevator_lock); mutex_lock(&ctx->bdev->bd_queue->rq_qos_mutex); return memflags; } /** * 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); /* * Similar to blkg_conf_exit, but also unfreezes the queue and releases * q->elevator_lock. Should be used when blkg_conf_open_bdev_frozen * is used to open the bdev. */ void blkg_conf_exit_frozen(struct blkg_conf_ctx *ctx, unsigned long memflags) { if (ctx->bdev) { struct request_queue *q = ctx->bdev->bd_queue; blkg_conf_exit(ctx); mutex_unlock(&q->elevator_lock); blk_mq_unfreeze_queue(q, memflags); } } 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); } class_dev_iter_exit(&iter); } 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; unsigned int memflags; 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)) memflags = 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, memflags); 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; unsigned int memflags; if (!blkcg_policy_enabled(q, pol)) return; if (queue_is_mq(q)) memflags = 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, memflags); } 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; /* * 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)) return -EINVAL; mutex_lock(&blkcg_pol_register_mutex); mutex_lock(&blkcg_pol_mutex); /* find an empty slot */ 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"); ret = -ENOSPC; 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) { ret = -ENOMEM; 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 == pol->legacy_cftypes) { WARN_ON(cgroup_add_cftypes(&io_cgrp_subsys, pol->dfl_cftypes)); } else { WARN_ON(cgroup_add_dfl_cftypes(&io_cgrp_subsys, pol->dfl_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"); |
| 11724 11724 2363 12 5 20 1774 1776 10 2 2 2 2059 44 2368 11722 379 3 593 11716 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_CPUMASK_H #define __LINUX_CPUMASK_H /* * Cpumasks provide a bitmap suitable for representing the * set of CPUs in a system, one bit position per CPU number. In general, * only nr_cpu_ids (<= NR_CPUS) bits are valid. */ #include <linux/cleanup.h> #include <linux/kernel.h> #include <linux/bitmap.h> #include <linux/cpumask_types.h> #include <linux/atomic.h> #include <linux/bug.h> #include <linux/gfp_types.h> #include <linux/numa.h> /** * cpumask_pr_args - printf args to output a cpumask * @maskp: cpumask to be printed * * Can be used to provide arguments for '%*pb[l]' when printing a cpumask. */ #define cpumask_pr_args(maskp) nr_cpu_ids, cpumask_bits(maskp) #if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) #define nr_cpu_ids ((unsigned int)NR_CPUS) #else extern unsigned int nr_cpu_ids; #endif static __always_inline void set_nr_cpu_ids(unsigned int nr) { #if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) WARN_ON(nr != nr_cpu_ids); #else nr_cpu_ids = nr; #endif } /* * We have several different "preferred sizes" for the cpumask * operations, depending on operation. * * For example, the bitmap scanning and operating operations have * optimized routines that work for the single-word case, but only when * the size is constant. So if NR_CPUS fits in one single word, we are * better off using that small constant, in order to trigger the * optimized bit finding. That is 'small_cpumask_size'. * * The clearing and copying operations will similarly perform better * with a constant size, but we limit that size arbitrarily to four * words. We call this 'large_cpumask_size'. * * Finally, some operations just want the exact limit, either because * they set bits or just don't have any faster fixed-sized versions. We * call this just 'nr_cpumask_bits'. * * Note that these optional constants are always guaranteed to be at * least as big as 'nr_cpu_ids' itself is, and all our cpumask * allocations are at least that size (see cpumask_size()). The * optimization comes from being able to potentially use a compile-time * constant instead of a run-time generated exact number of CPUs. */ #if NR_CPUS <= BITS_PER_LONG #define small_cpumask_bits ((unsigned int)NR_CPUS) #define large_cpumask_bits ((unsigned int)NR_CPUS) #elif NR_CPUS <= 4*BITS_PER_LONG #define small_cpumask_bits nr_cpu_ids #define large_cpumask_bits ((unsigned int)NR_CPUS) #else #define small_cpumask_bits nr_cpu_ids #define large_cpumask_bits nr_cpu_ids #endif #define nr_cpumask_bits nr_cpu_ids /* * The following particular system cpumasks and operations manage * possible, present, active and online cpus. * * cpu_possible_mask- has bit 'cpu' set iff cpu is populatable * cpu_present_mask - has bit 'cpu' set iff cpu is populated * cpu_enabled_mask - has bit 'cpu' set iff cpu can be brought online * cpu_online_mask - has bit 'cpu' set iff cpu available to scheduler * cpu_active_mask - has bit 'cpu' set iff cpu available to migration * * If !CONFIG_HOTPLUG_CPU, present == possible, and active == online. * * The cpu_possible_mask is fixed at boot time, as the set of CPU IDs * that it is possible might ever be plugged in at anytime during the * life of that system boot. The cpu_present_mask is dynamic(*), * representing which CPUs are currently plugged in. And * cpu_online_mask is the dynamic subset of cpu_present_mask, * indicating those CPUs available for scheduling. * * If HOTPLUG is enabled, then cpu_present_mask varies dynamically, * depending on what ACPI reports as currently plugged in, otherwise * cpu_present_mask is just a copy of cpu_possible_mask. * * (*) Well, cpu_present_mask is dynamic in the hotplug case. If not * hotplug, it's a copy of cpu_possible_mask, hence fixed at boot. * * Subtleties: * 1) UP ARCHes (NR_CPUS == 1, CONFIG_SMP not defined) hardcode * assumption that their single CPU is online. The UP * cpu_{online,possible,present}_masks are placebos. Changing them * will have no useful affect on the following num_*_cpus() * and cpu_*() macros in the UP case. This ugliness is a UP * optimization - don't waste any instructions or memory references * asking if you're online or how many CPUs there are if there is * only one CPU. */ extern struct cpumask __cpu_possible_mask; extern struct cpumask __cpu_online_mask; extern struct cpumask __cpu_enabled_mask; extern struct cpumask __cpu_present_mask; extern struct cpumask __cpu_active_mask; extern struct cpumask __cpu_dying_mask; #define cpu_possible_mask ((const struct cpumask *)&__cpu_possible_mask) #define cpu_online_mask ((const struct cpumask *)&__cpu_online_mask) #define cpu_enabled_mask ((const struct cpumask *)&__cpu_enabled_mask) #define cpu_present_mask ((const struct cpumask *)&__cpu_present_mask) #define cpu_active_mask ((const struct cpumask *)&__cpu_active_mask) #define cpu_dying_mask ((const struct cpumask *)&__cpu_dying_mask) extern atomic_t __num_online_cpus; extern cpumask_t cpus_booted_once_mask; static __always_inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits) { #ifdef CONFIG_DEBUG_PER_CPU_MAPS WARN_ON_ONCE(cpu >= bits); #endif /* CONFIG_DEBUG_PER_CPU_MAPS */ } /* verify cpu argument to cpumask_* operators */ static __always_inline unsigned int cpumask_check(unsigned int cpu) { cpu_max_bits_warn(cpu, small_cpumask_bits); return cpu; } /** * cpumask_first - get the first cpu in a cpumask * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if no cpus set. */ static __always_inline unsigned int cpumask_first(const struct cpumask *srcp) { return find_first_bit(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_first_zero - get the first unset cpu in a cpumask * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if all cpus are set. */ static __always_inline unsigned int cpumask_first_zero(const struct cpumask *srcp) { return find_first_zero_bit(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_first_and - return the first cpu from *srcp1 & *srcp2 * @srcp1: the first input * @srcp2: the second input * * Return: >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). */ static __always_inline unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } /** * cpumask_first_and_and - return the first cpu from *srcp1 & *srcp2 & *srcp3 * @srcp1: the first input * @srcp2: the second input * @srcp3: the third input * * Return: >= nr_cpu_ids if no cpus set in all. */ static __always_inline unsigned int cpumask_first_and_and(const struct cpumask *srcp1, const struct cpumask *srcp2, const struct cpumask *srcp3) { return find_first_and_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), cpumask_bits(srcp3), small_cpumask_bits); } /** * cpumask_last - get the last CPU in a cpumask * @srcp: - the cpumask pointer * * Return: >= nr_cpumask_bits if no CPUs set. */ static __always_inline unsigned int cpumask_last(const struct cpumask *srcp) { return find_last_bit(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_next - get the next cpu in a cpumask * @n: the cpu prior to the place to search (i.e. return will be > @n) * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if no further cpus set. */ static __always_inline unsigned int cpumask_next(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_bit(cpumask_bits(srcp), small_cpumask_bits, n + 1); } /** * cpumask_next_zero - get the next unset cpu in a cpumask * @n: the cpu prior to the place to search (i.e. return will be > @n) * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if no further cpus unset. */ static __always_inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_zero_bit(cpumask_bits(srcp), small_cpumask_bits, n+1); } #if NR_CPUS == 1 /* Uniprocessor: there is only one valid CPU */ static __always_inline unsigned int cpumask_local_spread(unsigned int i, int node) { return 0; } static __always_inline unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p) { return cpumask_first_and(src1p, src2p); } static __always_inline unsigned int cpumask_any_distribute(const struct cpumask *srcp) { return cpumask_first(srcp); } #else unsigned int cpumask_local_spread(unsigned int i, int node); unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p); unsigned int cpumask_any_distribute(const struct cpumask *srcp); #endif /* NR_CPUS */ /** * cpumask_next_and - get the next cpu in *src1p & *src2p * @n: the cpu prior to the place to search (i.e. return will be > @n) * @src1p: the first cpumask pointer * @src2p: the second cpumask pointer * * Return: >= nr_cpu_ids if no further cpus set in both. */ static __always_inline unsigned int cpumask_next_and(int n, const struct cpumask *src1p, const struct cpumask *src2p) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits, n + 1); } /** * cpumask_next_and_wrap - get the next cpu in *src1p & *src2p, starting from * @n+1. If nothing found, wrap around and start from * the beginning * @n: the cpu prior to the place to search (i.e. search starts from @n+1) * @src1p: the first cpumask pointer * @src2p: the second cpumask pointer * * Return: next set bit, wrapped if needed, or >= nr_cpu_ids if @src1p & @src2p is empty. */ static __always_inline unsigned int cpumask_next_and_wrap(int n, const struct cpumask *src1p, const struct cpumask *src2p) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_and_bit_wrap(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits, n + 1); } /** * cpumask_next_wrap - get the next cpu in *src, starting from @n+1. If nothing * found, wrap around and start from the beginning * @n: the cpu prior to the place to search (i.e. search starts from @n+1) * @src: cpumask pointer * * Return: next set bit, wrapped if needed, or >= nr_cpu_ids if @src is empty. */ static __always_inline unsigned int cpumask_next_wrap(int n, const struct cpumask *src) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_bit_wrap(cpumask_bits(src), small_cpumask_bits, n + 1); } /** * for_each_cpu - iterate over every cpu in a mask * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu(cpu, mask) \ for_each_set_bit(cpu, cpumask_bits(mask), small_cpumask_bits) /** * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer * @start: the start location * * The implementation does not assume any bit in @mask is set (including @start). * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_wrap(cpu, mask, start) \ for_each_set_bit_wrap(cpu, cpumask_bits(mask), small_cpumask_bits, start) /** * for_each_cpu_and - iterate over every cpu in both masks * @cpu: the (optionally unsigned) integer iterator * @mask1: the first cpumask pointer * @mask2: the second cpumask pointer * * This saves a temporary CPU mask in many places. It is equivalent to: * struct cpumask tmp; * cpumask_and(&tmp, &mask1, &mask2); * for_each_cpu(cpu, &tmp) * ... * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_and(cpu, mask1, mask2) \ for_each_and_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) /** * for_each_cpu_andnot - iterate over every cpu present in one mask, excluding * those present in another. * @cpu: the (optionally unsigned) integer iterator * @mask1: the first cpumask pointer * @mask2: the second cpumask pointer * * This saves a temporary CPU mask in many places. It is equivalent to: * struct cpumask tmp; * cpumask_andnot(&tmp, &mask1, &mask2); * for_each_cpu(cpu, &tmp) * ... * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_andnot(cpu, mask1, mask2) \ for_each_andnot_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) /** * for_each_cpu_or - iterate over every cpu present in either mask * @cpu: the (optionally unsigned) integer iterator * @mask1: the first cpumask pointer * @mask2: the second cpumask pointer * * This saves a temporary CPU mask in many places. It is equivalent to: * struct cpumask tmp; * cpumask_or(&tmp, &mask1, &mask2); * for_each_cpu(cpu, &tmp) * ... * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_or(cpu, mask1, mask2) \ for_each_or_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) /** * for_each_cpu_from - iterate over CPUs present in @mask, from @cpu to the end of @mask. * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_from(cpu, mask) \ for_each_set_bit_from(cpu, cpumask_bits(mask), small_cpumask_bits) /** * cpumask_any_but - return an arbitrary cpu in a cpumask, but not this one. * @mask: the cpumask to search * @cpu: the cpu to ignore. * * Often used to find any cpu but smp_processor_id() in a mask. * Return: >= nr_cpu_ids if no cpus set. */ static __always_inline unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) { unsigned int i; cpumask_check(cpu); for_each_cpu(i, mask) if (i != cpu) break; return i; } /** * cpumask_any_and_but - pick an arbitrary cpu from *mask1 & *mask2, but not this one. * @mask1: the first input cpumask * @mask2: the second input cpumask * @cpu: the cpu to ignore * * Returns >= nr_cpu_ids if no cpus set. */ static __always_inline unsigned int cpumask_any_and_but(const struct cpumask *mask1, const struct cpumask *mask2, unsigned int cpu) { unsigned int i; cpumask_check(cpu); i = cpumask_first_and(mask1, mask2); if (i != cpu) return i; return cpumask_next_and(cpu, mask1, mask2); } /** * cpumask_nth - get the Nth cpu in a cpumask * @srcp: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp) { return find_nth_bit(cpumask_bits(srcp), small_cpumask_bits, cpumask_check(cpu)); } /** * cpumask_nth_and - get the Nth cpu in 2 cpumasks * @srcp1: the cpumask pointer * @srcp2: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_nth_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits, cpumask_check(cpu)); } /** * cpumask_nth_andnot - get the Nth cpu set in 1st cpumask, and clear in 2nd. * @srcp1: the cpumask pointer * @srcp2: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_nth_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits, cpumask_check(cpu)); } /** * cpumask_nth_and_andnot - get the Nth cpu set in 1st and 2nd cpumask, and clear in 3rd. * @srcp1: the cpumask pointer * @srcp2: the cpumask pointer * @srcp3: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth_and_andnot(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2, const struct cpumask *srcp3) { return find_nth_and_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), cpumask_bits(srcp3), small_cpumask_bits, cpumask_check(cpu)); } #define CPU_BITS_NONE \ { \ [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ } #define CPU_BITS_CPU0 \ { \ [0] = 1UL \ } /** * cpumask_set_cpu - set a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ static __always_inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } static __always_inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { __set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } /** * cpumask_clear_cpu - clear a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ static __always_inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp) { clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } static __always_inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp) { __clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } /** * cpumask_assign_cpu - assign a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer * @bool: the value to assign */ static __always_inline void cpumask_assign_cpu(int cpu, struct cpumask *dstp, bool value) { assign_bit(cpumask_check(cpu), cpumask_bits(dstp), value); } static __always_inline void __cpumask_assign_cpu(int cpu, struct cpumask *dstp, bool value) { __assign_bit(cpumask_check(cpu), cpumask_bits(dstp), value); } /** * cpumask_test_cpu - test for a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * Return: true if @cpu is set in @cpumask, else returns false */ static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask) { return test_bit(cpumask_check(cpu), cpumask_bits((cpumask))); } /** * cpumask_test_and_set_cpu - atomically test and set a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * test_and_set_bit wrapper for cpumasks. * * Return: true if @cpu is set in old bitmap of @cpumask, else returns false */ static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) { return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } /** * cpumask_test_and_clear_cpu - atomically test and clear a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * test_and_clear_bit wrapper for cpumasks. * * Return: true if @cpu is set in old bitmap of @cpumask, else returns false */ static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) { return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } /** * cpumask_setall - set all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ static __always_inline void cpumask_setall(struct cpumask *dstp) { if (small_const_nbits(small_cpumask_bits)) { cpumask_bits(dstp)[0] = BITMAP_LAST_WORD_MASK(nr_cpumask_bits); return; } bitmap_fill(cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_clear - clear all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ static __always_inline void cpumask_clear(struct cpumask *dstp) { bitmap_zero(cpumask_bits(dstp), large_cpumask_bits); } /** * cpumask_and - *dstp = *src1p & *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input * * Return: false if *@dstp is empty, else returns true */ static __always_inline bool cpumask_and(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_or - *dstp = *src1p | *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input */ static __always_inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { bitmap_or(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_xor - *dstp = *src1p ^ *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input */ static __always_inline void cpumask_xor(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { bitmap_xor(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_andnot - *dstp = *src1p & ~*src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input * * Return: false if *@dstp is empty, else returns true */ static __always_inline bool cpumask_andnot(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_equal - *src1p == *src2p * @src1p: the first input * @src2p: the second input * * Return: true if the cpumasks are equal, false if not */ static __always_inline bool cpumask_equal(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_equal(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_or_equal - *src1p | *src2p == *src3p * @src1p: the first input * @src2p: the second input * @src3p: the third input * * Return: true if first cpumask ORed with second cpumask == third cpumask, * otherwise false */ static __always_inline bool cpumask_or_equal(const struct cpumask *src1p, const struct cpumask *src2p, const struct cpumask *src3p) { return bitmap_or_equal(cpumask_bits(src1p), cpumask_bits(src2p), cpumask_bits(src3p), small_cpumask_bits); } /** * cpumask_intersects - (*src1p & *src2p) != 0 * @src1p: the first input * @src2p: the second input * * Return: true if first cpumask ANDed with second cpumask is non-empty, * otherwise false */ static __always_inline bool cpumask_intersects(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_intersects(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_subset - (*src1p & ~*src2p) == 0 * @src1p: the first input * @src2p: the second input * * Return: true if *@src1p is a subset of *@src2p, else returns false */ static __always_inline bool cpumask_subset(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_empty - *srcp == 0 * @srcp: the cpumask to that all cpus < nr_cpu_ids are clear. * * Return: true if srcp is empty (has no bits set), else false */ static __always_inline bool cpumask_empty(const struct cpumask *srcp) { return bitmap_empty(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_full - *srcp == 0xFFFFFFFF... * @srcp: the cpumask to that all cpus < nr_cpu_ids are set. * * Return: true if srcp is full (has all bits set), else false */ static __always_inline bool cpumask_full(const struct cpumask *srcp) { return bitmap_full(cpumask_bits(srcp), nr_cpumask_bits); } /** * cpumask_weight - Count of bits in *srcp * @srcp: the cpumask to count bits (< nr_cpu_ids) in. * * Return: count of bits set in *srcp */ static __always_inline unsigned int cpumask_weight(const struct cpumask *srcp) { return bitmap_weight(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_weight_and - Count of bits in (*srcp1 & *srcp2) * @srcp1: the cpumask to count bits (< nr_cpu_ids) in. * @srcp2: the cpumask to count bits (< nr_cpu_ids) in. * * Return: count of bits set in both *srcp1 and *srcp2 */ static __always_inline unsigned int cpumask_weight_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } /** * cpumask_weight_andnot - Count of bits in (*srcp1 & ~*srcp2) * @srcp1: the cpumask to count bits (< nr_cpu_ids) in. * @srcp2: the cpumask to count bits (< nr_cpu_ids) in. * * Return: count of bits set in both *srcp1 and *srcp2 */ static __always_inline unsigned int cpumask_weight_andnot(const struct cpumask *srcp1, const struct cpumask *srcp2) { return bitmap_weight_andnot(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } /** * cpumask_shift_right - *dstp = *srcp >> n * @dstp: the cpumask result * @srcp: the input to shift * @n: the number of bits to shift by */ static __always_inline void cpumask_shift_right(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_right(cpumask_bits(dstp), cpumask_bits(srcp), n, small_cpumask_bits); } /** * cpumask_shift_left - *dstp = *srcp << n * @dstp: the cpumask result * @srcp: the input to shift * @n: the number of bits to shift by */ static __always_inline void cpumask_shift_left(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_left(cpumask_bits(dstp), cpumask_bits(srcp), n, nr_cpumask_bits); } /** * cpumask_copy - *dstp = *srcp * @dstp: the result * @srcp: the input cpumask */ static __always_inline void cpumask_copy(struct cpumask *dstp, const struct cpumask *srcp) { bitmap_copy(cpumask_bits(dstp), cpumask_bits(srcp), large_cpumask_bits); } /** * cpumask_any - pick an arbitrary cpu from *srcp * @srcp: the input cpumask * * Return: >= nr_cpu_ids if no cpus set. */ #define cpumask_any(srcp) cpumask_first(srcp) /** * cpumask_any_and - pick an arbitrary cpu from *mask1 & *mask2 * @mask1: the first input cpumask * @mask2: the second input cpumask * * Return: >= nr_cpu_ids if no cpus set. */ #define cpumask_any_and(mask1, mask2) cpumask_first_and((mask1), (mask2)) /** * cpumask_of - the cpumask containing just a given cpu * @cpu: the cpu (<= nr_cpu_ids) */ #define cpumask_of(cpu) (get_cpu_mask(cpu)) /** * cpumask_parse_user - extract a cpumask from a user string * @buf: the buffer to extract from * @len: the length of the buffer * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpumask_parse_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_parselist_user - extract a cpumask from a user string * @buf: the buffer to extract from * @len: the length of the buffer * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpumask_parselist_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parselist_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_parse - extract a cpumask from a string * @buf: the buffer to extract from * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpumask_parse(const char *buf, struct cpumask *dstp) { return bitmap_parse(buf, UINT_MAX, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpulist_parse - extract a cpumask from a user string of ranges * @buf: the buffer to extract from * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpulist_parse(const char *buf, struct cpumask *dstp) { return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_size - calculate size to allocate for a 'struct cpumask' in bytes * * Return: size to allocate for a &struct cpumask in bytes */ static __always_inline unsigned int cpumask_size(void) { return bitmap_size(large_cpumask_bits); } #ifdef CONFIG_CPUMASK_OFFSTACK #define this_cpu_cpumask_var_ptr(x) this_cpu_read(x) #define __cpumask_var_read_mostly __read_mostly bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node); } /** * alloc_cpumask_var - allocate a struct cpumask * @mask: pointer to cpumask_var_t where the cpumask is returned * @flags: GFP_ flags * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop returning a constant 1 (in <linux/cpumask.h>). * * See alloc_cpumask_var_node. * * Return: %true if allocation succeeded, %false if not */ static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE); } static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var(mask, flags | __GFP_ZERO); } void alloc_bootmem_cpumask_var(cpumask_var_t *mask); void free_cpumask_var(cpumask_var_t mask); void free_bootmem_cpumask_var(cpumask_var_t mask); static __always_inline bool cpumask_available(cpumask_var_t mask) { return mask != NULL; } #else #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x) #define __cpumask_var_read_mostly static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return true; } static __always_inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return true; } static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { cpumask_clear(*mask); return true; } static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { cpumask_clear(*mask); return true; } static __always_inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask) { } static __always_inline void free_cpumask_var(cpumask_var_t mask) { } static __always_inline void free_bootmem_cpumask_var(cpumask_var_t mask) { } static __always_inline bool cpumask_available(cpumask_var_t mask) { return true; } #endif /* CONFIG_CPUMASK_OFFSTACK */ DEFINE_FREE(free_cpumask_var, struct cpumask *, if (_T) free_cpumask_var(_T)); /* It's common to want to use cpu_all_mask in struct member initializers, * so it has to refer to an address rather than a pointer. */ extern const DECLARE_BITMAP(cpu_all_bits, NR_CPUS); #define cpu_all_mask to_cpumask(cpu_all_bits) /* First bits of cpu_bit_bitmap are in fact unset. */ #define cpu_none_mask to_cpumask(cpu_bit_bitmap[0]) #if NR_CPUS == 1 /* Uniprocessor: the possible/online/present masks are always "1" */ #define for_each_possible_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) #define for_each_online_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) #define for_each_present_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) #define for_each_possible_cpu_wrap(cpu, start) \ for ((void)(start), (cpu) = 0; (cpu) < 1; (cpu)++) #define for_each_online_cpu_wrap(cpu, start) \ for ((void)(start), (cpu) = 0; (cpu) < 1; (cpu)++) #else #define for_each_possible_cpu(cpu) for_each_cpu((cpu), cpu_possible_mask) #define for_each_online_cpu(cpu) for_each_cpu((cpu), cpu_online_mask) #define for_each_enabled_cpu(cpu) for_each_cpu((cpu), cpu_enabled_mask) #define for_each_present_cpu(cpu) for_each_cpu((cpu), cpu_present_mask) #define for_each_possible_cpu_wrap(cpu, start) \ for_each_cpu_wrap((cpu), cpu_possible_mask, (start)) #define for_each_online_cpu_wrap(cpu, start) \ for_each_cpu_wrap((cpu), cpu_online_mask, (start)) #endif /* Wrappers for arch boot code to manipulate normally-constant masks */ void init_cpu_present(const struct cpumask *src); void init_cpu_possible(const struct cpumask *src); #define assign_cpu(cpu, mask, val) \ assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val)) #define set_cpu_possible(cpu, possible) assign_cpu((cpu), &__cpu_possible_mask, (possible)) #define set_cpu_enabled(cpu, enabled) assign_cpu((cpu), &__cpu_enabled_mask, (enabled)) #define set_cpu_present(cpu, present) assign_cpu((cpu), &__cpu_present_mask, (present)) #define set_cpu_active(cpu, active) assign_cpu((cpu), &__cpu_active_mask, (active)) #define set_cpu_dying(cpu, dying) assign_cpu((cpu), &__cpu_dying_mask, (dying)) void set_cpu_online(unsigned int cpu, bool online); /** * to_cpumask - convert a NR_CPUS bitmap to a struct cpumask * * @bitmap: the bitmap * * There are a few places where cpumask_var_t isn't appropriate and * static cpumasks must be used (eg. very early boot), yet we don't * expose the definition of 'struct cpumask'. * * This does the conversion, and can be used as a constant initializer. */ #define to_cpumask(bitmap) \ ((struct cpumask *)(1 ? (bitmap) \ : (void *)sizeof(__check_is_bitmap(bitmap)))) static __always_inline int __check_is_bitmap(const unsigned long *bitmap) { return 1; } /* * Special-case data structure for "single bit set only" constant CPU masks. * * We pre-generate all the 64 (or 32) possible bit positions, with enough * padding to the left and the right, and return the constant pointer * appropriately offset. */ extern const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)]; static __always_inline const struct cpumask *get_cpu_mask(unsigned int cpu) { const unsigned long *p = cpu_bit_bitmap[1 + cpu % BITS_PER_LONG]; p -= cpu / BITS_PER_LONG; return to_cpumask(p); } #if NR_CPUS > 1 /** * num_online_cpus() - Read the number of online CPUs * * Despite the fact that __num_online_cpus is of type atomic_t, this * interface gives only a momentary snapshot and is not protected against * concurrent CPU hotplug operations unless invoked from a cpuhp_lock held * region. * * Return: momentary snapshot of the number of online CPUs */ static __always_inline unsigned int num_online_cpus(void) { return raw_atomic_read(&__num_online_cpus); } #define num_possible_cpus() cpumask_weight(cpu_possible_mask) #define num_enabled_cpus() cpumask_weight(cpu_enabled_mask) #define num_present_cpus() cpumask_weight(cpu_present_mask) #define num_active_cpus() cpumask_weight(cpu_active_mask) static __always_inline bool cpu_online(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_online_mask); } static __always_inline bool cpu_enabled(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_enabled_mask); } static __always_inline bool cpu_possible(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_possible_mask); } static __always_inline bool cpu_present(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_present_mask); } static __always_inline bool cpu_active(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_active_mask); } static __always_inline bool cpu_dying(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_dying_mask); } #else #define num_online_cpus() 1U #define num_possible_cpus() 1U #define num_enabled_cpus() 1U #define num_present_cpus() 1U #define num_active_cpus() 1U static __always_inline bool cpu_online(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_possible(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_enabled(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_present(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_active(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_dying(unsigned int cpu) { return false; } #endif /* NR_CPUS > 1 */ #define cpu_is_offline(cpu) unlikely(!cpu_online(cpu)) #if NR_CPUS <= BITS_PER_LONG #define CPU_BITS_ALL \ { \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } #else /* NR_CPUS > BITS_PER_LONG */ #define CPU_BITS_ALL \ { \ [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } #endif /* NR_CPUS > BITS_PER_LONG */ /** * cpumap_print_to_pagebuf - copies the cpumask into the buffer either * as comma-separated list of cpus or hex values of cpumask * @list: indicates whether the cpumap must be list * @mask: the cpumask to copy * @buf: the buffer to copy into * * Return: the length of the (null-terminated) @buf string, zero if * nothing is copied. */ static __always_inline ssize_t cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) { return bitmap_print_to_pagebuf(list, buf, cpumask_bits(mask), nr_cpu_ids); } /** * cpumap_print_bitmask_to_buf - copies the cpumask into the buffer as * hex values of cpumask * * @buf: the buffer to copy into * @mask: the cpumask to copy * @off: in the string from which we are copying, we copy to @buf * @count: the maximum number of bytes to print * * The function prints the cpumask into the buffer as hex values of * cpumask; Typically used by bin_attribute to export cpumask bitmask * ABI. * * Return: the length of how many bytes have been copied, excluding * terminating '\0'. */ static __always_inline ssize_t cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, loff_t off, size_t count) { return bitmap_print_bitmask_to_buf(buf, cpumask_bits(mask), nr_cpu_ids, off, count) - 1; } /** * cpumap_print_list_to_buf - copies the cpumask into the buffer as * comma-separated list of cpus * @buf: the buffer to copy into * @mask: the cpumask to copy * @off: in the string from which we are copying, we copy to @buf * @count: the maximum number of bytes to print * * Everything is same with the above cpumap_print_bitmask_to_buf() * except the print format. * * Return: the length of how many bytes have been copied, excluding * terminating '\0'. */ static __always_inline ssize_t cpumap_print_list_to_buf(char *buf, const struct cpumask *mask, loff_t off, size_t count) { return bitmap_print_list_to_buf(buf, cpumask_bits(mask), nr_cpu_ids, off, count) - 1; } #if NR_CPUS <= BITS_PER_LONG #define CPU_MASK_ALL \ (cpumask_t) { { \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } } #else #define CPU_MASK_ALL \ (cpumask_t) { { \ [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } } #endif /* NR_CPUS > BITS_PER_LONG */ #define CPU_MASK_NONE \ (cpumask_t) { { \ [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ } } #define CPU_MASK_CPU0 \ (cpumask_t) { { \ [0] = 1UL \ } } /* * Provide a valid theoretical max size for cpumap and cpulist sysfs files * to avoid breaking userspace which may allocate a buffer based on the size * reported by e.g. fstat. * * for cpumap NR_CPUS * 9/32 - 1 should be an exact length. * * For cpulist 7 is (ceil(log10(NR_CPUS)) + 1) allowing for NR_CPUS to be up * to 2 orders of magnitude larger than 8192. And then we divide by 2 to * cover a worst-case of every other cpu being on one of two nodes for a * very large NR_CPUS. * * Use PAGE_SIZE as a minimum for smaller configurations while avoiding * unsigned comparison to -1. */ #define CPUMAP_FILE_MAX_BYTES (((NR_CPUS * 9)/32 > PAGE_SIZE) \ ? (NR_CPUS * 9)/32 - 1 : PAGE_SIZE) #define CPULIST_FILE_MAX_BYTES (((NR_CPUS * 7)/2 > PAGE_SIZE) ? (NR_CPUS * 7)/2 : PAGE_SIZE) #endif /* __LINUX_CPUMASK_H */ |
| 6442 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM capability #if !defined(_TRACE_CAPABILITY_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_CAPABILITY_H #include <linux/cred.h> #include <linux/tracepoint.h> #include <linux/user_namespace.h> /** * cap_capable - called after it's determined if a task has a particular * effective capability * * @cred: The credentials used * @target_ns: The user namespace of the resource being accessed * @capable_ns: The user namespace in which the credential provides the * capability to access the targeted resource. * This will be NULL if ret is not 0. * @cap: The capability to check for * @ret: The return value of the check: 0 if it does, -ve if it does not * * Allows to trace calls to cap_capable in commoncap.c */ TRACE_EVENT(cap_capable, TP_PROTO(const struct cred *cred, struct user_namespace *target_ns, const struct user_namespace *capable_ns, int cap, int ret), TP_ARGS(cred, target_ns, capable_ns, cap, ret), TP_STRUCT__entry( __field(const struct cred *, cred) __field(struct user_namespace *, target_ns) __field(const struct user_namespace *, capable_ns) __field(int, cap) __field(int, ret) ), TP_fast_assign( __entry->cred = cred; __entry->target_ns = target_ns; __entry->capable_ns = ret == 0 ? capable_ns : NULL; __entry->cap = cap; __entry->ret = ret; ), TP_printk("cred %p, target_ns %p, capable_ns %p, cap %d, ret %d", __entry->cred, __entry->target_ns, __entry->capable_ns, __entry->cap, __entry->ret) ); #endif /* _TRACE_CAPABILITY_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 260 259 1 259 258 1 259 259 258 258 262 264 262 264 5 5 5 5 264 1 203 203 60 263 263 1 263 264 264 262 264 262 264 264 262 263 1 263 1 263 1 261 2 261 3 3 3 269 263 265 1 266 1 267 265 200 200 200 200 200 200 199 262 1 260 261 260 259 23 23 5 1 4 260 260 260 259 2 2 259 258 259 259 200 200 191 1 163 42 7 7 1 1 1 1 7 4 4 4 4 2 2 4 4 4 4 4 2 2 4 4 4 4 4 4 4 4 4 4 1 1 2 2 264 264 264 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 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2005 Silicon Graphics, Inc. * All Rights Reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_bit.h" #include "xfs_sb.h" #include "xfs_mount.h" #include "xfs_ialloc.h" #include "xfs_alloc.h" #include "xfs_error.h" #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_bmap_btree.h" #include "xfs_alloc_btree.h" #include "xfs_log.h" #include "xfs_rmap_btree.h" #include "xfs_refcount_btree.h" #include "xfs_da_format.h" #include "xfs_health.h" #include "xfs_ag.h" #include "xfs_rtbitmap.h" #include "xfs_exchrange.h" #include "xfs_rtgroup.h" #include "xfs_rtrmap_btree.h" #include "xfs_rtrefcount_btree.h" /* * Physical superblock buffer manipulations. Shared with libxfs in userspace. */ /* * Check that all the V4 feature bits that the V5 filesystem format requires are * correctly set. */ static bool xfs_sb_validate_v5_features( struct xfs_sb *sbp) { /* We must not have any unknown V4 feature bits set */ if (sbp->sb_versionnum & ~XFS_SB_VERSION_OKBITS) return false; /* * The CRC bit is considered an invalid V4 flag, so we have to add it * manually to the OKBITS mask. */ if (sbp->sb_features2 & ~(XFS_SB_VERSION2_OKBITS | XFS_SB_VERSION2_CRCBIT)) return false; /* Now check all the required V4 feature flags are set. */ #define V5_VERS_FLAGS (XFS_SB_VERSION_NLINKBIT | \ XFS_SB_VERSION_ALIGNBIT | \ XFS_SB_VERSION_LOGV2BIT | \ XFS_SB_VERSION_EXTFLGBIT | \ XFS_SB_VERSION_DIRV2BIT | \ XFS_SB_VERSION_MOREBITSBIT) #define V5_FEAT_FLAGS (XFS_SB_VERSION2_LAZYSBCOUNTBIT | \ XFS_SB_VERSION2_ATTR2BIT | \ XFS_SB_VERSION2_PROJID32BIT | \ XFS_SB_VERSION2_CRCBIT) if ((sbp->sb_versionnum & V5_VERS_FLAGS) != V5_VERS_FLAGS) return false; if ((sbp->sb_features2 & V5_FEAT_FLAGS) != V5_FEAT_FLAGS) return false; return true; } /* * We current support XFS v5 formats with known features and v4 superblocks with * at least V2 directories. */ bool xfs_sb_good_version( struct xfs_sb *sbp) { /* * All v5 filesystems are supported, but we must check that all the * required v4 feature flags are enabled correctly as the code checks * those flags and not for v5 support. */ if (xfs_sb_is_v5(sbp)) return xfs_sb_validate_v5_features(sbp); /* versions prior to v4 are not supported */ if (XFS_SB_VERSION_NUM(sbp) != XFS_SB_VERSION_4) return false; /* We must not have any unknown v4 feature bits set */ if ((sbp->sb_versionnum & ~XFS_SB_VERSION_OKBITS) || ((sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT) && (sbp->sb_features2 & ~XFS_SB_VERSION2_OKBITS))) return false; /* V4 filesystems need v2 directories and unwritten extents */ if (!(sbp->sb_versionnum & XFS_SB_VERSION_DIRV2BIT)) return false; if (!(sbp->sb_versionnum & XFS_SB_VERSION_EXTFLGBIT)) return false; /* It's a supported v4 filesystem */ return true; } uint64_t xfs_sb_version_to_features( struct xfs_sb *sbp) { uint64_t features = 0; /* optional V4 features */ if (sbp->sb_rblocks > 0) features |= XFS_FEAT_REALTIME; if (sbp->sb_versionnum & XFS_SB_VERSION_NLINKBIT) features |= XFS_FEAT_NLINK; if (sbp->sb_versionnum & XFS_SB_VERSION_ATTRBIT) features |= XFS_FEAT_ATTR; if (sbp->sb_versionnum & XFS_SB_VERSION_QUOTABIT) features |= XFS_FEAT_QUOTA; if (sbp->sb_versionnum & XFS_SB_VERSION_ALIGNBIT) features |= XFS_FEAT_ALIGN; if (sbp->sb_versionnum & XFS_SB_VERSION_LOGV2BIT) features |= XFS_FEAT_LOGV2; if (sbp->sb_versionnum & XFS_SB_VERSION_DALIGNBIT) features |= XFS_FEAT_DALIGN; if (sbp->sb_versionnum & XFS_SB_VERSION_EXTFLGBIT) features |= XFS_FEAT_EXTFLG; if (sbp->sb_versionnum & XFS_SB_VERSION_SECTORBIT) features |= XFS_FEAT_SECTOR; if (sbp->sb_versionnum & XFS_SB_VERSION_BORGBIT) features |= XFS_FEAT_ASCIICI; if (sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT) { if (sbp->sb_features2 & XFS_SB_VERSION2_LAZYSBCOUNTBIT) features |= XFS_FEAT_LAZYSBCOUNT; if (sbp->sb_features2 & XFS_SB_VERSION2_ATTR2BIT) features |= XFS_FEAT_ATTR2; if (sbp->sb_features2 & XFS_SB_VERSION2_PROJID32BIT) features |= XFS_FEAT_PROJID32; if (sbp->sb_features2 & XFS_SB_VERSION2_FTYPE) features |= XFS_FEAT_FTYPE; } if (!xfs_sb_is_v5(sbp)) return features; /* Always on V5 features */ features |= XFS_FEAT_ALIGN | XFS_FEAT_LOGV2 | XFS_FEAT_EXTFLG | XFS_FEAT_LAZYSBCOUNT | XFS_FEAT_ATTR2 | XFS_FEAT_PROJID32 | XFS_FEAT_V3INODES | XFS_FEAT_CRC | XFS_FEAT_PQUOTINO; /* Optional V5 features */ if (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_FINOBT) features |= XFS_FEAT_FINOBT; if (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_RMAPBT) features |= XFS_FEAT_RMAPBT; if (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_REFLINK) features |= XFS_FEAT_REFLINK; if (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_INOBTCNT) features |= XFS_FEAT_INOBTCNT; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_FTYPE) features |= XFS_FEAT_FTYPE; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_SPINODES) features |= XFS_FEAT_SPINODES; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_META_UUID) features |= XFS_FEAT_META_UUID; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_BIGTIME) features |= XFS_FEAT_BIGTIME; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_NEEDSREPAIR) features |= XFS_FEAT_NEEDSREPAIR; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_NREXT64) features |= XFS_FEAT_NREXT64; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_EXCHRANGE) features |= XFS_FEAT_EXCHANGE_RANGE; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_PARENT) features |= XFS_FEAT_PARENT; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) features |= XFS_FEAT_METADIR; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED) features |= XFS_FEAT_ZONED; return features; } /* Check all the superblock fields we care about when reading one in. */ STATIC int xfs_validate_sb_read( struct xfs_mount *mp, struct xfs_sb *sbp) { if (!xfs_sb_is_v5(sbp)) return 0; /* * Version 5 superblock feature mask validation. Reject combinations * the kernel cannot support up front before checking anything else. */ if (xfs_sb_has_compat_feature(sbp, XFS_SB_FEAT_COMPAT_UNKNOWN)) { xfs_warn(mp, "Superblock has unknown compatible features (0x%x) enabled.", (sbp->sb_features_compat & XFS_SB_FEAT_COMPAT_UNKNOWN)); xfs_warn(mp, "Using a more recent kernel is recommended."); } if (xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) { xfs_alert(mp, "Superblock has unknown read-only compatible features (0x%x) enabled.", (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_UNKNOWN)); if (!xfs_is_readonly(mp)) { xfs_warn(mp, "Attempted to mount read-only compatible filesystem read-write."); xfs_warn(mp, "Filesystem can only be safely mounted read only."); return -EINVAL; } } if (xfs_sb_has_incompat_feature(sbp, XFS_SB_FEAT_INCOMPAT_UNKNOWN)) { xfs_warn(mp, "Superblock has unknown incompatible features (0x%x) enabled.", (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_UNKNOWN)); xfs_warn(mp, "Filesystem cannot be safely mounted by this kernel."); return -EINVAL; } return 0; } /* Return the number of extents covered by a single rt bitmap file */ static xfs_rtbxlen_t xfs_extents_per_rbm( struct xfs_sb *sbp) { if (xfs_sb_is_v5(sbp) && (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) return sbp->sb_rgextents; return sbp->sb_rextents; } /* * Return the payload size of a single rt bitmap block (without the metadata * header if any). */ static inline unsigned int xfs_rtbmblock_size( struct xfs_sb *sbp) { if (xfs_sb_is_v5(sbp) && (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) return sbp->sb_blocksize - sizeof(struct xfs_rtbuf_blkinfo); return sbp->sb_blocksize; } static uint64_t xfs_expected_rbmblocks( struct xfs_sb *sbp) { if (xfs_sb_is_v5(sbp) && (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED)) return 0; return howmany_64(xfs_extents_per_rbm(sbp), NBBY * xfs_rtbmblock_size(sbp)); } /* Validate the realtime geometry */ bool xfs_validate_rt_geometry( struct xfs_sb *sbp) { if (xfs_sb_is_v5(sbp) && (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED)) { if (sbp->sb_rextsize != 1) return false; } else { if (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE || sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE) return false; } if (sbp->sb_rblocks == 0) { if (sbp->sb_rextents != 0 || sbp->sb_rbmblocks != 0 || sbp->sb_rextslog != 0 || sbp->sb_frextents != 0) return false; return true; } if (sbp->sb_rextents == 0 || sbp->sb_rextents != div_u64(sbp->sb_rblocks, sbp->sb_rextsize) || sbp->sb_rextslog != xfs_compute_rextslog(sbp->sb_rextents) || sbp->sb_rbmblocks != xfs_expected_rbmblocks(sbp)) return false; return true; } /* Check all the superblock fields we care about when writing one out. */ STATIC int xfs_validate_sb_write( struct xfs_mount *mp, struct xfs_buf *bp, struct xfs_sb *sbp) { /* * Carry out additional sb summary counter sanity checks when we write * the superblock. We skip this in the read validator because there * could be newer superblocks in the log and if the values are garbage * even after replay we'll recalculate them at the end of log mount. * * mkfs has traditionally written zeroed counters to inprogress and * secondary superblocks, so allow this usage to continue because * we never read counters from such superblocks. */ if (xfs_buf_daddr(bp) == XFS_SB_DADDR && !sbp->sb_inprogress && (sbp->sb_fdblocks > sbp->sb_dblocks || !xfs_verify_icount(mp, sbp->sb_icount) || sbp->sb_ifree > sbp->sb_icount)) { xfs_warn(mp, "SB summary counter sanity check failed"); return -EFSCORRUPTED; } if (!xfs_sb_is_v5(sbp)) return 0; /* * Version 5 superblock feature mask validation. Reject combinations * the kernel cannot support since we checked for unsupported bits in * the read verifier, which means that memory is corrupt. */ if (!xfs_is_readonly(mp) && xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) { xfs_alert(mp, "Corruption detected in superblock read-only compatible features (0x%x)!", (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_UNKNOWN)); return -EFSCORRUPTED; } if (xfs_sb_has_incompat_feature(sbp, XFS_SB_FEAT_INCOMPAT_UNKNOWN)) { xfs_warn(mp, "Corruption detected in superblock incompatible features (0x%x)!", (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_UNKNOWN)); return -EFSCORRUPTED; } if (xfs_sb_has_incompat_log_feature(sbp, XFS_SB_FEAT_INCOMPAT_LOG_UNKNOWN)) { xfs_warn(mp, "Corruption detected in superblock incompatible log features (0x%x)!", (sbp->sb_features_log_incompat & XFS_SB_FEAT_INCOMPAT_LOG_UNKNOWN)); return -EFSCORRUPTED; } /* * We can't read verify the sb LSN because the read verifier is called * before the log is allocated and processed. We know the log is set up * before write verifier calls, so check it here. */ if (!xfs_log_check_lsn(mp, sbp->sb_lsn)) return -EFSCORRUPTED; return 0; } int xfs_compute_rgblklog( xfs_rtxlen_t rgextents, xfs_rgblock_t rextsize) { uint64_t rgblocks = (uint64_t)rgextents * rextsize; return xfs_highbit64(rgblocks - 1) + 1; } static int xfs_validate_sb_rtgroups( struct xfs_mount *mp, struct xfs_sb *sbp) { uint64_t groups; int rgblklog; if (sbp->sb_rextsize == 0) { xfs_warn(mp, "Realtime extent size must not be zero."); return -EINVAL; } if (sbp->sb_rgextents > XFS_MAX_RGBLOCKS / sbp->sb_rextsize) { xfs_warn(mp, "Realtime group size (%u) must be less than %u rt extents.", sbp->sb_rgextents, XFS_MAX_RGBLOCKS / sbp->sb_rextsize); return -EINVAL; } if (sbp->sb_rgextents < XFS_MIN_RGEXTENTS) { xfs_warn(mp, "Realtime group size (%u) must be at least %u rt extents.", sbp->sb_rgextents, XFS_MIN_RGEXTENTS); return -EINVAL; } if (sbp->sb_rgcount > XFS_MAX_RGNUMBER) { xfs_warn(mp, "Realtime groups (%u) must be less than %u.", sbp->sb_rgcount, XFS_MAX_RGNUMBER); return -EINVAL; } groups = howmany_64(sbp->sb_rextents, sbp->sb_rgextents); if (groups != sbp->sb_rgcount) { xfs_warn(mp, "Realtime groups (%u) do not cover the entire rt section; need (%llu) groups.", sbp->sb_rgcount, groups); return -EINVAL; } /* Exchange-range is required for fsr to work on realtime files */ if (!(sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_EXCHRANGE)) { xfs_warn(mp, "Realtime groups feature requires exchange-range support."); return -EINVAL; } rgblklog = xfs_compute_rgblklog(sbp->sb_rgextents, sbp->sb_rextsize); if (sbp->sb_rgblklog != rgblklog) { xfs_warn(mp, "Realtime group log (%d) does not match expected value (%d).", sbp->sb_rgblklog, rgblklog); return -EINVAL; } return 0; } static int xfs_validate_sb_zoned( struct xfs_mount *mp, struct xfs_sb *sbp) { if (sbp->sb_frextents != 0) { xfs_warn(mp, "sb_frextents must be zero for zoned file systems."); return -EINVAL; } if (sbp->sb_rtstart && sbp->sb_rtstart < sbp->sb_dblocks) { xfs_warn(mp, "sb_rtstart (%lld) overlaps sb_dblocks (%lld).", sbp->sb_rtstart, sbp->sb_dblocks); return -EINVAL; } if (sbp->sb_rtreserved && sbp->sb_rtreserved >= sbp->sb_rblocks) { xfs_warn(mp, "sb_rtreserved (%lld) larger than sb_rblocks (%lld).", sbp->sb_rtreserved, sbp->sb_rblocks); return -EINVAL; } return 0; } /* Check the validity of the SB. */ STATIC int xfs_validate_sb_common( struct xfs_mount *mp, struct xfs_buf *bp, struct xfs_sb *sbp) { struct xfs_dsb *dsb = bp->b_addr; uint32_t agcount = 0; uint32_t rem; bool has_dalign; int error; if (!xfs_verify_magic(bp, dsb->sb_magicnum)) { xfs_warn(mp, "Superblock has bad magic number 0x%x. Not an XFS filesystem?", be32_to_cpu(dsb->sb_magicnum)); return -EWRONGFS; } if (!xfs_sb_good_version(sbp)) { xfs_warn(mp, "Superblock has unknown features enabled or corrupted feature masks."); return -EWRONGFS; } /* * Validate feature flags and state */ if (xfs_sb_is_v5(sbp)) { if (sbp->sb_blocksize < XFS_MIN_CRC_BLOCKSIZE) { xfs_notice(mp, "Block size (%u bytes) too small for Version 5 superblock (minimum %d bytes)", sbp->sb_blocksize, XFS_MIN_CRC_BLOCKSIZE); return -EFSCORRUPTED; } /* V5 has a separate project quota inode */ if (sbp->sb_qflags & (XFS_OQUOTA_ENFD | XFS_OQUOTA_CHKD)) { xfs_notice(mp, "Version 5 of Super block has XFS_OQUOTA bits."); return -EFSCORRUPTED; } /* * Full inode chunks must be aligned to inode chunk size when * sparse inodes are enabled to support the sparse chunk * allocation algorithm and prevent overlapping inode records. */ if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_SPINODES) { uint32_t align; align = XFS_INODES_PER_CHUNK * sbp->sb_inodesize >> sbp->sb_blocklog; if (sbp->sb_inoalignmt != align) { xfs_warn(mp, "Inode block alignment (%u) must match chunk size (%u) for sparse inodes.", sbp->sb_inoalignmt, align); return -EINVAL; } if (sbp->sb_spino_align && (sbp->sb_spino_align > sbp->sb_inoalignmt || (sbp->sb_inoalignmt % sbp->sb_spino_align) != 0)) { xfs_warn(mp, "Sparse inode alignment (%u) is invalid, must be integer factor of (%u).", sbp->sb_spino_align, sbp->sb_inoalignmt); return -EINVAL; } } else if (sbp->sb_spino_align) { xfs_warn(mp, "Sparse inode alignment (%u) should be zero.", sbp->sb_spino_align); return -EINVAL; } if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) { if (memchr_inv(sbp->sb_pad, 0, sizeof(sbp->sb_pad))) { xfs_warn(mp, "Metadir superblock padding fields must be zero."); return -EINVAL; } error = xfs_validate_sb_rtgroups(mp, sbp); if (error) return error; } if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED) { error = xfs_validate_sb_zoned(mp, sbp); if (error) return error; } } else if (sbp->sb_qflags & (XFS_PQUOTA_ENFD | XFS_GQUOTA_ENFD | XFS_PQUOTA_CHKD | XFS_GQUOTA_CHKD)) { xfs_notice(mp, "Superblock earlier than Version 5 has XFS_{P|G}QUOTA_{ENFD|CHKD} bits."); return -EFSCORRUPTED; } if (unlikely( sbp->sb_logstart == 0 && mp->m_logdev_targp == mp->m_ddev_targp)) { xfs_warn(mp, "filesystem is marked as having an external log; " "specify logdev on the mount command line."); return -EINVAL; } if (unlikely( sbp->sb_logstart != 0 && mp->m_logdev_targp != mp->m_ddev_targp)) { xfs_warn(mp, "filesystem is marked as having an internal log; " "do not specify logdev on the mount command line."); return -EINVAL; } /* Compute agcount for this number of dblocks and agblocks */ if (sbp->sb_agblocks) { agcount = div_u64_rem(sbp->sb_dblocks, sbp->sb_agblocks, &rem); if (rem) agcount++; } /* * More sanity checking. Most of these were stolen directly from * xfs_repair. */ if (unlikely( sbp->sb_agcount <= 0 || sbp->sb_sectsize < XFS_MIN_SECTORSIZE || sbp->sb_sectsize > XFS_MAX_SECTORSIZE || sbp->sb_sectlog < XFS_MIN_SECTORSIZE_LOG || sbp->sb_sectlog > XFS_MAX_SECTORSIZE_LOG || sbp->sb_sectsize != (1 << sbp->sb_sectlog) || sbp->sb_blocksize < XFS_MIN_BLOCKSIZE || sbp->sb_blocksize > XFS_MAX_BLOCKSIZE || sbp->sb_blocklog < XFS_MIN_BLOCKSIZE_LOG || sbp->sb_blocklog > XFS_MAX_BLOCKSIZE_LOG || sbp->sb_blocksize != (1 << sbp->sb_blocklog) || sbp->sb_dirblklog + sbp->sb_blocklog > XFS_MAX_BLOCKSIZE_LOG || sbp->sb_inodesize < XFS_DINODE_MIN_SIZE || sbp->sb_inodesize > XFS_DINODE_MAX_SIZE || sbp->sb_inodelog < XFS_DINODE_MIN_LOG || sbp->sb_inodelog > XFS_DINODE_MAX_LOG || sbp->sb_inodesize != (1 << sbp->sb_inodelog) || sbp->sb_inopblock != howmany(sbp->sb_blocksize,sbp->sb_inodesize) || XFS_FSB_TO_B(mp, sbp->sb_agblocks) < XFS_MIN_AG_BYTES || XFS_FSB_TO_B(mp, sbp->sb_agblocks) > XFS_MAX_AG_BYTES || sbp->sb_agblklog != xfs_highbit32(sbp->sb_agblocks - 1) + 1 || agcount == 0 || agcount != sbp->sb_agcount || (sbp->sb_blocklog - sbp->sb_inodelog != sbp->sb_inopblog) || (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE) || (sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE) || (sbp->sb_imax_pct > 100 /* zero sb_imax_pct is valid */) || sbp->sb_dblocks == 0 || sbp->sb_dblocks > XFS_MAX_DBLOCKS(sbp) || sbp->sb_dblocks < XFS_MIN_DBLOCKS(sbp) || sbp->sb_shared_vn != 0)) { xfs_notice(mp, "SB sanity check failed"); return -EFSCORRUPTED; } /* * Logs that are too large are not supported at all. Reject them * outright. Logs that are too small are tolerated on v4 filesystems, * but we can only check that when mounting the log. Hence we skip * those checks here. */ if (sbp->sb_logblocks > XFS_MAX_LOG_BLOCKS) { xfs_notice(mp, "Log size 0x%x blocks too large, maximum size is 0x%llx blocks", sbp->sb_logblocks, XFS_MAX_LOG_BLOCKS); return -EFSCORRUPTED; } if (XFS_FSB_TO_B(mp, sbp->sb_logblocks) > XFS_MAX_LOG_BYTES) { xfs_warn(mp, "log size 0x%llx bytes too large, maximum size is 0x%llx bytes", XFS_FSB_TO_B(mp, sbp->sb_logblocks), XFS_MAX_LOG_BYTES); return -EFSCORRUPTED; } /* * Do not allow filesystems with corrupted log sector or stripe units to * be mounted. We cannot safely size the iclogs or write to the log if * the log stripe unit is not valid. */ if (sbp->sb_versionnum & XFS_SB_VERSION_SECTORBIT) { if (sbp->sb_logsectsize != (1U << sbp->sb_logsectlog)) { xfs_notice(mp, "log sector size in bytes/log2 (0x%x/0x%x) must match", sbp->sb_logsectsize, 1U << sbp->sb_logsectlog); return -EFSCORRUPTED; } } else if (sbp->sb_logsectsize || sbp->sb_logsectlog) { xfs_notice(mp, "log sector size in bytes/log2 (0x%x/0x%x) are not zero", sbp->sb_logsectsize, sbp->sb_logsectlog); return -EFSCORRUPTED; } if (sbp->sb_logsunit > 1) { if (sbp->sb_logsunit % sbp->sb_blocksize) { xfs_notice(mp, "log stripe unit 0x%x bytes must be a multiple of block size", sbp->sb_logsunit); return -EFSCORRUPTED; } if (sbp->sb_logsunit > XLOG_MAX_RECORD_BSIZE) { xfs_notice(mp, "log stripe unit 0x%x bytes over maximum size (0x%x bytes)", sbp->sb_logsunit, XLOG_MAX_RECORD_BSIZE); return -EFSCORRUPTED; } } if (!xfs_validate_rt_geometry(sbp)) { xfs_notice(mp, "realtime %sgeometry check failed", sbp->sb_rblocks ? "" : "zeroed "); return -EFSCORRUPTED; } /* * Either (sb_unit and !hasdalign) or (!sb_unit and hasdalign) * would imply the image is corrupted. */ has_dalign = sbp->sb_versionnum & XFS_SB_VERSION_DALIGNBIT; if (!!sbp->sb_unit ^ has_dalign) { xfs_notice(mp, "SB stripe alignment sanity check failed"); return -EFSCORRUPTED; } if (!xfs_validate_stripe_geometry(mp, XFS_FSB_TO_B(mp, sbp->sb_unit), XFS_FSB_TO_B(mp, sbp->sb_width), 0, xfs_buf_daddr(bp) == XFS_SB_DADDR, false)) return -EFSCORRUPTED; /* * Currently only very few inode sizes are supported. */ switch (sbp->sb_inodesize) { case 256: case 512: case 1024: case 2048: break; default: xfs_warn(mp, "inode size of %d bytes not supported", sbp->sb_inodesize); return -ENOSYS; } return 0; } void xfs_sb_quota_from_disk(struct xfs_sb *sbp) { if (xfs_sb_is_v5(sbp) && (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) { sbp->sb_uquotino = NULLFSINO; sbp->sb_gquotino = NULLFSINO; sbp->sb_pquotino = NULLFSINO; return; } /* * older mkfs doesn't initialize quota inodes to NULLFSINO. This * leads to in-core values having two different values for a quota * inode to be invalid: 0 and NULLFSINO. Change it to a single value * NULLFSINO. * * Note that this change affect only the in-core values. These * values are not written back to disk unless any quota information * is written to the disk. Even in that case, sb_pquotino field is * not written to disk unless the superblock supports pquotino. */ if (sbp->sb_uquotino == 0) sbp->sb_uquotino = NULLFSINO; if (sbp->sb_gquotino == 0) sbp->sb_gquotino = NULLFSINO; if (sbp->sb_pquotino == 0) sbp->sb_pquotino = NULLFSINO; /* * We need to do these manipilations only if we are working * with an older version of on-disk superblock. */ if (xfs_sb_is_v5(sbp)) return; if (sbp->sb_qflags & XFS_OQUOTA_ENFD) sbp->sb_qflags |= (sbp->sb_qflags & XFS_PQUOTA_ACCT) ? XFS_PQUOTA_ENFD : XFS_GQUOTA_ENFD; if (sbp->sb_qflags & XFS_OQUOTA_CHKD) sbp->sb_qflags |= (sbp->sb_qflags & XFS_PQUOTA_ACCT) ? XFS_PQUOTA_CHKD : XFS_GQUOTA_CHKD; sbp->sb_qflags &= ~(XFS_OQUOTA_ENFD | XFS_OQUOTA_CHKD); if (sbp->sb_qflags & XFS_PQUOTA_ACCT && sbp->sb_gquotino != NULLFSINO) { /* * In older version of superblock, on-disk superblock only * has sb_gquotino, and in-core superblock has both sb_gquotino * and sb_pquotino. But, only one of them is supported at any * point of time. So, if PQUOTA is set in disk superblock, * copy over sb_gquotino to sb_pquotino. The NULLFSINO test * above is to make sure we don't do this twice and wipe them * both out! */ sbp->sb_pquotino = sbp->sb_gquotino; sbp->sb_gquotino = NULLFSINO; } } static void __xfs_sb_from_disk( struct xfs_sb *to, struct xfs_dsb *from, bool convert_xquota) { to->sb_magicnum = be32_to_cpu(from->sb_magicnum); to->sb_blocksize = be32_to_cpu(from->sb_blocksize); to->sb_dblocks = be64_to_cpu(from->sb_dblocks); to->sb_rblocks = be64_to_cpu(from->sb_rblocks); to->sb_rextents = be64_to_cpu(from->sb_rextents); memcpy(&to->sb_uuid, &from->sb_uuid, sizeof(to->sb_uuid)); to->sb_logstart = be64_to_cpu(from->sb_logstart); to->sb_rootino = be64_to_cpu(from->sb_rootino); to->sb_rbmino = be64_to_cpu(from->sb_rbmino); to->sb_rsumino = be64_to_cpu(from->sb_rsumino); to->sb_rextsize = be32_to_cpu(from->sb_rextsize); to->sb_agblocks = be32_to_cpu(from->sb_agblocks); to->sb_agcount = be32_to_cpu(from->sb_agcount); to->sb_rbmblocks = be32_to_cpu(from->sb_rbmblocks); to->sb_logblocks = be32_to_cpu(from->sb_logblocks); to->sb_versionnum = be16_to_cpu(from->sb_versionnum); to->sb_sectsize = be16_to_cpu(from->sb_sectsize); to->sb_inodesize = be16_to_cpu(from->sb_inodesize); to->sb_inopblock = be16_to_cpu(from->sb_inopblock); memcpy(&to->sb_fname, &from->sb_fname, sizeof(to->sb_fname)); to->sb_blocklog = from->sb_blocklog; to->sb_sectlog = from->sb_sectlog; to->sb_inodelog = from->sb_inodelog; to->sb_inopblog = from->sb_inopblog; to->sb_agblklog = from->sb_agblklog; to->sb_rextslog = from->sb_rextslog; to->sb_inprogress = from->sb_inprogress; to->sb_imax_pct = from->sb_imax_pct; to->sb_icount = be64_to_cpu(from->sb_icount); to->sb_ifree = be64_to_cpu(from->sb_ifree); to->sb_fdblocks = be64_to_cpu(from->sb_fdblocks); to->sb_frextents = be64_to_cpu(from->sb_frextents); to->sb_uquotino = be64_to_cpu(from->sb_uquotino); to->sb_gquotino = be64_to_cpu(from->sb_gquotino); to->sb_qflags = be16_to_cpu(from->sb_qflags); to->sb_flags = from->sb_flags; to->sb_shared_vn = from->sb_shared_vn; to->sb_inoalignmt = be32_to_cpu(from->sb_inoalignmt); to->sb_unit = be32_to_cpu(from->sb_unit); to->sb_width = be32_to_cpu(from->sb_width); to->sb_dirblklog = from->sb_dirblklog; to->sb_logsectlog = from->sb_logsectlog; to->sb_logsectsize = be16_to_cpu(from->sb_logsectsize); to->sb_logsunit = be32_to_cpu(from->sb_logsunit); to->sb_features2 = be32_to_cpu(from->sb_features2); to->sb_bad_features2 = be32_to_cpu(from->sb_bad_features2); to->sb_features_compat = be32_to_cpu(from->sb_features_compat); to->sb_features_ro_compat = be32_to_cpu(from->sb_features_ro_compat); to->sb_features_incompat = be32_to_cpu(from->sb_features_incompat); to->sb_features_log_incompat = be32_to_cpu(from->sb_features_log_incompat); /* crc is only used on disk, not in memory; just init to 0 here. */ to->sb_crc = 0; to->sb_spino_align = be32_to_cpu(from->sb_spino_align); to->sb_pquotino = be64_to_cpu(from->sb_pquotino); to->sb_lsn = be64_to_cpu(from->sb_lsn); /* * sb_meta_uuid is only on disk if it differs from sb_uuid and the * feature flag is set; if not set we keep it only in memory. */ if (xfs_sb_is_v5(to) && (to->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_META_UUID)) uuid_copy(&to->sb_meta_uuid, &from->sb_meta_uuid); else uuid_copy(&to->sb_meta_uuid, &from->sb_uuid); /* Convert on-disk flags to in-memory flags? */ if (convert_xquota) xfs_sb_quota_from_disk(to); if (to->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) { to->sb_metadirino = be64_to_cpu(from->sb_metadirino); to->sb_rgblklog = from->sb_rgblklog; memcpy(to->sb_pad, from->sb_pad, sizeof(to->sb_pad)); to->sb_rgcount = be32_to_cpu(from->sb_rgcount); to->sb_rgextents = be32_to_cpu(from->sb_rgextents); to->sb_rbmino = NULLFSINO; to->sb_rsumino = NULLFSINO; } else { to->sb_metadirino = NULLFSINO; to->sb_rgcount = 1; to->sb_rgextents = 0; } if (to->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED) { to->sb_rtstart = be64_to_cpu(from->sb_rtstart); to->sb_rtreserved = be64_to_cpu(from->sb_rtreserved); } else { to->sb_rtstart = 0; to->sb_rtreserved = 0; } } void xfs_sb_from_disk( struct xfs_sb *to, struct xfs_dsb *from) { __xfs_sb_from_disk(to, from, true); } static void xfs_sb_quota_to_disk( struct xfs_dsb *to, struct xfs_sb *from) { uint16_t qflags = from->sb_qflags; if (xfs_sb_is_v5(from) && (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) { to->sb_qflags = cpu_to_be16(from->sb_qflags); to->sb_uquotino = cpu_to_be64(0); to->sb_gquotino = cpu_to_be64(0); to->sb_pquotino = cpu_to_be64(0); return; } to->sb_uquotino = cpu_to_be64(from->sb_uquotino); /* * The in-memory superblock quota state matches the v5 on-disk format so * just write them out and return */ if (xfs_sb_is_v5(from)) { to->sb_qflags = cpu_to_be16(from->sb_qflags); to->sb_gquotino = cpu_to_be64(from->sb_gquotino); to->sb_pquotino = cpu_to_be64(from->sb_pquotino); return; } /* * For older superblocks (v4), the in-core version of sb_qflags do not * have XFS_OQUOTA_* flags, whereas the on-disk version does. So, * convert incore XFS_{PG}QUOTA_* flags to on-disk XFS_OQUOTA_* flags. */ qflags &= ~(XFS_PQUOTA_ENFD | XFS_PQUOTA_CHKD | XFS_GQUOTA_ENFD | XFS_GQUOTA_CHKD); if (from->sb_qflags & (XFS_PQUOTA_ENFD | XFS_GQUOTA_ENFD)) qflags |= XFS_OQUOTA_ENFD; if (from->sb_qflags & (XFS_PQUOTA_CHKD | XFS_GQUOTA_CHKD)) qflags |= XFS_OQUOTA_CHKD; to->sb_qflags = cpu_to_be16(qflags); /* * GQUOTINO and PQUOTINO cannot be used together in versions * of superblock that do not have pquotino. from->sb_flags * tells us which quota is active and should be copied to * disk. If neither are active, we should NULL the inode. * * In all cases, the separate pquotino must remain 0 because it * is beyond the "end" of the valid non-pquotino superblock. */ if (from->sb_qflags & XFS_GQUOTA_ACCT) to->sb_gquotino = cpu_to_be64(from->sb_gquotino); else if (from->sb_qflags & XFS_PQUOTA_ACCT) to->sb_gquotino = cpu_to_be64(from->sb_pquotino); else { /* * We can't rely on just the fields being logged to tell us * that it is safe to write NULLFSINO - we should only do that * if quotas are not actually enabled. Hence only write * NULLFSINO if both in-core quota inodes are NULL. */ if (from->sb_gquotino == NULLFSINO && from->sb_pquotino == NULLFSINO) to->sb_gquotino = cpu_to_be64(NULLFSINO); } to->sb_pquotino = 0; } void xfs_sb_to_disk( struct xfs_dsb *to, struct xfs_sb *from) { xfs_sb_quota_to_disk(to, from); to->sb_magicnum = cpu_to_be32(from->sb_magicnum); to->sb_blocksize = cpu_to_be32(from->sb_blocksize); to->sb_dblocks = cpu_to_be64(from->sb_dblocks); to->sb_rblocks = cpu_to_be64(from->sb_rblocks); to->sb_rextents = cpu_to_be64(from->sb_rextents); memcpy(&to->sb_uuid, &from->sb_uuid, sizeof(to->sb_uuid)); to->sb_logstart = cpu_to_be64(from->sb_logstart); to->sb_rootino = cpu_to_be64(from->sb_rootino); to->sb_rbmino = cpu_to_be64(from->sb_rbmino); to->sb_rsumino = cpu_to_be64(from->sb_rsumino); to->sb_rextsize = cpu_to_be32(from->sb_rextsize); to->sb_agblocks = cpu_to_be32(from->sb_agblocks); to->sb_agcount = cpu_to_be32(from->sb_agcount); to->sb_rbmblocks = cpu_to_be32(from->sb_rbmblocks); to->sb_logblocks = cpu_to_be32(from->sb_logblocks); to->sb_versionnum = cpu_to_be16(from->sb_versionnum); to->sb_sectsize = cpu_to_be16(from->sb_sectsize); to->sb_inodesize = cpu_to_be16(from->sb_inodesize); to->sb_inopblock = cpu_to_be16(from->sb_inopblock); memcpy(&to->sb_fname, &from->sb_fname, sizeof(to->sb_fname)); to->sb_blocklog = from->sb_blocklog; to->sb_sectlog = from->sb_sectlog; to->sb_inodelog = from->sb_inodelog; to->sb_inopblog = from->sb_inopblog; to->sb_agblklog = from->sb_agblklog; to->sb_rextslog = from->sb_rextslog; to->sb_inprogress = from->sb_inprogress; to->sb_imax_pct = from->sb_imax_pct; to->sb_icount = cpu_to_be64(from->sb_icount); to->sb_ifree = cpu_to_be64(from->sb_ifree); to->sb_fdblocks = cpu_to_be64(from->sb_fdblocks); to->sb_frextents = cpu_to_be64(from->sb_frextents); to->sb_flags = from->sb_flags; to->sb_shared_vn = from->sb_shared_vn; to->sb_inoalignmt = cpu_to_be32(from->sb_inoalignmt); to->sb_unit = cpu_to_be32(from->sb_unit); to->sb_width = cpu_to_be32(from->sb_width); to->sb_dirblklog = from->sb_dirblklog; to->sb_logsectlog = from->sb_logsectlog; to->sb_logsectsize = cpu_to_be16(from->sb_logsectsize); to->sb_logsunit = cpu_to_be32(from->sb_logsunit); /* * We need to ensure that bad_features2 always matches features2. * Hence we enforce that here rather than having to remember to do it * everywhere else that updates features2. */ from->sb_bad_features2 = from->sb_features2; to->sb_features2 = cpu_to_be32(from->sb_features2); to->sb_bad_features2 = cpu_to_be32(from->sb_bad_features2); if (!xfs_sb_is_v5(from)) return; to->sb_features_compat = cpu_to_be32(from->sb_features_compat); to->sb_features_ro_compat = cpu_to_be32(from->sb_features_ro_compat); to->sb_features_incompat = cpu_to_be32(from->sb_features_incompat); to->sb_features_log_incompat = cpu_to_be32(from->sb_features_log_incompat); to->sb_spino_align = cpu_to_be32(from->sb_spino_align); to->sb_lsn = cpu_to_be64(from->sb_lsn); if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_META_UUID) uuid_copy(&to->sb_meta_uuid, &from->sb_meta_uuid); if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) { to->sb_metadirino = cpu_to_be64(from->sb_metadirino); to->sb_rgblklog = from->sb_rgblklog; memset(to->sb_pad, 0, sizeof(to->sb_pad)); to->sb_rgcount = cpu_to_be32(from->sb_rgcount); to->sb_rgextents = cpu_to_be32(from->sb_rgextents); to->sb_rbmino = cpu_to_be64(0); to->sb_rsumino = cpu_to_be64(0); } if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED) { to->sb_rtstart = cpu_to_be64(from->sb_rtstart); to->sb_rtreserved = cpu_to_be64(from->sb_rtreserved); } } /* * If the superblock has the CRC feature bit set or the CRC field is non-null, * check that the CRC is valid. We check the CRC field is non-null because a * single bit error could clear the feature bit and unused parts of the * superblock are supposed to be zero. Hence a non-null crc field indicates that * we've potentially lost a feature bit and we should check it anyway. * * However, past bugs (i.e. in growfs) left non-zeroed regions beyond the * last field in V4 secondary superblocks. So for secondary superblocks, * we are more forgiving, and ignore CRC failures if the primary doesn't * indicate that the fs version is V5. */ static void xfs_sb_read_verify( struct xfs_buf *bp) { struct xfs_sb sb; struct xfs_mount *mp = bp->b_mount; struct xfs_dsb *dsb = bp->b_addr; int error; /* * open code the version check to avoid needing to convert the entire * superblock from disk order just to check the version number */ if (dsb->sb_magicnum == cpu_to_be32(XFS_SB_MAGIC) && (((be16_to_cpu(dsb->sb_versionnum) & XFS_SB_VERSION_NUMBITS) == XFS_SB_VERSION_5) || dsb->sb_crc != 0)) { if (!xfs_buf_verify_cksum(bp, XFS_SB_CRC_OFF)) { /* Only fail bad secondaries on a known V5 filesystem */ if (xfs_buf_daddr(bp) == XFS_SB_DADDR || xfs_has_crc(mp)) { error = -EFSBADCRC; goto out_error; } } } /* * Check all the superblock fields. Don't byteswap the xquota flags * because _verify_common checks the on-disk values. */ __xfs_sb_from_disk(&sb, dsb, false); error = xfs_validate_sb_common(mp, bp, &sb); if (error) goto out_error; error = xfs_validate_sb_read(mp, &sb); out_error: if (error == -EFSCORRUPTED || error == -EFSBADCRC) xfs_verifier_error(bp, error, __this_address); else if (error) xfs_buf_ioerror(bp, error); } /* * We may be probed for a filesystem match, so we may not want to emit * messages when the superblock buffer is not actually an XFS superblock. * If we find an XFS superblock, then run a normal, noisy mount because we are * really going to mount it and want to know about errors. */ static void xfs_sb_quiet_read_verify( struct xfs_buf *bp) { struct xfs_dsb *dsb = bp->b_addr; if (dsb->sb_magicnum == cpu_to_be32(XFS_SB_MAGIC)) { /* XFS filesystem, verify noisily! */ xfs_sb_read_verify(bp); return; } /* quietly fail */ xfs_buf_ioerror(bp, -EWRONGFS); } static void xfs_sb_write_verify( struct xfs_buf *bp) { struct xfs_sb sb; struct xfs_mount *mp = bp->b_mount; struct xfs_buf_log_item *bip = bp->b_log_item; struct xfs_dsb *dsb = bp->b_addr; int error; /* * Check all the superblock fields. Don't byteswap the xquota flags * because _verify_common checks the on-disk values. */ __xfs_sb_from_disk(&sb, dsb, false); error = xfs_validate_sb_common(mp, bp, &sb); if (error) goto out_error; error = xfs_validate_sb_write(mp, bp, &sb); if (error) goto out_error; if (!xfs_sb_is_v5(&sb)) return; if (bip) dsb->sb_lsn = cpu_to_be64(bip->bli_item.li_lsn); xfs_buf_update_cksum(bp, XFS_SB_CRC_OFF); return; out_error: xfs_verifier_error(bp, error, __this_address); } const struct xfs_buf_ops xfs_sb_buf_ops = { .name = "xfs_sb", .magic = { cpu_to_be32(XFS_SB_MAGIC), cpu_to_be32(XFS_SB_MAGIC) }, .verify_read = xfs_sb_read_verify, .verify_write = xfs_sb_write_verify, }; const struct xfs_buf_ops xfs_sb_quiet_buf_ops = { .name = "xfs_sb_quiet", .magic = { cpu_to_be32(XFS_SB_MAGIC), cpu_to_be32(XFS_SB_MAGIC) }, .verify_read = xfs_sb_quiet_read_verify, .verify_write = xfs_sb_write_verify, }; /* Compute cached rt geometry from the incore sb. */ void xfs_sb_mount_rextsize( struct xfs_mount *mp, struct xfs_sb *sbp) { struct xfs_groups *rgs = &mp->m_groups[XG_TYPE_RTG]; mp->m_rtxblklog = log2_if_power2(sbp->sb_rextsize); mp->m_rtxblkmask = mask64_if_power2(sbp->sb_rextsize); if (xfs_sb_is_v5(sbp) && (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) { rgs->blocks = sbp->sb_rgextents * sbp->sb_rextsize; rgs->blklog = mp->m_sb.sb_rgblklog; rgs->blkmask = xfs_mask32lo(mp->m_sb.sb_rgblklog); rgs->start_fsb = mp->m_sb.sb_rtstart; if (xfs_sb_has_incompat_feature(sbp, XFS_SB_FEAT_INCOMPAT_ZONE_GAPS)) rgs->has_daddr_gaps = true; } else { rgs->blocks = 0; rgs->blklog = 0; rgs->blkmask = (uint64_t)-1; } } /* Update incore sb rt extent size, then recompute the cached rt geometry. */ void xfs_mount_sb_set_rextsize( struct xfs_mount *mp, struct xfs_sb *sbp, xfs_agblock_t rextsize) { sbp->sb_rextsize = rextsize; if (xfs_sb_is_v5(sbp) && (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) sbp->sb_rgblklog = xfs_compute_rgblklog(sbp->sb_rgextents, rextsize); xfs_sb_mount_rextsize(mp, sbp); } /* * xfs_mount_common * * Mount initialization code establishing various mount * fields from the superblock associated with the given * mount structure. * * Inode geometry are calculated in xfs_ialloc_setup_geometry. */ void xfs_sb_mount_common( struct xfs_mount *mp, struct xfs_sb *sbp) { struct xfs_groups *ags = &mp->m_groups[XG_TYPE_AG]; mp->m_agfrotor = 0; atomic_set(&mp->m_agirotor, 0); mp->m_maxagi = mp->m_sb.sb_agcount; mp->m_blkbit_log = sbp->sb_blocklog + XFS_NBBYLOG; mp->m_blkbb_log = sbp->sb_blocklog - BBSHIFT; mp->m_sectbb_log = sbp->sb_sectlog - BBSHIFT; mp->m_agno_log = xfs_highbit32(sbp->sb_agcount - 1) + 1; mp->m_blockmask = sbp->sb_blocksize - 1; mp->m_blockwsize = xfs_rtbmblock_size(sbp) >> XFS_WORDLOG; mp->m_rtx_per_rbmblock = mp->m_blockwsize << XFS_NBWORDLOG; ags->blocks = mp->m_sb.sb_agblocks; ags->blklog = mp->m_sb.sb_agblklog; ags->blkmask = xfs_mask32lo(mp->m_sb.sb_agblklog); xfs_sb_mount_rextsize(mp, sbp); mp->m_alloc_mxr[0] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, true); mp->m_alloc_mxr[1] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, false); mp->m_alloc_mnr[0] = mp->m_alloc_mxr[0] / 2; mp->m_alloc_mnr[1] = mp->m_alloc_mxr[1] / 2; mp->m_bmap_dmxr[0] = xfs_bmbt_maxrecs(mp, sbp->sb_blocksize, true); mp->m_bmap_dmxr[1] = xfs_bmbt_maxrecs(mp, sbp->sb_blocksize, false); mp->m_bmap_dmnr[0] = mp->m_bmap_dmxr[0] / 2; mp->m_bmap_dmnr[1] = mp->m_bmap_dmxr[1] / 2; mp->m_rmap_mxr[0] = xfs_rmapbt_maxrecs(mp, sbp->sb_blocksize, true); mp->m_rmap_mxr[1] = xfs_rmapbt_maxrecs(mp, sbp->sb_blocksize, false); mp->m_rmap_mnr[0] = mp->m_rmap_mxr[0] / 2; mp->m_rmap_mnr[1] = mp->m_rmap_mxr[1] / 2; mp->m_rtrmap_mxr[0] = xfs_rtrmapbt_maxrecs(mp, sbp->sb_blocksize, true); mp->m_rtrmap_mxr[1] = xfs_rtrmapbt_maxrecs(mp, sbp->sb_blocksize, false); mp->m_rtrmap_mnr[0] = mp->m_rtrmap_mxr[0] / 2; mp->m_rtrmap_mnr[1] = mp->m_rtrmap_mxr[1] / 2; mp->m_refc_mxr[0] = xfs_refcountbt_maxrecs(mp, sbp->sb_blocksize, true); mp->m_refc_mxr[1] = xfs_refcountbt_maxrecs(mp, sbp->sb_blocksize, false); mp->m_refc_mnr[0] = mp->m_refc_mxr[0] / 2; mp->m_refc_mnr[1] = mp->m_refc_mxr[1] / 2; mp->m_rtrefc_mxr[0] = xfs_rtrefcountbt_maxrecs(mp, sbp->sb_blocksize, true); mp->m_rtrefc_mxr[1] = xfs_rtrefcountbt_maxrecs(mp, sbp->sb_blocksize, false); mp->m_rtrefc_mnr[0] = mp->m_rtrefc_mxr[0] / 2; mp->m_rtrefc_mnr[1] = mp->m_rtrefc_mxr[1] / 2; mp->m_bsize = XFS_FSB_TO_BB(mp, 1); mp->m_alloc_set_aside = xfs_alloc_set_aside(mp); mp->m_ag_max_usable = xfs_alloc_ag_max_usable(mp); } /* * xfs_log_sb() can be used to copy arbitrary changes to the in-core superblock * into the superblock buffer to be logged. It does not provide the higher * level of locking that is needed to protect the in-core superblock from * concurrent access. */ void xfs_log_sb( struct xfs_trans *tp) { struct xfs_mount *mp = tp->t_mountp; struct xfs_buf *bp = xfs_trans_getsb(tp); /* * Lazy sb counters don't update the in-core superblock so do that now. * If this is at unmount, the counters will be exactly correct, but at * any other time they will only be ballpark correct because of * reservations that have been taken out percpu counters. If we have an * unclean shutdown, this will be corrected by log recovery rebuilding * the counters from the AGF block counts. */ if (xfs_has_lazysbcount(mp)) { mp->m_sb.sb_icount = percpu_counter_sum_positive(&mp->m_icount); mp->m_sb.sb_ifree = min_t(uint64_t, percpu_counter_sum_positive(&mp->m_ifree), mp->m_sb.sb_icount); mp->m_sb.sb_fdblocks = xfs_sum_freecounter(mp, XC_FREE_BLOCKS); } /* * sb_frextents was added to the lazy sb counters when the rt groups * feature was introduced. This counter can go negative due to the way * we handle nearly-lockless reservations, so we must use the _positive * variant here to avoid writing out nonsense frextents. */ if (xfs_has_rtgroups(mp) && !xfs_has_zoned(mp)) { mp->m_sb.sb_frextents = xfs_sum_freecounter(mp, XC_FREE_RTEXTENTS); } xfs_sb_to_disk(bp->b_addr, &mp->m_sb); xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF); xfs_trans_log_buf(tp, bp, 0, sizeof(struct xfs_dsb) - 1); } /* * xfs_sync_sb * * Sync the superblock to disk. * * Note that the caller is responsible for checking the frozen state of the * filesystem. This procedure uses the non-blocking transaction allocator and * thus will allow modifications to a frozen fs. This is required because this * code can be called during the process of freezing where use of the high-level * allocator would deadlock. */ int xfs_sync_sb( struct xfs_mount *mp, bool wait) { struct xfs_trans *tp; int error; error = xfs_trans_alloc(mp, &M_RES(mp)->tr_sb, 0, 0, XFS_TRANS_NO_WRITECOUNT, &tp); if (error) return error; xfs_log_sb(tp); if (wait) xfs_trans_set_sync(tp); return xfs_trans_commit(tp); } /* * Update all the secondary superblocks to match the new state of the primary. * Because we are completely overwriting all the existing fields in the * secondary superblock buffers, there is no need to read them in from disk. * Just get a new buffer, stamp it and write it. * * The sb buffers need to be cached here so that we serialise against other * operations that access the secondary superblocks, but we don't want to keep * them in memory once it is written so we mark it as a one-shot buffer. */ int xfs_update_secondary_sbs( struct xfs_mount *mp) { struct xfs_perag *pag = NULL; int saved_error = 0; int error = 0; LIST_HEAD (buffer_list); /* update secondary superblocks. */ while ((pag = xfs_perag_next_from(mp, pag, 1))) { struct xfs_buf *bp; error = xfs_buf_get(mp->m_ddev_targp, XFS_AG_DADDR(mp, pag_agno(pag), XFS_SB_DADDR), XFS_FSS_TO_BB(mp, 1), &bp); /* * If we get an error reading or writing alternate superblocks, * continue. xfs_repair chooses the "best" superblock based * on most matches; if we break early, we'll leave more * superblocks un-updated than updated, and xfs_repair may * pick them over the properly-updated primary. */ if (error) { xfs_warn(mp, "error allocating secondary superblock for ag %d", pag_agno(pag)); if (!saved_error) saved_error = error; continue; } bp->b_ops = &xfs_sb_buf_ops; xfs_buf_oneshot(bp); xfs_buf_zero(bp, 0, BBTOB(bp->b_length)); xfs_sb_to_disk(bp->b_addr, &mp->m_sb); xfs_buf_delwri_queue(bp, &buffer_list); xfs_buf_relse(bp); /* don't hold too many buffers at once */ if (pag_agno(pag) % 16) continue; error = xfs_buf_delwri_submit(&buffer_list); if (error) { xfs_warn(mp, "write error %d updating a secondary superblock near ag %d", error, pag_agno(pag)); if (!saved_error) saved_error = error; continue; } } error = xfs_buf_delwri_submit(&buffer_list); if (error) xfs_warn(mp, "error %d writing secondary superblocks", error); return saved_error ? saved_error : error; } /* * Same behavior as xfs_sync_sb, except that it is always synchronous and it * also writes the superblock buffer to disk sector 0 immediately. */ int xfs_sync_sb_buf( struct xfs_mount *mp, bool update_rtsb) { struct xfs_trans *tp; struct xfs_buf *bp; struct xfs_buf *rtsb_bp = NULL; int error; error = xfs_trans_alloc(mp, &M_RES(mp)->tr_sb, 0, 0, 0, &tp); if (error) return error; bp = xfs_trans_getsb(tp); xfs_log_sb(tp); xfs_trans_bhold(tp, bp); if (update_rtsb) { rtsb_bp = xfs_log_rtsb(tp, bp); if (rtsb_bp) xfs_trans_bhold(tp, rtsb_bp); } xfs_trans_set_sync(tp); error = xfs_trans_commit(tp); if (error) goto out; /* * write out the sb buffer to get the changes to disk */ error = xfs_bwrite(bp); if (!error && rtsb_bp) error = xfs_bwrite(rtsb_bp); out: if (rtsb_bp) xfs_buf_relse(rtsb_bp); xfs_buf_relse(bp); return error; } void xfs_fs_geometry( struct xfs_mount *mp, struct xfs_fsop_geom *geo, int struct_version) { struct xfs_sb *sbp = &mp->m_sb; memset(geo, 0, sizeof(struct xfs_fsop_geom)); geo->blocksize = sbp->sb_blocksize; geo->rtextsize = sbp->sb_rextsize; geo->agblocks = sbp->sb_agblocks; geo->agcount = sbp->sb_agcount; geo->logblocks = sbp->sb_logblocks; geo->sectsize = sbp->sb_sectsize; geo->inodesize = sbp->sb_inodesize; geo->imaxpct = sbp->sb_imax_pct; geo->datablocks = sbp->sb_dblocks; geo->rtblocks = sbp->sb_rblocks; geo->rtextents = sbp->sb_rextents; geo->logstart = sbp->sb_logstart; BUILD_BUG_ON(sizeof(geo->uuid) != sizeof(sbp->sb_uuid)); memcpy(geo->uuid, &sbp->sb_uuid, sizeof(sbp->sb_uuid)); if (struct_version < 2) return; geo->sunit = sbp->sb_unit; geo->swidth = sbp->sb_width; if (struct_version < 3) return; geo->version = XFS_FSOP_GEOM_VERSION; geo->flags = XFS_FSOP_GEOM_FLAGS_NLINK | XFS_FSOP_GEOM_FLAGS_DIRV2 | XFS_FSOP_GEOM_FLAGS_EXTFLG; if (xfs_has_attr(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_ATTR; if (xfs_has_quota(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_QUOTA; if (xfs_has_align(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_IALIGN; if (xfs_has_dalign(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_DALIGN; if (xfs_has_asciici(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_DIRV2CI; if (xfs_has_lazysbcount(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_LAZYSB; if (xfs_has_attr2(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_ATTR2; if (xfs_has_projid32(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_PROJID32; if (xfs_has_crc(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_V5SB; if (xfs_has_ftype(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_FTYPE; if (xfs_has_finobt(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_FINOBT; if (xfs_has_sparseinodes(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_SPINODES; if (xfs_has_rmapbt(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_RMAPBT; if (xfs_has_reflink(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_REFLINK; if (xfs_has_bigtime(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_BIGTIME; if (xfs_has_inobtcounts(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_INOBTCNT; if (xfs_has_parent(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_PARENT; if (xfs_has_sector(mp)) { geo->flags |= XFS_FSOP_GEOM_FLAGS_SECTOR; geo->logsectsize = sbp->sb_logsectsize; } else { geo->logsectsize = BBSIZE; } if (xfs_has_large_extent_counts(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_NREXT64; if (xfs_has_exchange_range(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_EXCHANGE_RANGE; if (xfs_has_metadir(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_METADIR; if (xfs_has_zoned(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_ZONED; geo->rtsectsize = sbp->sb_blocksize; geo->dirblocksize = xfs_dir2_dirblock_bytes(sbp); if (struct_version < 4) return; if (xfs_has_logv2(mp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_LOGV2; geo->logsunit = sbp->sb_logsunit; if (struct_version < 5) return; geo->version = XFS_FSOP_GEOM_VERSION_V5; if (xfs_has_rtgroups(mp)) { geo->rgcount = sbp->sb_rgcount; geo->rgextents = sbp->sb_rgextents; } if (xfs_has_zoned(mp)) { geo->rtstart = sbp->sb_rtstart; geo->rtreserved = sbp->sb_rtreserved; } } /* Read a secondary superblock. */ int xfs_sb_read_secondary( struct xfs_mount *mp, struct xfs_trans *tp, xfs_agnumber_t agno, struct xfs_buf **bpp) { struct xfs_buf *bp; int error; ASSERT(agno != 0 && agno != NULLAGNUMBER); error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, XFS_AG_DADDR(mp, agno, XFS_SB_BLOCK(mp)), XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_sb_buf_ops); if (xfs_metadata_is_sick(error)) xfs_agno_mark_sick(mp, agno, XFS_SICK_AG_SB); if (error) return error; xfs_buf_set_ref(bp, XFS_SSB_REF); *bpp = bp; return 0; } /* Get an uninitialised secondary superblock buffer. */ int xfs_sb_get_secondary( struct xfs_mount *mp, struct xfs_trans *tp, xfs_agnumber_t agno, struct xfs_buf **bpp) { struct xfs_buf *bp; int error; ASSERT(agno != 0 && agno != NULLAGNUMBER); error = xfs_trans_get_buf(tp, mp->m_ddev_targp, XFS_AG_DADDR(mp, agno, XFS_SB_BLOCK(mp)), XFS_FSS_TO_BB(mp, 1), 0, &bp); if (error) return error; bp->b_ops = &xfs_sb_buf_ops; xfs_buf_oneshot(bp); *bpp = bp; return 0; } /* * sunit, swidth, sectorsize(optional with 0) should be all in bytes, so users * won't be confused by values in error messages. This function returns false * if the stripe geometry is invalid and the caller is unable to repair the * stripe configuration later in the mount process. */ bool xfs_validate_stripe_geometry( struct xfs_mount *mp, __s64 sunit, __s64 swidth, int sectorsize, bool may_repair, bool silent) { if (swidth > INT_MAX) { if (!silent) xfs_notice(mp, "stripe width (%lld) is too large", swidth); goto check_override; } if (sunit > swidth) { if (!silent) xfs_notice(mp, "stripe unit (%lld) is larger than the stripe width (%lld)", sunit, swidth); goto check_override; } if (sectorsize && (int)sunit % sectorsize) { if (!silent) xfs_notice(mp, "stripe unit (%lld) must be a multiple of the sector size (%d)", sunit, sectorsize); goto check_override; } if (sunit && !swidth) { if (!silent) xfs_notice(mp, "invalid stripe unit (%lld) and stripe width of 0", sunit); goto check_override; } if (!sunit && swidth) { if (!silent) xfs_notice(mp, "invalid stripe width (%lld) and stripe unit of 0", swidth); goto check_override; } if (sunit && (int)swidth % (int)sunit) { if (!silent) xfs_notice(mp, "stripe width (%lld) must be a multiple of the stripe unit (%lld)", swidth, sunit); goto check_override; } return true; check_override: if (!may_repair) return false; /* * During mount, mp->m_dalign will not be set unless the sunit mount * option was set. If it was set, ignore the bad stripe alignment values * and allow the validation and overwrite later in the mount process to * attempt to overwrite the bad stripe alignment values with the values * supplied by mount options. */ if (!mp->m_dalign) return false; if (!silent) xfs_notice(mp, "Will try to correct with specified mount options sunit (%d) and swidth (%d)", BBTOB(mp->m_dalign), BBTOB(mp->m_swidth)); return true; } /* * Compute the maximum level number of the realtime summary file, as defined by * mkfs. The historic use of highbit32 on a 64-bit quantity prohibited correct * use of rt volumes with more than 2^32 extents. */ uint8_t xfs_compute_rextslog( xfs_rtbxlen_t rtextents) { if (!rtextents) return 0; return xfs_highbit64(rtextents); } |
| 9102 9121 5 5 5 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 | // SPDX-License-Identifier: GPL-2.0-only /* * x86 APERF/MPERF KHz calculation for * /sys/.../cpufreq/scaling_cur_freq * * Copyright (C) 2017 Intel Corp. * Author: Len Brown <len.brown@intel.com> */ #include <linux/cpufreq.h> #include <linux/delay.h> #include <linux/ktime.h> #include <linux/math64.h> #include <linux/percpu.h> #include <linux/rcupdate.h> #include <linux/sched/isolation.h> #include <linux/sched/topology.h> #include <linux/smp.h> #include <linux/syscore_ops.h> #include <asm/cpu.h> #include <asm/cpu_device_id.h> #include <asm/intel-family.h> #include "cpu.h" struct aperfmperf { seqcount_t seq; unsigned long last_update; u64 acnt; u64 mcnt; u64 aperf; u64 mperf; }; static DEFINE_PER_CPU_SHARED_ALIGNED(struct aperfmperf, cpu_samples) = { .seq = SEQCNT_ZERO(cpu_samples.seq) }; static void init_counter_refs(void) { u64 aperf, mperf; rdmsrl(MSR_IA32_APERF, aperf); rdmsrl(MSR_IA32_MPERF, mperf); this_cpu_write(cpu_samples.aperf, aperf); this_cpu_write(cpu_samples.mperf, mperf); } #if defined(CONFIG_X86_64) && defined(CONFIG_SMP) /* * APERF/MPERF frequency ratio computation. * * The scheduler wants to do frequency invariant accounting and needs a <1 * ratio to account for the 'current' frequency, corresponding to * freq_curr / freq_max. * * Since the frequency freq_curr on x86 is controlled by micro-controller and * our P-state setting is little more than a request/hint, we need to observe * the effective frequency 'BusyMHz', i.e. the average frequency over a time * interval after discarding idle time. This is given by: * * BusyMHz = delta_APERF / delta_MPERF * freq_base * * where freq_base is the max non-turbo P-state. * * The freq_max term has to be set to a somewhat arbitrary value, because we * can't know which turbo states will be available at a given point in time: * it all depends on the thermal headroom of the entire package. We set it to * the turbo level with 4 cores active. * * Benchmarks show that's a good compromise between the 1C turbo ratio * (freq_curr/freq_max would rarely reach 1) and something close to freq_base, * which would ignore the entire turbo range (a conspicuous part, making * freq_curr/freq_max always maxed out). * * An exception to the heuristic above is the Atom uarch, where we choose the * highest turbo level for freq_max since Atom's are generally oriented towards * power efficiency. * * Setting freq_max to anything less than the 1C turbo ratio makes the ratio * freq_curr / freq_max to eventually grow >1, in which case we clip it to 1. */ DEFINE_STATIC_KEY_FALSE(arch_scale_freq_key); static u64 arch_turbo_freq_ratio = SCHED_CAPACITY_SCALE; static u64 arch_max_freq_ratio = SCHED_CAPACITY_SCALE; void arch_set_max_freq_ratio(bool turbo_disabled) { arch_max_freq_ratio = turbo_disabled ? SCHED_CAPACITY_SCALE : arch_turbo_freq_ratio; } EXPORT_SYMBOL_GPL(arch_set_max_freq_ratio); static bool __init turbo_disabled(void) { u64 misc_en; int err; err = rdmsrl_safe(MSR_IA32_MISC_ENABLE, &misc_en); if (err) return false; return (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE); } static bool __init slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) { int err; err = rdmsrl_safe(MSR_ATOM_CORE_RATIOS, base_freq); if (err) return false; err = rdmsrl_safe(MSR_ATOM_CORE_TURBO_RATIOS, turbo_freq); if (err) return false; *base_freq = (*base_freq >> 16) & 0x3F; /* max P state */ *turbo_freq = *turbo_freq & 0x3F; /* 1C turbo */ return true; } #define X86_MATCH(vfm) \ X86_MATCH_VFM_FEATURE(vfm, X86_FEATURE_APERFMPERF, NULL) static const struct x86_cpu_id has_knl_turbo_ratio_limits[] __initconst = { X86_MATCH(INTEL_XEON_PHI_KNL), X86_MATCH(INTEL_XEON_PHI_KNM), {} }; static const struct x86_cpu_id has_skx_turbo_ratio_limits[] __initconst = { X86_MATCH(INTEL_SKYLAKE_X), {} }; static const struct x86_cpu_id has_glm_turbo_ratio_limits[] __initconst = { X86_MATCH(INTEL_ATOM_GOLDMONT), X86_MATCH(INTEL_ATOM_GOLDMONT_D), X86_MATCH(INTEL_ATOM_GOLDMONT_PLUS), {} }; static bool __init knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int num_delta_fratio) { int fratio, delta_fratio, found; int err, i; u64 msr; err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); if (err) return false; *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr); if (err) return false; fratio = (msr >> 8) & 0xFF; i = 16; found = 0; do { if (found >= num_delta_fratio) { *turbo_freq = fratio; return true; } delta_fratio = (msr >> (i + 5)) & 0x7; if (delta_fratio) { found += 1; fratio -= delta_fratio; } i += 8; } while (i < 64); return true; } static bool __init skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size) { u64 ratios, counts; u32 group_size; int err, i; err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); if (err) return false; *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &ratios); if (err) return false; err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT1, &counts); if (err) return false; for (i = 0; i < 64; i += 8) { group_size = (counts >> i) & 0xFF; if (group_size >= size) { *turbo_freq = (ratios >> i) & 0xFF; return true; } } return false; } static bool __init core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) { u64 msr; int err; err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); if (err) return false; err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr); if (err) return false; *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ *turbo_freq = (msr >> 24) & 0xFF; /* 4C turbo */ /* The CPU may have less than 4 cores */ if (!*turbo_freq) *turbo_freq = msr & 0xFF; /* 1C turbo */ return true; } static bool __init intel_set_max_freq_ratio(void) { u64 base_freq, turbo_freq; u64 turbo_ratio; if (slv_set_max_freq_ratio(&base_freq, &turbo_freq)) goto out; if (x86_match_cpu(has_glm_turbo_ratio_limits) && skx_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) goto out; if (x86_match_cpu(has_knl_turbo_ratio_limits) && knl_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) goto out; if (x86_match_cpu(has_skx_turbo_ratio_limits) && skx_set_max_freq_ratio(&base_freq, &turbo_freq, 4)) goto out; if (core_set_max_freq_ratio(&base_freq, &turbo_freq)) goto out; return false; out: /* * Some hypervisors advertise X86_FEATURE_APERFMPERF * but then fill all MSR's with zeroes. * Some CPUs have turbo boost but don't declare any turbo ratio * in MSR_TURBO_RATIO_LIMIT. */ if (!base_freq || !turbo_freq) { pr_debug("Couldn't determine cpu base or turbo frequency, necessary for scale-invariant accounting.\n"); return false; } turbo_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE, base_freq); if (!turbo_ratio) { pr_debug("Non-zero turbo and base frequencies led to a 0 ratio.\n"); return false; } arch_turbo_freq_ratio = turbo_ratio; arch_set_max_freq_ratio(turbo_disabled()); return true; } #ifdef CONFIG_PM_SLEEP static struct syscore_ops freq_invariance_syscore_ops = { .resume = init_counter_refs, }; static void register_freq_invariance_syscore_ops(void) { register_syscore_ops(&freq_invariance_syscore_ops); } #else static inline void register_freq_invariance_syscore_ops(void) {} #endif static void freq_invariance_enable(void) { if (static_branch_unlikely(&arch_scale_freq_key)) { WARN_ON_ONCE(1); return; } static_branch_enable_cpuslocked(&arch_scale_freq_key); register_freq_invariance_syscore_ops(); pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio); } void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled) { arch_turbo_freq_ratio = ratio; arch_set_max_freq_ratio(turbo_disabled); freq_invariance_enable(); } static void __init bp_init_freq_invariance(void) { if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return; if (intel_set_max_freq_ratio()) { guard(cpus_read_lock)(); freq_invariance_enable(); } } static void disable_freq_invariance_workfn(struct work_struct *work) { int cpu; static_branch_disable(&arch_scale_freq_key); /* * Set arch_freq_scale to a default value on all cpus * This negates the effect of scaling */ for_each_possible_cpu(cpu) per_cpu(arch_freq_scale, cpu) = SCHED_CAPACITY_SCALE; } static DECLARE_WORK(disable_freq_invariance_work, disable_freq_invariance_workfn); DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE; EXPORT_PER_CPU_SYMBOL_GPL(arch_freq_scale); static DEFINE_STATIC_KEY_FALSE(arch_hybrid_cap_scale_key); struct arch_hybrid_cpu_scale { unsigned long capacity; unsigned long freq_ratio; }; static struct arch_hybrid_cpu_scale __percpu *arch_cpu_scale; /** * arch_enable_hybrid_capacity_scale() - Enable hybrid CPU capacity scaling * * Allocate memory for per-CPU data used by hybrid CPU capacity scaling, * initialize it and set the static key controlling its code paths. * * Must be called before arch_set_cpu_capacity(). */ bool arch_enable_hybrid_capacity_scale(void) { int cpu; if (static_branch_unlikely(&arch_hybrid_cap_scale_key)) { WARN_ONCE(1, "Hybrid CPU capacity scaling already enabled"); return true; } arch_cpu_scale = alloc_percpu(struct arch_hybrid_cpu_scale); if (!arch_cpu_scale) return false; for_each_possible_cpu(cpu) { per_cpu_ptr(arch_cpu_scale, cpu)->capacity = SCHED_CAPACITY_SCALE; per_cpu_ptr(arch_cpu_scale, cpu)->freq_ratio = arch_max_freq_ratio; } static_branch_enable(&arch_hybrid_cap_scale_key); pr_info("Hybrid CPU capacity scaling enabled\n"); return true; } /** * arch_set_cpu_capacity() - Set scale-invariance parameters for a CPU * @cpu: Target CPU. * @cap: Capacity of @cpu at its maximum frequency, relative to @max_cap. * @max_cap: System-wide maximum CPU capacity. * @cap_freq: Frequency of @cpu corresponding to @cap. * @base_freq: Frequency of @cpu at which MPERF counts. * * The units in which @cap and @max_cap are expressed do not matter, so long * as they are consistent, because the former is effectively divided by the * latter. Analogously for @cap_freq and @base_freq. * * After calling this function for all CPUs, call arch_rebuild_sched_domains() * to let the scheduler know that capacity-aware scheduling can be used going * forward. */ void arch_set_cpu_capacity(int cpu, unsigned long cap, unsigned long max_cap, unsigned long cap_freq, unsigned long base_freq) { if (static_branch_likely(&arch_hybrid_cap_scale_key)) { WRITE_ONCE(per_cpu_ptr(arch_cpu_scale, cpu)->capacity, div_u64(cap << SCHED_CAPACITY_SHIFT, max_cap)); WRITE_ONCE(per_cpu_ptr(arch_cpu_scale, cpu)->freq_ratio, div_u64(cap_freq << SCHED_CAPACITY_SHIFT, base_freq)); } else { WARN_ONCE(1, "Hybrid CPU capacity scaling not enabled"); } } unsigned long arch_scale_cpu_capacity(int cpu) { if (static_branch_unlikely(&arch_hybrid_cap_scale_key)) return READ_ONCE(per_cpu_ptr(arch_cpu_scale, cpu)->capacity); return SCHED_CAPACITY_SCALE; } EXPORT_SYMBOL_GPL(arch_scale_cpu_capacity); static void scale_freq_tick(u64 acnt, u64 mcnt) { u64 freq_scale, freq_ratio; if (!arch_scale_freq_invariant()) return; if (check_shl_overflow(acnt, 2*SCHED_CAPACITY_SHIFT, &acnt)) goto error; if (static_branch_unlikely(&arch_hybrid_cap_scale_key)) freq_ratio = READ_ONCE(this_cpu_ptr(arch_cpu_scale)->freq_ratio); else freq_ratio = arch_max_freq_ratio; if (check_mul_overflow(mcnt, freq_ratio, &mcnt) || !mcnt) goto error; freq_scale = div64_u64(acnt, mcnt); if (!freq_scale) goto error; if (freq_scale > SCHED_CAPACITY_SCALE) freq_scale = SCHED_CAPACITY_SCALE; this_cpu_write(arch_freq_scale, freq_scale); return; error: pr_warn("Scheduler frequency invariance went wobbly, disabling!\n"); schedule_work(&disable_freq_invariance_work); } #else static inline void bp_init_freq_invariance(void) { } static inline void scale_freq_tick(u64 acnt, u64 mcnt) { } #endif /* CONFIG_X86_64 && CONFIG_SMP */ void arch_scale_freq_tick(void) { struct aperfmperf *s = this_cpu_ptr(&cpu_samples); u64 acnt, mcnt, aperf, mperf; if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF)) return; rdmsrl(MSR_IA32_APERF, aperf); rdmsrl(MSR_IA32_MPERF, mperf); acnt = aperf - s->aperf; mcnt = mperf - s->mperf; s->aperf = aperf; s->mperf = mperf; raw_write_seqcount_begin(&s->seq); s->last_update = jiffies; s->acnt = acnt; s->mcnt = mcnt; raw_write_seqcount_end(&s->seq); scale_freq_tick(acnt, mcnt); } /* * Discard samples older than the define maximum sample age of 20ms. There * is no point in sending IPIs in such a case. If the scheduler tick was * not running then the CPU is either idle or isolated. */ #define MAX_SAMPLE_AGE ((unsigned long)HZ / 50) int arch_freq_get_on_cpu(int cpu) { struct aperfmperf *s = per_cpu_ptr(&cpu_samples, cpu); unsigned int seq, freq; unsigned long last; u64 acnt, mcnt; if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF)) goto fallback; do { seq = raw_read_seqcount_begin(&s->seq); last = s->last_update; acnt = s->acnt; mcnt = s->mcnt; } while (read_seqcount_retry(&s->seq, seq)); /* * Bail on invalid count and when the last update was too long ago, * which covers idle and NOHZ full CPUs. */ if (!mcnt || (jiffies - last) > MAX_SAMPLE_AGE) goto fallback; return div64_u64((cpu_khz * acnt), mcnt); fallback: freq = cpufreq_quick_get(cpu); return freq ? freq : cpu_khz; } static int __init bp_init_aperfmperf(void) { if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF)) return 0; init_counter_refs(); bp_init_freq_invariance(); return 0; } early_initcall(bp_init_aperfmperf); void ap_init_aperfmperf(void) { if (cpu_feature_enabled(X86_FEATURE_APERFMPERF)) init_counter_refs(); } |
| 98 98 98 98 116 116 10 1 9 9 9 10 10 1 9 8 121 8 5 106 5 5 121 2 7 106 1 5 5 1 4 23 17 7 22 1 23 17 7 7 26 5 17 3 3 21 2 2 2 2 2 2 1 1 1 2 2 2 22 22 27 21 6 8 20 26 2 27 20 16 4 9 6 4 4 3 8 5 3 7 1 11 11 1 8 2 2 8 3 3 3 1 2 3 4 13 14 1 13 17 17 4 3 11 3 1 10 3 11 12 5 21 2 6 6 10 10 8 7 10 22 22 1 21 5 16 14 2 3 5 7 6 12 17 13 2 2 1 3 8 9 1 7 7 9 1 8 12 3 2 3 3 14 9 1 4 11 3 5 9 7 7 5 12 2 1 1 1 2 1 2 2 2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * * Copyright (C) 2011 Novell Inc. */ #include <linux/fs.h> #include <linux/namei.h> #include <linux/xattr.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/module.h> #include <linux/posix_acl.h> #include <linux/posix_acl_xattr.h> #include <linux/atomic.h> #include <linux/ratelimit.h> #include <linux/backing-file.h> #include "overlayfs.h" static unsigned short ovl_redirect_max = 256; module_param_named(redirect_max, ovl_redirect_max, ushort, 0644); MODULE_PARM_DESC(redirect_max, "Maximum length of absolute redirect xattr value"); static int ovl_set_redirect(struct dentry *dentry, bool samedir); int ovl_cleanup(struct ovl_fs *ofs, struct inode *wdir, struct dentry *wdentry) { int err; dget(wdentry); if (d_is_dir(wdentry)) err = ovl_do_rmdir(ofs, wdir, wdentry); else err = ovl_do_unlink(ofs, wdir, wdentry); dput(wdentry); if (err) { pr_err("cleanup of '%pd2' failed (%i)\n", wdentry, err); } return err; } struct dentry *ovl_lookup_temp(struct ovl_fs *ofs, struct dentry *workdir) { struct dentry *temp; char name[20]; static atomic_t temp_id = ATOMIC_INIT(0); /* counter is allowed to wrap, since temp dentries are ephemeral */ snprintf(name, sizeof(name), "#%x", atomic_inc_return(&temp_id)); temp = ovl_lookup_upper(ofs, name, workdir, strlen(name)); if (!IS_ERR(temp) && temp->d_inode) { pr_err("workdir/%s already exists\n", name); dput(temp); temp = ERR_PTR(-EIO); } return temp; } /* caller holds i_mutex on workdir */ static struct dentry *ovl_whiteout(struct ovl_fs *ofs) { int err; struct dentry *whiteout; struct dentry *workdir = ofs->workdir; struct inode *wdir = workdir->d_inode; if (!ofs->whiteout) { whiteout = ovl_lookup_temp(ofs, workdir); if (IS_ERR(whiteout)) goto out; err = ovl_do_whiteout(ofs, wdir, whiteout); if (err) { dput(whiteout); whiteout = ERR_PTR(err); goto out; } ofs->whiteout = whiteout; } if (!ofs->no_shared_whiteout) { whiteout = ovl_lookup_temp(ofs, workdir); if (IS_ERR(whiteout)) goto out; err = ovl_do_link(ofs, ofs->whiteout, wdir, whiteout); if (!err) goto out; if (err != -EMLINK) { pr_warn("Failed to link whiteout - disabling whiteout inode sharing(nlink=%u, err=%i)\n", ofs->whiteout->d_inode->i_nlink, err); ofs->no_shared_whiteout = true; } dput(whiteout); } whiteout = ofs->whiteout; ofs->whiteout = NULL; out: return whiteout; } /* Caller must hold i_mutex on both workdir and dir */ int ovl_cleanup_and_whiteout(struct ovl_fs *ofs, struct inode *dir, struct dentry *dentry) { struct inode *wdir = ofs->workdir->d_inode; struct dentry *whiteout; int err; int flags = 0; whiteout = ovl_whiteout(ofs); err = PTR_ERR(whiteout); if (IS_ERR(whiteout)) return err; if (d_is_dir(dentry)) flags = RENAME_EXCHANGE; err = ovl_do_rename(ofs, wdir, whiteout, dir, dentry, flags); if (err) goto kill_whiteout; if (flags) ovl_cleanup(ofs, wdir, dentry); out: dput(whiteout); return err; kill_whiteout: ovl_cleanup(ofs, wdir, whiteout); goto out; } struct dentry *ovl_create_real(struct ovl_fs *ofs, struct inode *dir, struct dentry *newdentry, struct ovl_cattr *attr) { int err; if (IS_ERR(newdentry)) return newdentry; err = -ESTALE; if (newdentry->d_inode) goto out; if (attr->hardlink) { err = ovl_do_link(ofs, attr->hardlink, dir, newdentry); } else { switch (attr->mode & S_IFMT) { case S_IFREG: err = ovl_do_create(ofs, dir, newdentry, attr->mode); break; case S_IFDIR: /* mkdir is special... */ newdentry = ovl_do_mkdir(ofs, dir, newdentry, attr->mode); err = PTR_ERR_OR_ZERO(newdentry); break; case S_IFCHR: case S_IFBLK: case S_IFIFO: case S_IFSOCK: err = ovl_do_mknod(ofs, dir, newdentry, attr->mode, attr->rdev); break; case S_IFLNK: err = ovl_do_symlink(ofs, dir, newdentry, attr->link); break; default: err = -EPERM; } } if (!err && WARN_ON(!newdentry->d_inode)) { /* * Not quite sure if non-instantiated dentry is legal or not. * VFS doesn't seem to care so check and warn here. */ err = -EIO; } out: if (err) { if (!IS_ERR(newdentry)) dput(newdentry); return ERR_PTR(err); } return newdentry; } struct dentry *ovl_create_temp(struct ovl_fs *ofs, struct dentry *workdir, struct ovl_cattr *attr) { return ovl_create_real(ofs, d_inode(workdir), ovl_lookup_temp(ofs, workdir), attr); } static int ovl_set_opaque_xerr(struct dentry *dentry, struct dentry *upper, int xerr) { struct ovl_fs *ofs = OVL_FS(dentry->d_sb); int err; err = ovl_check_setxattr(ofs, upper, OVL_XATTR_OPAQUE, "y", 1, xerr); if (!err) ovl_dentry_set_opaque(dentry); return err; } static int ovl_set_opaque(struct dentry *dentry, struct dentry *upperdentry) { /* * Fail with -EIO when trying to create opaque dir and upper doesn't * support xattrs. ovl_rename() calls ovl_set_opaque_xerr(-EXDEV) to * return a specific error for noxattr case. */ return ovl_set_opaque_xerr(dentry, upperdentry, -EIO); } /* * Common operations required to be done after creation of file on upper. * If @hardlink is false, then @inode is a pre-allocated inode, we may or * may not use to instantiate the new dentry. */ static int ovl_instantiate(struct dentry *dentry, struct inode *inode, struct dentry *newdentry, bool hardlink, struct file *tmpfile) { struct ovl_inode_params oip = { .upperdentry = newdentry, .newinode = inode, }; ovl_dentry_set_upper_alias(dentry); ovl_dentry_init_reval(dentry, newdentry, NULL); if (!hardlink) { /* * ovl_obtain_alias() can be called after ovl_create_real() * and before we get here, so we may get an inode from cache * with the same real upperdentry that is not the inode we * pre-allocated. In this case we will use the cached inode * to instantiate the new dentry. * * XXX: if we ever use ovl_obtain_alias() to decode directory * file handles, need to use ovl_get_inode_locked() and * d_instantiate_new() here to prevent from creating two * hashed directory inode aliases. We then need to return * the obtained alias to ovl_mkdir(). */ inode = ovl_get_inode(dentry->d_sb, &oip); if (IS_ERR(inode)) return PTR_ERR(inode); if (inode == oip.newinode) ovl_set_flag(OVL_UPPERDATA, inode); } else { WARN_ON(ovl_inode_real(inode) != d_inode(newdentry)); dput(newdentry); inc_nlink(inode); } if (tmpfile) d_mark_tmpfile(tmpfile, inode); d_instantiate(dentry, inode); if (inode != oip.newinode) { pr_warn_ratelimited("newly created inode found in cache (%pd2)\n", dentry); } /* Force lookup of new upper hardlink to find its lower */ if (hardlink) d_drop(dentry); return 0; } static bool ovl_type_merge(struct dentry *dentry) { return OVL_TYPE_MERGE(ovl_path_type(dentry)); } static bool ovl_type_origin(struct dentry *dentry) { return OVL_TYPE_ORIGIN(ovl_path_type(dentry)); } static int ovl_create_upper(struct dentry *dentry, struct inode *inode, struct ovl_cattr *attr) { struct ovl_fs *ofs = OVL_FS(dentry->d_sb); struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent); struct inode *udir = upperdir->d_inode; struct dentry *newdentry; int err; inode_lock_nested(udir, I_MUTEX_PARENT); newdentry = ovl_create_real(ofs, udir, ovl_lookup_upper(ofs, dentry->d_name.name, upperdir, dentry->d_name.len), attr); err = PTR_ERR(newdentry); if (IS_ERR(newdentry)) goto out_unlock; if (ovl_type_merge(dentry->d_parent) && d_is_dir(newdentry) && !ovl_allow_offline_changes(ofs)) { /* Setting opaque here is just an optimization, allow to fail */ ovl_set_opaque(dentry, newdentry); } ovl_dir_modified(dentry->d_parent, false); err = ovl_instantiate(dentry, inode, newdentry, !!attr->hardlink, NULL); if (err) goto out_cleanup; out_unlock: inode_unlock(udir); return err; out_cleanup: ovl_cleanup(ofs, udir, newdentry); dput(newdentry); goto out_unlock; } static struct dentry *ovl_clear_empty(struct dentry *dentry, struct list_head *list) { struct ovl_fs *ofs = OVL_FS(dentry->d_sb); struct dentry *workdir = ovl_workdir(dentry); struct inode *wdir = workdir->d_inode; struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent); struct inode *udir = upperdir->d_inode; struct path upperpath; struct dentry *upper; struct dentry *opaquedir; struct kstat stat; int err; if (WARN_ON(!workdir)) return ERR_PTR(-EROFS); err = ovl_lock_rename_workdir(workdir, upperdir); if (err) goto out; ovl_path_upper(dentry, &upperpath); err = vfs_getattr(&upperpath, &stat, STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT); if (err) goto out_unlock; err = -ESTALE; if (!S_ISDIR(stat.mode)) goto out_unlock; upper = upperpath.dentry; if (upper->d_parent->d_inode != udir) goto out_unlock; opaquedir = ovl_create_temp(ofs, workdir, OVL_CATTR(stat.mode)); err = PTR_ERR(opaquedir); if (IS_ERR(opaquedir)) goto out_unlock; err = ovl_copy_xattr(dentry->d_sb, &upperpath, opaquedir); if (err) goto out_cleanup; err = ovl_set_opaque(dentry, opaquedir); if (err) goto out_cleanup; inode_lock(opaquedir->d_inode); err = ovl_set_attr(ofs, opaquedir, &stat); inode_unlock(opaquedir->d_inode); if (err) goto out_cleanup; err = ovl_do_rename(ofs, wdir, opaquedir, udir, upper, RENAME_EXCHANGE); if (err) goto out_cleanup; ovl_cleanup_whiteouts(ofs, upper, list); ovl_cleanup(ofs, wdir, upper); unlock_rename(workdir, upperdir); /* dentry's upper doesn't match now, get rid of it */ d_drop(dentry); return opaquedir; out_cleanup: ovl_cleanup(ofs, wdir, opaquedir); dput(opaquedir); out_unlock: unlock_rename(workdir, upperdir); out: return ERR_PTR(err); } static int ovl_set_upper_acl(struct ovl_fs *ofs, struct dentry *upperdentry, const char *acl_name, struct posix_acl *acl) { if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !acl) return 0; return ovl_do_set_acl(ofs, upperdentry, acl_name, acl); } static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode, struct ovl_cattr *cattr) { struct ovl_fs *ofs = OVL_FS(dentry->d_sb); struct dentry *workdir = ovl_workdir(dentry); struct inode *wdir = workdir->d_inode; struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent); struct inode *udir = upperdir->d_inode; struct dentry *upper; struct dentry *newdentry; int err; struct posix_acl *acl, *default_acl; bool hardlink = !!cattr->hardlink; if (WARN_ON(!workdir)) return -EROFS; if (!hardlink) { err = posix_acl_create(dentry->d_parent->d_inode, &cattr->mode, &default_acl, &acl); if (err) return err; } err = ovl_lock_rename_workdir(workdir, upperdir); if (err) goto out; upper = ovl_lookup_upper(ofs, dentry->d_name.name, upperdir, dentry->d_name.len); err = PTR_ERR(upper); if (IS_ERR(upper)) goto out_unlock; err = -ESTALE; if (d_is_negative(upper) || !ovl_upper_is_whiteout(ofs, upper)) goto out_dput; newdentry = ovl_create_temp(ofs, workdir, cattr); err = PTR_ERR(newdentry); if (IS_ERR(newdentry)) goto out_dput; /* * mode could have been mutilated due to umask (e.g. sgid directory) */ if (!hardlink && !S_ISLNK(cattr->mode) && newdentry->d_inode->i_mode != cattr->mode) { struct iattr attr = { .ia_valid = ATTR_MODE, .ia_mode = cattr->mode, }; inode_lock(newdentry->d_inode); err = ovl_do_notify_change(ofs, newdentry, &attr); inode_unlock(newdentry->d_inode); if (err) goto out_cleanup; } if (!hardlink) { err = ovl_set_upper_acl(ofs, newdentry, XATTR_NAME_POSIX_ACL_ACCESS, acl); if (err) goto out_cleanup; err = ovl_set_upper_acl(ofs, newdentry, XATTR_NAME_POSIX_ACL_DEFAULT, default_acl); if (err) goto out_cleanup; } if (!hardlink && S_ISDIR(cattr->mode)) { err = ovl_set_opaque(dentry, newdentry); if (err) goto out_cleanup; err = ovl_do_rename(ofs, wdir, newdentry, udir, upper, RENAME_EXCHANGE); if (err) goto out_cleanup; ovl_cleanup(ofs, wdir, upper); } else { err = ovl_do_rename(ofs, wdir, newdentry, udir, upper, 0); if (err) goto out_cleanup; } ovl_dir_modified(dentry->d_parent, false); err = ovl_instantiate(dentry, inode, newdentry, hardlink, NULL); if (err) { ovl_cleanup(ofs, udir, newdentry); dput(newdentry); } out_dput: dput(upper); out_unlock: unlock_rename(workdir, upperdir); out: if (!hardlink) { posix_acl_release(acl); posix_acl_release(default_acl); } return err; out_cleanup: ovl_cleanup(ofs, wdir, newdentry); dput(newdentry); goto out_dput; } static const struct cred *ovl_setup_cred_for_create(struct dentry *dentry, struct inode *inode, umode_t mode, const struct cred *old_cred) { int err; struct cred *override_cred; override_cred = prepare_creds(); if (!override_cred) return ERR_PTR(-ENOMEM); override_cred->fsuid = inode->i_uid; override_cred->fsgid = inode->i_gid; err = security_dentry_create_files_as(dentry, mode, &dentry->d_name, old_cred, override_cred); if (err) { put_cred(override_cred); return ERR_PTR(err); } /* * Caller is going to match this with revert_creds() and drop * referenec on the returned creds. * We must be called with creator creds already, otherwise we risk * leaking creds. */ old_cred = override_creds(override_cred); WARN_ON_ONCE(old_cred != ovl_creds(dentry->d_sb)); return override_cred; } static int ovl_create_or_link(struct dentry *dentry, struct inode *inode, struct ovl_cattr *attr, bool origin) { int err; const struct cred *old_cred, *new_cred = NULL; struct dentry *parent = dentry->d_parent; old_cred = ovl_override_creds(dentry->d_sb); /* * When linking a file with copy up origin into a new parent, mark the * new parent dir "impure". */ if (origin) { err = ovl_set_impure(parent, ovl_dentry_upper(parent)); if (err) goto out_revert_creds; } if (!attr->hardlink) { /* * In the creation cases(create, mkdir, mknod, symlink), * ovl should transfer current's fs{u,g}id to underlying * fs. Because underlying fs want to initialize its new * inode owner using current's fs{u,g}id. And in this * case, the @inode is a new inode that is initialized * in inode_init_owner() to current's fs{u,g}id. So use * the inode's i_{u,g}id to override the cred's fs{u,g}id. * * But in the other hardlink case, ovl_link() does not * create a new inode, so just use the ovl mounter's * fs{u,g}id. */ new_cred = ovl_setup_cred_for_create(dentry, inode, attr->mode, old_cred); err = PTR_ERR(new_cred); if (IS_ERR(new_cred)) { new_cred = NULL; goto out_revert_creds; } } if (!ovl_dentry_is_whiteout(dentry)) err = ovl_create_upper(dentry, inode, attr); else err = ovl_create_over_whiteout(dentry, inode, attr); out_revert_creds: ovl_revert_creds(old_cred); put_cred(new_cred); return err; } static int ovl_create_object(struct dentry *dentry, int mode, dev_t rdev, const char *link) { int err; struct inode *inode; struct ovl_cattr attr = { .rdev = rdev, .link = link, }; err = ovl_copy_up(dentry->d_parent); if (err) return err; err = ovl_want_write(dentry); if (err) goto out; /* Preallocate inode to be used by ovl_get_inode() */ err = -ENOMEM; inode = ovl_new_inode(dentry->d_sb, mode, rdev); if (!inode) goto out_drop_write; spin_lock(&inode->i_lock); inode->i_state |= I_CREATING; spin_unlock(&inode->i_lock); inode_init_owner(&nop_mnt_idmap, inode, dentry->d_parent->d_inode, mode); attr.mode = inode->i_mode; err = ovl_create_or_link(dentry, inode, &attr, false); /* Did we end up using the preallocated inode? */ if (inode != d_inode(dentry)) iput(inode); out_drop_write: ovl_drop_write(dentry); out: return err; } static int ovl_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { return ovl_create_object(dentry, (mode & 07777) | S_IFREG, 0, NULL); } static struct dentry *ovl_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { return ERR_PTR(ovl_create_object(dentry, (mode & 07777) | S_IFDIR, 0, NULL)); } static int ovl_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { /* Don't allow creation of "whiteout" on overlay */ if (S_ISCHR(mode) && rdev == WHITEOUT_DEV) return -EPERM; return ovl_create_object(dentry, mode, rdev, NULL); } static int ovl_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *link) { return ovl_create_object(dentry, S_IFLNK, 0, link); } static int ovl_set_link_redirect(struct dentry *dentry) { const struct cred *old_cred; int err; old_cred = ovl_override_creds(dentry->d_sb); err = ovl_set_redirect(dentry, false); ovl_revert_creds(old_cred); return err; } static int ovl_link(struct dentry *old, struct inode *newdir, struct dentry *new) { int err; struct inode *inode; err = ovl_copy_up(old); if (err) goto out; err = ovl_copy_up(new->d_parent); if (err) goto out; err = ovl_nlink_start(old); if (err) goto out; if (ovl_is_metacopy_dentry(old)) { err = ovl_set_link_redirect(old); if (err) goto out_nlink_end; } inode = d_inode(old); ihold(inode); err = ovl_create_or_link(new, inode, &(struct ovl_cattr) {.hardlink = ovl_dentry_upper(old)}, ovl_type_origin(old)); if (err) iput(inode); out_nlink_end: ovl_nlink_end(old); out: return err; } static bool ovl_matches_upper(struct dentry *dentry, struct dentry *upper) { return d_inode(ovl_dentry_upper(dentry)) == d_inode(upper); } static int ovl_remove_and_whiteout(struct dentry *dentry, struct list_head *list) { struct ovl_fs *ofs = OVL_FS(dentry->d_sb); struct dentry *workdir = ovl_workdir(dentry); struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent); struct dentry *upper; struct dentry *opaquedir = NULL; int err; if (WARN_ON(!workdir)) return -EROFS; if (!list_empty(list)) { opaquedir = ovl_clear_empty(dentry, list); err = PTR_ERR(opaquedir); if (IS_ERR(opaquedir)) goto out; } err = ovl_lock_rename_workdir(workdir, upperdir); if (err) goto out_dput; upper = ovl_lookup_upper(ofs, dentry->d_name.name, upperdir, dentry->d_name.len); err = PTR_ERR(upper); if (IS_ERR(upper)) goto out_unlock; err = -ESTALE; if ((opaquedir && upper != opaquedir) || (!opaquedir && ovl_dentry_upper(dentry) && !ovl_matches_upper(dentry, upper))) { goto out_dput_upper; } err = ovl_cleanup_and_whiteout(ofs, d_inode(upperdir), upper); if (err) goto out_d_drop; ovl_dir_modified(dentry->d_parent, true); out_d_drop: d_drop(dentry); out_dput_upper: dput(upper); out_unlock: unlock_rename(workdir, upperdir); out_dput: dput(opaquedir); out: return err; } static int ovl_remove_upper(struct dentry *dentry, bool is_dir, struct list_head *list) { struct ovl_fs *ofs = OVL_FS(dentry->d_sb); struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent); struct inode *dir = upperdir->d_inode; struct dentry *upper; struct dentry *opaquedir = NULL; int err; if (!list_empty(list)) { opaquedir = ovl_clear_empty(dentry, list); err = PTR_ERR(opaquedir); if (IS_ERR(opaquedir)) goto out; } inode_lock_nested(dir, I_MUTEX_PARENT); upper = ovl_lookup_upper(ofs, dentry->d_name.name, upperdir, dentry->d_name.len); err = PTR_ERR(upper); if (IS_ERR(upper)) goto out_unlock; err = -ESTALE; if ((opaquedir && upper != opaquedir) || (!opaquedir && !ovl_matches_upper(dentry, upper))) goto out_dput_upper; if (is_dir) err = ovl_do_rmdir(ofs, dir, upper); else err = ovl_do_unlink(ofs, dir, upper); ovl_dir_modified(dentry->d_parent, ovl_type_origin(dentry)); /* * Keeping this dentry hashed would mean having to release * upperpath/lowerpath, which could only be done if we are the * sole user of this dentry. Too tricky... Just unhash for * now. */ if (!err) d_drop(dentry); out_dput_upper: dput(upper); out_unlock: inode_unlock(dir); dput(opaquedir); out: return err; } static bool ovl_pure_upper(struct dentry *dentry) { return !ovl_dentry_lower(dentry) && !ovl_test_flag(OVL_WHITEOUTS, d_inode(dentry)); } static void ovl_drop_nlink(struct dentry *dentry) { struct inode *inode = d_inode(dentry); struct dentry *alias; /* Try to find another, hashed alias */ spin_lock(&inode->i_lock); hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { if (alias != dentry && !d_unhashed(alias)) break; } spin_unlock(&inode->i_lock); /* * Changes to underlying layers may cause i_nlink to lose sync with * reality. In this case prevent the link count from going to zero * prematurely. */ if (inode->i_nlink > !!alias) drop_nlink(inode); } static int ovl_do_remove(struct dentry *dentry, bool is_dir) { int err; const struct cred *old_cred; bool lower_positive = ovl_lower_positive(dentry); LIST_HEAD(list); /* No need to clean pure upper removed by vfs_rmdir() */ if (is_dir && (lower_positive || !ovl_pure_upper(dentry))) { err = ovl_check_empty_dir(dentry, &list); if (err) goto out; } err = ovl_copy_up(dentry->d_parent); if (err) goto out; err = ovl_nlink_start(dentry); if (err) goto out; old_cred = ovl_override_creds(dentry->d_sb); if (!lower_positive) err = ovl_remove_upper(dentry, is_dir, &list); else err = ovl_remove_and_whiteout(dentry, &list); ovl_revert_creds(old_cred); if (!err) { if (is_dir) clear_nlink(dentry->d_inode); else ovl_drop_nlink(dentry); } ovl_nlink_end(dentry); /* * Copy ctime * * Note: we fail to update ctime if there was no copy-up, only a * whiteout */ if (ovl_dentry_upper(dentry)) ovl_copyattr(d_inode(dentry)); out: ovl_cache_free(&list); return err; } static int ovl_unlink(struct inode *dir, struct dentry *dentry) { return ovl_do_remove(dentry, false); } static int ovl_rmdir(struct inode *dir, struct dentry *dentry) { return ovl_do_remove(dentry, true); } static bool ovl_type_merge_or_lower(struct dentry *dentry) { enum ovl_path_type type = ovl_path_type(dentry); return OVL_TYPE_MERGE(type) || !OVL_TYPE_UPPER(type); } static bool ovl_can_move(struct dentry *dentry) { return ovl_redirect_dir(OVL_FS(dentry->d_sb)) || !d_is_dir(dentry) || !ovl_type_merge_or_lower(dentry); } static char *ovl_get_redirect(struct dentry *dentry, bool abs_redirect) { char *buf, *ret; struct dentry *d, *tmp; int buflen = ovl_redirect_max + 1; if (!abs_redirect) { ret = kstrndup(dentry->d_name.name, dentry->d_name.len, GFP_KERNEL); goto out; } buf = ret = kmalloc(buflen, GFP_KERNEL); if (!buf) goto out; buflen--; buf[buflen] = '\0'; for (d = dget(dentry); !IS_ROOT(d);) { const char *name; int thislen; spin_lock(&d->d_lock); name = ovl_dentry_get_redirect(d); if (name) { thislen = strlen(name); } else { name = d->d_name.name; thislen = d->d_name.len; } /* If path is too long, fall back to userspace move */ if (thislen + (name[0] != '/') > buflen) { ret = ERR_PTR(-EXDEV); spin_unlock(&d->d_lock); goto out_put; } buflen -= thislen; memcpy(&buf[buflen], name, thislen); spin_unlock(&d->d_lock); tmp = dget_parent(d); dput(d); d = tmp; /* Absolute redirect: finished */ if (buf[buflen] == '/') break; buflen--; buf[buflen] = '/'; } ret = kstrdup(&buf[buflen], GFP_KERNEL); out_put: dput(d); kfree(buf); out: return ret ? ret : ERR_PTR(-ENOMEM); } static bool ovl_need_absolute_redirect(struct dentry *dentry, bool samedir) { struct dentry *lowerdentry; if (!samedir) return true; if (d_is_dir(dentry)) return false; /* * For non-dir hardlinked files, we need absolute redirects * in general as two upper hardlinks could be in different * dirs. We could put a relative redirect now and convert * it to absolute redirect later. But when nlink > 1 and * indexing is on, that means relative redirect needs to be * converted to absolute during copy up of another lower * hardllink as well. * * So without optimizing too much, just check if lower is * a hard link or not. If lower is hard link, put absolute * redirect. */ lowerdentry = ovl_dentry_lower(dentry); return (d_inode(lowerdentry)->i_nlink > 1); } static int ovl_set_redirect(struct dentry *dentry, bool samedir) { int err; struct ovl_fs *ofs = OVL_FS(dentry->d_sb); const char *redirect = ovl_dentry_get_redirect(dentry); bool absolute_redirect = ovl_need_absolute_redirect(dentry, samedir); if (redirect && (!absolute_redirect || redirect[0] == '/')) return 0; redirect = ovl_get_redirect(dentry, absolute_redirect); if (IS_ERR(redirect)) return PTR_ERR(redirect); err = ovl_check_setxattr(ofs, ovl_dentry_upper(dentry), OVL_XATTR_REDIRECT, redirect, strlen(redirect), -EXDEV); if (!err) { spin_lock(&dentry->d_lock); ovl_dentry_set_redirect(dentry, redirect); spin_unlock(&dentry->d_lock); } else { kfree(redirect); pr_warn_ratelimited("failed to set redirect (%i)\n", err); /* Fall back to userspace copy-up */ err = -EXDEV; } return err; } static int ovl_rename(struct mnt_idmap *idmap, struct inode *olddir, struct dentry *old, struct inode *newdir, struct dentry *new, unsigned int flags) { int err; struct dentry *old_upperdir; struct dentry *new_upperdir; struct dentry *olddentry; struct dentry *newdentry; struct dentry *trap; bool old_opaque; bool new_opaque; bool cleanup_whiteout = false; bool update_nlink = false; bool overwrite = !(flags & RENAME_EXCHANGE); bool is_dir = d_is_dir(old); bool new_is_dir = d_is_dir(new); bool samedir = olddir == newdir; struct dentry *opaquedir = NULL; const struct cred *old_cred = NULL; struct ovl_fs *ofs = OVL_FS(old->d_sb); LIST_HEAD(list); err = -EINVAL; if (flags & ~(RENAME_EXCHANGE | RENAME_NOREPLACE)) goto out; flags &= ~RENAME_NOREPLACE; /* Don't copy up directory trees */ err = -EXDEV; if (!ovl_can_move(old)) goto out; if (!overwrite && !ovl_can_move(new)) goto out; if (overwrite && new_is_dir && !ovl_pure_upper(new)) { err = ovl_check_empty_dir(new, &list); if (err) goto out; } if (overwrite) { if (ovl_lower_positive(old)) { if (!ovl_dentry_is_whiteout(new)) { /* Whiteout source */ flags |= RENAME_WHITEOUT; } else { /* Switch whiteouts */ flags |= RENAME_EXCHANGE; } } else if (is_dir && ovl_dentry_is_whiteout(new)) { flags |= RENAME_EXCHANGE; cleanup_whiteout = true; } } err = ovl_copy_up(old); if (err) goto out; err = ovl_copy_up(new->d_parent); if (err) goto out; if (!overwrite) { err = ovl_copy_up(new); if (err) goto out; } else if (d_inode(new)) { err = ovl_nlink_start(new); if (err) goto out; update_nlink = true; } if (!update_nlink) { /* ovl_nlink_start() took ovl_want_write() */ err = ovl_want_write(old); if (err) goto out; } old_cred = ovl_override_creds(old->d_sb); if (!list_empty(&list)) { opaquedir = ovl_clear_empty(new, &list); err = PTR_ERR(opaquedir); if (IS_ERR(opaquedir)) { opaquedir = NULL; goto out_revert_creds; } } old_upperdir = ovl_dentry_upper(old->d_parent); new_upperdir = ovl_dentry_upper(new->d_parent); if (!samedir) { /* * When moving a merge dir or non-dir with copy up origin into * a new parent, we are marking the new parent dir "impure". * When ovl_iterate() iterates an "impure" upper dir, it will * lookup the origin inodes of the entries to fill d_ino. */ if (ovl_type_origin(old)) { err = ovl_set_impure(new->d_parent, new_upperdir); if (err) goto out_revert_creds; } if (!overwrite && ovl_type_origin(new)) { err = ovl_set_impure(old->d_parent, old_upperdir); if (err) goto out_revert_creds; } } trap = lock_rename(new_upperdir, old_upperdir); if (IS_ERR(trap)) { err = PTR_ERR(trap); goto out_revert_creds; } olddentry = ovl_lookup_upper(ofs, old->d_name.name, old_upperdir, old->d_name.len); err = PTR_ERR(olddentry); if (IS_ERR(olddentry)) goto out_unlock; err = -ESTALE; if (!ovl_matches_upper(old, olddentry)) goto out_dput_old; newdentry = ovl_lookup_upper(ofs, new->d_name.name, new_upperdir, new->d_name.len); err = PTR_ERR(newdentry); if (IS_ERR(newdentry)) goto out_dput_old; old_opaque = ovl_dentry_is_opaque(old); new_opaque = ovl_dentry_is_opaque(new); err = -ESTALE; if (d_inode(new) && ovl_dentry_upper(new)) { if (opaquedir) { if (newdentry != opaquedir) goto out_dput; } else { if (!ovl_matches_upper(new, newdentry)) goto out_dput; } } else { if (!d_is_negative(newdentry)) { if (!new_opaque || !ovl_upper_is_whiteout(ofs, newdentry)) goto out_dput; } else { if (flags & RENAME_EXCHANGE) goto out_dput; } } if (olddentry == trap) goto out_dput; if (newdentry == trap) goto out_dput; if (olddentry->d_inode == newdentry->d_inode) goto out_dput; err = 0; if (ovl_type_merge_or_lower(old)) err = ovl_set_redirect(old, samedir); else if (is_dir && !old_opaque && ovl_type_merge(new->d_parent)) err = ovl_set_opaque_xerr(old, olddentry, -EXDEV); if (err) goto out_dput; if (!overwrite && ovl_type_merge_or_lower(new)) err = ovl_set_redirect(new, samedir); else if (!overwrite && new_is_dir && !new_opaque && ovl_type_merge(old->d_parent)) err = ovl_set_opaque_xerr(new, newdentry, -EXDEV); if (err) goto out_dput; err = ovl_do_rename(ofs, old_upperdir->d_inode, olddentry, new_upperdir->d_inode, newdentry, flags); if (err) goto out_dput; if (cleanup_whiteout) ovl_cleanup(ofs, old_upperdir->d_inode, newdentry); if (overwrite && d_inode(new)) { if (new_is_dir) clear_nlink(d_inode(new)); else ovl_drop_nlink(new); } ovl_dir_modified(old->d_parent, ovl_type_origin(old) || (!overwrite && ovl_type_origin(new))); ovl_dir_modified(new->d_parent, ovl_type_origin(old) || (d_inode(new) && ovl_type_origin(new))); /* copy ctime: */ ovl_copyattr(d_inode(old)); if (d_inode(new) && ovl_dentry_upper(new)) ovl_copyattr(d_inode(new)); out_dput: dput(newdentry); out_dput_old: dput(olddentry); out_unlock: unlock_rename(new_upperdir, old_upperdir); out_revert_creds: ovl_revert_creds(old_cred); if (update_nlink) ovl_nlink_end(new); else ovl_drop_write(old); out: dput(opaquedir); ovl_cache_free(&list); return err; } static int ovl_create_tmpfile(struct file *file, struct dentry *dentry, struct inode *inode, umode_t mode) { const struct cred *old_cred, *new_cred = NULL; struct path realparentpath; struct file *realfile; struct ovl_file *of; struct dentry *newdentry; /* It's okay to set O_NOATIME, since the owner will be current fsuid */ int flags = file->f_flags | OVL_OPEN_FLAGS; int err; old_cred = ovl_override_creds(dentry->d_sb); new_cred = ovl_setup_cred_for_create(dentry, inode, mode, old_cred); err = PTR_ERR(new_cred); if (IS_ERR(new_cred)) { new_cred = NULL; goto out_revert_creds; } ovl_path_upper(dentry->d_parent, &realparentpath); realfile = backing_tmpfile_open(&file->f_path, flags, &realparentpath, mode, current_cred()); err = PTR_ERR_OR_ZERO(realfile); pr_debug("tmpfile/open(%pd2, 0%o) = %i\n", realparentpath.dentry, mode, err); if (err) goto out_revert_creds; of = ovl_file_alloc(realfile); if (!of) { fput(realfile); err = -ENOMEM; goto out_revert_creds; } /* ovl_instantiate() consumes the newdentry reference on success */ newdentry = dget(realfile->f_path.dentry); err = ovl_instantiate(dentry, inode, newdentry, false, file); if (!err) { file->private_data = of; } else { dput(newdentry); ovl_file_free(of); } out_revert_creds: ovl_revert_creds(old_cred); put_cred(new_cred); return err; } static int ovl_dummy_open(struct inode *inode, struct file *file) { return 0; } static int ovl_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode) { int err; struct dentry *dentry = file->f_path.dentry; struct inode *inode; if (!OVL_FS(dentry->d_sb)->tmpfile) return -EOPNOTSUPP; err = ovl_copy_up(dentry->d_parent); if (err) return err; err = ovl_want_write(dentry); if (err) return err; err = -ENOMEM; inode = ovl_new_inode(dentry->d_sb, mode, 0); if (!inode) goto drop_write; inode_init_owner(&nop_mnt_idmap, inode, dir, mode); err = ovl_create_tmpfile(file, dentry, inode, inode->i_mode); if (err) goto put_inode; /* * Check if the preallocated inode was actually used. Having something * else assigned to the dentry shouldn't happen as that would indicate * that the backing tmpfile "leaked" out of overlayfs. */ err = -EIO; if (WARN_ON(inode != d_inode(dentry))) goto put_realfile; /* inode reference was transferred to dentry */ inode = NULL; err = finish_open(file, dentry, ovl_dummy_open); put_realfile: /* Without FMODE_OPENED ->release() won't be called on @file */ if (!(file->f_mode & FMODE_OPENED)) ovl_file_free(file->private_data); put_inode: iput(inode); drop_write: ovl_drop_write(dentry); return err; } const struct inode_operations ovl_dir_inode_operations = { .lookup = ovl_lookup, .mkdir = ovl_mkdir, .symlink = ovl_symlink, .unlink = ovl_unlink, .rmdir = ovl_rmdir, .rename = ovl_rename, .link = ovl_link, .setattr = ovl_setattr, .create = ovl_create, .mknod = ovl_mknod, .permission = ovl_permission, .getattr = ovl_getattr, .listxattr = ovl_listxattr, .get_inode_acl = ovl_get_inode_acl, .get_acl = ovl_get_acl, .set_acl = ovl_set_acl, .update_time = ovl_update_time, .fileattr_get = ovl_fileattr_get, .fileattr_set = ovl_fileattr_set, .tmpfile = ovl_tmpfile, }; |
| 2 2 14 12 13 13 3 9 13 13 13 5 10 8 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef __SOUND_PCM_H #define __SOUND_PCM_H /* * Digital Audio (PCM) abstract layer * Copyright (c) by Jaroslav Kysela <perex@perex.cz> * Abramo Bagnara <abramo@alsa-project.org> */ #include <sound/asound.h> #include <sound/memalloc.h> #include <sound/minors.h> #include <linux/poll.h> #include <linux/mm.h> #include <linux/bitops.h> #include <linux/pm_qos.h> #include <linux/refcount.h> #include <linux/uio.h> #define snd_pcm_substream_chip(substream) ((substream)->private_data) #define snd_pcm_chip(pcm) ((pcm)->private_data) #if IS_ENABLED(CONFIG_SND_PCM_OSS) #include <sound/pcm_oss.h> #endif /* * Hardware (lowlevel) section */ struct snd_pcm_hardware { unsigned int info; /* SNDRV_PCM_INFO_* */ u64 formats; /* SNDRV_PCM_FMTBIT_* */ u32 subformats; /* for S32_LE, SNDRV_PCM_SUBFMTBIT_* */ unsigned int rates; /* SNDRV_PCM_RATE_* */ unsigned int rate_min; /* min rate */ unsigned int rate_max; /* max rate */ unsigned int channels_min; /* min channels */ unsigned int channels_max; /* max channels */ size_t buffer_bytes_max; /* max buffer size */ size_t period_bytes_min; /* min period size */ size_t period_bytes_max; /* max period size */ unsigned int periods_min; /* min # of periods */ unsigned int periods_max; /* max # of periods */ size_t fifo_size; /* fifo size in bytes */ }; struct snd_pcm_status64; struct snd_pcm_substream; struct snd_pcm_audio_tstamp_config; /* definitions further down */ struct snd_pcm_audio_tstamp_report; struct snd_pcm_ops { int (*open)(struct snd_pcm_substream *substream); int (*close)(struct snd_pcm_substream *substream); int (*ioctl)(struct snd_pcm_substream * substream, unsigned int cmd, void *arg); int (*hw_params)(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params); int (*hw_free)(struct snd_pcm_substream *substream); int (*prepare)(struct snd_pcm_substream *substream); int (*trigger)(struct snd_pcm_substream *substream, int cmd); int (*sync_stop)(struct snd_pcm_substream *substream); snd_pcm_uframes_t (*pointer)(struct snd_pcm_substream *substream); int (*get_time_info)(struct snd_pcm_substream *substream, struct timespec64 *system_ts, struct timespec64 *audio_ts, struct snd_pcm_audio_tstamp_config *audio_tstamp_config, struct snd_pcm_audio_tstamp_report *audio_tstamp_report); int (*fill_silence)(struct snd_pcm_substream *substream, int channel, unsigned long pos, unsigned long bytes); int (*copy)(struct snd_pcm_substream *substream, int channel, unsigned long pos, struct iov_iter *iter, unsigned long bytes); struct page *(*page)(struct snd_pcm_substream *substream, unsigned long offset); int (*mmap)(struct snd_pcm_substream *substream, struct vm_area_struct *vma); int (*ack)(struct snd_pcm_substream *substream); }; /* * */ #if defined(CONFIG_SND_DYNAMIC_MINORS) #define SNDRV_PCM_DEVICES (SNDRV_OS_MINORS-2) #else #define SNDRV_PCM_DEVICES 8 #endif #define SNDRV_PCM_IOCTL1_RESET 0 /* 1 is absent slot. */ #define SNDRV_PCM_IOCTL1_CHANNEL_INFO 2 /* 3 is absent slot. */ #define SNDRV_PCM_IOCTL1_FIFO_SIZE 4 #define SNDRV_PCM_IOCTL1_SYNC_ID 5 #define SNDRV_PCM_TRIGGER_STOP 0 #define SNDRV_PCM_TRIGGER_START 1 #define SNDRV_PCM_TRIGGER_PAUSE_PUSH 2 #define SNDRV_PCM_TRIGGER_PAUSE_RELEASE 3 #define SNDRV_PCM_TRIGGER_SUSPEND 4 #define SNDRV_PCM_TRIGGER_RESUME 5 #define SNDRV_PCM_TRIGGER_DRAIN 6 #define SNDRV_PCM_POS_XRUN ((snd_pcm_uframes_t)-1) /* If you change this don't forget to change rates[] table in pcm_native.c */ #define SNDRV_PCM_RATE_5512 (1U<<0) /* 5512Hz */ #define SNDRV_PCM_RATE_8000 (1U<<1) /* 8000Hz */ #define SNDRV_PCM_RATE_11025 (1U<<2) /* 11025Hz */ #define SNDRV_PCM_RATE_16000 (1U<<3) /* 16000Hz */ #define SNDRV_PCM_RATE_22050 (1U<<4) /* 22050Hz */ #define SNDRV_PCM_RATE_32000 (1U<<5) /* 32000Hz */ #define SNDRV_PCM_RATE_44100 (1U<<6) /* 44100Hz */ #define SNDRV_PCM_RATE_48000 (1U<<7) /* 48000Hz */ #define SNDRV_PCM_RATE_64000 (1U<<8) /* 64000Hz */ #define SNDRV_PCM_RATE_88200 (1U<<9) /* 88200Hz */ #define SNDRV_PCM_RATE_96000 (1U<<10) /* 96000Hz */ #define SNDRV_PCM_RATE_176400 (1U<<11) /* 176400Hz */ #define SNDRV_PCM_RATE_192000 (1U<<12) /* 192000Hz */ #define SNDRV_PCM_RATE_352800 (1U<<13) /* 352800Hz */ #define SNDRV_PCM_RATE_384000 (1U<<14) /* 384000Hz */ #define SNDRV_PCM_RATE_705600 (1U<<15) /* 705600Hz */ #define SNDRV_PCM_RATE_768000 (1U<<16) /* 768000Hz */ /* extended rates since 6.12 */ #define SNDRV_PCM_RATE_12000 (1U<<17) /* 12000Hz */ #define SNDRV_PCM_RATE_24000 (1U<<18) /* 24000Hz */ #define SNDRV_PCM_RATE_128000 (1U<<19) /* 128000Hz */ #define SNDRV_PCM_RATE_CONTINUOUS (1U<<30) /* continuous range */ #define SNDRV_PCM_RATE_KNOT (1U<<31) /* supports more non-continuous rates */ #define SNDRV_PCM_RATE_8000_44100 (SNDRV_PCM_RATE_8000|SNDRV_PCM_RATE_11025|\ SNDRV_PCM_RATE_16000|SNDRV_PCM_RATE_22050|\ SNDRV_PCM_RATE_32000|SNDRV_PCM_RATE_44100) #define SNDRV_PCM_RATE_8000_48000 (SNDRV_PCM_RATE_8000_44100|SNDRV_PCM_RATE_48000) #define SNDRV_PCM_RATE_8000_96000 (SNDRV_PCM_RATE_8000_48000|SNDRV_PCM_RATE_64000|\ SNDRV_PCM_RATE_88200|SNDRV_PCM_RATE_96000) #define SNDRV_PCM_RATE_8000_192000 (SNDRV_PCM_RATE_8000_96000|SNDRV_PCM_RATE_176400|\ SNDRV_PCM_RATE_192000) #define SNDRV_PCM_RATE_8000_384000 (SNDRV_PCM_RATE_8000_192000|\ SNDRV_PCM_RATE_352800|\ SNDRV_PCM_RATE_384000) #define SNDRV_PCM_RATE_8000_768000 (SNDRV_PCM_RATE_8000_384000|\ SNDRV_PCM_RATE_705600|\ SNDRV_PCM_RATE_768000) #define _SNDRV_PCM_FMTBIT(fmt) (1ULL << (__force int)SNDRV_PCM_FORMAT_##fmt) #define SNDRV_PCM_FMTBIT_S8 _SNDRV_PCM_FMTBIT(S8) #define SNDRV_PCM_FMTBIT_U8 _SNDRV_PCM_FMTBIT(U8) #define SNDRV_PCM_FMTBIT_S16_LE _SNDRV_PCM_FMTBIT(S16_LE) #define SNDRV_PCM_FMTBIT_S16_BE _SNDRV_PCM_FMTBIT(S16_BE) #define SNDRV_PCM_FMTBIT_U16_LE _SNDRV_PCM_FMTBIT(U16_LE) #define SNDRV_PCM_FMTBIT_U16_BE _SNDRV_PCM_FMTBIT(U16_BE) #define SNDRV_PCM_FMTBIT_S24_LE _SNDRV_PCM_FMTBIT(S24_LE) #define SNDRV_PCM_FMTBIT_S24_BE _SNDRV_PCM_FMTBIT(S24_BE) #define SNDRV_PCM_FMTBIT_U24_LE _SNDRV_PCM_FMTBIT(U24_LE) #define SNDRV_PCM_FMTBIT_U24_BE _SNDRV_PCM_FMTBIT(U24_BE) // For S32/U32 formats, 'msbits' hardware parameter is often used to deliver information about the // available bit count in most significant bit. It's for the case of so-called 'left-justified' or // `right-padding` sample which has less width than 32 bit. #define SNDRV_PCM_FMTBIT_S32_LE _SNDRV_PCM_FMTBIT(S32_LE) #define SNDRV_PCM_FMTBIT_S32_BE _SNDRV_PCM_FMTBIT(S32_BE) #define SNDRV_PCM_FMTBIT_U32_LE _SNDRV_PCM_FMTBIT(U32_LE) #define SNDRV_PCM_FMTBIT_U32_BE _SNDRV_PCM_FMTBIT(U32_BE) #define SNDRV_PCM_FMTBIT_FLOAT_LE _SNDRV_PCM_FMTBIT(FLOAT_LE) #define SNDRV_PCM_FMTBIT_FLOAT_BE _SNDRV_PCM_FMTBIT(FLOAT_BE) #define SNDRV_PCM_FMTBIT_FLOAT64_LE _SNDRV_PCM_FMTBIT(FLOAT64_LE) #define SNDRV_PCM_FMTBIT_FLOAT64_BE _SNDRV_PCM_FMTBIT(FLOAT64_BE) #define SNDRV_PCM_FMTBIT_IEC958_SUBFRAME_LE _SNDRV_PCM_FMTBIT(IEC958_SUBFRAME_LE) #define SNDRV_PCM_FMTBIT_IEC958_SUBFRAME_BE _SNDRV_PCM_FMTBIT(IEC958_SUBFRAME_BE) #define SNDRV_PCM_FMTBIT_MU_LAW _SNDRV_PCM_FMTBIT(MU_LAW) #define SNDRV_PCM_FMTBIT_A_LAW _SNDRV_PCM_FMTBIT(A_LAW) #define SNDRV_PCM_FMTBIT_IMA_ADPCM _SNDRV_PCM_FMTBIT(IMA_ADPCM) #define SNDRV_PCM_FMTBIT_MPEG _SNDRV_PCM_FMTBIT(MPEG) #define SNDRV_PCM_FMTBIT_GSM _SNDRV_PCM_FMTBIT(GSM) #define SNDRV_PCM_FMTBIT_S20_LE _SNDRV_PCM_FMTBIT(S20_LE) #define SNDRV_PCM_FMTBIT_U20_LE _SNDRV_PCM_FMTBIT(U20_LE) #define SNDRV_PCM_FMTBIT_S20_BE _SNDRV_PCM_FMTBIT(S20_BE) #define SNDRV_PCM_FMTBIT_U20_BE _SNDRV_PCM_FMTBIT(U20_BE) #define SNDRV_PCM_FMTBIT_SPECIAL _SNDRV_PCM_FMTBIT(SPECIAL) #define SNDRV_PCM_FMTBIT_S24_3LE _SNDRV_PCM_FMTBIT(S24_3LE) #define SNDRV_PCM_FMTBIT_U24_3LE _SNDRV_PCM_FMTBIT(U24_3LE) #define SNDRV_PCM_FMTBIT_S24_3BE _SNDRV_PCM_FMTBIT(S24_3BE) #define SNDRV_PCM_FMTBIT_U24_3BE _SNDRV_PCM_FMTBIT(U24_3BE) #define SNDRV_PCM_FMTBIT_S20_3LE _SNDRV_PCM_FMTBIT(S20_3LE) #define SNDRV_PCM_FMTBIT_U20_3LE _SNDRV_PCM_FMTBIT(U20_3LE) #define SNDRV_PCM_FMTBIT_S20_3BE _SNDRV_PCM_FMTBIT(S20_3BE) #define SNDRV_PCM_FMTBIT_U20_3BE _SNDRV_PCM_FMTBIT(U20_3BE) #define SNDRV_PCM_FMTBIT_S18_3LE _SNDRV_PCM_FMTBIT(S18_3LE) #define SNDRV_PCM_FMTBIT_U18_3LE _SNDRV_PCM_FMTBIT(U18_3LE) #define SNDRV_PCM_FMTBIT_S18_3BE _SNDRV_PCM_FMTBIT(S18_3BE) #define SNDRV_PCM_FMTBIT_U18_3BE _SNDRV_PCM_FMTBIT(U18_3BE) #define SNDRV_PCM_FMTBIT_G723_24 _SNDRV_PCM_FMTBIT(G723_24) #define SNDRV_PCM_FMTBIT_G723_24_1B _SNDRV_PCM_FMTBIT(G723_24_1B) #define SNDRV_PCM_FMTBIT_G723_40 _SNDRV_PCM_FMTBIT(G723_40) #define SNDRV_PCM_FMTBIT_G723_40_1B _SNDRV_PCM_FMTBIT(G723_40_1B) #define SNDRV_PCM_FMTBIT_DSD_U8 _SNDRV_PCM_FMTBIT(DSD_U8) #define SNDRV_PCM_FMTBIT_DSD_U16_LE _SNDRV_PCM_FMTBIT(DSD_U16_LE) #define SNDRV_PCM_FMTBIT_DSD_U32_LE _SNDRV_PCM_FMTBIT(DSD_U32_LE) #define SNDRV_PCM_FMTBIT_DSD_U16_BE _SNDRV_PCM_FMTBIT(DSD_U16_BE) #define SNDRV_PCM_FMTBIT_DSD_U32_BE _SNDRV_PCM_FMTBIT(DSD_U32_BE) #ifdef SNDRV_LITTLE_ENDIAN #define SNDRV_PCM_FMTBIT_S16 SNDRV_PCM_FMTBIT_S16_LE #define SNDRV_PCM_FMTBIT_U16 SNDRV_PCM_FMTBIT_U16_LE #define SNDRV_PCM_FMTBIT_S24 SNDRV_PCM_FMTBIT_S24_LE #define SNDRV_PCM_FMTBIT_U24 SNDRV_PCM_FMTBIT_U24_LE #define SNDRV_PCM_FMTBIT_S32 SNDRV_PCM_FMTBIT_S32_LE #define SNDRV_PCM_FMTBIT_U32 SNDRV_PCM_FMTBIT_U32_LE #define SNDRV_PCM_FMTBIT_FLOAT SNDRV_PCM_FMTBIT_FLOAT_LE #define SNDRV_PCM_FMTBIT_FLOAT64 SNDRV_PCM_FMTBIT_FLOAT64_LE #define SNDRV_PCM_FMTBIT_IEC958_SUBFRAME SNDRV_PCM_FMTBIT_IEC958_SUBFRAME_LE #define SNDRV_PCM_FMTBIT_S20 SNDRV_PCM_FMTBIT_S20_LE #define SNDRV_PCM_FMTBIT_U20 SNDRV_PCM_FMTBIT_U20_LE #endif #ifdef SNDRV_BIG_ENDIAN #define SNDRV_PCM_FMTBIT_S16 SNDRV_PCM_FMTBIT_S16_BE #define SNDRV_PCM_FMTBIT_U16 SNDRV_PCM_FMTBIT_U16_BE #define SNDRV_PCM_FMTBIT_S24 SNDRV_PCM_FMTBIT_S24_BE #define SNDRV_PCM_FMTBIT_U24 SNDRV_PCM_FMTBIT_U24_BE #define SNDRV_PCM_FMTBIT_S32 SNDRV_PCM_FMTBIT_S32_BE #define SNDRV_PCM_FMTBIT_U32 SNDRV_PCM_FMTBIT_U32_BE #define SNDRV_PCM_FMTBIT_FLOAT SNDRV_PCM_FMTBIT_FLOAT_BE #define SNDRV_PCM_FMTBIT_FLOAT64 SNDRV_PCM_FMTBIT_FLOAT64_BE #define SNDRV_PCM_FMTBIT_IEC958_SUBFRAME SNDRV_PCM_FMTBIT_IEC958_SUBFRAME_BE #define SNDRV_PCM_FMTBIT_S20 SNDRV_PCM_FMTBIT_S20_BE #define SNDRV_PCM_FMTBIT_U20 SNDRV_PCM_FMTBIT_U20_BE #endif #define _SNDRV_PCM_SUBFMTBIT(fmt) BIT((__force int)SNDRV_PCM_SUBFORMAT_##fmt) #define SNDRV_PCM_SUBFMTBIT_STD _SNDRV_PCM_SUBFMTBIT(STD) #define SNDRV_PCM_SUBFMTBIT_MSBITS_MAX _SNDRV_PCM_SUBFMTBIT(MSBITS_MAX) #define SNDRV_PCM_SUBFMTBIT_MSBITS_20 _SNDRV_PCM_SUBFMTBIT(MSBITS_20) #define SNDRV_PCM_SUBFMTBIT_MSBITS_24 _SNDRV_PCM_SUBFMTBIT(MSBITS_24) struct snd_pcm_file { struct snd_pcm_substream *substream; int no_compat_mmap; unsigned int user_pversion; /* supported protocol version */ }; struct snd_pcm_hw_rule; typedef int (*snd_pcm_hw_rule_func_t)(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule); struct snd_pcm_hw_rule { unsigned int cond; int var; int deps[5]; snd_pcm_hw_rule_func_t func; void *private; }; struct snd_pcm_hw_constraints { struct snd_mask masks[SNDRV_PCM_HW_PARAM_LAST_MASK - SNDRV_PCM_HW_PARAM_FIRST_MASK + 1]; struct snd_interval intervals[SNDRV_PCM_HW_PARAM_LAST_INTERVAL - SNDRV_PCM_HW_PARAM_FIRST_INTERVAL + 1]; unsigned int rules_num; unsigned int rules_all; struct snd_pcm_hw_rule *rules; }; static inline struct snd_mask *constrs_mask(struct snd_pcm_hw_constraints *constrs, snd_pcm_hw_param_t var) { return &constrs->masks[var - SNDRV_PCM_HW_PARAM_FIRST_MASK]; } static inline struct snd_interval *constrs_interval(struct snd_pcm_hw_constraints *constrs, snd_pcm_hw_param_t var) { return &constrs->intervals[var - SNDRV_PCM_HW_PARAM_FIRST_INTERVAL]; } struct snd_ratnum { unsigned int num; unsigned int den_min, den_max, den_step; }; struct snd_ratden { unsigned int num_min, num_max, num_step; unsigned int den; }; struct snd_pcm_hw_constraint_ratnums { int nrats; const struct snd_ratnum *rats; }; struct snd_pcm_hw_constraint_ratdens { int nrats; const struct snd_ratden *rats; }; struct snd_pcm_hw_constraint_list { const unsigned int *list; unsigned int count; unsigned int mask; }; struct snd_pcm_hw_constraint_ranges { unsigned int count; const struct snd_interval *ranges; unsigned int mask; }; /* * userspace-provided audio timestamp config to kernel, * structure is for internal use only and filled with dedicated unpack routine */ struct snd_pcm_audio_tstamp_config { /* 5 of max 16 bits used */ u32 type_requested:4; u32 report_delay:1; /* add total delay to A/D or D/A */ }; static inline void snd_pcm_unpack_audio_tstamp_config(__u32 data, struct snd_pcm_audio_tstamp_config *config) { config->type_requested = data & 0xF; config->report_delay = (data >> 4) & 1; } /* * kernel-provided audio timestamp report to user-space * structure is for internal use only and read by dedicated pack routine */ struct snd_pcm_audio_tstamp_report { /* 6 of max 16 bits used for bit-fields */ /* for backwards compatibility */ u32 valid:1; /* actual type if hardware could not support requested timestamp */ u32 actual_type:4; /* accuracy represented in ns units */ u32 accuracy_report:1; /* 0 if accuracy unknown, 1 if accuracy field is valid */ u32 accuracy; /* up to 4.29s, will be packed in separate field */ }; static inline void snd_pcm_pack_audio_tstamp_report(__u32 *data, __u32 *accuracy, const struct snd_pcm_audio_tstamp_report *report) { u32 tmp; tmp = report->accuracy_report; tmp <<= 4; tmp |= report->actual_type; tmp <<= 1; tmp |= report->valid; *data &= 0xffff; /* zero-clear MSBs */ *data |= (tmp << 16); *accuracy = report->accuracy; } struct snd_pcm_runtime { /* -- Status -- */ snd_pcm_state_t state; /* stream state */ snd_pcm_state_t suspended_state; /* suspended stream state */ struct snd_pcm_substream *trigger_master; struct timespec64 trigger_tstamp; /* trigger timestamp */ bool trigger_tstamp_latched; /* trigger timestamp latched in low-level driver/hardware */ int overrange; snd_pcm_uframes_t avail_max; snd_pcm_uframes_t hw_ptr_base; /* Position at buffer restart */ snd_pcm_uframes_t hw_ptr_interrupt; /* Position at interrupt time */ unsigned long hw_ptr_jiffies; /* Time when hw_ptr is updated */ unsigned long hw_ptr_buffer_jiffies; /* buffer time in jiffies */ snd_pcm_sframes_t delay; /* extra delay; typically FIFO size */ u64 hw_ptr_wrap; /* offset for hw_ptr due to boundary wrap-around */ /* -- HW params -- */ snd_pcm_access_t access; /* access mode */ snd_pcm_format_t format; /* SNDRV_PCM_FORMAT_* */ snd_pcm_subformat_t subformat; /* subformat */ unsigned int rate; /* rate in Hz */ unsigned int channels; /* channels */ snd_pcm_uframes_t period_size; /* period size */ unsigned int periods; /* periods */ snd_pcm_uframes_t buffer_size; /* buffer size */ snd_pcm_uframes_t min_align; /* Min alignment for the format */ size_t byte_align; unsigned int frame_bits; unsigned int sample_bits; unsigned int info; unsigned int rate_num; unsigned int rate_den; unsigned int no_period_wakeup: 1; /* -- SW params; see struct snd_pcm_sw_params for comments -- */ int tstamp_mode; unsigned int period_step; snd_pcm_uframes_t start_threshold; snd_pcm_uframes_t stop_threshold; snd_pcm_uframes_t silence_threshold; snd_pcm_uframes_t silence_size; snd_pcm_uframes_t boundary; /* internal data of auto-silencer */ snd_pcm_uframes_t silence_start; /* starting pointer to silence area */ snd_pcm_uframes_t silence_filled; /* already filled part of silence area */ bool std_sync_id; /* hardware synchronization - standard per card ID */ /* -- mmap -- */ struct snd_pcm_mmap_status *status; struct snd_pcm_mmap_control *control; /* -- locking / scheduling -- */ snd_pcm_uframes_t twake; /* do transfer (!poll) wakeup if non-zero */ wait_queue_head_t sleep; /* poll sleep */ wait_queue_head_t tsleep; /* transfer sleep */ struct snd_fasync *fasync; bool stop_operating; /* sync_stop will be called */ struct mutex buffer_mutex; /* protect for buffer changes */ atomic_t buffer_accessing; /* >0: in r/w operation, <0: blocked */ /* -- private section -- */ void *private_data; void (*private_free)(struct snd_pcm_runtime *runtime); /* -- hardware description -- */ struct snd_pcm_hardware hw; struct snd_pcm_hw_constraints hw_constraints; /* -- timer -- */ unsigned int timer_resolution; /* timer resolution */ int tstamp_type; /* timestamp type */ /* -- DMA -- */ unsigned char *dma_area; /* DMA area */ dma_addr_t dma_addr; /* physical bus address (not accessible from main CPU) */ size_t dma_bytes; /* size of DMA area */ struct snd_dma_buffer *dma_buffer_p; /* allocated buffer */ unsigned int buffer_changed:1; /* buffer allocation changed; set only in managed mode */ /* -- audio timestamp config -- */ struct snd_pcm_audio_tstamp_config audio_tstamp_config; struct snd_pcm_audio_tstamp_report audio_tstamp_report; struct timespec64 driver_tstamp; #if IS_ENABLED(CONFIG_SND_PCM_OSS) /* -- OSS things -- */ struct snd_pcm_oss_runtime oss; #endif }; struct snd_pcm_group { /* keep linked substreams */ spinlock_t lock; struct mutex mutex; struct list_head substreams; refcount_t refs; }; struct pid; struct snd_pcm_substream { struct snd_pcm *pcm; struct snd_pcm_str *pstr; void *private_data; /* copied from pcm->private_data */ int number; char name[32]; /* substream name */ int stream; /* stream (direction) */ struct pm_qos_request latency_pm_qos_req; /* pm_qos request */ size_t buffer_bytes_max; /* limit ring buffer size */ struct snd_dma_buffer dma_buffer; size_t dma_max; /* -- hardware operations -- */ const struct snd_pcm_ops *ops; /* -- runtime information -- */ struct snd_pcm_runtime *runtime; /* -- timer section -- */ struct snd_timer *timer; /* timer */ unsigned timer_running: 1; /* time is running */ long wait_time; /* time in ms for R/W to wait for avail */ /* -- next substream -- */ struct snd_pcm_substream *next; /* -- linked substreams -- */ struct list_head link_list; /* linked list member */ struct snd_pcm_group self_group; /* fake group for non linked substream (with substream lock inside) */ struct snd_pcm_group *group; /* pointer to current group */ /* -- assigned files -- */ int ref_count; atomic_t mmap_count; unsigned int f_flags; void (*pcm_release)(struct snd_pcm_substream *); struct pid *pid; #if IS_ENABLED(CONFIG_SND_PCM_OSS) /* -- OSS things -- */ struct snd_pcm_oss_substream oss; #endif #ifdef CONFIG_SND_VERBOSE_PROCFS struct snd_info_entry *proc_root; #endif /* CONFIG_SND_VERBOSE_PROCFS */ /* misc flags */ unsigned int hw_opened: 1; unsigned int managed_buffer_alloc:1; #ifdef CONFIG_SND_PCM_XRUN_DEBUG unsigned int xrun_counter; /* number of times xrun happens */ #endif /* CONFIG_SND_PCM_XRUN_DEBUG */ }; #define SUBSTREAM_BUSY(substream) ((substream)->ref_count > 0) struct snd_pcm_str { int stream; /* stream (direction) */ struct snd_pcm *pcm; /* -- substreams -- */ unsigned int substream_count; unsigned int substream_opened; struct snd_pcm_substream *substream; #if IS_ENABLED(CONFIG_SND_PCM_OSS) /* -- OSS things -- */ struct snd_pcm_oss_stream oss; #endif #ifdef CONFIG_SND_VERBOSE_PROCFS struct snd_info_entry *proc_root; #ifdef CONFIG_SND_PCM_XRUN_DEBUG unsigned int xrun_debug; /* 0 = disabled, 1 = verbose, 2 = stacktrace */ #endif #endif struct snd_kcontrol *chmap_kctl; /* channel-mapping controls */ struct device *dev; }; struct snd_pcm { struct snd_card *card; struct list_head list; int device; /* device number */ unsigned int info_flags; unsigned short dev_class; unsigned short dev_subclass; char id[64]; char name[80]; struct snd_pcm_str streams[2]; struct mutex open_mutex; wait_queue_head_t open_wait; void *private_data; void (*private_free) (struct snd_pcm *pcm); bool internal; /* pcm is for internal use only */ bool nonatomic; /* whole PCM operations are in non-atomic context */ bool no_device_suspend; /* don't invoke device PM suspend */ #if IS_ENABLED(CONFIG_SND_PCM_OSS) struct snd_pcm_oss oss; #endif }; /* * Registering */ extern const struct file_operations snd_pcm_f_ops[2]; int snd_pcm_new(struct snd_card *card, const char *id, int device, int playback_count, int capture_count, struct snd_pcm **rpcm); int snd_pcm_new_internal(struct snd_card *card, const char *id, int device, int playback_count, int capture_count, struct snd_pcm **rpcm); int snd_pcm_new_stream(struct snd_pcm *pcm, int stream, int substream_count); #if IS_ENABLED(CONFIG_SND_PCM_OSS) struct snd_pcm_notify { int (*n_register) (struct snd_pcm * pcm); int (*n_disconnect) (struct snd_pcm * pcm); int (*n_unregister) (struct snd_pcm * pcm); struct list_head list; }; int snd_pcm_notify(struct snd_pcm_notify *notify, int nfree); #endif /* * Native I/O */ int snd_pcm_info(struct snd_pcm_substream *substream, struct snd_pcm_info *info); int snd_pcm_info_user(struct snd_pcm_substream *substream, struct snd_pcm_info __user *info); int snd_pcm_status64(struct snd_pcm_substream *substream, struct snd_pcm_status64 *status); int snd_pcm_start(struct snd_pcm_substream *substream); int snd_pcm_stop(struct snd_pcm_substream *substream, snd_pcm_state_t status); int snd_pcm_drain_done(struct snd_pcm_substream *substream); int snd_pcm_stop_xrun(struct snd_pcm_substream *substream); #ifdef CONFIG_PM int snd_pcm_suspend_all(struct snd_pcm *pcm); #else static inline int snd_pcm_suspend_all(struct snd_pcm *pcm) { return 0; } #endif int snd_pcm_kernel_ioctl(struct snd_pcm_substream *substream, unsigned int cmd, void *arg); int snd_pcm_open_substream(struct snd_pcm *pcm, int stream, struct file *file, struct snd_pcm_substream **rsubstream); void snd_pcm_release_substream(struct snd_pcm_substream *substream); int snd_pcm_attach_substream(struct snd_pcm *pcm, int stream, struct file *file, struct snd_pcm_substream **rsubstream); void snd_pcm_detach_substream(struct snd_pcm_substream *substream); int snd_pcm_mmap_data(struct snd_pcm_substream *substream, struct file *file, struct vm_area_struct *area); #ifdef CONFIG_SND_DEBUG void snd_pcm_debug_name(struct snd_pcm_substream *substream, char *name, size_t len); #else static inline void snd_pcm_debug_name(struct snd_pcm_substream *substream, char *buf, size_t size) { *buf = 0; } #endif /* * PCM library */ /** * snd_pcm_stream_linked - Check whether the substream is linked with others * @substream: substream to check * * Return: true if the given substream is being linked with others */ static inline int snd_pcm_stream_linked(struct snd_pcm_substream *substream) { return substream->group != &substream->self_group; } void snd_pcm_stream_lock(struct snd_pcm_substream *substream); void snd_pcm_stream_unlock(struct snd_pcm_substream *substream); void snd_pcm_stream_lock_irq(struct snd_pcm_substream *substream); void snd_pcm_stream_unlock_irq(struct snd_pcm_substream *substream); unsigned long _snd_pcm_stream_lock_irqsave(struct snd_pcm_substream *substream); unsigned long _snd_pcm_stream_lock_irqsave_nested(struct snd_pcm_substream *substream); /** * snd_pcm_stream_lock_irqsave - Lock the PCM stream * @substream: PCM substream * @flags: irq flags * * This locks the PCM stream like snd_pcm_stream_lock() but with the local * IRQ (only when nonatomic is false). In nonatomic case, this is identical * as snd_pcm_stream_lock(). */ #define snd_pcm_stream_lock_irqsave(substream, flags) \ do { \ typecheck(unsigned long, flags); \ flags = _snd_pcm_stream_lock_irqsave(substream); \ } while (0) void snd_pcm_stream_unlock_irqrestore(struct snd_pcm_substream *substream, unsigned long flags); /** * snd_pcm_stream_lock_irqsave_nested - Single-nested PCM stream locking * @substream: PCM substream * @flags: irq flags * * This locks the PCM stream like snd_pcm_stream_lock_irqsave() but with * the single-depth lockdep subclass. */ #define snd_pcm_stream_lock_irqsave_nested(substream, flags) \ do { \ typecheck(unsigned long, flags); \ flags = _snd_pcm_stream_lock_irqsave_nested(substream); \ } while (0) /* definitions for guard(); use like guard(pcm_stream_lock) */ DEFINE_LOCK_GUARD_1(pcm_stream_lock, struct snd_pcm_substream, snd_pcm_stream_lock(_T->lock), snd_pcm_stream_unlock(_T->lock)) DEFINE_LOCK_GUARD_1(pcm_stream_lock_irq, struct snd_pcm_substream, snd_pcm_stream_lock_irq(_T->lock), snd_pcm_stream_unlock_irq(_T->lock)) DEFINE_LOCK_GUARD_1(pcm_stream_lock_irqsave, struct snd_pcm_substream, snd_pcm_stream_lock_irqsave(_T->lock, _T->flags), snd_pcm_stream_unlock_irqrestore(_T->lock, _T->flags), unsigned long flags) /** * snd_pcm_group_for_each_entry - iterate over the linked substreams * @s: the iterator * @substream: the substream * * Iterate over the all linked substreams to the given @substream. * When @substream isn't linked with any others, this gives returns @substream * itself once. */ #define snd_pcm_group_for_each_entry(s, substream) \ list_for_each_entry(s, &substream->group->substreams, link_list) #define for_each_pcm_streams(stream) \ for (stream = SNDRV_PCM_STREAM_PLAYBACK; \ stream <= SNDRV_PCM_STREAM_LAST; \ stream++) /** * snd_pcm_running - Check whether the substream is in a running state * @substream: substream to check * * Return: true if the given substream is in the state RUNNING, or in the * state DRAINING for playback. */ static inline int snd_pcm_running(struct snd_pcm_substream *substream) { return (substream->runtime->state == SNDRV_PCM_STATE_RUNNING || (substream->runtime->state == SNDRV_PCM_STATE_DRAINING && substream->stream == SNDRV_PCM_STREAM_PLAYBACK)); } /** * __snd_pcm_set_state - Change the current PCM state * @runtime: PCM runtime to set * @state: the current state to set * * Call within the stream lock */ static inline void __snd_pcm_set_state(struct snd_pcm_runtime *runtime, snd_pcm_state_t state) { runtime->state = state; runtime->status->state = state; /* copy for mmap */ } /** * bytes_to_samples - Unit conversion of the size from bytes to samples * @runtime: PCM runtime instance * @size: size in bytes * * Return: the size in samples */ static inline ssize_t bytes_to_samples(struct snd_pcm_runtime *runtime, ssize_t size) { return size * 8 / runtime->sample_bits; } /** * bytes_to_frames - Unit conversion of the size from bytes to frames * @runtime: PCM runtime instance * @size: size in bytes * * Return: the size in frames */ static inline snd_pcm_sframes_t bytes_to_frames(struct snd_pcm_runtime *runtime, ssize_t size) { return size * 8 / runtime->frame_bits; } /** * samples_to_bytes - Unit conversion of the size from samples to bytes * @runtime: PCM runtime instance * @size: size in samples * * Return: the byte size */ static inline ssize_t samples_to_bytes(struct snd_pcm_runtime *runtime, ssize_t size) { return size * runtime->sample_bits / 8; } /** * frames_to_bytes - Unit conversion of the size from frames to bytes * @runtime: PCM runtime instance * @size: size in frames * * Return: the byte size */ static inline ssize_t frames_to_bytes(struct snd_pcm_runtime *runtime, snd_pcm_sframes_t size) { return size * runtime->frame_bits / 8; } /** * frame_aligned - Check whether the byte size is aligned to frames * @runtime: PCM runtime instance * @bytes: size in bytes * * Return: true if aligned, or false if not */ static inline int frame_aligned(struct snd_pcm_runtime *runtime, ssize_t bytes) { return bytes % runtime->byte_align == 0; } /** * snd_pcm_lib_buffer_bytes - Get the buffer size of the current PCM in bytes * @substream: PCM substream * * Return: buffer byte size */ static inline size_t snd_pcm_lib_buffer_bytes(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; return frames_to_bytes(runtime, runtime->buffer_size); } /** * snd_pcm_lib_period_bytes - Get the period size of the current PCM in bytes * @substream: PCM substream * * Return: period byte size */ static inline size_t snd_pcm_lib_period_bytes(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; return frames_to_bytes(runtime, runtime->period_size); } /** * snd_pcm_playback_avail - Get the available (writable) space for playback * @runtime: PCM runtime instance * * Result is between 0 ... (boundary - 1) * * Return: available frame size */ static inline snd_pcm_uframes_t snd_pcm_playback_avail(struct snd_pcm_runtime *runtime) { snd_pcm_sframes_t avail = runtime->status->hw_ptr + runtime->buffer_size - runtime->control->appl_ptr; if (avail < 0) avail += runtime->boundary; else if ((snd_pcm_uframes_t) avail >= runtime->boundary) avail -= runtime->boundary; return avail; } /** * snd_pcm_capture_avail - Get the available (readable) space for capture * @runtime: PCM runtime instance * * Result is between 0 ... (boundary - 1) * * Return: available frame size */ static inline snd_pcm_uframes_t snd_pcm_capture_avail(struct snd_pcm_runtime *runtime) { snd_pcm_sframes_t avail = runtime->status->hw_ptr - runtime->control->appl_ptr; if (avail < 0) avail += runtime->boundary; return avail; } /** * snd_pcm_playback_hw_avail - Get the queued space for playback * @runtime: PCM runtime instance * * Return: available frame size */ static inline snd_pcm_sframes_t snd_pcm_playback_hw_avail(struct snd_pcm_runtime *runtime) { return runtime->buffer_size - snd_pcm_playback_avail(runtime); } /** * snd_pcm_capture_hw_avail - Get the free space for capture * @runtime: PCM runtime instance * * Return: available frame size */ static inline snd_pcm_sframes_t snd_pcm_capture_hw_avail(struct snd_pcm_runtime *runtime) { return runtime->buffer_size - snd_pcm_capture_avail(runtime); } /** * snd_pcm_playback_ready - check whether the playback buffer is available * @substream: the pcm substream instance * * Checks whether enough free space is available on the playback buffer. * * Return: Non-zero if available, or zero if not. */ static inline int snd_pcm_playback_ready(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; return snd_pcm_playback_avail(runtime) >= runtime->control->avail_min; } /** * snd_pcm_capture_ready - check whether the capture buffer is available * @substream: the pcm substream instance * * Checks whether enough capture data is available on the capture buffer. * * Return: Non-zero if available, or zero if not. */ static inline int snd_pcm_capture_ready(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; return snd_pcm_capture_avail(runtime) >= runtime->control->avail_min; } /** * snd_pcm_playback_data - check whether any data exists on the playback buffer * @substream: the pcm substream instance * * Checks whether any data exists on the playback buffer. * * Return: Non-zero if any data exists, or zero if not. If stop_threshold * is bigger or equal to boundary, then this function returns always non-zero. */ static inline int snd_pcm_playback_data(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; if (runtime->stop_threshold >= runtime->boundary) return 1; return snd_pcm_playback_avail(runtime) < runtime->buffer_size; } /** * snd_pcm_playback_empty - check whether the playback buffer is empty * @substream: the pcm substream instance * * Checks whether the playback buffer is empty. * * Return: Non-zero if empty, or zero if not. */ static inline int snd_pcm_playback_empty(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; return snd_pcm_playback_avail(runtime) >= runtime->buffer_size; } /** * snd_pcm_capture_empty - check whether the capture buffer is empty * @substream: the pcm substream instance * * Checks whether the capture buffer is empty. * * Return: Non-zero if empty, or zero if not. */ static inline int snd_pcm_capture_empty(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; return snd_pcm_capture_avail(runtime) == 0; } /** * snd_pcm_trigger_done - Mark the master substream * @substream: the pcm substream instance * @master: the linked master substream * * When multiple substreams of the same card are linked and the hardware * supports the single-shot operation, the driver calls this in the loop * in snd_pcm_group_for_each_entry() for marking the substream as "done". * Then most of trigger operations are performed only to the given master * substream. * * The trigger_master mark is cleared at timestamp updates at the end * of trigger operations. */ static inline void snd_pcm_trigger_done(struct snd_pcm_substream *substream, struct snd_pcm_substream *master) { substream->runtime->trigger_master = master; } static inline int hw_is_mask(int var) { return var >= SNDRV_PCM_HW_PARAM_FIRST_MASK && var <= SNDRV_PCM_HW_PARAM_LAST_MASK; } static inline int hw_is_interval(int var) { return var >= SNDRV_PCM_HW_PARAM_FIRST_INTERVAL && var <= SNDRV_PCM_HW_PARAM_LAST_INTERVAL; } static inline struct snd_mask *hw_param_mask(struct snd_pcm_hw_params *params, snd_pcm_hw_param_t var) { return ¶ms->masks[var - SNDRV_PCM_HW_PARAM_FIRST_MASK]; } static inline struct snd_interval *hw_param_interval(struct snd_pcm_hw_params *params, snd_pcm_hw_param_t var) { return ¶ms->intervals[var - SNDRV_PCM_HW_PARAM_FIRST_INTERVAL]; } static inline const struct snd_mask *hw_param_mask_c(const struct snd_pcm_hw_params *params, snd_pcm_hw_param_t var) { return ¶ms->masks[var - SNDRV_PCM_HW_PARAM_FIRST_MASK]; } static inline const struct snd_interval *hw_param_interval_c(const struct snd_pcm_hw_params *params, snd_pcm_hw_param_t var) { return ¶ms->intervals[var - SNDRV_PCM_HW_PARAM_FIRST_INTERVAL]; } /** * params_channels - Get the number of channels from the hw params * @p: hw params * * Return: the number of channels */ static inline unsigned int params_channels(const struct snd_pcm_hw_params *p) { return hw_param_interval_c(p, SNDRV_PCM_HW_PARAM_CHANNELS)->min; } /** * params_rate - Get the sample rate from the hw params * @p: hw params * * Return: the sample rate */ static inline unsigned int params_rate(const struct snd_pcm_hw_params *p) { return hw_param_interval_c(p, SNDRV_PCM_HW_PARAM_RATE)->min; } /** * params_period_size - Get the period size (in frames) from the hw params * @p: hw params * * Return: the period size in frames */ static inline unsigned int params_period_size(const struct snd_pcm_hw_params *p) { return hw_param_interval_c(p, SNDRV_PCM_HW_PARAM_PERIOD_SIZE)->min; } /** * params_periods - Get the number of periods from the hw params * @p: hw params * * Return: the number of periods */ static inline unsigned int params_periods(const struct snd_pcm_hw_params *p) { return hw_param_interval_c(p, SNDRV_PCM_HW_PARAM_PERIODS)->min; } /** * params_buffer_size - Get the buffer size (in frames) from the hw params * @p: hw params * * Return: the buffer size in frames */ static inline unsigned int params_buffer_size(const struct snd_pcm_hw_params *p) { return hw_param_interval_c(p, SNDRV_PCM_HW_PARAM_BUFFER_SIZE)->min; } /** * params_buffer_bytes - Get the buffer size (in bytes) from the hw params * @p: hw params * * Return: the buffer size in bytes */ static inline unsigned int params_buffer_bytes(const struct snd_pcm_hw_params *p) { return hw_param_interval_c(p, SNDRV_PCM_HW_PARAM_BUFFER_BYTES)->min; } int snd_interval_refine(struct snd_interval *i, const struct snd_interval *v); int snd_interval_list(struct snd_interval *i, unsigned int count, const unsigned int *list, unsigned int mask); int snd_interval_ranges(struct snd_interval *i, unsigned int count, const struct snd_interval *list, unsigned int mask); int snd_interval_ratnum(struct snd_interval *i, unsigned int rats_count, const struct snd_ratnum *rats, unsigned int *nump, unsigned int *denp); void _snd_pcm_hw_params_any(struct snd_pcm_hw_params *params); void _snd_pcm_hw_param_setempty(struct snd_pcm_hw_params *params, snd_pcm_hw_param_t var); int snd_pcm_hw_refine(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params); int snd_pcm_hw_constraint_mask64(struct snd_pcm_runtime *runtime, snd_pcm_hw_param_t var, u_int64_t mask); int snd_pcm_hw_constraint_minmax(struct snd_pcm_runtime *runtime, snd_pcm_hw_param_t var, unsigned int min, unsigned int max); int snd_pcm_hw_constraint_integer(struct snd_pcm_runtime *runtime, snd_pcm_hw_param_t var); int snd_pcm_hw_constraint_list(struct snd_pcm_runtime *runtime, unsigned int cond, snd_pcm_hw_param_t var, const struct snd_pcm_hw_constraint_list *l); int snd_pcm_hw_constraint_ranges(struct snd_pcm_runtime *runtime, unsigned int cond, snd_pcm_hw_param_t var, const struct snd_pcm_hw_constraint_ranges *r); int snd_pcm_hw_constraint_ratnums(struct snd_pcm_runtime *runtime, unsigned int cond, snd_pcm_hw_param_t var, const struct snd_pcm_hw_constraint_ratnums *r); int snd_pcm_hw_constraint_ratdens(struct snd_pcm_runtime *runtime, unsigned int cond, snd_pcm_hw_param_t var, const struct snd_pcm_hw_constraint_ratdens *r); int snd_pcm_hw_constraint_msbits(struct snd_pcm_runtime *runtime, unsigned int cond, unsigned int width, unsigned int msbits); int snd_pcm_hw_constraint_step(struct snd_pcm_runtime *runtime, unsigned int cond, snd_pcm_hw_param_t var, unsigned long step); int snd_pcm_hw_constraint_pow2(struct snd_pcm_runtime *runtime, unsigned int cond, snd_pcm_hw_param_t var); int snd_pcm_hw_rule_noresample(struct snd_pcm_runtime *runtime, unsigned int base_rate); int snd_pcm_hw_rule_add(struct snd_pcm_runtime *runtime, unsigned int cond, int var, snd_pcm_hw_rule_func_t func, void *private, int dep, ...); /** * snd_pcm_hw_constraint_single() - Constrain parameter to a single value * @runtime: PCM runtime instance * @var: The hw_params variable to constrain * @val: The value to constrain to * * Return: Positive if the value is changed, zero if it's not changed, or a * negative error code. */ static inline int snd_pcm_hw_constraint_single( struct snd_pcm_runtime *runtime, snd_pcm_hw_param_t var, unsigned int val) { return snd_pcm_hw_constraint_minmax(runtime, var, val, val); } int snd_pcm_format_signed(snd_pcm_format_t format); int snd_pcm_format_unsigned(snd_pcm_format_t format); int snd_pcm_format_linear(snd_pcm_format_t format); int snd_pcm_format_little_endian(snd_pcm_format_t format); int snd_pcm_format_big_endian(snd_pcm_format_t format); #if 0 /* just for kernel-doc */ /** * snd_pcm_format_cpu_endian - Check the PCM format is CPU-endian * @format: the format to check * * Return: 1 if the given PCM format is CPU-endian, 0 if * opposite, or a negative error code if endian not specified. */ int snd_pcm_format_cpu_endian(snd_pcm_format_t format); #endif /* DocBook */ #ifdef SNDRV_LITTLE_ENDIAN #define snd_pcm_format_cpu_endian(format) snd_pcm_format_little_endian(format) #else #define snd_pcm_format_cpu_endian(format) snd_pcm_format_big_endian(format) #endif int snd_pcm_format_width(snd_pcm_format_t format); /* in bits */ int snd_pcm_format_physical_width(snd_pcm_format_t format); /* in bits */ ssize_t snd_pcm_format_size(snd_pcm_format_t format, size_t samples); const unsigned char *snd_pcm_format_silence_64(snd_pcm_format_t format); int snd_pcm_format_set_silence(snd_pcm_format_t format, void *buf, unsigned int frames); void snd_pcm_set_ops(struct snd_pcm * pcm, int direction, const struct snd_pcm_ops *ops); void snd_pcm_set_sync_per_card(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params, const unsigned char *id, unsigned int len); /** * snd_pcm_set_sync - set the PCM sync id * @substream: the pcm substream * * Use the default PCM sync identifier for the specific card. */ static inline void snd_pcm_set_sync(struct snd_pcm_substream *substream) { substream->runtime->std_sync_id = true; } int snd_pcm_lib_ioctl(struct snd_pcm_substream *substream, unsigned int cmd, void *arg); void snd_pcm_period_elapsed_under_stream_lock(struct snd_pcm_substream *substream); void snd_pcm_period_elapsed(struct snd_pcm_substream *substream); snd_pcm_sframes_t __snd_pcm_lib_xfer(struct snd_pcm_substream *substream, void *buf, bool interleaved, snd_pcm_uframes_t frames, bool in_kernel); static inline snd_pcm_sframes_t snd_pcm_lib_write(struct snd_pcm_substream *substream, const void __user *buf, snd_pcm_uframes_t frames) { return __snd_pcm_lib_xfer(substream, (void __force *)buf, true, frames, false); } static inline snd_pcm_sframes_t snd_pcm_lib_read(struct snd_pcm_substream *substream, void __user *buf, snd_pcm_uframes_t frames) { return __snd_pcm_lib_xfer(substream, (void __force *)buf, true, frames, false); } static inline snd_pcm_sframes_t snd_pcm_lib_writev(struct snd_pcm_substream *substream, void __user **bufs, snd_pcm_uframes_t frames) { return __snd_pcm_lib_xfer(substream, (void *)bufs, false, frames, false); } static inline snd_pcm_sframes_t snd_pcm_lib_readv(struct snd_pcm_substream *substream, void __user **bufs, snd_pcm_uframes_t frames) { return __snd_pcm_lib_xfer(substream, (void *)bufs, false, frames, false); } static inline snd_pcm_sframes_t snd_pcm_kernel_write(struct snd_pcm_substream *substream, const void *buf, snd_pcm_uframes_t frames) { return __snd_pcm_lib_xfer(substream, (void *)buf, true, frames, true); } static inline snd_pcm_sframes_t snd_pcm_kernel_read(struct snd_pcm_substream *substream, void *buf, snd_pcm_uframes_t frames) { return __snd_pcm_lib_xfer(substream, buf, true, frames, true); } static inline snd_pcm_sframes_t snd_pcm_kernel_writev(struct snd_pcm_substream *substream, void **bufs, snd_pcm_uframes_t frames) { return __snd_pcm_lib_xfer(substream, bufs, false, frames, true); } static inline snd_pcm_sframes_t snd_pcm_kernel_readv(struct snd_pcm_substream *substream, void **bufs, snd_pcm_uframes_t frames) { return __snd_pcm_lib_xfer(substream, bufs, false, frames, true); } int snd_pcm_hw_limit_rates(struct snd_pcm_hardware *hw); static inline int snd_pcm_limit_hw_rates(struct snd_pcm_runtime *runtime) { return snd_pcm_hw_limit_rates(&runtime->hw); } unsigned int snd_pcm_rate_to_rate_bit(unsigned int rate); unsigned int snd_pcm_rate_bit_to_rate(unsigned int rate_bit); unsigned int snd_pcm_rate_mask_intersect(unsigned int rates_a, unsigned int rates_b); unsigned int snd_pcm_rate_range_to_bits(unsigned int rate_min, unsigned int rate_max); /** * snd_pcm_set_runtime_buffer - Set the PCM runtime buffer * @substream: PCM substream to set * @bufp: the buffer information, NULL to clear * * Copy the buffer information to runtime->dma_buffer when @bufp is non-NULL. * Otherwise it clears the current buffer information. */ static inline void snd_pcm_set_runtime_buffer(struct snd_pcm_substream *substream, struct snd_dma_buffer *bufp) { struct snd_pcm_runtime *runtime = substream->runtime; if (bufp) { runtime->dma_buffer_p = bufp; runtime->dma_area = bufp->area; runtime->dma_addr = bufp->addr; runtime->dma_bytes = bufp->bytes; } else { runtime->dma_buffer_p = NULL; runtime->dma_area = NULL; runtime->dma_addr = 0; runtime->dma_bytes = 0; } } /** * snd_pcm_gettime - Fill the timespec64 depending on the timestamp mode * @runtime: PCM runtime instance * @tv: timespec64 to fill */ static inline void snd_pcm_gettime(struct snd_pcm_runtime *runtime, struct timespec64 *tv) { switch (runtime->tstamp_type) { case SNDRV_PCM_TSTAMP_TYPE_MONOTONIC: ktime_get_ts64(tv); break; case SNDRV_PCM_TSTAMP_TYPE_MONOTONIC_RAW: ktime_get_raw_ts64(tv); break; default: ktime_get_real_ts64(tv); break; } } /* * Memory */ void snd_pcm_lib_preallocate_free(struct snd_pcm_substream *substream); void snd_pcm_lib_preallocate_free_for_all(struct snd_pcm *pcm); void snd_pcm_lib_preallocate_pages(struct snd_pcm_substream *substream, int type, struct device *data, size_t size, size_t max); void snd_pcm_lib_preallocate_pages_for_all(struct snd_pcm *pcm, int type, void *data, size_t size, size_t max); int snd_pcm_lib_malloc_pages(struct snd_pcm_substream *substream, size_t size); int snd_pcm_lib_free_pages(struct snd_pcm_substream *substream); int snd_pcm_set_managed_buffer(struct snd_pcm_substream *substream, int type, struct device *data, size_t size, size_t max); int snd_pcm_set_managed_buffer_all(struct snd_pcm *pcm, int type, struct device *data, size_t size, size_t max); /** * snd_pcm_set_fixed_buffer - Preallocate and set up the fixed size PCM buffer * @substream: the pcm substream instance * @type: DMA type (SNDRV_DMA_TYPE_*) * @data: DMA type dependent data * @size: the requested pre-allocation size in bytes * * This is a variant of snd_pcm_set_managed_buffer(), but this pre-allocates * only the given sized buffer and doesn't allow re-allocation nor dynamic * allocation of a larger buffer unlike the standard one. * The function may return -ENOMEM error, hence the caller must check it. * * Return: zero if successful, or a negative error code */ static inline int __must_check snd_pcm_set_fixed_buffer(struct snd_pcm_substream *substream, int type, struct device *data, size_t size) { return snd_pcm_set_managed_buffer(substream, type, data, size, 0); } /** * snd_pcm_set_fixed_buffer_all - Preallocate and set up the fixed size PCM buffer * @pcm: the pcm instance * @type: DMA type (SNDRV_DMA_TYPE_*) * @data: DMA type dependent data * @size: the requested pre-allocation size in bytes * * Apply the set up of the fixed buffer via snd_pcm_set_fixed_buffer() for * all substream. If any of allocation fails, it returns -ENOMEM, hence the * caller must check the return value. * * Return: zero if successful, or a negative error code */ static inline int __must_check snd_pcm_set_fixed_buffer_all(struct snd_pcm *pcm, int type, struct device *data, size_t size) { return snd_pcm_set_managed_buffer_all(pcm, type, data, size, 0); } #define snd_pcm_get_dma_buf(substream) ((substream)->runtime->dma_buffer_p) /** * snd_pcm_sgbuf_get_addr - Get the DMA address at the corresponding offset * @substream: PCM substream * @ofs: byte offset * * Return: DMA address */ static inline dma_addr_t snd_pcm_sgbuf_get_addr(struct snd_pcm_substream *substream, unsigned int ofs) { return snd_sgbuf_get_addr(snd_pcm_get_dma_buf(substream), ofs); } /** * snd_pcm_sgbuf_get_chunk_size - Compute the max size that fits within the * contig. page from the given size * @substream: PCM substream * @ofs: byte offset * @size: byte size to examine * * Return: chunk size */ static inline unsigned int snd_pcm_sgbuf_get_chunk_size(struct snd_pcm_substream *substream, unsigned int ofs, unsigned int size) { return snd_sgbuf_get_chunk_size(snd_pcm_get_dma_buf(substream), ofs, size); } int snd_pcm_lib_default_mmap(struct snd_pcm_substream *substream, struct vm_area_struct *area); /* mmap for io-memory area */ #if defined(CONFIG_X86) || defined(CONFIG_PPC) || defined(CONFIG_ALPHA) #define SNDRV_PCM_INFO_MMAP_IOMEM SNDRV_PCM_INFO_MMAP int snd_pcm_lib_mmap_iomem(struct snd_pcm_substream *substream, struct vm_area_struct *area); #else #define SNDRV_PCM_INFO_MMAP_IOMEM 0 #define snd_pcm_lib_mmap_iomem NULL #endif /** * snd_pcm_limit_isa_dma_size - Get the max size fitting with ISA DMA transfer * @dma: DMA number * @max: pointer to store the max size */ static inline void snd_pcm_limit_isa_dma_size(int dma, size_t *max) { *max = dma < 4 ? 64 * 1024 : 128 * 1024; } /* * Misc */ #define SNDRV_PCM_DEFAULT_CON_SPDIF (IEC958_AES0_CON_EMPHASIS_NONE|\ (IEC958_AES1_CON_ORIGINAL<<8)|\ (IEC958_AES1_CON_PCM_CODER<<8)|\ (IEC958_AES3_CON_FS_48000<<24)) const char *snd_pcm_format_name(snd_pcm_format_t format); /** * snd_pcm_direction_name - Get a string naming the direction of a stream * @direction: Stream's direction, one of SNDRV_PCM_STREAM_XXX * * Returns a string naming the direction of the stream. */ static inline const char *snd_pcm_direction_name(int direction) { if (direction == SNDRV_PCM_STREAM_PLAYBACK) return "Playback"; else return "Capture"; } /** * snd_pcm_stream_str - Get a string naming the direction of a stream * @substream: the pcm substream instance * * Return: A string naming the direction of the stream. */ static inline const char *snd_pcm_stream_str(struct snd_pcm_substream *substream) { return snd_pcm_direction_name(substream->stream); } /* * PCM channel-mapping control API */ /* array element of channel maps */ struct snd_pcm_chmap_elem { unsigned char channels; unsigned char map[15]; }; /* channel map information; retrieved via snd_kcontrol_chip() */ struct snd_pcm_chmap { struct snd_pcm *pcm; /* assigned PCM instance */ int stream; /* PLAYBACK or CAPTURE */ struct snd_kcontrol *kctl; const struct snd_pcm_chmap_elem *chmap; unsigned int max_channels; unsigned int channel_mask; /* optional: active channels bitmask */ void *private_data; /* optional: private data pointer */ }; /** * snd_pcm_chmap_substream - get the PCM substream assigned to the given chmap info * @info: chmap information * @idx: the substream number index * * Return: the matched PCM substream, or NULL if not found */ static inline struct snd_pcm_substream * snd_pcm_chmap_substream(struct snd_pcm_chmap *info, unsigned int idx) { struct snd_pcm_substream *s; for (s = info->pcm->streams[info->stream].substream; s; s = s->next) if (s->number == idx) return s; return NULL; } /* ALSA-standard channel maps (RL/RR prior to C/LFE) */ extern const struct snd_pcm_chmap_elem snd_pcm_std_chmaps[]; /* Other world's standard channel maps (C/LFE prior to RL/RR) */ extern const struct snd_pcm_chmap_elem snd_pcm_alt_chmaps[]; /* bit masks to be passed to snd_pcm_chmap.channel_mask field */ #define SND_PCM_CHMAP_MASK_24 ((1U << 2) | (1U << 4)) #define SND_PCM_CHMAP_MASK_246 (SND_PCM_CHMAP_MASK_24 | (1U << 6)) #define SND_PCM_CHMAP_MASK_2468 (SND_PCM_CHMAP_MASK_246 | (1U << 8)) int snd_pcm_add_chmap_ctls(struct snd_pcm *pcm, int stream, const struct snd_pcm_chmap_elem *chmap, int max_channels, unsigned long private_value, struct snd_pcm_chmap **info_ret); /** * pcm_format_to_bits - Strong-typed conversion of pcm_format to bitwise * @pcm_format: PCM format * * Return: 64bit mask corresponding to the given PCM format */ static inline u64 pcm_format_to_bits(snd_pcm_format_t pcm_format) { return 1ULL << (__force int) pcm_format; } /** * pcm_for_each_format - helper to iterate for each format type * @f: the iterator variable in snd_pcm_format_t type */ #define pcm_for_each_format(f) \ for ((f) = SNDRV_PCM_FORMAT_FIRST; \ (__force int)(f) <= (__force int)SNDRV_PCM_FORMAT_LAST; \ (f) = (__force snd_pcm_format_t)((__force int)(f) + 1)) /* printk helpers */ #define pcm_err(pcm, fmt, args...) \ dev_err((pcm)->card->dev, fmt, ##args) #define pcm_warn(pcm, fmt, args...) \ dev_warn((pcm)->card->dev, fmt, ##args) #define pcm_dbg(pcm, fmt, args...) \ dev_dbg((pcm)->card->dev, fmt, ##args) /* helpers for copying between iov_iter and iomem */ size_t copy_to_iter_fromio(const void __iomem *src, size_t bytes, struct iov_iter *iter) __must_check; size_t copy_from_iter_toio(void __iomem *dst, size_t bytes, struct iov_iter *iter) __must_check; struct snd_pcm_status64 { snd_pcm_state_t state; /* stream state */ u8 rsvd[4]; s64 trigger_tstamp_sec; /* time when stream was started/stopped/paused */ s64 trigger_tstamp_nsec; s64 tstamp_sec; /* reference timestamp */ s64 tstamp_nsec; snd_pcm_uframes_t appl_ptr; /* appl ptr */ snd_pcm_uframes_t hw_ptr; /* hw ptr */ snd_pcm_sframes_t delay; /* current delay in frames */ snd_pcm_uframes_t avail; /* number of frames available */ snd_pcm_uframes_t avail_max; /* max frames available on hw since last status */ snd_pcm_uframes_t overrange; /* count of ADC (capture) overrange detections from last status */ snd_pcm_state_t suspended_state; /* suspended stream state */ __u32 audio_tstamp_data; /* needed for 64-bit alignment, used for configs/report to/from userspace */ s64 audio_tstamp_sec; /* sample counter, wall clock, PHC or on-demand sync'ed */ s64 audio_tstamp_nsec; s64 driver_tstamp_sec; /* useful in case reference system tstamp is reported with delay */ s64 driver_tstamp_nsec; __u32 audio_tstamp_accuracy; /* in ns units, only valid if indicated in audio_tstamp_data */ unsigned char reserved[52-4*sizeof(s64)]; /* must be filled with zero */ }; #define SNDRV_PCM_IOCTL_STATUS64 _IOR('A', 0x20, struct snd_pcm_status64) #define SNDRV_PCM_IOCTL_STATUS_EXT64 _IOWR('A', 0x24, struct snd_pcm_status64) struct snd_pcm_status32 { snd_pcm_state_t state; /* stream state */ s32 trigger_tstamp_sec; /* time when stream was started/stopped/paused */ s32 trigger_tstamp_nsec; s32 tstamp_sec; /* reference timestamp */ s32 tstamp_nsec; u32 appl_ptr; /* appl ptr */ u32 hw_ptr; /* hw ptr */ s32 delay; /* current delay in frames */ u32 avail; /* number of frames available */ u32 avail_max; /* max frames available on hw since last status */ u32 overrange; /* count of ADC (capture) overrange detections from last status */ snd_pcm_state_t suspended_state; /* suspended stream state */ u32 audio_tstamp_data; /* needed for 64-bit alignment, used for configs/report to/from userspace */ s32 audio_tstamp_sec; /* sample counter, wall clock, PHC or on-demand sync'ed */ s32 audio_tstamp_nsec; s32 driver_tstamp_sec; /* useful in case reference system tstamp is reported with delay */ s32 driver_tstamp_nsec; u32 audio_tstamp_accuracy; /* in ns units, only valid if indicated in audio_tstamp_data */ unsigned char reserved[52-4*sizeof(s32)]; /* must be filled with zero */ }; #define SNDRV_PCM_IOCTL_STATUS32 _IOR('A', 0x20, struct snd_pcm_status32) #define SNDRV_PCM_IOCTL_STATUS_EXT32 _IOWR('A', 0x24, struct snd_pcm_status32) #endif /* __SOUND_PCM_H */ |
| 644 4334 546 1130 360 73 109 1851 769 770 7 1828 2057 43 397 4368 4 3857 4916 4874 4651 36 96 7 1155 401 2518 3060 542 4549 821 88 286 128 159 2 159 52 188 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/buffer_head.h * * Everything to do with buffer_heads. */ #ifndef _LINUX_BUFFER_HEAD_H #define _LINUX_BUFFER_HEAD_H #include <linux/types.h> #include <linux/blk_types.h> #include <linux/fs.h> #include <linux/linkage.h> #include <linux/pagemap.h> #include <linux/wait.h> #include <linux/atomic.h> enum bh_state_bits { BH_Uptodate, /* Contains valid data */ BH_Dirty, /* Is dirty */ BH_Lock, /* Is locked */ BH_Req, /* Has been submitted for I/O */ BH_Mapped, /* Has a disk mapping */ BH_New, /* Disk mapping was newly created by get_block */ BH_Async_Read, /* Is under end_buffer_async_read I/O */ BH_Async_Write, /* Is under end_buffer_async_write I/O */ BH_Delay, /* Buffer is not yet allocated on disk */ BH_Boundary, /* Block is followed by a discontiguity */ BH_Write_EIO, /* I/O error on write */ BH_Unwritten, /* Buffer is allocated on disk but not written */ BH_Quiet, /* Buffer Error Prinks to be quiet */ BH_Meta, /* Buffer contains metadata */ BH_Prio, /* Buffer should be submitted with REQ_PRIO */ BH_Defer_Completion, /* Defer AIO completion to workqueue */ BH_Migrate, /* Buffer is being migrated (norefs) */ BH_PrivateStart,/* not a state bit, but the first bit available * for private allocation by other entities */ }; #define MAX_BUF_PER_PAGE (PAGE_SIZE / 512) struct page; struct buffer_head; struct address_space; typedef void (bh_end_io_t)(struct buffer_head *bh, int uptodate); /* * Historically, a buffer_head was used to map a single block * within a page, and of course as the unit of I/O through the * filesystem and block layers. Nowadays the basic I/O unit * is the bio, and buffer_heads are used for extracting block * mappings (via a get_block_t call), for tracking state within * a folio (via a folio_mapping) and for wrapping bio submission * for backward compatibility reasons (e.g. submit_bh). */ struct buffer_head { unsigned long b_state; /* buffer state bitmap (see above) */ struct buffer_head *b_this_page;/* circular list of page's buffers */ union { struct page *b_page; /* the page this bh is mapped to */ struct folio *b_folio; /* the folio this bh is mapped to */ }; sector_t b_blocknr; /* start block number */ size_t b_size; /* size of mapping */ char *b_data; /* pointer to data within the page */ struct block_device *b_bdev; bh_end_io_t *b_end_io; /* I/O completion */ void *b_private; /* reserved for b_end_io */ struct list_head b_assoc_buffers; /* associated with another mapping */ struct address_space *b_assoc_map; /* mapping this buffer is associated with */ atomic_t b_count; /* users using this buffer_head */ spinlock_t b_uptodate_lock; /* Used by the first bh in a page, to * serialise IO completion of other * buffers in the page */ }; /* * macro tricks to expand the set_buffer_foo(), clear_buffer_foo() * and buffer_foo() functions. * To avoid reset buffer flags that are already set, because that causes * a costly cache line transition, check the flag first. */ #define BUFFER_FNS(bit, name) \ static __always_inline void set_buffer_##name(struct buffer_head *bh) \ { \ if (!test_bit(BH_##bit, &(bh)->b_state)) \ set_bit(BH_##bit, &(bh)->b_state); \ } \ static __always_inline void clear_buffer_##name(struct buffer_head *bh) \ { \ clear_bit(BH_##bit, &(bh)->b_state); \ } \ static __always_inline int buffer_##name(const struct buffer_head *bh) \ { \ return test_bit(BH_##bit, &(bh)->b_state); \ } /* * test_set_buffer_foo() and test_clear_buffer_foo() */ #define TAS_BUFFER_FNS(bit, name) \ static __always_inline int test_set_buffer_##name(struct buffer_head *bh) \ { \ return test_and_set_bit(BH_##bit, &(bh)->b_state); \ } \ static __always_inline int test_clear_buffer_##name(struct buffer_head *bh) \ { \ return test_and_clear_bit(BH_##bit, &(bh)->b_state); \ } \ /* * Emit the buffer bitops functions. Note that there are also functions * of the form "mark_buffer_foo()". These are higher-level functions which * do something in addition to setting a b_state bit. */ BUFFER_FNS(Dirty, dirty) TAS_BUFFER_FNS(Dirty, dirty) BUFFER_FNS(Lock, locked) BUFFER_FNS(Req, req) TAS_BUFFER_FNS(Req, req) BUFFER_FNS(Mapped, mapped) BUFFER_FNS(New, new) BUFFER_FNS(Async_Read, async_read) BUFFER_FNS(Async_Write, async_write) BUFFER_FNS(Delay, delay) BUFFER_FNS(Boundary, boundary) BUFFER_FNS(Write_EIO, write_io_error) BUFFER_FNS(Unwritten, unwritten) BUFFER_FNS(Meta, meta) BUFFER_FNS(Prio, prio) BUFFER_FNS(Defer_Completion, defer_completion) static __always_inline void set_buffer_uptodate(struct buffer_head *bh) { /* * If somebody else already set this uptodate, they will * have done the memory barrier, and a reader will thus * see *some* valid buffer state. * * Any other serialization (with IO errors or whatever that * might clear the bit) has to come from other state (eg BH_Lock). */ if (test_bit(BH_Uptodate, &bh->b_state)) return; /* * make it consistent with folio_mark_uptodate * pairs with smp_load_acquire in buffer_uptodate */ smp_mb__before_atomic(); set_bit(BH_Uptodate, &bh->b_state); } static __always_inline void clear_buffer_uptodate(struct buffer_head *bh) { clear_bit(BH_Uptodate, &bh->b_state); } static __always_inline int buffer_uptodate(const struct buffer_head *bh) { /* * make it consistent with folio_test_uptodate * pairs with smp_mb__before_atomic in set_buffer_uptodate */ return test_bit_acquire(BH_Uptodate, &bh->b_state); } static inline unsigned long bh_offset(const struct buffer_head *bh) { return (unsigned long)(bh)->b_data & (page_size(bh->b_page) - 1); } /* If we *know* page->private refers to buffer_heads */ #define page_buffers(page) \ ({ \ BUG_ON(!PagePrivate(page)); \ ((struct buffer_head *)page_private(page)); \ }) #define folio_buffers(folio) folio_get_private(folio) void buffer_check_dirty_writeback(struct folio *folio, bool *dirty, bool *writeback); /* * Declarations */ void mark_buffer_dirty(struct buffer_head *bh); void mark_buffer_write_io_error(struct buffer_head *bh); void touch_buffer(struct buffer_head *bh); void folio_set_bh(struct buffer_head *bh, struct folio *folio, unsigned long offset); struct buffer_head *folio_alloc_buffers(struct folio *folio, unsigned long size, gfp_t gfp); struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size); struct buffer_head *create_empty_buffers(struct folio *folio, unsigned long blocksize, unsigned long b_state); void end_buffer_read_sync(struct buffer_head *bh, int uptodate); void end_buffer_write_sync(struct buffer_head *bh, int uptodate); /* Things to do with buffers at mapping->private_list */ void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode); int generic_buffers_fsync_noflush(struct file *file, loff_t start, loff_t end, bool datasync); int generic_buffers_fsync(struct file *file, loff_t start, loff_t end, bool datasync); void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len); static inline void clean_bdev_bh_alias(struct buffer_head *bh) { clean_bdev_aliases(bh->b_bdev, bh->b_blocknr, 1); } void mark_buffer_async_write(struct buffer_head *bh); void __wait_on_buffer(struct buffer_head *); wait_queue_head_t *bh_waitq_head(struct buffer_head *bh); struct buffer_head *__find_get_block(struct block_device *bdev, sector_t block, unsigned size); struct buffer_head *__find_get_block_nonatomic(struct block_device *bdev, sector_t block, unsigned size); struct buffer_head *bdev_getblk(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp); void __brelse(struct buffer_head *); void __bforget(struct buffer_head *); void __breadahead(struct block_device *, sector_t block, unsigned int size); struct buffer_head *__bread_gfp(struct block_device *, sector_t block, unsigned size, gfp_t gfp); struct buffer_head *alloc_buffer_head(gfp_t gfp_flags); void free_buffer_head(struct buffer_head * bh); void unlock_buffer(struct buffer_head *bh); void __lock_buffer(struct buffer_head *bh); int sync_dirty_buffer(struct buffer_head *bh); int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags); void write_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags); void submit_bh(blk_opf_t, struct buffer_head *); void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize); int bh_uptodate_or_lock(struct buffer_head *bh); int __bh_read(struct buffer_head *bh, blk_opf_t op_flags, bool wait); void __bh_read_batch(int nr, struct buffer_head *bhs[], blk_opf_t op_flags, bool force_lock); /* * Generic address_space_operations implementations for buffer_head-backed * address_spaces. */ void block_invalidate_folio(struct folio *folio, size_t offset, size_t length); int block_write_full_folio(struct folio *folio, struct writeback_control *wbc, void *get_block); int __block_write_full_folio(struct inode *inode, struct folio *folio, get_block_t *get_block, struct writeback_control *wbc); int block_read_full_folio(struct folio *, get_block_t *); bool block_is_partially_uptodate(struct folio *, size_t from, size_t count); int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, get_block_t *get_block); int __block_write_begin(struct folio *folio, loff_t pos, unsigned len, get_block_t *get_block); int block_write_end(struct file *, struct address_space *, loff_t, unsigned len, unsigned copied, struct folio *, void *); int generic_write_end(struct file *, struct address_space *, loff_t, unsigned len, unsigned copied, struct folio *, void *); void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to); int cont_write_begin(struct file *, struct address_space *, loff_t, unsigned, struct folio **, void **, get_block_t *, loff_t *); int generic_cont_expand_simple(struct inode *inode, loff_t size); void block_commit_write(struct folio *folio, size_t from, size_t to); int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block); sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *); int block_truncate_page(struct address_space *, loff_t, get_block_t *); #ifdef CONFIG_MIGRATION extern int buffer_migrate_folio(struct address_space *, struct folio *dst, struct folio *src, enum migrate_mode); extern int buffer_migrate_folio_norefs(struct address_space *, struct folio *dst, struct folio *src, enum migrate_mode); #else #define buffer_migrate_folio NULL #define buffer_migrate_folio_norefs NULL #endif /* * inline definitions */ static inline void get_bh(struct buffer_head *bh) { atomic_inc(&bh->b_count); } static inline void put_bh(struct buffer_head *bh) { smp_mb__before_atomic(); atomic_dec(&bh->b_count); } /** * brelse - Release a buffer. * @bh: The buffer to release. * * Decrement a buffer_head's reference count. If @bh is NULL, this * function is a no-op. * * If all buffers on a folio have zero reference count, are clean * and unlocked, and if the folio is unlocked and not under writeback * then try_to_free_buffers() may strip the buffers from the folio in * preparation for freeing it (sometimes, rarely, buffers are removed * from a folio but it ends up not being freed, and buffers may later * be reattached). * * Context: Any context. */ static inline void brelse(struct buffer_head *bh) { if (bh) __brelse(bh); } /** * bforget - Discard any dirty data in a buffer. * @bh: The buffer to forget. * * Call this function instead of brelse() if the data written to a buffer * no longer needs to be written back. It will clear the buffer's dirty * flag so writeback of this buffer will be skipped. * * Context: Any context. */ static inline void bforget(struct buffer_head *bh) { if (bh) __bforget(bh); } static inline struct buffer_head * sb_bread(struct super_block *sb, sector_t block) { return __bread_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE); } static inline struct buffer_head * sb_bread_unmovable(struct super_block *sb, sector_t block) { return __bread_gfp(sb->s_bdev, block, sb->s_blocksize, 0); } static inline void sb_breadahead(struct super_block *sb, sector_t block) { __breadahead(sb->s_bdev, block, sb->s_blocksize); } static inline struct buffer_head *getblk_unmovable(struct block_device *bdev, sector_t block, unsigned size) { gfp_t gfp; gfp = mapping_gfp_constraint(bdev->bd_mapping, ~__GFP_FS); gfp |= __GFP_NOFAIL; return bdev_getblk(bdev, block, size, gfp); } static inline struct buffer_head *__getblk(struct block_device *bdev, sector_t block, unsigned size) { gfp_t gfp; gfp = mapping_gfp_constraint(bdev->bd_mapping, ~__GFP_FS); gfp |= __GFP_MOVABLE | __GFP_NOFAIL; return bdev_getblk(bdev, block, size, gfp); } static inline struct buffer_head *sb_getblk(struct super_block *sb, sector_t block) { return __getblk(sb->s_bdev, block, sb->s_blocksize); } static inline struct buffer_head *sb_getblk_gfp(struct super_block *sb, sector_t block, gfp_t gfp) { return bdev_getblk(sb->s_bdev, block, sb->s_blocksize, gfp); } static inline struct buffer_head * sb_find_get_block(struct super_block *sb, sector_t block) { return __find_get_block(sb->s_bdev, block, sb->s_blocksize); } static inline struct buffer_head * sb_find_get_block_nonatomic(struct super_block *sb, sector_t block) { return __find_get_block_nonatomic(sb->s_bdev, block, sb->s_blocksize); } static inline void map_bh(struct buffer_head *bh, struct super_block *sb, sector_t block) { set_buffer_mapped(bh); bh->b_bdev = sb->s_bdev; bh->b_blocknr = block; bh->b_size = sb->s_blocksize; } static inline void wait_on_buffer(struct buffer_head *bh) { might_sleep(); if (buffer_locked(bh)) __wait_on_buffer(bh); } static inline int trylock_buffer(struct buffer_head *bh) { return likely(!test_and_set_bit_lock(BH_Lock, &bh->b_state)); } static inline void lock_buffer(struct buffer_head *bh) { might_sleep(); if (!trylock_buffer(bh)) __lock_buffer(bh); } static inline void bh_readahead(struct buffer_head *bh, blk_opf_t op_flags) { if (!buffer_uptodate(bh) && trylock_buffer(bh)) { if (!buffer_uptodate(bh)) __bh_read(bh, op_flags, false); else unlock_buffer(bh); } } static inline void bh_read_nowait(struct buffer_head *bh, blk_opf_t op_flags) { if (!bh_uptodate_or_lock(bh)) __bh_read(bh, op_flags, false); } /* Returns 1 if buffer uptodated, 0 on success, and -EIO on error. */ static inline int bh_read(struct buffer_head *bh, blk_opf_t op_flags) { if (bh_uptodate_or_lock(bh)) return 1; return __bh_read(bh, op_flags, true); } static inline void bh_read_batch(int nr, struct buffer_head *bhs[]) { __bh_read_batch(nr, bhs, 0, true); } static inline void bh_readahead_batch(int nr, struct buffer_head *bhs[], blk_opf_t op_flags) { __bh_read_batch(nr, bhs, op_flags, false); } /** * __bread() - Read a block. * @bdev: The block device to read from. * @block: Block number in units of block size. * @size: The block size of this device in bytes. * * Read a specified block, and return the buffer head that refers * to it. The memory is allocated from the movable area so that it can * be migrated. The returned buffer head has its refcount increased. * The caller should call brelse() when it has finished with the buffer. * * Context: May sleep waiting for I/O. * Return: NULL if the block was unreadable. */ static inline struct buffer_head *__bread(struct block_device *bdev, sector_t block, unsigned size) { return __bread_gfp(bdev, block, size, __GFP_MOVABLE); } /** * get_nth_bh - Get a reference on the n'th buffer after this one. * @bh: The buffer to start counting from. * @count: How many buffers to skip. * * This is primarily useful for finding the nth buffer in a folio; in * that case you pass the head buffer and the byte offset in the folio * divided by the block size. It can be used for other purposes, but * it will wrap at the end of the folio rather than returning NULL or * proceeding to the next folio for you. * * Return: The requested buffer with an elevated refcount. */ static inline __must_check struct buffer_head *get_nth_bh(struct buffer_head *bh, unsigned int count) { while (count--) bh = bh->b_this_page; get_bh(bh); return bh; } bool block_dirty_folio(struct address_space *mapping, struct folio *folio); #ifdef CONFIG_BUFFER_HEAD void buffer_init(void); bool try_to_free_buffers(struct folio *folio); int inode_has_buffers(struct inode *inode); void invalidate_inode_buffers(struct inode *inode); int remove_inode_buffers(struct inode *inode); int sync_mapping_buffers(struct address_space *mapping); void invalidate_bh_lrus(void); void invalidate_bh_lrus_cpu(void); bool has_bh_in_lru(int cpu, void *dummy); extern int buffer_heads_over_limit; #else /* CONFIG_BUFFER_HEAD */ static inline void buffer_init(void) {} static inline bool try_to_free_buffers(struct folio *folio) { return true; } static inline int inode_has_buffers(struct inode *inode) { return 0; } static inline void invalidate_inode_buffers(struct inode *inode) {} static inline int remove_inode_buffers(struct inode *inode) { return 1; } static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; } static inline void invalidate_bh_lrus(void) {} static inline void invalidate_bh_lrus_cpu(void) {} static inline bool has_bh_in_lru(int cpu, void *dummy) { return false; } #define buffer_heads_over_limit 0 #endif /* CONFIG_BUFFER_HEAD */ #endif /* _LINUX_BUFFER_HEAD_H */ |
| 39 23 9 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FILEATTR_H #define _LINUX_FILEATTR_H /* Flags shared betwen flags/xflags */ #define FS_COMMON_FL \ (FS_SYNC_FL | FS_IMMUTABLE_FL | FS_APPEND_FL | \ FS_NODUMP_FL | FS_NOATIME_FL | FS_DAX_FL | \ FS_PROJINHERIT_FL) #define FS_XFLAG_COMMON \ (FS_XFLAG_SYNC | FS_XFLAG_IMMUTABLE | FS_XFLAG_APPEND | \ FS_XFLAG_NODUMP | FS_XFLAG_NOATIME | FS_XFLAG_DAX | \ FS_XFLAG_PROJINHERIT) /* * Merged interface for miscellaneous file attributes. 'flags' originates from * ext* and 'fsx_flags' from xfs. There's some overlap between the two, which * is handled by the VFS helpers, so filesystems are free to implement just one * or both of these sub-interfaces. */ struct fileattr { u32 flags; /* flags (FS_IOC_GETFLAGS/FS_IOC_SETFLAGS) */ /* struct fsxattr: */ u32 fsx_xflags; /* xflags field value (get/set) */ u32 fsx_extsize; /* extsize field value (get/set)*/ u32 fsx_nextents; /* nextents field value (get) */ u32 fsx_projid; /* project identifier (get/set) */ u32 fsx_cowextsize; /* CoW extsize field value (get/set)*/ /* selectors: */ bool flags_valid:1; bool fsx_valid:1; }; int copy_fsxattr_to_user(const struct fileattr *fa, struct fsxattr __user *ufa); void fileattr_fill_xflags(struct fileattr *fa, u32 xflags); void fileattr_fill_flags(struct fileattr *fa, u32 flags); /** * fileattr_has_fsx - check for extended flags/attributes * @fa: fileattr pointer * * Return: true if any attributes are present that are not represented in * ->flags. */ static inline bool fileattr_has_fsx(const struct fileattr *fa) { return fa->fsx_valid && ((fa->fsx_xflags & ~FS_XFLAG_COMMON) || fa->fsx_extsize != 0 || fa->fsx_projid != 0 || fa->fsx_cowextsize != 0); } int vfs_fileattr_get(struct dentry *dentry, struct fileattr *fa); int vfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); #endif /* _LINUX_FILEATTR_H */ |
| 16 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _SCSI_SCSI_CMND_H #define _SCSI_SCSI_CMND_H #include <linux/dma-mapping.h> #include <linux/blkdev.h> #include <linux/t10-pi.h> #include <linux/list.h> #include <linux/types.h> #include <linux/timer.h> #include <linux/scatterlist.h> #include <scsi/scsi_device.h> struct Scsi_Host; /* * MAX_COMMAND_SIZE is: * The longest fixed-length SCSI CDB as per the SCSI standard. * fixed-length means: commands that their size can be determined * by their opcode and the CDB does not carry a length specifier, (unlike * the VARIABLE_LENGTH_CMD(0x7f) command). This is actually not exactly * true and the SCSI standard also defines extended commands and * vendor specific commands that can be bigger than 16 bytes. The kernel * will support these using the same infrastructure used for VARLEN CDB's. * So in effect MAX_COMMAND_SIZE means the maximum size command scsi-ml * supports without specifying a cmd_len by ULD's */ #define MAX_COMMAND_SIZE 16 struct scsi_data_buffer { struct sg_table table; unsigned length; }; /* embedded in scsi_cmnd */ struct scsi_pointer { char *ptr; /* data pointer */ int this_residual; /* left in this buffer */ struct scatterlist *buffer; /* which buffer */ int buffers_residual; /* how many buffers left */ dma_addr_t dma_handle; volatile int Status; volatile int Message; volatile int have_data_in; volatile int sent_command; volatile int phase; }; /* for scmd->flags */ #define SCMD_TAGGED (1 << 0) #define SCMD_INITIALIZED (1 << 1) #define SCMD_LAST (1 << 2) /* * libata uses SCSI EH to fetch sense data for successful commands. * SCSI EH should not overwrite scmd->result when SCMD_FORCE_EH_SUCCESS is set. */ #define SCMD_FORCE_EH_SUCCESS (1 << 3) #define SCMD_FAIL_IF_RECOVERING (1 << 4) /* flags preserved across unprep / reprep */ #define SCMD_PRESERVED_FLAGS (SCMD_INITIALIZED | SCMD_FAIL_IF_RECOVERING) /* for scmd->state */ #define SCMD_STATE_COMPLETE 0 #define SCMD_STATE_INFLIGHT 1 enum scsi_cmnd_submitter { SUBMITTED_BY_BLOCK_LAYER = 0, SUBMITTED_BY_SCSI_ERROR_HANDLER = 1, SUBMITTED_BY_SCSI_RESET_IOCTL = 2, } __packed; struct scsi_cmnd { struct scsi_device *device; struct list_head eh_entry; /* entry for the host eh_abort_list/eh_cmd_q */ struct delayed_work abort_work; struct rcu_head rcu; int eh_eflags; /* Used by error handlr */ int budget_token; /* * This is set to jiffies as it was when the command was first * allocated. It is used to time how long the command has * been outstanding */ unsigned long jiffies_at_alloc; int retries; int allowed; unsigned char prot_op; unsigned char prot_type; unsigned char prot_flags; enum scsi_cmnd_submitter submitter; unsigned short cmd_len; enum dma_data_direction sc_data_direction; unsigned char cmnd[32]; /* SCSI CDB */ /* These elements define the operation we ultimately want to perform */ struct scsi_data_buffer sdb; struct scsi_data_buffer *prot_sdb; unsigned underflow; /* Return error if less than this amount is transferred */ unsigned transfersize; /* How much we are guaranteed to transfer with each SCSI transfer (ie, between disconnect / reconnects. Probably == sector size */ unsigned resid_len; /* residual count */ unsigned sense_len; unsigned char *sense_buffer; /* obtained by REQUEST SENSE when * CHECK CONDITION is received on original * command (auto-sense). Length must be * SCSI_SENSE_BUFFERSIZE bytes. */ int flags; /* Command flags */ unsigned long state; /* Command completion state */ unsigned int extra_len; /* length of alignment and padding */ /* * The fields below can be modified by the LLD but the fields above * must not be modified. */ unsigned char *host_scribble; /* The host adapter is allowed to * call scsi_malloc and get some memory * and hang it here. The host adapter * is also expected to call scsi_free * to release this memory. (The memory * obtained by scsi_malloc is guaranteed * to be at an address < 16Mb). */ int result; /* Status code from lower level driver */ }; /* Variant of blk_mq_rq_from_pdu() that verifies the type of its argument. */ static inline struct request *scsi_cmd_to_rq(struct scsi_cmnd *scmd) { return blk_mq_rq_from_pdu(scmd); } /* * Return the driver private allocation behind the command. * Only works if cmd_size is set in the host template. */ static inline void *scsi_cmd_priv(struct scsi_cmnd *cmd) { return cmd + 1; } void scsi_done(struct scsi_cmnd *cmd); void scsi_done_direct(struct scsi_cmnd *cmd); extern void scsi_finish_command(struct scsi_cmnd *cmd); extern void *scsi_kmap_atomic_sg(struct scatterlist *sg, int sg_count, size_t *offset, size_t *len); extern void scsi_kunmap_atomic_sg(void *virt); blk_status_t scsi_alloc_sgtables(struct scsi_cmnd *cmd); void scsi_free_sgtables(struct scsi_cmnd *cmd); #ifdef CONFIG_SCSI_DMA extern int scsi_dma_map(struct scsi_cmnd *cmd); extern void scsi_dma_unmap(struct scsi_cmnd *cmd); #else /* !CONFIG_SCSI_DMA */ static inline int scsi_dma_map(struct scsi_cmnd *cmd) { return -ENOSYS; } static inline void scsi_dma_unmap(struct scsi_cmnd *cmd) { } #endif /* !CONFIG_SCSI_DMA */ static inline unsigned scsi_sg_count(struct scsi_cmnd *cmd) { return cmd->sdb.table.nents; } static inline struct scatterlist *scsi_sglist(struct scsi_cmnd *cmd) { return cmd->sdb.table.sgl; } static inline unsigned scsi_bufflen(struct scsi_cmnd *cmd) { return cmd->sdb.length; } static inline void scsi_set_resid(struct scsi_cmnd *cmd, unsigned int resid) { cmd->resid_len = resid; } static inline unsigned int scsi_get_resid(struct scsi_cmnd *cmd) { return cmd->resid_len; } #define scsi_for_each_sg(cmd, sg, nseg, __i) \ for_each_sg(scsi_sglist(cmd), sg, nseg, __i) static inline int scsi_sg_copy_from_buffer(struct scsi_cmnd *cmd, const void *buf, int buflen) { return sg_copy_from_buffer(scsi_sglist(cmd), scsi_sg_count(cmd), buf, buflen); } static inline int scsi_sg_copy_to_buffer(struct scsi_cmnd *cmd, void *buf, int buflen) { return sg_copy_to_buffer(scsi_sglist(cmd), scsi_sg_count(cmd), buf, buflen); } static inline sector_t scsi_get_sector(struct scsi_cmnd *scmd) { return blk_rq_pos(scsi_cmd_to_rq(scmd)); } static inline sector_t scsi_get_lba(struct scsi_cmnd *scmd) { unsigned int shift = ilog2(scmd->device->sector_size) - SECTOR_SHIFT; return blk_rq_pos(scsi_cmd_to_rq(scmd)) >> shift; } static inline unsigned int scsi_logical_block_count(struct scsi_cmnd *scmd) { unsigned int shift = ilog2(scmd->device->sector_size); return blk_rq_bytes(scsi_cmd_to_rq(scmd)) >> shift; } /* * The operations below are hints that tell the controller driver how * to handle I/Os with DIF or similar types of protection information. */ enum scsi_prot_operations { /* Normal I/O */ SCSI_PROT_NORMAL = 0, /* OS-HBA: Protected, HBA-Target: Unprotected */ SCSI_PROT_READ_INSERT, SCSI_PROT_WRITE_STRIP, /* OS-HBA: Unprotected, HBA-Target: Protected */ SCSI_PROT_READ_STRIP, SCSI_PROT_WRITE_INSERT, /* OS-HBA: Protected, HBA-Target: Protected */ SCSI_PROT_READ_PASS, SCSI_PROT_WRITE_PASS, }; static inline void scsi_set_prot_op(struct scsi_cmnd *scmd, unsigned char op) { scmd->prot_op = op; } static inline unsigned char scsi_get_prot_op(struct scsi_cmnd *scmd) { return scmd->prot_op; } enum scsi_prot_flags { SCSI_PROT_TRANSFER_PI = 1 << 0, SCSI_PROT_GUARD_CHECK = 1 << 1, SCSI_PROT_REF_CHECK = 1 << 2, SCSI_PROT_REF_INCREMENT = 1 << 3, SCSI_PROT_IP_CHECKSUM = 1 << 4, }; /* * The controller usually does not know anything about the target it * is communicating with. However, when DIX is enabled the controller * must be know target type so it can verify the protection * information passed along with the I/O. */ enum scsi_prot_target_type { SCSI_PROT_DIF_TYPE0 = 0, SCSI_PROT_DIF_TYPE1, SCSI_PROT_DIF_TYPE2, SCSI_PROT_DIF_TYPE3, }; static inline void scsi_set_prot_type(struct scsi_cmnd *scmd, unsigned char type) { scmd->prot_type = type; } static inline unsigned char scsi_get_prot_type(struct scsi_cmnd *scmd) { return scmd->prot_type; } static inline u32 scsi_prot_ref_tag(struct scsi_cmnd *scmd) { struct request *rq = blk_mq_rq_from_pdu(scmd); return t10_pi_ref_tag(rq); } static inline unsigned int scsi_prot_interval(struct scsi_cmnd *scmd) { return scmd->device->sector_size; } static inline unsigned scsi_prot_sg_count(struct scsi_cmnd *cmd) { return cmd->prot_sdb ? cmd->prot_sdb->table.nents : 0; } static inline struct scatterlist *scsi_prot_sglist(struct scsi_cmnd *cmd) { return cmd->prot_sdb ? cmd->prot_sdb->table.sgl : NULL; } static inline struct scsi_data_buffer *scsi_prot(struct scsi_cmnd *cmd) { return cmd->prot_sdb; } #define scsi_for_each_prot_sg(cmd, sg, nseg, __i) \ for_each_sg(scsi_prot_sglist(cmd), sg, nseg, __i) static inline void set_status_byte(struct scsi_cmnd *cmd, char status) { cmd->result = (cmd->result & 0xffffff00) | status; } static inline u8 get_status_byte(struct scsi_cmnd *cmd) { return cmd->result & 0xff; } static inline void set_host_byte(struct scsi_cmnd *cmd, char status) { cmd->result = (cmd->result & 0xff00ffff) | (status << 16); } static inline u8 get_host_byte(struct scsi_cmnd *cmd) { return (cmd->result >> 16) & 0xff; } /** * scsi_msg_to_host_byte() - translate message byte * @cmd: the SCSI command * @msg: the SCSI parallel message byte to translate * * Translate the SCSI parallel message byte to a matching * host byte setting. A message of COMMAND_COMPLETE indicates * a successful command execution, any other message indicate * an error. As the messages themselves only have a meaning * for the SCSI parallel protocol this function translates * them into a matching host byte value for SCSI EH. */ static inline void scsi_msg_to_host_byte(struct scsi_cmnd *cmd, u8 msg) { switch (msg) { case COMMAND_COMPLETE: break; case ABORT_TASK_SET: set_host_byte(cmd, DID_ABORT); break; case TARGET_RESET: set_host_byte(cmd, DID_RESET); break; default: set_host_byte(cmd, DID_ERROR); break; } } static inline unsigned scsi_transfer_length(struct scsi_cmnd *scmd) { unsigned int xfer_len = scmd->sdb.length; unsigned int prot_interval = scsi_prot_interval(scmd); if (scmd->prot_flags & SCSI_PROT_TRANSFER_PI) xfer_len += (xfer_len >> ilog2(prot_interval)) * 8; return xfer_len; } extern void scsi_build_sense(struct scsi_cmnd *scmd, int desc, u8 key, u8 asc, u8 ascq); struct request *scsi_alloc_request(struct request_queue *q, blk_opf_t opf, blk_mq_req_flags_t flags); #endif /* _SCSI_SCSI_CMND_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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef __DSA_USER_H #define __DSA_USER_H #include <linux/if_bridge.h> #include <linux/if_vlan.h> #include <linux/list.h> #include <linux/netpoll.h> #include <linux/types.h> #include <net/dsa.h> #include <net/gro_cells.h> struct net_device; struct netlink_ext_ack; extern struct notifier_block dsa_user_switchdev_notifier; extern struct notifier_block dsa_user_switchdev_blocking_notifier; struct dsa_user_priv { /* Copy of CPU port xmit for faster access in user transmit hot path */ struct sk_buff * (*xmit)(struct sk_buff *skb, struct net_device *dev); struct gro_cells gcells; /* DSA port data, such as switch, port index, etc. */ struct dsa_port *dp; #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *netpoll; #endif /* TC context */ struct list_head mall_tc_list; }; void dsa_user_mii_bus_init(struct dsa_switch *ds); int dsa_user_create(struct dsa_port *dp); void dsa_user_destroy(struct net_device *user_dev); int dsa_user_suspend(struct net_device *user_dev); int dsa_user_resume(struct net_device *user_dev); int dsa_user_register_notifier(void); void dsa_user_unregister_notifier(void); int dsa_user_host_uc_install(struct net_device *dev, const u8 *addr); void dsa_user_host_uc_uninstall(struct net_device *dev); void dsa_user_sync_ha(struct net_device *dev); void dsa_user_unsync_ha(struct net_device *dev); void dsa_user_setup_tagger(struct net_device *user); int dsa_user_change_mtu(struct net_device *dev, int new_mtu); int dsa_user_change_conduit(struct net_device *dev, struct net_device *conduit, struct netlink_ext_ack *extack); int dsa_user_manage_vlan_filtering(struct net_device *dev, bool vlan_filtering); static inline struct dsa_port *dsa_user_to_port(const struct net_device *dev) { struct dsa_user_priv *p = netdev_priv(dev); return p->dp; } static inline struct net_device * dsa_user_to_conduit(const struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); return dsa_port_to_conduit(dp); } #endif |
| 211 210 4 4 1 1 1 1 88 19 74 13 6 17 2 88 88 88 88 88 88 247 3 88 88 3 3 3 3 3 211 211 211 1 23 23 23 88 88 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2005 Silicon Graphics, Inc. * Copyright (c) 2013 Red Hat, Inc. * All Rights Reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_sb.h" #include "xfs_mount.h" #include "xfs_da_format.h" #include "xfs_da_btree.h" #include "xfs_inode.h" #include "xfs_trans.h" #include "xfs_bmap_btree.h" #include "xfs_bmap.h" #include "xfs_attr_sf.h" #include "xfs_attr.h" #include "xfs_attr_remote.h" #include "xfs_attr_leaf.h" #include "xfs_error.h" #include "xfs_trace.h" #include "xfs_buf_item.h" #include "xfs_dir2.h" #include "xfs_log.h" #include "xfs_ag.h" #include "xfs_errortag.h" #include "xfs_health.h" /* * xfs_attr_leaf.c * * Routines to implement leaf blocks of attributes as Btrees of hashed names. */ /*======================================================================== * Function prototypes for the kernel. *========================================================================*/ /* * Routines used for growing the Btree. */ STATIC int xfs_attr3_leaf_create(struct xfs_da_args *args, xfs_dablk_t which_block, struct xfs_buf **bpp); STATIC void xfs_attr3_leaf_add_work(struct xfs_buf *leaf_buffer, struct xfs_attr3_icleaf_hdr *ichdr, struct xfs_da_args *args, int freemap_index); STATIC void xfs_attr3_leaf_compact(struct xfs_da_args *args, struct xfs_attr3_icleaf_hdr *ichdr, struct xfs_buf *leaf_buffer); STATIC void xfs_attr3_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1, xfs_da_state_blk_t *blk2); STATIC int xfs_attr3_leaf_figure_balance(xfs_da_state_t *state, xfs_da_state_blk_t *leaf_blk_1, struct xfs_attr3_icleaf_hdr *ichdr1, xfs_da_state_blk_t *leaf_blk_2, struct xfs_attr3_icleaf_hdr *ichdr2, int *number_entries_in_blk1, int *number_usedbytes_in_blk1); /* * Utility routines. */ STATIC void xfs_attr3_leaf_moveents(struct xfs_da_args *args, struct xfs_attr_leafblock *src_leaf, struct xfs_attr3_icleaf_hdr *src_ichdr, int src_start, struct xfs_attr_leafblock *dst_leaf, struct xfs_attr3_icleaf_hdr *dst_ichdr, int dst_start, int move_count); STATIC int xfs_attr_leaf_entsize(xfs_attr_leafblock_t *leaf, int index); /* * attr3 block 'firstused' conversion helpers. * * firstused refers to the offset of the first used byte of the nameval region * of an attr leaf block. The region starts at the tail of the block and expands * backwards towards the middle. As such, firstused is initialized to the block * size for an empty leaf block and is reduced from there. * * The attr3 block size is pegged to the fsb size and the maximum fsb is 64k. * The in-core firstused field is 32-bit and thus supports the maximum fsb size. * The on-disk field is only 16-bit, however, and overflows at 64k. Since this * only occurs at exactly 64k, we use zero as a magic on-disk value to represent * the attr block size. The following helpers manage the conversion between the * in-core and on-disk formats. */ static void xfs_attr3_leaf_firstused_from_disk( struct xfs_da_geometry *geo, struct xfs_attr3_icleaf_hdr *to, struct xfs_attr_leafblock *from) { struct xfs_attr3_leaf_hdr *hdr3; if (from->hdr.info.magic == cpu_to_be16(XFS_ATTR3_LEAF_MAGIC)) { hdr3 = (struct xfs_attr3_leaf_hdr *) from; to->firstused = be16_to_cpu(hdr3->firstused); } else { to->firstused = be16_to_cpu(from->hdr.firstused); } /* * Convert from the magic fsb size value to actual blocksize. This * should only occur for empty blocks when the block size overflows * 16-bits. */ if (to->firstused == XFS_ATTR3_LEAF_NULLOFF) { ASSERT(!to->count && !to->usedbytes); ASSERT(geo->blksize > USHRT_MAX); to->firstused = geo->blksize; } } static void xfs_attr3_leaf_firstused_to_disk( struct xfs_da_geometry *geo, struct xfs_attr_leafblock *to, struct xfs_attr3_icleaf_hdr *from) { struct xfs_attr3_leaf_hdr *hdr3; uint32_t firstused; /* magic value should only be seen on disk */ ASSERT(from->firstused != XFS_ATTR3_LEAF_NULLOFF); /* * Scale down the 32-bit in-core firstused value to the 16-bit on-disk * value. This only overflows at the max supported value of 64k. Use the * magic on-disk value to represent block size in this case. */ firstused = from->firstused; if (firstused > USHRT_MAX) { ASSERT(from->firstused == geo->blksize); firstused = XFS_ATTR3_LEAF_NULLOFF; } if (from->magic == XFS_ATTR3_LEAF_MAGIC) { hdr3 = (struct xfs_attr3_leaf_hdr *) to; hdr3->firstused = cpu_to_be16(firstused); } else { to->hdr.firstused = cpu_to_be16(firstused); } } void xfs_attr3_leaf_hdr_from_disk( struct xfs_da_geometry *geo, struct xfs_attr3_icleaf_hdr *to, struct xfs_attr_leafblock *from) { int i; ASSERT(from->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC) || from->hdr.info.magic == cpu_to_be16(XFS_ATTR3_LEAF_MAGIC)); if (from->hdr.info.magic == cpu_to_be16(XFS_ATTR3_LEAF_MAGIC)) { struct xfs_attr3_leaf_hdr *hdr3 = (struct xfs_attr3_leaf_hdr *)from; to->forw = be32_to_cpu(hdr3->info.hdr.forw); to->back = be32_to_cpu(hdr3->info.hdr.back); to->magic = be16_to_cpu(hdr3->info.hdr.magic); to->count = be16_to_cpu(hdr3->count); to->usedbytes = be16_to_cpu(hdr3->usedbytes); xfs_attr3_leaf_firstused_from_disk(geo, to, from); to->holes = hdr3->holes; for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) { to->freemap[i].base = be16_to_cpu(hdr3->freemap[i].base); to->freemap[i].size = be16_to_cpu(hdr3->freemap[i].size); } return; } to->forw = be32_to_cpu(from->hdr.info.forw); to->back = be32_to_cpu(from->hdr.info.back); to->magic = be16_to_cpu(from->hdr.info.magic); to->count = be16_to_cpu(from->hdr.count); to->usedbytes = be16_to_cpu(from->hdr.usedbytes); xfs_attr3_leaf_firstused_from_disk(geo, to, from); to->holes = from->hdr.holes; for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) { to->freemap[i].base = be16_to_cpu(from->hdr.freemap[i].base); to->freemap[i].size = be16_to_cpu(from->hdr.freemap[i].size); } } void xfs_attr3_leaf_hdr_to_disk( struct xfs_da_geometry *geo, struct xfs_attr_leafblock *to, struct xfs_attr3_icleaf_hdr *from) { int i; ASSERT(from->magic == XFS_ATTR_LEAF_MAGIC || from->magic == XFS_ATTR3_LEAF_MAGIC); if (from->magic == XFS_ATTR3_LEAF_MAGIC) { struct xfs_attr3_leaf_hdr *hdr3 = (struct xfs_attr3_leaf_hdr *)to; hdr3->info.hdr.forw = cpu_to_be32(from->forw); hdr3->info.hdr.back = cpu_to_be32(from->back); hdr3->info.hdr.magic = cpu_to_be16(from->magic); hdr3->count = cpu_to_be16(from->count); hdr3->usedbytes = cpu_to_be16(from->usedbytes); xfs_attr3_leaf_firstused_to_disk(geo, to, from); hdr3->holes = from->holes; hdr3->pad1 = 0; for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) { hdr3->freemap[i].base = cpu_to_be16(from->freemap[i].base); hdr3->freemap[i].size = cpu_to_be16(from->freemap[i].size); } return; } to->hdr.info.forw = cpu_to_be32(from->forw); to->hdr.info.back = cpu_to_be32(from->back); to->hdr.info.magic = cpu_to_be16(from->magic); to->hdr.count = cpu_to_be16(from->count); to->hdr.usedbytes = cpu_to_be16(from->usedbytes); xfs_attr3_leaf_firstused_to_disk(geo, to, from); to->hdr.holes = from->holes; to->hdr.pad1 = 0; for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) { to->hdr.freemap[i].base = cpu_to_be16(from->freemap[i].base); to->hdr.freemap[i].size = cpu_to_be16(from->freemap[i].size); } } static xfs_failaddr_t xfs_attr3_leaf_verify_entry( struct xfs_mount *mp, char *buf_end, struct xfs_attr_leafblock *leaf, struct xfs_attr3_icleaf_hdr *leafhdr, struct xfs_attr_leaf_entry *ent, int idx, __u32 *last_hashval) { struct xfs_attr_leaf_name_local *lentry; struct xfs_attr_leaf_name_remote *rentry; char *name_end; unsigned int nameidx; unsigned int namesize; __u32 hashval; /* hash order check */ hashval = be32_to_cpu(ent->hashval); if (hashval < *last_hashval) return __this_address; *last_hashval = hashval; nameidx = be16_to_cpu(ent->nameidx); if (nameidx < leafhdr->firstused || nameidx >= mp->m_attr_geo->blksize) return __this_address; /* * Check the name information. The namelen fields are u8 so we can't * possibly exceed the maximum name length of 255 bytes. */ if (ent->flags & XFS_ATTR_LOCAL) { lentry = xfs_attr3_leaf_name_local(leaf, idx); namesize = xfs_attr_leaf_entsize_local(lentry->namelen, be16_to_cpu(lentry->valuelen)); name_end = (char *)lentry + namesize; if (lentry->namelen == 0) return __this_address; } else { rentry = xfs_attr3_leaf_name_remote(leaf, idx); namesize = xfs_attr_leaf_entsize_remote(rentry->namelen); name_end = (char *)rentry + namesize; if (rentry->namelen == 0) return __this_address; if (!(ent->flags & XFS_ATTR_INCOMPLETE) && rentry->valueblk == 0) return __this_address; } if (name_end > buf_end) return __this_address; return NULL; } /* * Validate an attribute leaf block. * * Empty leaf blocks can occur under the following circumstances: * * 1. setxattr adds a new extended attribute to a file; * 2. The file has zero existing attributes; * 3. The attribute is too large to fit in the attribute fork; * 4. The attribute is small enough to fit in a leaf block; * 5. A log flush occurs after committing the transaction that creates * the (empty) leaf block; and * 6. The filesystem goes down after the log flush but before the new * attribute can be committed to the leaf block. * * Hence we need to ensure that we don't fail the validation purely * because the leaf is empty. */ static xfs_failaddr_t xfs_attr3_leaf_verify( struct xfs_buf *bp) { struct xfs_attr3_icleaf_hdr ichdr; struct xfs_mount *mp = bp->b_mount; struct xfs_attr_leafblock *leaf = bp->b_addr; struct xfs_attr_leaf_entry *entries; struct xfs_attr_leaf_entry *ent; char *buf_end; uint32_t end; /* must be 32bit - see below */ __u32 last_hashval = 0; int i; xfs_failaddr_t fa; xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, leaf); fa = xfs_da3_blkinfo_verify(bp, bp->b_addr); if (fa) return fa; /* * firstused is the block offset of the first name info structure. * Make sure it doesn't go off the block or crash into the header. */ if (ichdr.firstused > mp->m_attr_geo->blksize) return __this_address; if (ichdr.firstused < xfs_attr3_leaf_hdr_size(leaf)) return __this_address; /* Make sure the entries array doesn't crash into the name info. */ entries = xfs_attr3_leaf_entryp(bp->b_addr); if ((char *)&entries[ichdr.count] > (char *)bp->b_addr + ichdr.firstused) return __this_address; /* * NOTE: This verifier historically failed empty leaf buffers because * we expect the fork to be in another format. Empty attr fork format * conversions are possible during xattr set, however, and format * conversion is not atomic with the xattr set that triggers it. We * cannot assume leaf blocks are non-empty until that is addressed. */ buf_end = (char *)bp->b_addr + mp->m_attr_geo->blksize; for (i = 0, ent = entries; i < ichdr.count; ent++, i++) { fa = xfs_attr3_leaf_verify_entry(mp, buf_end, leaf, &ichdr, ent, i, &last_hashval); if (fa) return fa; } /* * Quickly check the freemap information. Attribute data has to be * aligned to 4-byte boundaries, and likewise for the free space. * * Note that for 64k block size filesystems, the freemap entries cannot * overflow as they are only be16 fields. However, when checking end * pointer of the freemap, we have to be careful to detect overflows and * so use uint32_t for those checks. */ for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) { if (ichdr.freemap[i].base > mp->m_attr_geo->blksize) return __this_address; if (ichdr.freemap[i].base & 0x3) return __this_address; if (ichdr.freemap[i].size > mp->m_attr_geo->blksize) return __this_address; if (ichdr.freemap[i].size & 0x3) return __this_address; /* be care of 16 bit overflows here */ end = (uint32_t)ichdr.freemap[i].base + ichdr.freemap[i].size; if (end < ichdr.freemap[i].base) return __this_address; if (end > mp->m_attr_geo->blksize) return __this_address; } return NULL; } xfs_failaddr_t xfs_attr3_leaf_header_check( struct xfs_buf *bp, xfs_ino_t owner) { struct xfs_mount *mp = bp->b_mount; if (xfs_has_crc(mp)) { struct xfs_attr3_leafblock *hdr3 = bp->b_addr; if (hdr3->hdr.info.hdr.magic != cpu_to_be16(XFS_ATTR3_LEAF_MAGIC)) return __this_address; if (be64_to_cpu(hdr3->hdr.info.owner) != owner) return __this_address; } return NULL; } static void xfs_attr3_leaf_write_verify( struct xfs_buf *bp) { struct xfs_mount *mp = bp->b_mount; struct xfs_buf_log_item *bip = bp->b_log_item; struct xfs_attr3_leaf_hdr *hdr3 = bp->b_addr; xfs_failaddr_t fa; fa = xfs_attr3_leaf_verify(bp); if (fa) { xfs_verifier_error(bp, -EFSCORRUPTED, fa); return; } if (!xfs_has_crc(mp)) return; if (bip) hdr3->info.lsn = cpu_to_be64(bip->bli_item.li_lsn); xfs_buf_update_cksum(bp, XFS_ATTR3_LEAF_CRC_OFF); } /* * leaf/node format detection on trees is sketchy, so a node read can be done on * leaf level blocks when detection identifies the tree as a node format tree * incorrectly. In this case, we need to swap the verifier to match the correct * format of the block being read. */ static void xfs_attr3_leaf_read_verify( struct xfs_buf *bp) { struct xfs_mount *mp = bp->b_mount; xfs_failaddr_t fa; if (xfs_has_crc(mp) && !xfs_buf_verify_cksum(bp, XFS_ATTR3_LEAF_CRC_OFF)) xfs_verifier_error(bp, -EFSBADCRC, __this_address); else { fa = xfs_attr3_leaf_verify(bp); if (fa) xfs_verifier_error(bp, -EFSCORRUPTED, fa); } } const struct xfs_buf_ops xfs_attr3_leaf_buf_ops = { .name = "xfs_attr3_leaf", .magic16 = { cpu_to_be16(XFS_ATTR_LEAF_MAGIC), cpu_to_be16(XFS_ATTR3_LEAF_MAGIC) }, .verify_read = xfs_attr3_leaf_read_verify, .verify_write = xfs_attr3_leaf_write_verify, .verify_struct = xfs_attr3_leaf_verify, }; int xfs_attr3_leaf_read( struct xfs_trans *tp, struct xfs_inode *dp, xfs_ino_t owner, xfs_dablk_t bno, struct xfs_buf **bpp) { xfs_failaddr_t fa; int err; err = xfs_da_read_buf(tp, dp, bno, 0, bpp, XFS_ATTR_FORK, &xfs_attr3_leaf_buf_ops); if (err || !(*bpp)) return err; fa = xfs_attr3_leaf_header_check(*bpp, owner); if (fa) { __xfs_buf_mark_corrupt(*bpp, fa); xfs_trans_brelse(tp, *bpp); *bpp = NULL; xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK); return -EFSCORRUPTED; } if (tp) xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_ATTR_LEAF_BUF); return 0; } /*======================================================================== * Namespace helper routines *========================================================================*/ /* * If we are in log recovery, then we want the lookup to ignore the INCOMPLETE * flag on disk - if there's an incomplete attr then recovery needs to tear it * down. If there's no incomplete attr, then recovery needs to tear that attr * down to replace it with the attr that has been logged. In this case, the * INCOMPLETE flag will not be set in attr->attr_filter, but rather * XFS_DA_OP_RECOVERY will be set in args->op_flags. */ static inline unsigned int xfs_attr_match_mask(const struct xfs_da_args *args) { if (args->op_flags & XFS_DA_OP_RECOVERY) return XFS_ATTR_NSP_ONDISK_MASK; return XFS_ATTR_NSP_ONDISK_MASK | XFS_ATTR_INCOMPLETE; } static inline bool xfs_attr_parent_match( const struct xfs_da_args *args, const void *value, unsigned int valuelen) { ASSERT(args->value != NULL); /* Parent pointers do not use remote values */ if (!value) return false; /* * The only value we support is a parent rec. However, we'll accept * any valuelen so that offline repair can delete ATTR_PARENT values * that are not parent pointers. */ if (valuelen != args->valuelen) return false; return memcmp(args->value, value, valuelen) == 0; } static bool xfs_attr_match( struct xfs_da_args *args, unsigned int attr_flags, const unsigned char *name, unsigned int namelen, const void *value, unsigned int valuelen) { unsigned int mask = xfs_attr_match_mask(args); if (args->namelen != namelen) return false; if ((args->attr_filter & mask) != (attr_flags & mask)) return false; if (memcmp(args->name, name, namelen) != 0) return false; if (attr_flags & XFS_ATTR_PARENT) return xfs_attr_parent_match(args, value, valuelen); return true; } static int xfs_attr_copy_value( struct xfs_da_args *args, unsigned char *value, int valuelen) { /* * Parent pointer lookups require the caller to specify the name and * value, so don't copy anything. */ if (args->attr_filter & XFS_ATTR_PARENT) return 0; /* * No copy if all we have to do is get the length */ if (!args->valuelen) { args->valuelen = valuelen; return 0; } /* * No copy if the length of the existing buffer is too small */ if (args->valuelen < valuelen) { args->valuelen = valuelen; return -ERANGE; } if (!args->value) { args->value = kvmalloc(valuelen, GFP_KERNEL | __GFP_NOLOCKDEP); if (!args->value) return -ENOMEM; } args->valuelen = valuelen; /* remote block xattr requires IO for copy-in */ if (args->rmtblkno) return xfs_attr_rmtval_get(args); /* * This is to prevent a GCC warning because the remote xattr case * doesn't have a value to pass in. In that case, we never reach here, * but GCC can't work that out and so throws a "passing NULL to * memcpy" warning. */ if (!value) return -EINVAL; memcpy(args->value, value, valuelen); return 0; } /*======================================================================== * External routines when attribute fork size < XFS_LITINO(mp). *========================================================================*/ /* * Query whether the total requested number of attr fork bytes of extended * attribute space will be able to fit inline. * * Returns zero if not, else the i_forkoff fork offset to be used in the * literal area for attribute data once the new bytes have been added. * * i_forkoff must be 8 byte aligned, hence is stored as a >>3 value; * special case for dev/uuid inodes, they have fixed size data forks. */ int xfs_attr_shortform_bytesfit( struct xfs_inode *dp, int bytes) { struct xfs_mount *mp = dp->i_mount; int64_t dsize; int minforkoff; int maxforkoff; int offset; /* * Check if the new size could fit at all first: */ if (bytes > XFS_LITINO(mp)) return 0; /* rounded down */ offset = (XFS_LITINO(mp) - bytes) >> 3; if (dp->i_df.if_format == XFS_DINODE_FMT_DEV) { minforkoff = roundup(sizeof(xfs_dev_t), 8) >> 3; return (offset >= minforkoff) ? minforkoff : 0; } /* * If the requested numbers of bytes is smaller or equal to the * current attribute fork size we can always proceed. * * Note that if_bytes in the data fork might actually be larger than * the current data fork size is due to delalloc extents. In that * case either the extent count will go down when they are converted * to real extents, or the delalloc conversion will take care of the * literal area rebalancing. */ if (bytes <= xfs_inode_attr_fork_size(dp)) return dp->i_forkoff; /* * For attr2 we can try to move the forkoff if there is space in the * literal area, but for the old format we are done if there is no * space in the fixed attribute fork. */ if (!xfs_has_attr2(mp)) return 0; dsize = dp->i_df.if_bytes; switch (dp->i_df.if_format) { case XFS_DINODE_FMT_EXTENTS: /* * If there is no attr fork and the data fork is extents, * determine if creating the default attr fork will result * in the extents form migrating to btree. If so, the * minimum offset only needs to be the space required for * the btree root. */ if (!dp->i_forkoff && dp->i_df.if_bytes > xfs_default_attroffset(dp)) dsize = xfs_bmdr_space_calc(MINDBTPTRS); break; case XFS_DINODE_FMT_BTREE: /* * If we have a data btree then keep forkoff if we have one, * otherwise we are adding a new attr, so then we set * minforkoff to where the btree root can finish so we have * plenty of room for attrs */ if (dp->i_forkoff) { if (offset < dp->i_forkoff) return 0; return dp->i_forkoff; } dsize = xfs_bmap_bmdr_space(dp->i_df.if_broot); break; } /* * A data fork btree root must have space for at least * MINDBTPTRS key/ptr pairs if the data fork is small or empty. */ minforkoff = max_t(int64_t, dsize, xfs_bmdr_space_calc(MINDBTPTRS)); minforkoff = roundup(minforkoff, 8) >> 3; /* attr fork btree root can have at least this many key/ptr pairs */ maxforkoff = XFS_LITINO(mp) - xfs_bmdr_space_calc(MINABTPTRS); maxforkoff = maxforkoff >> 3; /* rounded down */ if (offset >= maxforkoff) return maxforkoff; if (offset >= minforkoff) return offset; return 0; } /* * Switch on the ATTR2 superblock bit (implies also FEATURES2) unless: * - noattr2 mount option is set, * - on-disk version bit says it is already set, or * - the attr2 mount option is not set to enable automatic upgrade from attr1. */ STATIC void xfs_sbversion_add_attr2( struct xfs_mount *mp, struct xfs_trans *tp) { if (xfs_has_noattr2(mp)) return; if (mp->m_sb.sb_features2 & XFS_SB_VERSION2_ATTR2BIT) return; if (!xfs_has_attr2(mp)) return; spin_lock(&mp->m_sb_lock); xfs_add_attr2(mp); spin_unlock(&mp->m_sb_lock); xfs_log_sb(tp); } /* * Create the initial contents of a shortform attribute list. */ void xfs_attr_shortform_create( struct xfs_da_args *args) { struct xfs_inode *dp = args->dp; struct xfs_ifork *ifp = &dp->i_af; struct xfs_attr_sf_hdr *hdr; trace_xfs_attr_sf_create(args); ASSERT(ifp->if_bytes == 0); if (ifp->if_format == XFS_DINODE_FMT_EXTENTS) ifp->if_format = XFS_DINODE_FMT_LOCAL; hdr = xfs_idata_realloc(dp, sizeof(*hdr), XFS_ATTR_FORK); memset(hdr, 0, sizeof(*hdr)); hdr->totsize = cpu_to_be16(sizeof(*hdr)); xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_ADATA); } /* * Return the entry if the attr in args is found, or NULL if not. */ struct xfs_attr_sf_entry * xfs_attr_sf_findname( struct xfs_da_args *args) { struct xfs_attr_sf_hdr *sf = args->dp->i_af.if_data; struct xfs_attr_sf_entry *sfe; for (sfe = xfs_attr_sf_firstentry(sf); sfe < xfs_attr_sf_endptr(sf); sfe = xfs_attr_sf_nextentry(sfe)) { if (xfs_attr_match(args, sfe->flags, sfe->nameval, sfe->namelen, &sfe->nameval[sfe->namelen], sfe->valuelen)) return sfe; } return NULL; } /* * Add a name/value pair to the shortform attribute list. * Overflow from the inode has already been checked for. */ void xfs_attr_shortform_add( struct xfs_da_args *args, int forkoff) { struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; struct xfs_ifork *ifp = &dp->i_af; struct xfs_attr_sf_hdr *sf = ifp->if_data; struct xfs_attr_sf_entry *sfe; int size; trace_xfs_attr_sf_add(args); dp->i_forkoff = forkoff; ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL); ASSERT(!xfs_attr_sf_findname(args)); size = xfs_attr_sf_entsize_byname(args->namelen, args->valuelen); sf = xfs_idata_realloc(dp, size, XFS_ATTR_FORK); sfe = xfs_attr_sf_endptr(sf); sfe->namelen = args->namelen; sfe->valuelen = args->valuelen; sfe->flags = args->attr_filter; memcpy(sfe->nameval, args->name, args->namelen); memcpy(&sfe->nameval[args->namelen], args->value, args->valuelen); sf->count++; be16_add_cpu(&sf->totsize, size); xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_ADATA); xfs_sbversion_add_attr2(mp, args->trans); } /* * After the last attribute is removed revert to original inode format, * making all literal area available to the data fork once more. */ void xfs_attr_fork_remove( struct xfs_inode *ip, struct xfs_trans *tp) { ASSERT(ip->i_af.if_nextents == 0); xfs_ifork_zap_attr(ip); ip->i_forkoff = 0; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); } /* * Remove an attribute from the shortform attribute list structure. */ int xfs_attr_sf_removename( struct xfs_da_args *args) { struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; struct xfs_attr_sf_hdr *sf = dp->i_af.if_data; struct xfs_attr_sf_entry *sfe; uint16_t totsize = be16_to_cpu(sf->totsize); void *next, *end; int size = 0; trace_xfs_attr_sf_remove(args); sfe = xfs_attr_sf_findname(args); if (!sfe) { /* * If we are recovering an operation, finding nothing to remove * is not an error, it just means there was nothing to clean up. */ if (args->op_flags & XFS_DA_OP_RECOVERY) return 0; return -ENOATTR; } /* * Fix up the attribute fork data, covering the hole */ size = xfs_attr_sf_entsize(sfe); next = xfs_attr_sf_nextentry(sfe); end = xfs_attr_sf_endptr(sf); if (next < end) memmove(sfe, next, end - next); sf->count--; totsize -= size; sf->totsize = cpu_to_be16(totsize); /* * Fix up the start offset of the attribute fork */ if (totsize == sizeof(struct xfs_attr_sf_hdr) && xfs_has_attr2(mp) && (dp->i_df.if_format != XFS_DINODE_FMT_BTREE) && !(args->op_flags & (XFS_DA_OP_ADDNAME | XFS_DA_OP_REPLACE)) && !xfs_has_parent(mp)) { xfs_attr_fork_remove(dp, args->trans); } else { xfs_idata_realloc(dp, -size, XFS_ATTR_FORK); dp->i_forkoff = xfs_attr_shortform_bytesfit(dp, totsize); ASSERT(dp->i_forkoff); ASSERT(totsize > sizeof(struct xfs_attr_sf_hdr) || (args->op_flags & XFS_DA_OP_ADDNAME) || !xfs_has_attr2(mp) || dp->i_df.if_format == XFS_DINODE_FMT_BTREE || xfs_has_parent(mp)); xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_ADATA); } xfs_sbversion_add_attr2(mp, args->trans); return 0; } /* * Retrieve the attribute value and length. * * If args->valuelen is zero, only the length needs to be returned. Unlike a * lookup, we only return an error if the attribute does not exist or we can't * retrieve the value. */ int xfs_attr_shortform_getvalue( struct xfs_da_args *args) { struct xfs_attr_sf_entry *sfe; ASSERT(args->dp->i_af.if_format == XFS_DINODE_FMT_LOCAL); trace_xfs_attr_sf_lookup(args); sfe = xfs_attr_sf_findname(args); if (!sfe) return -ENOATTR; return xfs_attr_copy_value(args, &sfe->nameval[args->namelen], sfe->valuelen); } /* Convert from using the shortform to the leaf format. */ int xfs_attr_shortform_to_leaf( struct xfs_da_args *args) { struct xfs_inode *dp = args->dp; struct xfs_ifork *ifp = &dp->i_af; struct xfs_attr_sf_hdr *sf = ifp->if_data; struct xfs_attr_sf_entry *sfe; int size = be16_to_cpu(sf->totsize); struct xfs_da_args nargs; char *tmpbuffer; int error, i; xfs_dablk_t blkno; struct xfs_buf *bp; trace_xfs_attr_sf_to_leaf(args); tmpbuffer = kmalloc(size, GFP_KERNEL | __GFP_NOFAIL); memcpy(tmpbuffer, ifp->if_data, size); sf = (struct xfs_attr_sf_hdr *)tmpbuffer; xfs_idata_realloc(dp, -size, XFS_ATTR_FORK); xfs_bmap_local_to_extents_empty(args->trans, dp, XFS_ATTR_FORK); bp = NULL; error = xfs_da_grow_inode(args, &blkno); if (error) goto out; ASSERT(blkno == 0); error = xfs_attr3_leaf_create(args, blkno, &bp); if (error) goto out; memset((char *)&nargs, 0, sizeof(nargs)); nargs.dp = dp; nargs.geo = args->geo; nargs.total = args->total; nargs.whichfork = XFS_ATTR_FORK; nargs.trans = args->trans; nargs.op_flags = XFS_DA_OP_OKNOENT; nargs.owner = args->owner; sfe = xfs_attr_sf_firstentry(sf); for (i = 0; i < sf->count; i++) { nargs.name = sfe->nameval; nargs.namelen = sfe->namelen; nargs.value = &sfe->nameval[nargs.namelen]; nargs.valuelen = sfe->valuelen; nargs.attr_filter = sfe->flags & XFS_ATTR_NSP_ONDISK_MASK; if (!xfs_attr_check_namespace(sfe->flags)) { xfs_da_mark_sick(args); error = -EFSCORRUPTED; goto out; } xfs_attr_sethash(&nargs); error = xfs_attr3_leaf_lookup_int(bp, &nargs); /* set a->index */ ASSERT(error == -ENOATTR); if (!xfs_attr3_leaf_add(bp, &nargs)) ASSERT(0); sfe = xfs_attr_sf_nextentry(sfe); } error = 0; out: kfree(tmpbuffer); return error; } /* * Check a leaf attribute block to see if all the entries would fit into * a shortform attribute list. */ int xfs_attr_shortform_allfit( struct xfs_buf *bp, struct xfs_inode *dp) { struct xfs_attr_leafblock *leaf; struct xfs_attr_leaf_entry *entry; xfs_attr_leaf_name_local_t *name_loc; struct xfs_attr3_icleaf_hdr leafhdr; int bytes; int i; struct xfs_mount *mp = bp->b_mount; leaf = bp->b_addr; xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &leafhdr, leaf); entry = xfs_attr3_leaf_entryp(leaf); bytes = sizeof(struct xfs_attr_sf_hdr); for (i = 0; i < leafhdr.count; entry++, i++) { if (entry->flags & XFS_ATTR_INCOMPLETE) continue; /* don't copy partial entries */ if (!(entry->flags & XFS_ATTR_LOCAL)) return 0; name_loc = xfs_attr3_leaf_name_local(leaf, i); if (name_loc->namelen >= XFS_ATTR_SF_ENTSIZE_MAX) return 0; if (be16_to_cpu(name_loc->valuelen) >= XFS_ATTR_SF_ENTSIZE_MAX) return 0; bytes += xfs_attr_sf_entsize_byname(name_loc->namelen, be16_to_cpu(name_loc->valuelen)); } if (xfs_has_attr2(dp->i_mount) && (dp->i_df.if_format != XFS_DINODE_FMT_BTREE) && (bytes == sizeof(struct xfs_attr_sf_hdr))) return -1; return xfs_attr_shortform_bytesfit(dp, bytes); } /* Verify the consistency of a raw inline attribute fork. */ xfs_failaddr_t xfs_attr_shortform_verify( struct xfs_attr_sf_hdr *sfp, size_t size) { struct xfs_attr_sf_entry *sfep = xfs_attr_sf_firstentry(sfp); struct xfs_attr_sf_entry *next_sfep; char *endp; int i; /* * Give up if the attribute is way too short. */ if (size < sizeof(struct xfs_attr_sf_hdr)) return __this_address; endp = (char *)sfp + size; /* Check all reported entries */ for (i = 0; i < sfp->count; i++) { /* * struct xfs_attr_sf_entry has a variable length. * Check the fixed-offset parts of the structure are * within the data buffer. * xfs_attr_sf_entry is defined with a 1-byte variable * array at the end, so we must subtract that off. */ if (((char *)sfep + sizeof(*sfep)) >= endp) return __this_address; /* Don't allow names with known bad length. */ if (sfep->namelen == 0) return __this_address; /* * Check that the variable-length part of the structure is * within the data buffer. The next entry starts after the * name component, so nextentry is an acceptable test. */ next_sfep = xfs_attr_sf_nextentry(sfep); if ((char *)next_sfep > endp) return __this_address; /* * Check for unknown flags. Short form doesn't support * the incomplete or local bits, so we can use the namespace * mask here. */ if (sfep->flags & ~XFS_ATTR_NSP_ONDISK_MASK) return __this_address; /* * Check for invalid namespace combinations. We only allow * one namespace flag per xattr, so we can just count the * bits (i.e. hweight) here. */ if (!xfs_attr_check_namespace(sfep->flags)) return __this_address; sfep = next_sfep; } if ((void *)sfep != (void *)endp) return __this_address; return NULL; } /* * Convert a leaf attribute list to shortform attribute list */ int xfs_attr3_leaf_to_shortform( struct xfs_buf *bp, struct xfs_da_args *args, int forkoff) { struct xfs_attr_leafblock *leaf; struct xfs_attr3_icleaf_hdr ichdr; struct xfs_attr_leaf_entry *entry; struct xfs_attr_leaf_name_local *name_loc; struct xfs_da_args nargs; struct xfs_inode *dp = args->dp; char *tmpbuffer; int error; int i; trace_xfs_attr_leaf_to_sf(args); tmpbuffer = kvmalloc(args->geo->blksize, GFP_KERNEL | __GFP_NOFAIL); memcpy(tmpbuffer, bp->b_addr, args->geo->blksize); leaf = (xfs_attr_leafblock_t *)tmpbuffer; xfs_attr3_leaf_hdr_from_disk(args->geo, &ichdr, leaf); entry = xfs_attr3_leaf_entryp(leaf); /* XXX (dgc): buffer is about to be marked stale - why zero it? */ memset(bp->b_addr, 0, args->geo->blksize); /* * Clean out the prior contents of the attribute list. */ error = xfs_da_shrink_inode(args, 0, bp); if (error) goto out; if (forkoff == -1) { /* * Don't remove the attr fork if this operation is the first * part of a attr replace operations. We're going to add a new * attr immediately, so we need to keep the attr fork around in * this case. */ if (!(args->op_flags & XFS_DA_OP_REPLACE)) { ASSERT(xfs_has_attr2(dp->i_mount)); ASSERT(dp->i_df.if_format != XFS_DINODE_FMT_BTREE); xfs_attr_fork_remove(dp, args->trans); } goto out; } xfs_attr_shortform_create(args); /* * Copy the attributes */ memset((char *)&nargs, 0, sizeof(nargs)); nargs.geo = args->geo; nargs.dp = dp; nargs.total = args->total; nargs.whichfork = XFS_ATTR_FORK; nargs.trans = args->trans; nargs.op_flags = XFS_DA_OP_OKNOENT; nargs.owner = args->owner; for (i = 0; i < ichdr.count; entry++, i++) { if (entry->flags & XFS_ATTR_INCOMPLETE) continue; /* don't copy partial entries */ if (!entry->nameidx) continue; ASSERT(entry->flags & XFS_ATTR_LOCAL); name_loc = xfs_attr3_leaf_name_local(leaf, i); nargs.name = name_loc->nameval; nargs.namelen = name_loc->namelen; nargs.value = &name_loc->nameval[nargs.namelen]; nargs.valuelen = be16_to_cpu(name_loc->valuelen); nargs.hashval = be32_to_cpu(entry->hashval); nargs.attr_filter = entry->flags & XFS_ATTR_NSP_ONDISK_MASK; xfs_attr_shortform_add(&nargs, forkoff); } error = 0; out: kvfree(tmpbuffer); return error; } /* * Convert from using a single leaf to a root node and a leaf. */ int xfs_attr3_leaf_to_node( struct xfs_da_args *args) { struct xfs_attr_leafblock *leaf; struct xfs_attr3_icleaf_hdr icleafhdr; struct xfs_attr_leaf_entry *entries; struct xfs_da3_icnode_hdr icnodehdr; struct xfs_da_intnode *node; struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; struct xfs_buf *bp1 = NULL; struct xfs_buf *bp2 = NULL; xfs_dablk_t blkno; int error; trace_xfs_attr_leaf_to_node(args); if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_ATTR_LEAF_TO_NODE)) { error = -EIO; goto out; } error = xfs_da_grow_inode(args, &blkno); if (error) goto out; error = xfs_attr3_leaf_read(args->trans, dp, args->owner, 0, &bp1); if (error) goto out; error = xfs_da_get_buf(args->trans, dp, blkno, &bp2, XFS_ATTR_FORK); if (error) goto out; /* * Copy leaf to new buffer and log it. */ xfs_da_buf_copy(bp2, bp1, args->geo->blksize); xfs_trans_log_buf(args->trans, bp2, 0, args->geo->blksize - 1); /* * Set up the new root node. */ error = xfs_da3_node_create(args, 0, 1, &bp1, XFS_ATTR_FORK); if (error) goto out; node = bp1->b_addr; xfs_da3_node_hdr_from_disk(mp, &icnodehdr, node); leaf = bp2->b_addr; xfs_attr3_leaf_hdr_from_disk(args->geo, &icleafhdr, leaf); entries = xfs_attr3_leaf_entryp(leaf); /* both on-disk, don't endian-flip twice */ icnodehdr.btree[0].hashval = entries[icleafhdr.count - 1].hashval; icnodehdr.btree[0].before = cpu_to_be32(blkno); icnodehdr.count = 1; xfs_da3_node_hdr_to_disk(dp->i_mount, node, &icnodehdr); xfs_trans_log_buf(args->trans, bp1, 0, args->geo->blksize - 1); error = 0; out: return error; } /*======================================================================== * Routines used for growing the Btree. *========================================================================*/ /* * Create the initial contents of a leaf attribute list * or a leaf in a node attribute list. */ STATIC int xfs_attr3_leaf_create( struct xfs_da_args *args, xfs_dablk_t blkno, struct xfs_buf **bpp) { struct xfs_attr_leafblock *leaf; struct xfs_attr3_icleaf_hdr ichdr; struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; struct xfs_buf *bp; int error; trace_xfs_attr_leaf_create(args); error = xfs_da_get_buf(args->trans, args->dp, blkno, &bp, XFS_ATTR_FORK); if (error) return error; bp->b_ops = &xfs_attr3_leaf_buf_ops; xfs_trans_buf_set_type(args->trans, bp, XFS_BLFT_ATTR_LEAF_BUF); leaf = bp->b_addr; memset(leaf, 0, args->geo->blksize); memset(&ichdr, 0, sizeof(ichdr)); ichdr.firstused = args->geo->blksize; if (xfs_has_crc(mp)) { struct xfs_da3_blkinfo *hdr3 = bp->b_addr; ichdr.magic = XFS_ATTR3_LEAF_MAGIC; hdr3->blkno = cpu_to_be64(xfs_buf_daddr(bp)); hdr3->owner = cpu_to_be64(args->owner); uuid_copy(&hdr3->uuid, &mp->m_sb.sb_meta_uuid); ichdr.freemap[0].base = sizeof(struct xfs_attr3_leaf_hdr); } else { ichdr.magic = XFS_ATTR_LEAF_MAGIC; ichdr.freemap[0].base = sizeof(struct xfs_attr_leaf_hdr); } ichdr.freemap[0].size = ichdr.firstused - ichdr.freemap[0].base; xfs_attr3_leaf_hdr_to_disk(args->geo, leaf, &ichdr); xfs_trans_log_buf(args->trans, bp, 0, args->geo->blksize - 1); *bpp = bp; return 0; } /* * Split the leaf node, rebalance, then add the new entry. * * Returns 0 if the entry was added, 1 if a further split is needed or a * negative error number otherwise. */ int xfs_attr3_leaf_split( struct xfs_da_state *state, struct xfs_da_state_blk *oldblk, struct xfs_da_state_blk *newblk) { bool added; xfs_dablk_t blkno; int error; trace_xfs_attr_leaf_split(state->args); /* * Allocate space for a new leaf node. */ ASSERT(oldblk->magic == XFS_ATTR_LEAF_MAGIC); error = xfs_da_grow_inode(state->args, &blkno); if (error) return error; error = xfs_attr3_leaf_create(state->args, blkno, &newblk->bp); if (error) return error; newblk->blkno = blkno; newblk->magic = XFS_ATTR_LEAF_MAGIC; /* * Rebalance the entries across the two leaves. * NOTE: rebalance() currently depends on the 2nd block being empty. */ xfs_attr3_leaf_rebalance(state, oldblk, newblk); error = xfs_da3_blk_link(state, oldblk, newblk); if (error) return error; /* * Save info on "old" attribute for "atomic rename" ops, leaf_add() * modifies the index/blkno/rmtblk/rmtblkcnt fields to show the * "new" attrs info. Will need the "old" info to remove it later. * * Insert the "new" entry in the correct block. */ if (state->inleaf) { trace_xfs_attr_leaf_add_old(state->args); added = xfs_attr3_leaf_add(oldblk->bp, state->args); } else { trace_xfs_attr_leaf_add_new(state->args); added = xfs_attr3_leaf_add(newblk->bp, state->args); } /* * Update last hashval in each block since we added the name. */ oldblk->hashval = xfs_attr_leaf_lasthash(oldblk->bp, NULL); newblk->hashval = xfs_attr_leaf_lasthash(newblk->bp, NULL); if (!added) return 1; return 0; } /* * Add a name to the leaf attribute list structure. */ bool xfs_attr3_leaf_add( struct xfs_buf *bp, struct xfs_da_args *args) { struct xfs_attr_leafblock *leaf; struct xfs_attr3_icleaf_hdr ichdr; int tablesize; int entsize; bool added = true; int sum; int tmp; int i; trace_xfs_attr_leaf_add(args); leaf = bp->b_addr; xfs_attr3_leaf_hdr_from_disk(args->geo, &ichdr, leaf); ASSERT(args->index >= 0 && args->index <= ichdr.count); entsize = xfs_attr_leaf_newentsize(args, NULL); /* * Search through freemap for first-fit on new name length. * (may need to figure in size of entry struct too) */ tablesize = (ichdr.count + 1) * sizeof(xfs_attr_leaf_entry_t) + xfs_attr3_leaf_hdr_size(leaf); for (sum = 0, i = XFS_ATTR_LEAF_MAPSIZE - 1; i >= 0; i--) { if (tablesize > ichdr.firstused) { sum += ichdr.freemap[i].size; continue; } if (!ichdr.freemap[i].size) continue; /* no space in this map */ tmp = entsize; if (ichdr.freemap[i].base < ichdr.firstused) tmp += sizeof(xfs_attr_leaf_entry_t); if (ichdr.freemap[i].size >= tmp) { xfs_attr3_leaf_add_work(bp, &ichdr, args, i); goto out_log_hdr; } sum += ichdr.freemap[i].size; } /* * If there are no holes in the address space of the block, * and we don't have enough freespace, then compaction will do us * no good and we should just give up. */ if (!ichdr.holes && sum < entsize) return false; /* * Compact the entries to coalesce free space. * This may change the hdr->count via dropping INCOMPLETE entries. */ xfs_attr3_leaf_compact(args, &ichdr, bp); /* * After compaction, the block is guaranteed to have only one * free region, in freemap[0]. If it is not big enough, give up. */ if (ichdr.freemap[0].size < (entsize + sizeof(xfs_attr_leaf_entry_t))) { added = false; goto out_log_hdr; } xfs_attr3_leaf_add_work(bp, &ichdr, args, 0); out_log_hdr: xfs_attr3_leaf_hdr_to_disk(args->geo, leaf, &ichdr); xfs_trans_log_buf(args->trans, bp, XFS_DA_LOGRANGE(leaf, &leaf->hdr, xfs_attr3_leaf_hdr_size(leaf))); return added; } /* * Add a name to a leaf attribute list structure. */ STATIC void xfs_attr3_leaf_add_work( struct xfs_buf *bp, struct xfs_attr3_icleaf_hdr *ichdr, struct xfs_da_args *args, int mapindex) { struct xfs_attr_leafblock *leaf; struct xfs_attr_leaf_entry *entry; struct xfs_attr_leaf_name_local *name_loc; struct xfs_attr_leaf_name_remote *name_rmt; struct xfs_mount *mp; int tmp; int i; trace_xfs_attr_leaf_add_work(args); leaf = bp->b_addr; ASSERT(mapindex >= 0 && mapindex < XFS_ATTR_LEAF_MAPSIZE); ASSERT(args->index >= 0 && args->index <= ichdr->count); /* * Force open some space in the entry array and fill it in. */ entry = &xfs_attr3_leaf_entryp(leaf)[args->index]; if (args->index < ichdr->count) { tmp = ichdr->count - args->index; tmp *= sizeof(xfs_attr_leaf_entry_t); memmove(entry + 1, entry, tmp); xfs_trans_log_buf(args->trans, bp, XFS_DA_LOGRANGE(leaf, entry, tmp + sizeof(*entry))); } ichdr->count++; /* * Allocate space for the new string (at the end of the run). */ mp = args->trans->t_mountp; ASSERT(ichdr->freemap[mapindex].base < args->geo->blksize); ASSERT((ichdr->freemap[mapindex].base & 0x3) == 0); ASSERT(ichdr->freemap[mapindex].size >= xfs_attr_leaf_newentsize(args, NULL)); ASSERT(ichdr->freemap[mapindex].size < args->geo->blksize); ASSERT((ichdr->freemap[mapindex].size & 0x3) == 0); ichdr->freemap[mapindex].size -= xfs_attr_leaf_newentsize(args, &tmp); entry->nameidx = cpu_to_be16(ichdr->freemap[mapindex].base + ichdr->freemap[mapindex].size); entry->hashval = cpu_to_be32(args->hashval); entry->flags = args->attr_filter; if (tmp) entry->flags |= XFS_ATTR_LOCAL; if (args->op_flags & XFS_DA_OP_REPLACE) { if (!(args->op_flags & XFS_DA_OP_LOGGED)) entry->flags |= XFS_ATTR_INCOMPLETE; if ((args->blkno2 == args->blkno) && (args->index2 <= args->index)) { args->index2++; } } xfs_trans_log_buf(args->trans, bp, XFS_DA_LOGRANGE(leaf, entry, sizeof(*entry))); ASSERT((args->index == 0) || (be32_to_cpu(entry->hashval) >= be32_to_cpu((entry-1)->hashval))); ASSERT((args->index == ichdr->count - 1) || (be32_to_cpu(entry->hashval) <= be32_to_cpu((entry+1)->hashval))); /* * For "remote" attribute values, simply note that we need to * allocate space for the "remote" value. We can't actually * allocate the extents in this transaction, and we can't decide * which blocks they should be as we might allocate more blocks * as part of this transaction (a split operation for example). */ if (entry->flags & XFS_ATTR_LOCAL) { name_loc = xfs_attr3_leaf_name_local(leaf, args->index); name_loc->namelen = args->namelen; name_loc->valuelen = cpu_to_be16(args->valuelen); memcpy((char *)name_loc->nameval, args->name, args->namelen); memcpy((char *)&name_loc->nameval[args->namelen], args->value, be16_to_cpu(name_loc->valuelen)); } else { name_rmt = xfs_attr3_leaf_name_remote(leaf, args->index); name_rmt->namelen = args->namelen; memcpy((char *)name_rmt->name, args->name, args->namelen); entry->flags |= XFS_ATTR_INCOMPLETE; /* just in case */ name_rmt->valuelen = 0; name_rmt->valueblk = 0; args->rmtblkno = 1; args->rmtblkcnt = xfs_attr3_rmt_blocks(mp, args->valuelen); args->rmtvaluelen = args->valuelen; } xfs_trans_log_buf(args->trans, bp, XFS_DA_LOGRANGE(leaf, xfs_attr3_leaf_name(leaf, args->index), xfs_attr_leaf_entsize(leaf, args->index))); /* * Update the control info for this leaf node */ if (be16_to_cpu(entry->nameidx) < ichdr->firstused) ichdr->firstused = be16_to_cpu(entry->nameidx); ASSERT(ichdr->firstused >= ichdr->count * sizeof(xfs_attr_leaf_entry_t) + xfs_attr3_leaf_hdr_size(leaf)); tmp = (ichdr->count - 1) * sizeof(xfs_attr_leaf_entry_t) + xfs_attr3_leaf_hdr_size(leaf); for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) { if (ichdr->freemap[i].base == tmp) { ichdr->freemap[i].base += sizeof(xfs_attr_leaf_entry_t); ichdr->freemap[i].size -= min_t(uint16_t, ichdr->freemap[i].size, sizeof(xfs_attr_leaf_entry_t)); } } ichdr->usedbytes += xfs_attr_leaf_entsize(leaf, args->index); } /* * Garbage collect a leaf attribute list block by copying it to a new buffer. */ STATIC void xfs_attr3_leaf_compact( struct xfs_da_args *args, struct xfs_attr3_icleaf_hdr *ichdr_dst, struct xfs_buf *bp) { struct xfs_attr_leafblock *leaf_src; struct xfs_attr_leafblock *leaf_dst; struct xfs_attr3_icleaf_hdr ichdr_src; struct xfs_trans *trans = args->trans; char *tmpbuffer; trace_xfs_attr_leaf_compact(args); tmpbuffer = kvmalloc(args->geo->blksize, GFP_KERNEL | __GFP_NOFAIL); memcpy(tmpbuffer, bp->b_addr, args->geo->blksize); memset(bp->b_addr, 0, args->geo->blksize); leaf_src = (xfs_attr_leafblock_t *)tmpbuffer; leaf_dst = bp->b_addr; /* * Copy the on-disk header back into the destination buffer to ensure * all the information in the header that is not part of the incore * header structure is preserved. */ memcpy(bp->b_addr, tmpbuffer, xfs_attr3_leaf_hdr_size(leaf_src)); /* Initialise the incore headers */ ichdr_src = *ichdr_dst; /* struct copy */ ichdr_dst->firstused = args->geo->blksize; ichdr_dst->usedbytes = 0; ichdr_dst->count = 0; ichdr_dst->holes = 0; ichdr_dst->freemap[0].base = xfs_attr3_leaf_hdr_size(leaf_src); ichdr_dst->freemap[0].size = ichdr_dst->firstused - ichdr_dst->freemap[0].base; /* write the header back to initialise the underlying buffer */ xfs_attr3_leaf_hdr_to_disk(args->geo, leaf_dst, ichdr_dst); /* * Copy all entry's in the same (sorted) order, * but allocate name/value pairs packed and in sequence. */ xfs_attr3_leaf_moveents(args, leaf_src, &ichdr_src, 0, leaf_dst, ichdr_dst, 0, ichdr_src.count); /* * this logs the entire buffer, but the caller must write the header * back to the buffer when it is finished modifying it. */ xfs_trans_log_buf(trans, bp, 0, args->geo->blksize - 1); kvfree(tmpbuffer); } /* * Compare two leaf blocks "order". * Return 0 unless leaf2 should go before leaf1. */ static int xfs_attr3_leaf_order( struct xfs_buf *leaf1_bp, struct xfs_attr3_icleaf_hdr *leaf1hdr, struct xfs_buf *leaf2_bp, struct xfs_attr3_icleaf_hdr *leaf2hdr) { struct xfs_attr_leaf_entry *entries1; struct xfs_attr_leaf_entry *entries2; entries1 = xfs_attr3_leaf_entryp(leaf1_bp->b_addr); entries2 = xfs_attr3_leaf_entryp(leaf2_bp->b_addr); if (leaf1hdr->count > 0 && leaf2hdr->count > 0 && ((be32_to_cpu(entries2[0].hashval) < be32_to_cpu(entries1[0].hashval)) || (be32_to_cpu(entries2[leaf2hdr->count - 1].hashval) < be32_to_cpu(entries1[leaf1hdr->count - 1].hashval)))) { return 1; } return 0; } int xfs_attr_leaf_order( struct xfs_buf *leaf1_bp, struct xfs_buf *leaf2_bp) { struct xfs_attr3_icleaf_hdr ichdr1; struct xfs_attr3_icleaf_hdr ichdr2; struct xfs_mount *mp = leaf1_bp->b_mount; xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr1, leaf1_bp->b_addr); xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr2, leaf2_bp->b_addr); return xfs_attr3_leaf_order(leaf1_bp, &ichdr1, leaf2_bp, &ichdr2); } /* * Redistribute the attribute list entries between two leaf nodes, * taking into account the size of the new entry. * * NOTE: if new block is empty, then it will get the upper half of the * old block. At present, all (one) callers pass in an empty second block. * * This code adjusts the args->index/blkno and args->index2/blkno2 fields * to match what it is doing in splitting the attribute leaf block. Those * values are used in "atomic rename" operations on attributes. Note that * the "new" and "old" values can end up in different blocks. */ STATIC void xfs_attr3_leaf_rebalance( struct xfs_da_state *state, struct xfs_da_state_blk *blk1, struct xfs_da_state_blk *blk2) { struct xfs_da_args *args; struct xfs_attr_leafblock *leaf1; struct xfs_attr_leafblock *leaf2; struct xfs_attr3_icleaf_hdr ichdr1; struct xfs_attr3_icleaf_hdr ichdr2; struct xfs_attr_leaf_entry *entries1; struct xfs_attr_leaf_entry *entries2; int count; int totallen; int max; int space; int swap; /* * Set up environment. */ ASSERT(blk1->magic == XFS_ATTR_LEAF_MAGIC); ASSERT(blk2->magic == XFS_ATTR_LEAF_MAGIC); leaf1 = blk1->bp->b_addr; leaf2 = blk2->bp->b_addr; xfs_attr3_leaf_hdr_from_disk(state->args->geo, &ichdr1, leaf1); xfs_attr3_leaf_hdr_from_disk(state->args->geo, &ichdr2, leaf2); ASSERT(ichdr2.count == 0); args = state->args; trace_xfs_attr_leaf_rebalance(args); /* * Check ordering of blocks, reverse if it makes things simpler. * * NOTE: Given that all (current) callers pass in an empty * second block, this code should never set "swap". */ swap = 0; if (xfs_attr3_leaf_order(blk1->bp, &ichdr1, blk2->bp, &ichdr2)) { swap(blk1, blk2); /* swap structures rather than reconverting them */ swap(ichdr1, ichdr2); leaf1 = blk1->bp->b_addr; leaf2 = blk2->bp->b_addr; swap = 1; } /* * Examine entries until we reduce the absolute difference in * byte usage between the two blocks to a minimum. Then get * the direction to copy and the number of elements to move. * * "inleaf" is true if the new entry should be inserted into blk1. * If "swap" is also true, then reverse the sense of "inleaf". */ state->inleaf = xfs_attr3_leaf_figure_balance(state, blk1, &ichdr1, blk2, &ichdr2, &count, &totallen); if (swap) state->inleaf = !state->inleaf; /* * Move any entries required from leaf to leaf: */ if (count < ichdr1.count) { /* * Figure the total bytes to be added to the destination leaf. */ /* number entries being moved */ count = ichdr1.count - count; space = ichdr1.usedbytes - totallen; space += count * sizeof(xfs_attr_leaf_entry_t); /* * leaf2 is the destination, compact it if it looks tight. */ max = ichdr2.firstused - xfs_attr3_leaf_hdr_size(leaf1); max -= ichdr2.count * sizeof(xfs_attr_leaf_entry_t); if (space > max) xfs_attr3_leaf_compact(args, &ichdr2, blk2->bp); /* * Move high entries from leaf1 to low end of leaf2. */ xfs_attr3_leaf_moveents(args, leaf1, &ichdr1, ichdr1.count - count, leaf2, &ichdr2, 0, count); } else if (count > ichdr1.count) { /* * I assert that since all callers pass in an empty * second buffer, this code should never execute. */ ASSERT(0); /* * Figure the total bytes to be added to the destination leaf. */ /* number entries being moved */ count -= ichdr1.count; space = totallen - ichdr1.usedbytes; space += count * sizeof(xfs_attr_leaf_entry_t); /* * leaf1 is the destination, compact it if it looks tight. */ max = ichdr1.firstused - xfs_attr3_leaf_hdr_size(leaf1); max -= ichdr1.count * sizeof(xfs_attr_leaf_entry_t); if (space > max) xfs_attr3_leaf_compact(args, &ichdr1, blk1->bp); /* * Move low entries from leaf2 to high end of leaf1. */ xfs_attr3_leaf_moveents(args, leaf2, &ichdr2, 0, leaf1, &ichdr1, ichdr1.count, count); } xfs_attr3_leaf_hdr_to_disk(state->args->geo, leaf1, &ichdr1); xfs_attr3_leaf_hdr_to_disk(state->args->geo, leaf2, &ichdr2); xfs_trans_log_buf(args->trans, blk1->bp, 0, args->geo->blksize - 1); xfs_trans_log_buf(args->trans, blk2->bp, 0, args->geo->blksize - 1); /* * Copy out last hashval in each block for B-tree code. */ entries1 = xfs_attr3_leaf_entryp(leaf1); entries2 = xfs_attr3_leaf_entryp(leaf2); blk1->hashval = be32_to_cpu(entries1[ichdr1.count - 1].hashval); blk2->hashval = be32_to_cpu(entries2[ichdr2.count - 1].hashval); /* * Adjust the expected index for insertion. * NOTE: this code depends on the (current) situation that the * second block was originally empty. * * If the insertion point moved to the 2nd block, we must adjust * the index. We must also track the entry just following the * new entry for use in an "atomic rename" operation, that entry * is always the "old" entry and the "new" entry is what we are * inserting. The index/blkno fields refer to the "old" entry, * while the index2/blkno2 fields refer to the "new" entry. */ if (blk1->index > ichdr1.count) { ASSERT(state->inleaf == 0); blk2->index = blk1->index - ichdr1.count; args->index = args->index2 = blk2->index; args->blkno = args->blkno2 = blk2->blkno; } else if (blk1->index == ichdr1.count) { if (state->inleaf) { args->index = blk1->index; args->blkno = blk1->blkno; args->index2 = 0; args->blkno2 = blk2->blkno; } else { /* * On a double leaf split, the original attr location * is already stored in blkno2/index2, so don't * overwrite it overwise we corrupt the tree. */ blk2->index = blk1->index - ichdr1.count; args->index = blk2->index; args->blkno = blk2->blkno; if (!state->extravalid) { /* * set the new attr location to match the old * one and let the higher level split code * decide where in the leaf to place it. */ args->index2 = blk2->index; args->blkno2 = blk2->blkno; } } } else { ASSERT(state->inleaf == 1); args->index = args->index2 = blk1->index; args->blkno = args->blkno2 = blk1->blkno; } } /* * Examine entries until we reduce the absolute difference in * byte usage between the two blocks to a minimum. * GROT: Is this really necessary? With other than a 512 byte blocksize, * GROT: there will always be enough room in either block for a new entry. * GROT: Do a double-split for this case? */ STATIC int xfs_attr3_leaf_figure_balance( struct xfs_da_state *state, struct xfs_da_state_blk *blk1, struct xfs_attr3_icleaf_hdr *ichdr1, struct xfs_da_state_blk *blk2, struct xfs_attr3_icleaf_hdr *ichdr2, int *countarg, int *usedbytesarg) { struct xfs_attr_leafblock *leaf1 = blk1->bp->b_addr; struct xfs_attr_leafblock *leaf2 = blk2->bp->b_addr; struct xfs_attr_leaf_entry *entry; int count; int max; int index; int totallen = 0; int half; int lastdelta; int foundit = 0; int tmp; /* * Examine entries until we reduce the absolute difference in * byte usage between the two blocks to a minimum. */ max = ichdr1->count + ichdr2->count; half = (max + 1) * sizeof(*entry); half += ichdr1->usedbytes + ichdr2->usedbytes + xfs_attr_leaf_newentsize(state->args, NULL); half /= 2; lastdelta = state->args->geo->blksize; entry = xfs_attr3_leaf_entryp(leaf1); for (count = index = 0; count < max; entry++, index++, count++) { #define XFS_ATTR_ABS(A) (((A) < 0) ? -(A) : (A)) /* * The new entry is in the first block, account for it. */ if (count == blk1->index) { tmp = totallen + sizeof(*entry) + xfs_attr_leaf_newentsize(state->args, NULL); if (XFS_ATTR_ABS(half - tmp) > lastdelta) break; lastdelta = XFS_ATTR_ABS(half - tmp); totallen = tmp; foundit = 1; } /* * Wrap around into the second block if necessary. */ if (count == ichdr1->count) { leaf1 = leaf2; entry = xfs_attr3_leaf_entryp(leaf1); index = 0; } /* * Figure out if next leaf entry would be too much. */ tmp = totallen + sizeof(*entry) + xfs_attr_leaf_entsize(leaf1, index); if (XFS_ATTR_ABS(half - tmp) > lastdelta) break; lastdelta = XFS_ATTR_ABS(half - tmp); totallen = tmp; #undef XFS_ATTR_ABS } /* * Calculate the number of usedbytes that will end up in lower block. * If new entry not in lower block, fix up the count. */ totallen -= count * sizeof(*entry); if (foundit) { totallen -= sizeof(*entry) + xfs_attr_leaf_newentsize(state->args, NULL); } *countarg = count; *usedbytesarg = totallen; return foundit; } /*======================================================================== * Routines used for shrinking the Btree. *========================================================================*/ /* * Check a leaf block and its neighbors to see if the block should be * collapsed into one or the other neighbor. Always keep the block * with the smaller block number. * If the current block is over 50% full, don't try to join it, return 0. * If the block is empty, fill in the state structure and return 2. * If it can be collapsed, fill in the state structure and return 1. * If nothing can be done, return 0. * * GROT: allow for INCOMPLETE entries in calculation. */ int xfs_attr3_leaf_toosmall( struct xfs_da_state *state, int *action) { struct xfs_attr_leafblock *leaf; struct xfs_da_state_blk *blk; struct xfs_attr3_icleaf_hdr ichdr; struct xfs_buf *bp; xfs_dablk_t blkno; int bytes; int forward; int error; int retval; int i; trace_xfs_attr_leaf_toosmall(state->args); /* * Check for the degenerate case of the block being over 50% full. * If so, it's not worth even looking to see if we might be able * to coalesce with a sibling. */ blk = &state->path.blk[ state->path.active-1 ]; leaf = blk->bp->b_addr; xfs_attr3_leaf_hdr_from_disk(state->args->geo, &ichdr, leaf); bytes = xfs_attr3_leaf_hdr_size(leaf) + ichdr.count * sizeof(xfs_attr_leaf_entry_t) + ichdr.usedbytes; if (bytes > (state->args->geo->blksize >> 1)) { *action = 0; /* blk over 50%, don't try to join */ return 0; } /* * Check for the degenerate case of the block being empty. * If the block is empty, we'll simply delete it, no need to * coalesce it with a sibling block. We choose (arbitrarily) * to merge with the forward block unless it is NULL. */ if (ichdr.count == 0) { /* * Make altpath point to the block we want to keep and * path point to the block we want to drop (this one). */ forward = (ichdr.forw != 0); memcpy(&state->altpath, &state->path, sizeof(state->path)); error = xfs_da3_path_shift(state, &state->altpath, forward, 0, &retval); if (error) return error; if (retval) { *action = 0; } else { *action = 2; } return 0; } /* * Examine each sibling block to see if we can coalesce with * at least 25% free space to spare. We need to figure out * whether to merge with the forward or the backward block. * We prefer coalescing with the lower numbered sibling so as * to shrink an attribute list over time. */ /* start with smaller blk num */ forward = ichdr.forw < ichdr.back; for (i = 0; i < 2; forward = !forward, i++) { struct xfs_attr3_icleaf_hdr ichdr2; if (forward) blkno = ichdr.forw; else blkno = ichdr.back; if (blkno == 0) continue; error = xfs_attr3_leaf_read(state->args->trans, state->args->dp, state->args->owner, blkno, &bp); if (error) return error; xfs_attr3_leaf_hdr_from_disk(state->args->geo, &ichdr2, bp->b_addr); bytes = state->args->geo->blksize - (state->args->geo->blksize >> 2) - ichdr.usedbytes - ichdr2.usedbytes - ((ichdr.count + ichdr2.count) * sizeof(xfs_attr_leaf_entry_t)) - xfs_attr3_leaf_hdr_size(leaf); xfs_trans_brelse(state->args->trans, bp); if (bytes >= 0) break; /* fits with at least 25% to spare */ } if (i >= 2) { *action = 0; return 0; } /* * Make altpath point to the block we want to keep (the lower * numbered block) and path point to the block we want to drop. */ memcpy(&state->altpath, &state->path, sizeof(state->path)); if (blkno < blk->blkno) { error = xfs_da3_path_shift(state, &state->altpath, forward, 0, &retval); } else { error = xfs_da3_path_shift(state, &state->path, forward, 0, &retval); } if (error) return error; if (retval) { *action = 0; } else { *action = 1; } return 0; } /* * Remove a name from the leaf attribute list structure. * * Return 1 if leaf is less than 37% full, 0 if >= 37% full. * If two leaves are 37% full, when combined they will leave 25% free. */ int xfs_attr3_leaf_remove( struct xfs_buf *bp, struct xfs_da_args *args) { struct xfs_attr_leafblock *leaf; struct xfs_attr3_icleaf_hdr ichdr; struct xfs_attr_leaf_entry *entry; int before; int after; int smallest; int entsize; int tablesize; int tmp; int i; trace_xfs_attr_leaf_remove(args); leaf = bp->b_addr; xfs_attr3_leaf_hdr_from_disk(args->geo, &ichdr, leaf); ASSERT(ichdr.count > 0 && ichdr.count < args->geo->blksize / 8); ASSERT(args->index >= 0 && args->index < ichdr.count); ASSERT(ichdr.firstused >= ichdr.count * sizeof(*entry) + xfs_attr3_leaf_hdr_size(leaf)); entry = &xfs_attr3_leaf_entryp(leaf)[args->index]; ASSERT(be16_to_cpu(entry->nameidx) >= ichdr.firstused); ASSERT(be16_to_cpu(entry->nameidx) < args->geo->blksize); /* * Scan through free region table: * check for adjacency of free'd entry with an existing one, * find smallest free region in case we need to replace it, * adjust any map that borders the entry table, */ tablesize = ichdr.count * sizeof(xfs_attr_leaf_entry_t) + xfs_attr3_leaf_hdr_size(leaf); tmp = ichdr.freemap[0].size; before = after = -1; smallest = XFS_ATTR_LEAF_MAPSIZE - 1; entsize = xfs_attr_leaf_entsize(leaf, args->index); for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) { ASSERT(ichdr.freemap[i].base < args->geo->blksize); ASSERT(ichdr.freemap[i].size < args->geo->blksize); if (ichdr.freemap[i].base == tablesize) { ichdr.freemap[i].base -= sizeof(xfs_attr_leaf_entry_t); ichdr.freemap[i].size += sizeof(xfs_attr_leaf_entry_t); } if (ichdr.freemap[i].base + ichdr.freemap[i].size == be16_to_cpu(entry->nameidx)) { before = i; } else if (ichdr.freemap[i].base == (be16_to_cpu(entry->nameidx) + entsize)) { after = i; } else if (ichdr.freemap[i].size < tmp) { tmp = ichdr.freemap[i].size; smallest = i; } } /* * Coalesce adjacent freemap regions, * or replace the smallest region. */ if ((before >= 0) || (after >= 0)) { if ((before >= 0) && (after >= 0)) { ichdr.freemap[before].size += entsize; ichdr.freemap[before].size += ichdr.freemap[after].size; ichdr.freemap[after].base = 0; ichdr.freemap[after].size = 0; } else if (before >= 0) { ichdr.freemap[before].size += entsize; } else { ichdr.freemap[after].base = be16_to_cpu(entry->nameidx); ichdr.freemap[after].size += entsize; } } else { /* * Replace smallest region (if it is smaller than free'd entry) */ if (ichdr.freemap[smallest].size < entsize) { ichdr.freemap[smallest].base = be16_to_cpu(entry->nameidx); ichdr.freemap[smallest].size = entsize; } } /* * Did we remove the first entry? */ if (be16_to_cpu(entry->nameidx) == ichdr.firstused) smallest = 1; else smallest = 0; /* * Compress the remaining entries and zero out the removed stuff. */ memset(xfs_attr3_leaf_name(leaf, args->index), 0, entsize); ichdr.usedbytes -= entsize; xfs_trans_log_buf(args->trans, bp, XFS_DA_LOGRANGE(leaf, xfs_attr3_leaf_name(leaf, args->index), entsize)); tmp = (ichdr.count - args->index) * sizeof(xfs_attr_leaf_entry_t); memmove(entry, entry + 1, tmp); ichdr.count--; xfs_trans_log_buf(args->trans, bp, XFS_DA_LOGRANGE(leaf, entry, tmp + sizeof(xfs_attr_leaf_entry_t))); entry = &xfs_attr3_leaf_entryp(leaf)[ichdr.count]; memset(entry, 0, sizeof(xfs_attr_leaf_entry_t)); /* * If we removed the first entry, re-find the first used byte * in the name area. Note that if the entry was the "firstused", * then we don't have a "hole" in our block resulting from * removing the name. */ if (smallest) { tmp = args->geo->blksize; entry = xfs_attr3_leaf_entryp(leaf); for (i = ichdr.count - 1; i >= 0; entry++, i--) { ASSERT(be16_to_cpu(entry->nameidx) >= ichdr.firstused); ASSERT(be16_to_cpu(entry->nameidx) < args->geo->blksize); if (be16_to_cpu(entry->nameidx) < tmp) tmp = be16_to_cpu(entry->nameidx); } ichdr.firstused = tmp; ASSERT(ichdr.firstused != 0); } else { ichdr.holes = 1; /* mark as needing compaction */ } xfs_attr3_leaf_hdr_to_disk(args->geo, leaf, &ichdr); xfs_trans_log_buf(args->trans, bp, XFS_DA_LOGRANGE(leaf, &leaf->hdr, xfs_attr3_leaf_hdr_size(leaf))); /* * Check if leaf is less than 50% full, caller may want to * "join" the leaf with a sibling if so. */ tmp = ichdr.usedbytes + xfs_attr3_leaf_hdr_size(leaf) + ichdr.count * sizeof(xfs_attr_leaf_entry_t); return tmp < args->geo->magicpct; /* leaf is < 37% full */ } /* * Move all the attribute list entries from drop_leaf into save_leaf. */ void xfs_attr3_leaf_unbalance( struct xfs_da_state *state, struct xfs_da_state_blk *drop_blk, struct xfs_da_state_blk *save_blk) { struct xfs_attr_leafblock *drop_leaf = drop_blk->bp->b_addr; struct xfs_attr_leafblock *save_leaf = save_blk->bp->b_addr; struct xfs_attr3_icleaf_hdr drophdr; struct xfs_attr3_icleaf_hdr savehdr; struct xfs_attr_leaf_entry *entry; trace_xfs_attr_leaf_unbalance(state->args); xfs_attr3_leaf_hdr_from_disk(state->args->geo, &drophdr, drop_leaf); xfs_attr3_leaf_hdr_from_disk(state->args->geo, &savehdr, save_leaf); entry = xfs_attr3_leaf_entryp(drop_leaf); /* * Save last hashval from dying block for later Btree fixup. */ drop_blk->hashval = be32_to_cpu(entry[drophdr.count - 1].hashval); /* * Check if we need a temp buffer, or can we do it in place. * Note that we don't check "leaf" for holes because we will * always be dropping it, toosmall() decided that for us already. */ if (savehdr.holes == 0) { /* * dest leaf has no holes, so we add there. May need * to make some room in the entry array. */ if (xfs_attr3_leaf_order(save_blk->bp, &savehdr, drop_blk->bp, &drophdr)) { xfs_attr3_leaf_moveents(state->args, drop_leaf, &drophdr, 0, save_leaf, &savehdr, 0, drophdr.count); } else { xfs_attr3_leaf_moveents(state->args, drop_leaf, &drophdr, 0, save_leaf, &savehdr, savehdr.count, drophdr.count); } } else { /* * Destination has holes, so we make a temporary copy * of the leaf and add them both to that. */ struct xfs_attr_leafblock *tmp_leaf; struct xfs_attr3_icleaf_hdr tmphdr; tmp_leaf = kvzalloc(state->args->geo->blksize, GFP_KERNEL | __GFP_NOFAIL); /* * Copy the header into the temp leaf so that all the stuff * not in the incore header is present and gets copied back in * once we've moved all the entries. */ memcpy(tmp_leaf, save_leaf, xfs_attr3_leaf_hdr_size(save_leaf)); memset(&tmphdr, 0, sizeof(tmphdr)); tmphdr.magic = savehdr.magic; tmphdr.forw = savehdr.forw; tmphdr.back = savehdr.back; tmphdr.firstused = state->args->geo->blksize; /* write the header to the temp buffer to initialise it */ xfs_attr3_leaf_hdr_to_disk(state->args->geo, tmp_leaf, &tmphdr); if (xfs_attr3_leaf_order(save_blk->bp, &savehdr, drop_blk->bp, &drophdr)) { xfs_attr3_leaf_moveents(state->args, drop_leaf, &drophdr, 0, tmp_leaf, &tmphdr, 0, drophdr.count); xfs_attr3_leaf_moveents(state->args, save_leaf, &savehdr, 0, tmp_leaf, &tmphdr, tmphdr.count, savehdr.count); } else { xfs_attr3_leaf_moveents(state->args, save_leaf, &savehdr, 0, tmp_leaf, &tmphdr, 0, savehdr.count); xfs_attr3_leaf_moveents(state->args, drop_leaf, &drophdr, 0, tmp_leaf, &tmphdr, tmphdr.count, drophdr.count); } memcpy(save_leaf, tmp_leaf, state->args->geo->blksize); savehdr = tmphdr; /* struct copy */ kvfree(tmp_leaf); } xfs_attr3_leaf_hdr_to_disk(state->args->geo, save_leaf, &savehdr); xfs_trans_log_buf(state->args->trans, save_blk->bp, 0, state->args->geo->blksize - 1); /* * Copy out last hashval in each block for B-tree code. */ entry = xfs_attr3_leaf_entryp(save_leaf); save_blk->hashval = be32_to_cpu(entry[savehdr.count - 1].hashval); } /*======================================================================== * Routines used for finding things in the Btree. *========================================================================*/ /* * Look up a name in a leaf attribute list structure. * This is the internal routine, it uses the caller's buffer. * * Note that duplicate keys are allowed, but only check within the * current leaf node. The Btree code must check in adjacent leaf nodes. * * Return in args->index the index into the entry[] array of either * the found entry, or where the entry should have been (insert before * that entry). * * Don't change the args->value unless we find the attribute. */ int xfs_attr3_leaf_lookup_int( struct xfs_buf *bp, struct xfs_da_args *args) { struct xfs_attr_leafblock *leaf; struct xfs_attr3_icleaf_hdr ichdr; struct xfs_attr_leaf_entry *entry; struct xfs_attr_leaf_entry *entries; struct xfs_attr_leaf_name_local *name_loc; struct xfs_attr_leaf_name_remote *name_rmt; xfs_dahash_t hashval; int probe; int span; trace_xfs_attr_leaf_lookup(args); leaf = bp->b_addr; xfs_attr3_leaf_hdr_from_disk(args->geo, &ichdr, leaf); entries = xfs_attr3_leaf_entryp(leaf); if (ichdr.count >= args->geo->blksize / 8) { xfs_buf_mark_corrupt(bp); xfs_da_mark_sick(args); return -EFSCORRUPTED; } /* * Binary search. (note: small blocks will skip this loop) */ hashval = args->hashval; probe = span = ichdr.count / 2; for (entry = &entries[probe]; span > 4; entry = &entries[probe]) { span /= 2; if (be32_to_cpu(entry->hashval) < hashval) probe += span; else if (be32_to_cpu(entry->hashval) > hashval) probe -= span; else break; } if (!(probe >= 0 && (!ichdr.count || probe < ichdr.count))) { xfs_buf_mark_corrupt(bp); xfs_da_mark_sick(args); return -EFSCORRUPTED; } if (!(span <= 4 || be32_to_cpu(entry->hashval) == hashval)) { xfs_buf_mark_corrupt(bp); xfs_da_mark_sick(args); return -EFSCORRUPTED; } /* * Since we may have duplicate hashval's, find the first matching * hashval in the leaf. */ while (probe > 0 && be32_to_cpu(entry->hashval) >= hashval) { entry--; probe--; } while (probe < ichdr.count && be32_to_cpu(entry->hashval) < hashval) { entry++; probe++; } if (probe == ichdr.count || be32_to_cpu(entry->hashval) != hashval) { args->index = probe; return -ENOATTR; } /* * Duplicate keys may be present, so search all of them for a match. */ for (; probe < ichdr.count && (be32_to_cpu(entry->hashval) == hashval); entry++, probe++) { /* * GROT: Add code to remove incomplete entries. */ if (entry->flags & XFS_ATTR_LOCAL) { name_loc = xfs_attr3_leaf_name_local(leaf, probe); if (!xfs_attr_match(args, entry->flags, name_loc->nameval, name_loc->namelen, &name_loc->nameval[name_loc->namelen], be16_to_cpu(name_loc->valuelen))) continue; args->index = probe; return -EEXIST; } else { unsigned int valuelen; name_rmt = xfs_attr3_leaf_name_remote(leaf, probe); valuelen = be32_to_cpu(name_rmt->valuelen); if (!xfs_attr_match(args, entry->flags, name_rmt->name, name_rmt->namelen, NULL, valuelen)) continue; args->index = probe; args->rmtvaluelen = valuelen; args->rmtblkno = be32_to_cpu(name_rmt->valueblk); args->rmtblkcnt = xfs_attr3_rmt_blocks( args->dp->i_mount, args->rmtvaluelen); return -EEXIST; } } args->index = probe; return -ENOATTR; } /* * Get the value associated with an attribute name from a leaf attribute * list structure. * * If args->valuelen is zero, only the length needs to be returned. Unlike a * lookup, we only return an error if the attribute does not exist or we can't * retrieve the value. */ int xfs_attr3_leaf_getvalue( struct xfs_buf *bp, struct xfs_da_args *args) { struct xfs_attr_leafblock *leaf; struct xfs_attr3_icleaf_hdr ichdr; struct xfs_attr_leaf_entry *entry; struct xfs_attr_leaf_name_local *name_loc; struct xfs_attr_leaf_name_remote *name_rmt; leaf = bp->b_addr; xfs_attr3_leaf_hdr_from_disk(args->geo, &ichdr, leaf); ASSERT(ichdr.count < args->geo->blksize / 8); ASSERT(args->index < ichdr.count); entry = &xfs_attr3_leaf_entryp(leaf)[args->index]; if (entry->flags & XFS_ATTR_LOCAL) { name_loc = xfs_attr3_leaf_name_local(leaf, args->index); ASSERT(name_loc->namelen == args->namelen); ASSERT(memcmp(args->name, name_loc->nameval, args->namelen) == 0); return xfs_attr_copy_value(args, &name_loc->nameval[args->namelen], be16_to_cpu(name_loc->valuelen)); } name_rmt = xfs_attr3_leaf_name_remote(leaf, args->index); ASSERT(name_rmt->namelen == args->namelen); ASSERT(memcmp(args->name, name_rmt->name, args->namelen) == 0); args->rmtvaluelen = be32_to_cpu(name_rmt->valuelen); args->rmtblkno = be32_to_cpu(name_rmt->valueblk); args->rmtblkcnt = xfs_attr3_rmt_blocks(args->dp->i_mount, args->rmtvaluelen); return xfs_attr_copy_value(args, NULL, args->rmtvaluelen); } /*======================================================================== * Utility routines. *========================================================================*/ /* * Move the indicated entries from one leaf to another. * NOTE: this routine modifies both source and destination leaves. */ /*ARGSUSED*/ STATIC void xfs_attr3_leaf_moveents( struct xfs_da_args *args, struct xfs_attr_leafblock *leaf_s, struct xfs_attr3_icleaf_hdr *ichdr_s, int start_s, struct xfs_attr_leafblock *leaf_d, struct xfs_attr3_icleaf_hdr *ichdr_d, int start_d, int count) { struct xfs_attr_leaf_entry *entry_s; struct xfs_attr_leaf_entry *entry_d; int desti; int tmp; int i; /* * Check for nothing to do. */ if (count == 0) return; /* * Set up environment. */ ASSERT(ichdr_s->magic == XFS_ATTR_LEAF_MAGIC || ichdr_s->magic == XFS_ATTR3_LEAF_MAGIC); ASSERT(ichdr_s->magic == ichdr_d->magic); ASSERT(ichdr_s->count > 0 && ichdr_s->count < args->geo->blksize / 8); ASSERT(ichdr_s->firstused >= (ichdr_s->count * sizeof(*entry_s)) + xfs_attr3_leaf_hdr_size(leaf_s)); ASSERT(ichdr_d->count < args->geo->blksize / 8); ASSERT(ichdr_d->firstused >= (ichdr_d->count * sizeof(*entry_d)) + xfs_attr3_leaf_hdr_size(leaf_d)); ASSERT(start_s < ichdr_s->count); ASSERT(start_d <= ichdr_d->count); ASSERT(count <= ichdr_s->count); /* * Move the entries in the destination leaf up to make a hole? */ if (start_d < ichdr_d->count) { tmp = ichdr_d->count - start_d; tmp *= sizeof(xfs_attr_leaf_entry_t); entry_s = &xfs_attr3_leaf_entryp(leaf_d)[start_d]; entry_d = &xfs_attr3_leaf_entryp(leaf_d)[start_d + count]; memmove(entry_d, entry_s, tmp); } /* * Copy all entry's in the same (sorted) order, * but allocate attribute info packed and in sequence. */ entry_s = &xfs_attr3_leaf_entryp(leaf_s)[start_s]; entry_d = &xfs_attr3_leaf_entryp(leaf_d)[start_d]; desti = start_d; for (i = 0; i < count; entry_s++, entry_d++, desti++, i++) { ASSERT(be16_to_cpu(entry_s->nameidx) >= ichdr_s->firstused); tmp = xfs_attr_leaf_entsize(leaf_s, start_s + i); #ifdef GROT /* * Code to drop INCOMPLETE entries. Difficult to use as we * may also need to change the insertion index. Code turned * off for 6.2, should be revisited later. */ if (entry_s->flags & XFS_ATTR_INCOMPLETE) { /* skip partials? */ memset(xfs_attr3_leaf_name(leaf_s, start_s + i), 0, tmp); ichdr_s->usedbytes -= tmp; ichdr_s->count -= 1; entry_d--; /* to compensate for ++ in loop hdr */ desti--; if ((start_s + i) < offset) result++; /* insertion index adjustment */ } else { #endif /* GROT */ ichdr_d->firstused -= tmp; /* both on-disk, don't endian flip twice */ entry_d->hashval = entry_s->hashval; entry_d->nameidx = cpu_to_be16(ichdr_d->firstused); entry_d->flags = entry_s->flags; ASSERT(be16_to_cpu(entry_d->nameidx) + tmp <= args->geo->blksize); memmove(xfs_attr3_leaf_name(leaf_d, desti), xfs_attr3_leaf_name(leaf_s, start_s + i), tmp); ASSERT(be16_to_cpu(entry_s->nameidx) + tmp <= args->geo->blksize); memset(xfs_attr3_leaf_name(leaf_s, start_s + i), 0, tmp); ichdr_s->usedbytes -= tmp; ichdr_d->usedbytes += tmp; ichdr_s->count -= 1; ichdr_d->count += 1; tmp = ichdr_d->count * sizeof(xfs_attr_leaf_entry_t) + xfs_attr3_leaf_hdr_size(leaf_d); ASSERT(ichdr_d->firstused >= tmp); #ifdef GROT } #endif /* GROT */ } /* * Zero out the entries we just copied. */ if (start_s == ichdr_s->count) { tmp = count * sizeof(xfs_attr_leaf_entry_t); entry_s = &xfs_attr3_leaf_entryp(leaf_s)[start_s]; ASSERT(((char *)entry_s + tmp) <= ((char *)leaf_s + args->geo->blksize)); memset(entry_s, 0, tmp); } else { /* * Move the remaining entries down to fill the hole, * then zero the entries at the top. */ tmp = (ichdr_s->count - count) * sizeof(xfs_attr_leaf_entry_t); entry_s = &xfs_attr3_leaf_entryp(leaf_s)[start_s + count]; entry_d = &xfs_attr3_leaf_entryp(leaf_s)[start_s]; memmove(entry_d, entry_s, tmp); tmp = count * sizeof(xfs_attr_leaf_entry_t); entry_s = &xfs_attr3_leaf_entryp(leaf_s)[ichdr_s->count]; ASSERT(((char *)entry_s + tmp) <= ((char *)leaf_s + args->geo->blksize)); memset(entry_s, 0, tmp); } /* * Fill in the freemap information */ ichdr_d->freemap[0].base = xfs_attr3_leaf_hdr_size(leaf_d); ichdr_d->freemap[0].base += ichdr_d->count * sizeof(xfs_attr_leaf_entry_t); ichdr_d->freemap[0].size = ichdr_d->firstused - ichdr_d->freemap[0].base; ichdr_d->freemap[1].base = 0; ichdr_d->freemap[2].base = 0; ichdr_d->freemap[1].size = 0; ichdr_d->freemap[2].size = 0; ichdr_s->holes = 1; /* leaf may not be compact */ } /* * Pick up the last hashvalue from a leaf block. */ xfs_dahash_t xfs_attr_leaf_lasthash( struct xfs_buf *bp, int *count) { struct xfs_attr3_icleaf_hdr ichdr; struct xfs_attr_leaf_entry *entries; struct xfs_mount *mp = bp->b_mount; xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, bp->b_addr); entries = xfs_attr3_leaf_entryp(bp->b_addr); if (count) *count = ichdr.count; if (!ichdr.count) return 0; return be32_to_cpu(entries[ichdr.count - 1].hashval); } /* * Calculate the number of bytes used to store the indicated attribute * (whether local or remote only calculate bytes in this block). */ STATIC int xfs_attr_leaf_entsize(xfs_attr_leafblock_t *leaf, int index) { struct xfs_attr_leaf_entry *entries; xfs_attr_leaf_name_local_t *name_loc; xfs_attr_leaf_name_remote_t *name_rmt; int size; entries = xfs_attr3_leaf_entryp(leaf); if (entries[index].flags & XFS_ATTR_LOCAL) { name_loc = xfs_attr3_leaf_name_local(leaf, index); size = xfs_attr_leaf_entsize_local(name_loc->namelen, be16_to_cpu(name_loc->valuelen)); } else { name_rmt = xfs_attr3_leaf_name_remote(leaf, index); size = xfs_attr_leaf_entsize_remote(name_rmt->namelen); } return size; } /* * Calculate the number of bytes that would be required to store the new * attribute (whether local or remote only calculate bytes in this block). * This routine decides as a side effect whether the attribute will be * a "local" or a "remote" attribute. */ int xfs_attr_leaf_newentsize( struct xfs_da_args *args, int *local) { int size; size = xfs_attr_leaf_entsize_local(args->namelen, args->valuelen); if (size < xfs_attr_leaf_entsize_local_max(args->geo->blksize)) { if (local) *local = 1; return size; } if (local) *local = 0; return xfs_attr_leaf_entsize_remote(args->namelen); } /*======================================================================== * Manage the INCOMPLETE flag in a leaf entry *========================================================================*/ /* * Clear the INCOMPLETE flag on an entry in a leaf block. */ int xfs_attr3_leaf_clearflag( struct xfs_da_args *args) { struct xfs_attr_leafblock *leaf; struct xfs_attr_leaf_entry *entry; struct xfs_attr_leaf_name_remote *name_rmt; struct xfs_buf *bp; int error; #ifdef DEBUG struct xfs_attr3_icleaf_hdr ichdr; xfs_attr_leaf_name_local_t *name_loc; int namelen; char *name; #endif /* DEBUG */ trace_xfs_attr_leaf_clearflag(args); /* * Set up the operation. */ error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, args->blkno, &bp); if (error) return error; leaf = bp->b_addr; entry = &xfs_attr3_leaf_entryp(leaf)[args->index]; ASSERT(entry->flags & XFS_ATTR_INCOMPLETE); #ifdef DEBUG xfs_attr3_leaf_hdr_from_disk(args->geo, &ichdr, leaf); ASSERT(args->index < ichdr.count); ASSERT(args->index >= 0); if (entry->flags & XFS_ATTR_LOCAL) { name_loc = xfs_attr3_leaf_name_local(leaf, args->index); namelen = name_loc->namelen; name = (char *)name_loc->nameval; } else { name_rmt = xfs_attr3_leaf_name_remote(leaf, args->index); namelen = name_rmt->namelen; name = (char *)name_rmt->name; } ASSERT(be32_to_cpu(entry->hashval) == args->hashval); ASSERT(namelen == args->namelen); ASSERT(memcmp(name, args->name, namelen) == 0); #endif /* DEBUG */ entry->flags &= ~XFS_ATTR_INCOMPLETE; xfs_trans_log_buf(args->trans, bp, XFS_DA_LOGRANGE(leaf, entry, sizeof(*entry))); if (args->rmtblkno) { ASSERT((entry->flags & XFS_ATTR_LOCAL) == 0); name_rmt = xfs_attr3_leaf_name_remote(leaf, args->index); name_rmt->valueblk = cpu_to_be32(args->rmtblkno); name_rmt->valuelen = cpu_to_be32(args->rmtvaluelen); xfs_trans_log_buf(args->trans, bp, XFS_DA_LOGRANGE(leaf, name_rmt, sizeof(*name_rmt))); } return 0; } /* * Set the INCOMPLETE flag on an entry in a leaf block. */ int xfs_attr3_leaf_setflag( struct xfs_da_args *args) { struct xfs_attr_leafblock *leaf; struct xfs_attr_leaf_entry *entry; struct xfs_attr_leaf_name_remote *name_rmt; struct xfs_buf *bp; int error; #ifdef DEBUG struct xfs_attr3_icleaf_hdr ichdr; #endif trace_xfs_attr_leaf_setflag(args); /* * Set up the operation. */ error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, args->blkno, &bp); if (error) return error; leaf = bp->b_addr; #ifdef DEBUG xfs_attr3_leaf_hdr_from_disk(args->geo, &ichdr, leaf); ASSERT(args->index < ichdr.count); ASSERT(args->index >= 0); #endif entry = &xfs_attr3_leaf_entryp(leaf)[args->index]; ASSERT((entry->flags & XFS_ATTR_INCOMPLETE) == 0); entry->flags |= XFS_ATTR_INCOMPLETE; xfs_trans_log_buf(args->trans, bp, XFS_DA_LOGRANGE(leaf, entry, sizeof(*entry))); if ((entry->flags & XFS_ATTR_LOCAL) == 0) { name_rmt = xfs_attr3_leaf_name_remote(leaf, args->index); name_rmt->valueblk = 0; name_rmt->valuelen = 0; xfs_trans_log_buf(args->trans, bp, XFS_DA_LOGRANGE(leaf, name_rmt, sizeof(*name_rmt))); } return 0; } /* * In a single transaction, clear the INCOMPLETE flag on the leaf entry * given by args->blkno/index and set the INCOMPLETE flag on the leaf * entry given by args->blkno2/index2. * * Note that they could be in different blocks, or in the same block. */ int xfs_attr3_leaf_flipflags( struct xfs_da_args *args) { struct xfs_attr_leafblock *leaf1; struct xfs_attr_leafblock *leaf2; struct xfs_attr_leaf_entry *entry1; struct xfs_attr_leaf_entry *entry2; struct xfs_attr_leaf_name_remote *name_rmt; struct xfs_buf *bp1; struct xfs_buf *bp2; int error; #ifdef DEBUG struct xfs_attr3_icleaf_hdr ichdr1; struct xfs_attr3_icleaf_hdr ichdr2; xfs_attr_leaf_name_local_t *name_loc; int namelen1, namelen2; char *name1, *name2; #endif /* DEBUG */ trace_xfs_attr_leaf_flipflags(args); /* * Read the block containing the "old" attr */ error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, args->blkno, &bp1); if (error) return error; /* * Read the block containing the "new" attr, if it is different */ if (args->blkno2 != args->blkno) { error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, args->blkno2, &bp2); if (error) return error; } else { bp2 = bp1; } leaf1 = bp1->b_addr; entry1 = &xfs_attr3_leaf_entryp(leaf1)[args->index]; leaf2 = bp2->b_addr; entry2 = &xfs_attr3_leaf_entryp(leaf2)[args->index2]; #ifdef DEBUG xfs_attr3_leaf_hdr_from_disk(args->geo, &ichdr1, leaf1); ASSERT(args->index < ichdr1.count); ASSERT(args->index >= 0); xfs_attr3_leaf_hdr_from_disk(args->geo, &ichdr2, leaf2); ASSERT(args->index2 < ichdr2.count); ASSERT(args->index2 >= 0); if (entry1->flags & XFS_ATTR_LOCAL) { name_loc = xfs_attr3_leaf_name_local(leaf1, args->index); namelen1 = name_loc->namelen; name1 = (char *)name_loc->nameval; } else { name_rmt = xfs_attr3_leaf_name_remote(leaf1, args->index); namelen1 = name_rmt->namelen; name1 = (char *)name_rmt->name; } if (entry2->flags & XFS_ATTR_LOCAL) { name_loc = xfs_attr3_leaf_name_local(leaf2, args->index2); namelen2 = name_loc->namelen; name2 = (char *)name_loc->nameval; } else { name_rmt = xfs_attr3_leaf_name_remote(leaf2, args->index2); namelen2 = name_rmt->namelen; name2 = (char *)name_rmt->name; } ASSERT(be32_to_cpu(entry1->hashval) == be32_to_cpu(entry2->hashval)); ASSERT(namelen1 == namelen2); ASSERT(memcmp(name1, name2, namelen1) == 0); #endif /* DEBUG */ ASSERT(entry1->flags & XFS_ATTR_INCOMPLETE); ASSERT((entry2->flags & XFS_ATTR_INCOMPLETE) == 0); entry1->flags &= ~XFS_ATTR_INCOMPLETE; xfs_trans_log_buf(args->trans, bp1, XFS_DA_LOGRANGE(leaf1, entry1, sizeof(*entry1))); if (args->rmtblkno) { ASSERT((entry1->flags & XFS_ATTR_LOCAL) == 0); name_rmt = xfs_attr3_leaf_name_remote(leaf1, args->index); name_rmt->valueblk = cpu_to_be32(args->rmtblkno); name_rmt->valuelen = cpu_to_be32(args->rmtvaluelen); xfs_trans_log_buf(args->trans, bp1, XFS_DA_LOGRANGE(leaf1, name_rmt, sizeof(*name_rmt))); } entry2->flags |= XFS_ATTR_INCOMPLETE; xfs_trans_log_buf(args->trans, bp2, XFS_DA_LOGRANGE(leaf2, entry2, sizeof(*entry2))); if ((entry2->flags & XFS_ATTR_LOCAL) == 0) { name_rmt = xfs_attr3_leaf_name_remote(leaf2, args->index2); name_rmt->valueblk = 0; name_rmt->valuelen = 0; xfs_trans_log_buf(args->trans, bp2, XFS_DA_LOGRANGE(leaf2, name_rmt, sizeof(*name_rmt))); } return 0; } |
| 1 1 1 1 1 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2017 Red Hat, Inc. */ #include "fuse_i.h" #include <linux/uio.h> #include <linux/compat.h> #include <linux/fileattr.h> #include <linux/fsverity.h> #define FUSE_VERITY_ENABLE_ARG_MAX_PAGES 256 static ssize_t fuse_send_ioctl(struct fuse_mount *fm, struct fuse_args *args, struct fuse_ioctl_out *outarg) { ssize_t ret; args->out_args[0].size = sizeof(*outarg); args->out_args[0].value = outarg; ret = fuse_simple_request(fm, args); /* Translate ENOSYS, which shouldn't be returned from fs */ if (ret == -ENOSYS) ret = -ENOTTY; if (ret >= 0 && outarg->result == -ENOSYS) outarg->result = -ENOTTY; return ret; } /* * CUSE servers compiled on 32bit broke on 64bit kernels because the * ABI was defined to be 'struct iovec' which is different on 32bit * and 64bit. Fortunately we can determine which structure the server * used from the size of the reply. */ static int fuse_copy_ioctl_iovec_old(struct iovec *dst, void *src, size_t transferred, unsigned count, bool is_compat) { #ifdef CONFIG_COMPAT if (count * sizeof(struct compat_iovec) == transferred) { struct compat_iovec *ciov = src; unsigned i; /* * With this interface a 32bit server cannot support * non-compat (i.e. ones coming from 64bit apps) ioctl * requests */ if (!is_compat) return -EINVAL; for (i = 0; i < count; i++) { dst[i].iov_base = compat_ptr(ciov[i].iov_base); dst[i].iov_len = ciov[i].iov_len; } return 0; } #endif if (count * sizeof(struct iovec) != transferred) return -EIO; memcpy(dst, src, transferred); return 0; } /* Make sure iov_length() won't overflow */ static int fuse_verify_ioctl_iov(struct fuse_conn *fc, struct iovec *iov, size_t count) { size_t n; u32 max = fc->max_pages << PAGE_SHIFT; for (n = 0; n < count; n++, iov++) { if (iov->iov_len > (size_t) max) return -ENOMEM; max -= iov->iov_len; } return 0; } static int fuse_copy_ioctl_iovec(struct fuse_conn *fc, struct iovec *dst, void *src, size_t transferred, unsigned count, bool is_compat) { unsigned i; struct fuse_ioctl_iovec *fiov = src; if (fc->minor < 16) { return fuse_copy_ioctl_iovec_old(dst, src, transferred, count, is_compat); } if (count * sizeof(struct fuse_ioctl_iovec) != transferred) return -EIO; for (i = 0; i < count; i++) { /* Did the server supply an inappropriate value? */ if (fiov[i].base != (unsigned long) fiov[i].base || fiov[i].len != (unsigned long) fiov[i].len) return -EIO; dst[i].iov_base = (void __user *) (unsigned long) fiov[i].base; dst[i].iov_len = (size_t) fiov[i].len; #ifdef CONFIG_COMPAT if (is_compat && (ptr_to_compat(dst[i].iov_base) != fiov[i].base || (compat_size_t) dst[i].iov_len != fiov[i].len)) return -EIO; #endif } return 0; } /* For fs-verity, determine iov lengths from input */ static int fuse_setup_measure_verity(unsigned long arg, struct iovec *iov) { __u16 digest_size; struct fsverity_digest __user *uarg = (void __user *)arg; if (copy_from_user(&digest_size, &uarg->digest_size, sizeof(digest_size))) return -EFAULT; if (digest_size > SIZE_MAX - sizeof(struct fsverity_digest)) return -EINVAL; iov->iov_len = sizeof(struct fsverity_digest) + digest_size; return 0; } static int fuse_setup_enable_verity(unsigned long arg, struct iovec *iov, unsigned int *in_iovs) { struct fsverity_enable_arg enable; struct fsverity_enable_arg __user *uarg = (void __user *)arg; const __u32 max_buffer_len = FUSE_VERITY_ENABLE_ARG_MAX_PAGES * PAGE_SIZE; if (copy_from_user(&enable, uarg, sizeof(enable))) return -EFAULT; if (enable.salt_size > max_buffer_len || enable.sig_size > max_buffer_len) return -ENOMEM; if (enable.salt_size > 0) { iov++; (*in_iovs)++; iov->iov_base = u64_to_user_ptr(enable.salt_ptr); iov->iov_len = enable.salt_size; } if (enable.sig_size > 0) { iov++; (*in_iovs)++; iov->iov_base = u64_to_user_ptr(enable.sig_ptr); iov->iov_len = enable.sig_size; } return 0; } /* * For ioctls, there is no generic way to determine how much memory * needs to be read and/or written. Furthermore, ioctls are allowed * to dereference the passed pointer, so the parameter requires deep * copying but FUSE has no idea whatsoever about what to copy in or * out. * * This is solved by allowing FUSE server to retry ioctl with * necessary in/out iovecs. Let's assume the ioctl implementation * needs to read in the following structure. * * struct a { * char *buf; * size_t buflen; * } * * On the first callout to FUSE server, inarg->in_size and * inarg->out_size will be NULL; then, the server completes the ioctl * with FUSE_IOCTL_RETRY set in out->flags, out->in_iovs set to 1 and * the actual iov array to * * { { .iov_base = inarg.arg, .iov_len = sizeof(struct a) } } * * which tells FUSE to copy in the requested area and retry the ioctl. * On the second round, the server has access to the structure and * from that it can tell what to look for next, so on the invocation, * it sets FUSE_IOCTL_RETRY, out->in_iovs to 2 and iov array to * * { { .iov_base = inarg.arg, .iov_len = sizeof(struct a) }, * { .iov_base = a.buf, .iov_len = a.buflen } } * * FUSE will copy both struct a and the pointed buffer from the * process doing the ioctl and retry ioctl with both struct a and the * buffer. * * This time, FUSE server has everything it needs and completes ioctl * without FUSE_IOCTL_RETRY which finishes the ioctl call. * * Copying data out works the same way. * * Note that if FUSE_IOCTL_UNRESTRICTED is clear, the kernel * automatically initializes in and out iovs by decoding @cmd with * _IOC_* macros and the server is not allowed to request RETRY. This * limits ioctl data transfers to well-formed ioctls and is the forced * behavior for all FUSE servers. */ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg, unsigned int flags) { struct fuse_file *ff = file->private_data; struct fuse_mount *fm = ff->fm; struct fuse_ioctl_in inarg = { .fh = ff->fh, .cmd = cmd, .arg = arg, .flags = flags }; struct fuse_ioctl_out outarg; struct iovec *iov_page = NULL; struct iovec *in_iov = NULL, *out_iov = NULL; unsigned int in_iovs = 0, out_iovs = 0, max_pages; size_t in_size, out_size, c; ssize_t transferred; int err, i; struct iov_iter ii; struct fuse_args_pages ap = {}; #if BITS_PER_LONG == 32 inarg.flags |= FUSE_IOCTL_32BIT; #else if (flags & FUSE_IOCTL_COMPAT) { inarg.flags |= FUSE_IOCTL_32BIT; #ifdef CONFIG_X86_X32_ABI if (in_x32_syscall()) inarg.flags |= FUSE_IOCTL_COMPAT_X32; #endif } #endif /* assume all the iovs returned by client always fits in a page */ BUILD_BUG_ON(sizeof(struct fuse_ioctl_iovec) * FUSE_IOCTL_MAX_IOV > PAGE_SIZE); err = -ENOMEM; ap.folios = fuse_folios_alloc(fm->fc->max_pages, GFP_KERNEL, &ap.descs); iov_page = (struct iovec *) __get_free_page(GFP_KERNEL); if (!ap.folios || !iov_page) goto out; fuse_folio_descs_length_init(ap.descs, 0, fm->fc->max_pages); /* * If restricted, initialize IO parameters as encoded in @cmd. * RETRY from server is not allowed. */ if (!(flags & FUSE_IOCTL_UNRESTRICTED)) { struct iovec *iov = iov_page; iov->iov_base = (void __user *)arg; iov->iov_len = _IOC_SIZE(cmd); if (_IOC_DIR(cmd) & _IOC_WRITE) { in_iov = iov; in_iovs = 1; } if (_IOC_DIR(cmd) & _IOC_READ) { out_iov = iov; out_iovs = 1; } err = 0; switch (cmd) { case FS_IOC_MEASURE_VERITY: err = fuse_setup_measure_verity(arg, iov); break; case FS_IOC_ENABLE_VERITY: err = fuse_setup_enable_verity(arg, iov, &in_iovs); break; } if (err) goto out; } retry: inarg.in_size = in_size = iov_length(in_iov, in_iovs); inarg.out_size = out_size = iov_length(out_iov, out_iovs); /* * Out data can be used either for actual out data or iovs, * make sure there always is at least one page. */ out_size = max_t(size_t, out_size, PAGE_SIZE); max_pages = DIV_ROUND_UP(max(in_size, out_size), PAGE_SIZE); /* make sure there are enough buffer pages and init request with them */ err = -ENOMEM; if (max_pages > fm->fc->max_pages) goto out; while (ap.num_folios < max_pages) { ap.folios[ap.num_folios] = folio_alloc(GFP_KERNEL | __GFP_HIGHMEM, 0); if (!ap.folios[ap.num_folios]) goto out; ap.num_folios++; } /* okay, let's send it to the client */ ap.args.opcode = FUSE_IOCTL; ap.args.nodeid = ff->nodeid; ap.args.in_numargs = 1; ap.args.in_args[0].size = sizeof(inarg); ap.args.in_args[0].value = &inarg; if (in_size) { ap.args.in_numargs++; ap.args.in_args[1].size = in_size; ap.args.in_pages = true; err = -EFAULT; iov_iter_init(&ii, ITER_SOURCE, in_iov, in_iovs, in_size); for (i = 0; iov_iter_count(&ii) && !WARN_ON(i >= ap.num_folios); i++) { c = copy_folio_from_iter(ap.folios[i], 0, PAGE_SIZE, &ii); if (c != PAGE_SIZE && iov_iter_count(&ii)) goto out; } } ap.args.out_numargs = 2; ap.args.out_args[1].size = out_size; ap.args.out_pages = true; ap.args.out_argvar = true; transferred = fuse_send_ioctl(fm, &ap.args, &outarg); err = transferred; if (transferred < 0) goto out; /* did it ask for retry? */ if (outarg.flags & FUSE_IOCTL_RETRY) { void *vaddr; /* no retry if in restricted mode */ err = -EIO; if (!(flags & FUSE_IOCTL_UNRESTRICTED)) goto out; in_iovs = outarg.in_iovs; out_iovs = outarg.out_iovs; /* * Make sure things are in boundary, separate checks * are to protect against overflow. */ err = -ENOMEM; if (in_iovs > FUSE_IOCTL_MAX_IOV || out_iovs > FUSE_IOCTL_MAX_IOV || in_iovs + out_iovs > FUSE_IOCTL_MAX_IOV) goto out; vaddr = kmap_local_folio(ap.folios[0], 0); err = fuse_copy_ioctl_iovec(fm->fc, iov_page, vaddr, transferred, in_iovs + out_iovs, (flags & FUSE_IOCTL_COMPAT) != 0); kunmap_local(vaddr); if (err) goto out; in_iov = iov_page; out_iov = in_iov + in_iovs; err = fuse_verify_ioctl_iov(fm->fc, in_iov, in_iovs); if (err) goto out; err = fuse_verify_ioctl_iov(fm->fc, out_iov, out_iovs); if (err) goto out; goto retry; } err = -EIO; if (transferred > inarg.out_size) goto out; err = -EFAULT; iov_iter_init(&ii, ITER_DEST, out_iov, out_iovs, transferred); for (i = 0; iov_iter_count(&ii) && !WARN_ON(i >= ap.num_folios); i++) { c = copy_folio_to_iter(ap.folios[i], 0, PAGE_SIZE, &ii); if (c != PAGE_SIZE && iov_iter_count(&ii)) goto out; } err = 0; out: free_page((unsigned long) iov_page); while (ap.num_folios) folio_put(ap.folios[--ap.num_folios]); kfree(ap.folios); return err ? err : outarg.result; } EXPORT_SYMBOL_GPL(fuse_do_ioctl); long fuse_ioctl_common(struct file *file, unsigned int cmd, unsigned long arg, unsigned int flags) { struct inode *inode = file_inode(file); struct fuse_conn *fc = get_fuse_conn(inode); if (!fuse_allow_current_process(fc)) return -EACCES; if (fuse_is_bad(inode)) return -EIO; return fuse_do_ioctl(file, cmd, arg, flags); } long fuse_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return fuse_ioctl_common(file, cmd, arg, 0); } long fuse_file_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return fuse_ioctl_common(file, cmd, arg, FUSE_IOCTL_COMPAT); } static int fuse_priv_ioctl(struct inode *inode, struct fuse_file *ff, unsigned int cmd, void *ptr, size_t size) { struct fuse_mount *fm = ff->fm; struct fuse_ioctl_in inarg; struct fuse_ioctl_out outarg; FUSE_ARGS(args); int err; memset(&inarg, 0, sizeof(inarg)); inarg.fh = ff->fh; inarg.cmd = cmd; #if BITS_PER_LONG == 32 inarg.flags |= FUSE_IOCTL_32BIT; #endif if (S_ISDIR(inode->i_mode)) inarg.flags |= FUSE_IOCTL_DIR; if (_IOC_DIR(cmd) & _IOC_READ) inarg.out_size = size; if (_IOC_DIR(cmd) & _IOC_WRITE) inarg.in_size = size; args.opcode = FUSE_IOCTL; args.nodeid = ff->nodeid; args.in_numargs = 2; args.in_args[0].size = sizeof(inarg); args.in_args[0].value = &inarg; args.in_args[1].size = inarg.in_size; args.in_args[1].value = ptr; args.out_numargs = 2; args.out_args[1].size = inarg.out_size; args.out_args[1].value = ptr; err = fuse_send_ioctl(fm, &args, &outarg); if (!err) { if (outarg.result < 0) err = outarg.result; else if (outarg.flags & FUSE_IOCTL_RETRY) err = -EIO; } return err; } static struct fuse_file *fuse_priv_ioctl_prepare(struct inode *inode) { struct fuse_mount *fm = get_fuse_mount(inode); bool isdir = S_ISDIR(inode->i_mode); if (!fuse_allow_current_process(fm->fc)) return ERR_PTR(-EACCES); if (fuse_is_bad(inode)) return ERR_PTR(-EIO); if (!S_ISREG(inode->i_mode) && !isdir) return ERR_PTR(-ENOTTY); return fuse_file_open(fm, get_node_id(inode), O_RDONLY, isdir); } static void fuse_priv_ioctl_cleanup(struct inode *inode, struct fuse_file *ff) { fuse_file_release(inode, ff, O_RDONLY, NULL, S_ISDIR(inode->i_mode)); } int fuse_fileattr_get(struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); struct fuse_file *ff; unsigned int flags; struct fsxattr xfa; int err; ff = fuse_priv_ioctl_prepare(inode); if (IS_ERR(ff)) return PTR_ERR(ff); if (fa->flags_valid) { err = fuse_priv_ioctl(inode, ff, FS_IOC_GETFLAGS, &flags, sizeof(flags)); if (err) goto cleanup; fileattr_fill_flags(fa, flags); } else { err = fuse_priv_ioctl(inode, ff, FS_IOC_FSGETXATTR, &xfa, sizeof(xfa)); if (err) goto cleanup; fileattr_fill_xflags(fa, xfa.fsx_xflags); fa->fsx_extsize = xfa.fsx_extsize; fa->fsx_nextents = xfa.fsx_nextents; fa->fsx_projid = xfa.fsx_projid; fa->fsx_cowextsize = xfa.fsx_cowextsize; } cleanup: fuse_priv_ioctl_cleanup(inode, ff); return err; } int fuse_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); struct fuse_file *ff; unsigned int flags = fa->flags; struct fsxattr xfa; int err; ff = fuse_priv_ioctl_prepare(inode); if (IS_ERR(ff)) return PTR_ERR(ff); if (fa->flags_valid) { err = fuse_priv_ioctl(inode, ff, FS_IOC_SETFLAGS, &flags, sizeof(flags)); if (err) goto cleanup; } else { memset(&xfa, 0, sizeof(xfa)); xfa.fsx_xflags = fa->fsx_xflags; xfa.fsx_extsize = fa->fsx_extsize; xfa.fsx_nextents = fa->fsx_nextents; xfa.fsx_projid = fa->fsx_projid; xfa.fsx_cowextsize = fa->fsx_cowextsize; err = fuse_priv_ioctl(inode, ff, FS_IOC_FSSETXATTR, &xfa, sizeof(xfa)); } cleanup: fuse_priv_ioctl_cleanup(inode, ff); return err; } |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/nfs/dir.c * * Copyright (C) 1992 Rick Sladkey * * nfs directory handling functions * * 10 Apr 1996 Added silly rename for unlink --okir * 28 Sep 1996 Improved directory cache --okir * 23 Aug 1997 Claus Heine claus@momo.math.rwth-aachen.de * Re-implemented silly rename for unlink, newly implemented * silly rename for nfs_rename() following the suggestions * of Olaf Kirch (okir) found in this file. * Following Linus comments on my original hack, this version * depends only on the dcache stuff and doesn't touch the inode * layer (iput() and friends). * 6 Jun 1999 Cache readdir lookups in the page cache. -DaveM */ #include <linux/compat.h> #include <linux/module.h> #include <linux/time.h> #include <linux/errno.h> #include <linux/stat.h> #include <linux/fcntl.h> #include <linux/string.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/sunrpc/clnt.h> #include <linux/nfs_fs.h> #include <linux/nfs_mount.h> #include <linux/pagemap.h> #include <linux/pagevec.h> #include <linux/namei.h> #include <linux/mount.h> #include <linux/swap.h> #include <linux/sched.h> #include <linux/kmemleak.h> #include <linux/xattr.h> #include <linux/hash.h> #include "delegation.h" #include "iostat.h" #include "internal.h" #include "fscache.h" #include "nfstrace.h" /* #define NFS_DEBUG_VERBOSE 1 */ static int nfs_opendir(struct inode *, struct file *); static int nfs_closedir(struct inode *, struct file *); static int nfs_readdir(struct file *, struct dir_context *); static int nfs_fsync_dir(struct file *, loff_t, loff_t, int); static loff_t nfs_llseek_dir(struct file *, loff_t, int); static void nfs_readdir_clear_array(struct folio *); static int nfs_do_create(struct inode *dir, struct dentry *dentry, umode_t mode, int open_flags); const struct file_operations nfs_dir_operations = { .llseek = nfs_llseek_dir, .read = generic_read_dir, .iterate_shared = nfs_readdir, .open = nfs_opendir, .release = nfs_closedir, .fsync = nfs_fsync_dir, }; const struct address_space_operations nfs_dir_aops = { .free_folio = nfs_readdir_clear_array, }; #define NFS_INIT_DTSIZE PAGE_SIZE static struct nfs_open_dir_context * alloc_nfs_open_dir_context(struct inode *dir) { struct nfs_inode *nfsi = NFS_I(dir); struct nfs_open_dir_context *ctx; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL_ACCOUNT); if (ctx != NULL) { ctx->attr_gencount = nfsi->attr_gencount; ctx->dtsize = NFS_INIT_DTSIZE; spin_lock(&dir->i_lock); if (list_empty(&nfsi->open_files) && (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER)) nfs_set_cache_invalid(dir, NFS_INO_INVALID_DATA | NFS_INO_REVAL_FORCED); list_add_tail_rcu(&ctx->list, &nfsi->open_files); memcpy(ctx->verf, nfsi->cookieverf, sizeof(ctx->verf)); spin_unlock(&dir->i_lock); return ctx; } return ERR_PTR(-ENOMEM); } static void put_nfs_open_dir_context(struct inode *dir, struct nfs_open_dir_context *ctx) { spin_lock(&dir->i_lock); list_del_rcu(&ctx->list); spin_unlock(&dir->i_lock); kfree_rcu(ctx, rcu_head); } /* * Open file */ static int nfs_opendir(struct inode *inode, struct file *filp) { int res = 0; struct nfs_open_dir_context *ctx; dfprintk(FILE, "NFS: open dir(%pD2)\n", filp); nfs_inc_stats(inode, NFSIOS_VFSOPEN); ctx = alloc_nfs_open_dir_context(inode); if (IS_ERR(ctx)) { res = PTR_ERR(ctx); goto out; } filp->private_data = ctx; out: return res; } static int nfs_closedir(struct inode *inode, struct file *filp) { put_nfs_open_dir_context(file_inode(filp), filp->private_data); return 0; } struct nfs_cache_array_entry { u64 cookie; u64 ino; const char *name; unsigned int name_len; unsigned char d_type; }; struct nfs_cache_array { u64 change_attr; u64 last_cookie; unsigned int size; unsigned char folio_full : 1, folio_is_eof : 1, cookies_are_ordered : 1; struct nfs_cache_array_entry array[] __counted_by(size); }; struct nfs_readdir_descriptor { struct file *file; struct folio *folio; struct dir_context *ctx; pgoff_t folio_index; pgoff_t folio_index_max; u64 dir_cookie; u64 last_cookie; loff_t current_index; __be32 verf[NFS_DIR_VERIFIER_SIZE]; unsigned long dir_verifier; unsigned long timestamp; unsigned long gencount; unsigned long attr_gencount; unsigned int cache_entry_index; unsigned int buffer_fills; unsigned int dtsize; bool clear_cache; bool plus; bool eob; bool eof; }; static void nfs_set_dtsize(struct nfs_readdir_descriptor *desc, unsigned int sz) { struct nfs_server *server = NFS_SERVER(file_inode(desc->file)); unsigned int maxsize = server->dtsize; if (sz > maxsize) sz = maxsize; if (sz < NFS_MIN_FILE_IO_SIZE) sz = NFS_MIN_FILE_IO_SIZE; desc->dtsize = sz; } static void nfs_shrink_dtsize(struct nfs_readdir_descriptor *desc) { nfs_set_dtsize(desc, desc->dtsize >> 1); } static void nfs_grow_dtsize(struct nfs_readdir_descriptor *desc) { nfs_set_dtsize(desc, desc->dtsize << 1); } static void nfs_readdir_folio_init_array(struct folio *folio, u64 last_cookie, u64 change_attr) { struct nfs_cache_array *array; array = kmap_local_folio(folio, 0); array->change_attr = change_attr; array->last_cookie = last_cookie; array->size = 0; array->folio_full = 0; array->folio_is_eof = 0; array->cookies_are_ordered = 1; kunmap_local(array); } /* * we are freeing strings created by nfs_add_to_readdir_array() */ static void nfs_readdir_clear_array(struct folio *folio) { struct nfs_cache_array *array; unsigned int i; array = kmap_local_folio(folio, 0); for (i = 0; i < array->size; i++) kfree(array->array[i].name); array->size = 0; kunmap_local(array); } static void nfs_readdir_folio_reinit_array(struct folio *folio, u64 last_cookie, u64 change_attr) { nfs_readdir_clear_array(folio); nfs_readdir_folio_init_array(folio, last_cookie, change_attr); } static struct folio * nfs_readdir_folio_array_alloc(u64 last_cookie, gfp_t gfp_flags) { struct folio *folio = folio_alloc(gfp_flags, 0); if (folio) nfs_readdir_folio_init_array(folio, last_cookie, 0); return folio; } static void nfs_readdir_folio_array_free(struct folio *folio) { if (folio) { nfs_readdir_clear_array(folio); folio_put(folio); } } static u64 nfs_readdir_array_index_cookie(struct nfs_cache_array *array) { return array->size == 0 ? array->last_cookie : array->array[0].cookie; } static void nfs_readdir_array_set_eof(struct nfs_cache_array *array) { array->folio_is_eof = 1; array->folio_full = 1; } static bool nfs_readdir_array_is_full(struct nfs_cache_array *array) { return array->folio_full; } /* * the caller is responsible for freeing qstr.name * when called by nfs_readdir_add_to_array, the strings will be freed in * nfs_clear_readdir_array() */ static const char *nfs_readdir_copy_name(const char *name, unsigned int len) { const char *ret = kmemdup_nul(name, len, GFP_KERNEL); /* * Avoid a kmemleak false positive. The pointer to the name is stored * in a page cache page which kmemleak does not scan. */ if (ret != NULL) kmemleak_not_leak(ret); return ret; } static size_t nfs_readdir_array_maxentries(void) { return (PAGE_SIZE - sizeof(struct nfs_cache_array)) / sizeof(struct nfs_cache_array_entry); } /* * Check that the next array entry lies entirely within the page bounds */ static int nfs_readdir_array_can_expand(struct nfs_cache_array *array) { if (array->folio_full) return -ENOSPC; if (array->size == nfs_readdir_array_maxentries()) { array->folio_full = 1; return -ENOSPC; } return 0; } static int nfs_readdir_folio_array_append(struct folio *folio, const struct nfs_entry *entry, u64 *cookie) { struct nfs_cache_array *array; struct nfs_cache_array_entry *cache_entry; const char *name; int ret = -ENOMEM; name = nfs_readdir_copy_name(entry->name, entry->len); array = kmap_local_folio(folio, 0); if (!name) goto out; ret = nfs_readdir_array_can_expand(array); if (ret) { kfree(name); goto out; } array->size++; cache_entry = &array->array[array->size - 1]; cache_entry->cookie = array->last_cookie; cache_entry->ino = entry->ino; cache_entry->d_type = entry->d_type; cache_entry->name_len = entry->len; cache_entry->name = name; array->last_cookie = entry->cookie; if (array->last_cookie <= cache_entry->cookie) array->cookies_are_ordered = 0; if (entry->eof != 0) nfs_readdir_array_set_eof(array); out: *cookie = array->last_cookie; kunmap_local(array); return ret; } #define NFS_READDIR_COOKIE_MASK (U32_MAX >> 14) /* * Hash algorithm allowing content addressible access to sequences * of directory cookies. Content is addressed by the value of the * cookie index of the first readdir entry in a page. * * We select only the first 18 bits to avoid issues with excessive * memory use for the page cache XArray. 18 bits should allow the caching * of 262144 pages of sequences of readdir entries. Since each page holds * 127 readdir entries for a typical 64-bit system, that works out to a * cache of ~ 33 million entries per directory. */ static pgoff_t nfs_readdir_folio_cookie_hash(u64 cookie) { if (cookie == 0) return 0; return hash_64(cookie, 18); } static bool nfs_readdir_folio_validate(struct folio *folio, u64 last_cookie, u64 change_attr) { struct nfs_cache_array *array = kmap_local_folio(folio, 0); int ret = true; if (array->change_attr != change_attr) ret = false; if (nfs_readdir_array_index_cookie(array) != last_cookie) ret = false; kunmap_local(array); return ret; } static void nfs_readdir_folio_unlock_and_put(struct folio *folio) { folio_unlock(folio); folio_put(folio); } static void nfs_readdir_folio_init_and_validate(struct folio *folio, u64 cookie, u64 change_attr) { if (folio_test_uptodate(folio)) { if (nfs_readdir_folio_validate(folio, cookie, change_attr)) return; nfs_readdir_clear_array(folio); } nfs_readdir_folio_init_array(folio, cookie, change_attr); folio_mark_uptodate(folio); } static struct folio *nfs_readdir_folio_get_locked(struct address_space *mapping, u64 cookie, u64 change_attr) { pgoff_t index = nfs_readdir_folio_cookie_hash(cookie); struct folio *folio; folio = filemap_grab_folio(mapping, index); if (IS_ERR(folio)) return NULL; nfs_readdir_folio_init_and_validate(folio, cookie, change_attr); return folio; } static u64 nfs_readdir_folio_last_cookie(struct folio *folio) { struct nfs_cache_array *array; u64 ret; array = kmap_local_folio(folio, 0); ret = array->last_cookie; kunmap_local(array); return ret; } static bool nfs_readdir_folio_needs_filling(struct folio *folio) { struct nfs_cache_array *array; bool ret; array = kmap_local_folio(folio, 0); ret = !nfs_readdir_array_is_full(array); kunmap_local(array); return ret; } static void nfs_readdir_folio_set_eof(struct folio *folio) { struct nfs_cache_array *array; array = kmap_local_folio(folio, 0); nfs_readdir_array_set_eof(array); kunmap_local(array); } static struct folio *nfs_readdir_folio_get_next(struct address_space *mapping, u64 cookie, u64 change_attr) { pgoff_t index = nfs_readdir_folio_cookie_hash(cookie); struct folio *folio; folio = __filemap_get_folio(mapping, index, FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) return NULL; nfs_readdir_folio_init_and_validate(folio, cookie, change_attr); if (nfs_readdir_folio_last_cookie(folio) != cookie) nfs_readdir_folio_reinit_array(folio, cookie, change_attr); return folio; } static inline int is_32bit_api(void) { #ifdef CONFIG_COMPAT return in_compat_syscall(); #else return (BITS_PER_LONG == 32); #endif } static bool nfs_readdir_use_cookie(const struct file *filp) { if ((filp->f_mode & FMODE_32BITHASH) || (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api())) return false; return true; } static void nfs_readdir_seek_next_array(struct nfs_cache_array *array, struct nfs_readdir_descriptor *desc) { if (array->folio_full) { desc->last_cookie = array->last_cookie; desc->current_index += array->size; desc->cache_entry_index = 0; desc->folio_index++; } else desc->last_cookie = nfs_readdir_array_index_cookie(array); } static void nfs_readdir_rewind_search(struct nfs_readdir_descriptor *desc) { desc->current_index = 0; desc->last_cookie = 0; desc->folio_index = 0; } static int nfs_readdir_search_for_pos(struct nfs_cache_array *array, struct nfs_readdir_descriptor *desc) { loff_t diff = desc->ctx->pos - desc->current_index; unsigned int index; if (diff < 0) goto out_eof; if (diff >= array->size) { if (array->folio_is_eof) goto out_eof; nfs_readdir_seek_next_array(array, desc); return -EAGAIN; } index = (unsigned int)diff; desc->dir_cookie = array->array[index].cookie; desc->cache_entry_index = index; return 0; out_eof: desc->eof = true; return -EBADCOOKIE; } static bool nfs_readdir_array_cookie_in_range(struct nfs_cache_array *array, u64 cookie) { if (!array->cookies_are_ordered) return true; /* Optimisation for monotonically increasing cookies */ if (cookie >= array->last_cookie) return false; if (array->size && cookie < array->array[0].cookie) return false; return true; } static int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, struct nfs_readdir_descriptor *desc) { unsigned int i; int status = -EAGAIN; if (!nfs_readdir_array_cookie_in_range(array, desc->dir_cookie)) goto check_eof; for (i = 0; i < array->size; i++) { if (array->array[i].cookie == desc->dir_cookie) { if (nfs_readdir_use_cookie(desc->file)) desc->ctx->pos = desc->dir_cookie; else desc->ctx->pos = desc->current_index + i; desc->cache_entry_index = i; return 0; } } check_eof: if (array->folio_is_eof) { status = -EBADCOOKIE; if (desc->dir_cookie == array->last_cookie) desc->eof = true; } else nfs_readdir_seek_next_array(array, desc); return status; } static int nfs_readdir_search_array(struct nfs_readdir_descriptor *desc) { struct nfs_cache_array *array; int status; array = kmap_local_folio(desc->folio, 0); if (desc->dir_cookie == 0) status = nfs_readdir_search_for_pos(array, desc); else status = nfs_readdir_search_for_cookie(array, desc); kunmap_local(array); return status; } /* Fill a page with xdr information before transferring to the cache page */ static int nfs_readdir_xdr_filler(struct nfs_readdir_descriptor *desc, __be32 *verf, u64 cookie, struct page **pages, size_t bufsize, __be32 *verf_res) { struct inode *inode = file_inode(desc->file); struct nfs_readdir_arg arg = { .dentry = file_dentry(desc->file), .cred = desc->file->f_cred, .verf = verf, .cookie = cookie, .pages = pages, .page_len = bufsize, .plus = desc->plus, }; struct nfs_readdir_res res = { .verf = verf_res, }; unsigned long timestamp, gencount; int error; again: timestamp = jiffies; gencount = nfs_inc_attr_generation_counter(); desc->dir_verifier = nfs_save_change_attribute(inode); error = NFS_PROTO(inode)->readdir(&arg, &res); if (error < 0) { /* We requested READDIRPLUS, but the server doesn't grok it */ if (error == -ENOTSUPP && desc->plus) { NFS_SERVER(inode)->caps &= ~NFS_CAP_READDIRPLUS; desc->plus = arg.plus = false; goto again; } goto error; } desc->timestamp = timestamp; desc->gencount = gencount; error: return error; } static int xdr_decode(struct nfs_readdir_descriptor *desc, struct nfs_entry *entry, struct xdr_stream *xdr) { struct inode *inode = file_inode(desc->file); int error; error = NFS_PROTO(inode)->decode_dirent(xdr, entry, desc->plus); if (error) return error; entry->fattr->time_start = desc->timestamp; entry->fattr->gencount = desc->gencount; return 0; } /* Match file and dirent using either filehandle or fileid * Note: caller is responsible for checking the fsid */ static int nfs_same_file(struct dentry *dentry, struct nfs_entry *entry) { struct inode *inode; struct nfs_inode *nfsi; if (d_really_is_negative(dentry)) return 0; inode = d_inode(dentry); if (is_bad_inode(inode) || NFS_STALE(inode)) return 0; nfsi = NFS_I(inode); if (entry->fattr->fileid != nfsi->fileid) return 0; if (entry->fh->size && nfs_compare_fh(entry->fh, &nfsi->fh) != 0) return 0; return 1; } #define NFS_READDIR_CACHE_USAGE_THRESHOLD (8UL) static bool nfs_use_readdirplus(struct inode *dir, struct dir_context *ctx, unsigned int cache_hits, unsigned int cache_misses) { if (!nfs_server_capable(dir, NFS_CAP_READDIRPLUS)) return false; if (NFS_SERVER(dir)->flags & NFS_MOUNT_FORCE_RDIRPLUS) return true; if (ctx->pos == 0 || cache_hits + cache_misses > NFS_READDIR_CACHE_USAGE_THRESHOLD) return true; return false; } /* * This function is called by the getattr code to request the * use of readdirplus to accelerate any future lookups in the same * directory. */ void nfs_readdir_record_entry_cache_hit(struct inode *dir) { struct nfs_inode *nfsi = NFS_I(dir); struct nfs_open_dir_context *ctx; if (nfs_server_capable(dir, NFS_CAP_READDIRPLUS) && S_ISDIR(dir->i_mode)) { rcu_read_lock(); list_for_each_entry_rcu (ctx, &nfsi->open_files, list) atomic_inc(&ctx->cache_hits); rcu_read_unlock(); } } /* * This function is mainly for use by nfs_getattr(). * * If this is an 'ls -l', we want to force use of readdirplus. */ void nfs_readdir_record_entry_cache_miss(struct inode *dir) { struct nfs_inode *nfsi = NFS_I(dir); struct nfs_open_dir_context *ctx; if (nfs_server_capable(dir, NFS_CAP_READDIRPLUS) && S_ISDIR(dir->i_mode)) { rcu_read_lock(); list_for_each_entry_rcu (ctx, &nfsi->open_files, list) atomic_inc(&ctx->cache_misses); rcu_read_unlock(); } } static void nfs_lookup_advise_force_readdirplus(struct inode *dir, unsigned int flags) { if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE)) return; if (flags & (LOOKUP_EXCL | LOOKUP_PARENT | LOOKUP_REVAL)) return; nfs_readdir_record_entry_cache_miss(dir); } static void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry, unsigned long dir_verifier) { struct qstr filename = QSTR_INIT(entry->name, entry->len); DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); struct dentry *dentry; struct dentry *alias; struct inode *inode; int status; if (!(entry->fattr->valid & NFS_ATTR_FATTR_FILEID)) return; if (!(entry->fattr->valid & NFS_ATTR_FATTR_FSID)) return; if (filename.len == 0) return; /* Validate that the name doesn't contain any illegal '\0' */ if (strnlen(filename.name, filename.len) != filename.len) return; /* ...or '/' */ if (strnchr(filename.name, filename.len, '/')) return; if (filename.name[0] == '.') { if (filename.len == 1) return; if (filename.len == 2 && filename.name[1] == '.') return; } filename.hash = full_name_hash(parent, filename.name, filename.len); dentry = d_lookup(parent, &filename); again: if (!dentry) { dentry = d_alloc_parallel(parent, &filename, &wq); if (IS_ERR(dentry)) return; } if (!d_in_lookup(dentry)) { /* Is there a mountpoint here? If so, just exit */ if (!nfs_fsid_equal(&NFS_SB(dentry->d_sb)->fsid, &entry->fattr->fsid)) goto out; if (nfs_same_file(dentry, entry)) { if (!entry->fh->size) goto out; nfs_set_verifier(dentry, dir_verifier); status = nfs_refresh_inode(d_inode(dentry), entry->fattr); if (!status) nfs_setsecurity(d_inode(dentry), entry->fattr); trace_nfs_readdir_lookup_revalidate(d_inode(parent), dentry, 0, status); goto out; } else { trace_nfs_readdir_lookup_revalidate_failed( d_inode(parent), dentry, 0); d_invalidate(dentry); dput(dentry); dentry = NULL; goto again; } } if (!entry->fh->size) { d_lookup_done(dentry); goto out; } inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr); alias = d_splice_alias(inode, dentry); d_lookup_done(dentry); if (alias) { if (IS_ERR(alias)) goto out; dput(dentry); dentry = alias; } nfs_set_verifier(dentry, dir_verifier); trace_nfs_readdir_lookup(d_inode(parent), dentry, 0); out: dput(dentry); } static int nfs_readdir_entry_decode(struct nfs_readdir_descriptor *desc, struct nfs_entry *entry, struct xdr_stream *stream) { int ret; if (entry->fattr->label) entry->fattr->label->len = NFS4_MAXLABELLEN; ret = xdr_decode(desc, entry, stream); if (ret || !desc->plus) return ret; nfs_prime_dcache(file_dentry(desc->file), entry, desc->dir_verifier); return 0; } /* Perform conversion from xdr to cache array */ static int nfs_readdir_folio_filler(struct nfs_readdir_descriptor *desc, struct nfs_entry *entry, struct page **xdr_pages, unsigned int buflen, struct folio **arrays, size_t narrays, u64 change_attr) { struct address_space *mapping = desc->file->f_mapping; struct folio *new, *folio = *arrays; struct xdr_stream stream; struct page *scratch; struct xdr_buf buf; u64 cookie; int status; scratch = alloc_page(GFP_KERNEL); if (scratch == NULL) return -ENOMEM; xdr_init_decode_pages(&stream, &buf, xdr_pages, buflen); xdr_set_scratch_page(&stream, scratch); do { status = nfs_readdir_entry_decode(desc, entry, &stream); if (status != 0) break; status = nfs_readdir_folio_array_append(folio, entry, &cookie); if (status != -ENOSPC) continue; if (folio->mapping != mapping) { if (!--narrays) break; new = nfs_readdir_folio_array_alloc(cookie, GFP_KERNEL); if (!new) break; arrays++; *arrays = folio = new; } else { new = nfs_readdir_folio_get_next(mapping, cookie, change_attr); if (!new) break; if (folio != *arrays) nfs_readdir_folio_unlock_and_put(folio); folio = new; } desc->folio_index_max++; status = nfs_readdir_folio_array_append(folio, entry, &cookie); } while (!status && !entry->eof); switch (status) { case -EBADCOOKIE: if (!entry->eof) break; nfs_readdir_folio_set_eof(folio); fallthrough; case -EAGAIN: status = 0; break; case -ENOSPC: status = 0; if (!desc->plus) break; while (!nfs_readdir_entry_decode(desc, entry, &stream)) ; } if (folio != *arrays) nfs_readdir_folio_unlock_and_put(folio); put_page(scratch); return status; } static void nfs_readdir_free_pages(struct page **pages, size_t npages) { while (npages--) put_page(pages[npages]); kfree(pages); } /* * nfs_readdir_alloc_pages() will allocate pages that must be freed with a call * to nfs_readdir_free_pages() */ static struct page **nfs_readdir_alloc_pages(size_t npages) { struct page **pages; size_t i; pages = kmalloc_array(npages, sizeof(*pages), GFP_KERNEL); if (!pages) return NULL; for (i = 0; i < npages; i++) { struct page *page = alloc_page(GFP_KERNEL); if (page == NULL) goto out_freepages; pages[i] = page; } return pages; out_freepages: nfs_readdir_free_pages(pages, i); return NULL; } static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc, __be32 *verf_arg, __be32 *verf_res, struct folio **arrays, size_t narrays) { u64 change_attr; struct page **pages; struct folio *folio = *arrays; struct nfs_entry *entry; size_t array_size; struct inode *inode = file_inode(desc->file); unsigned int dtsize = desc->dtsize; unsigned int pglen; int status = -ENOMEM; entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return -ENOMEM; entry->cookie = nfs_readdir_folio_last_cookie(folio); entry->fh = nfs_alloc_fhandle(); entry->fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); entry->server = NFS_SERVER(inode); if (entry->fh == NULL || entry->fattr == NULL) goto out; array_size = (dtsize + PAGE_SIZE - 1) >> PAGE_SHIFT; pages = nfs_readdir_alloc_pages(array_size); if (!pages) goto out; change_attr = inode_peek_iversion_raw(inode); status = nfs_readdir_xdr_filler(desc, verf_arg, entry->cookie, pages, dtsize, verf_res); if (status < 0) goto free_pages; pglen = status; if (pglen != 0) status = nfs_readdir_folio_filler(desc, entry, pages, pglen, arrays, narrays, change_attr); else nfs_readdir_folio_set_eof(folio); desc->buffer_fills++; free_pages: nfs_readdir_free_pages(pages, array_size); out: nfs_free_fattr(entry->fattr); nfs_free_fhandle(entry->fh); kfree(entry); return status; } static void nfs_readdir_folio_put(struct nfs_readdir_descriptor *desc) { folio_put(desc->folio); desc->folio = NULL; } static void nfs_readdir_folio_unlock_and_put_cached(struct nfs_readdir_descriptor *desc) { folio_unlock(desc->folio); nfs_readdir_folio_put(desc); } static struct folio * nfs_readdir_folio_get_cached(struct nfs_readdir_descriptor *desc) { struct address_space *mapping = desc->file->f_mapping; u64 change_attr = inode_peek_iversion_raw(mapping->host); u64 cookie = desc->last_cookie; struct folio *folio; folio = nfs_readdir_folio_get_locked(mapping, cookie, change_attr); if (!folio) return NULL; if (desc->clear_cache && !nfs_readdir_folio_needs_filling(folio)) nfs_readdir_folio_reinit_array(folio, cookie, change_attr); return folio; } /* * Returns 0 if desc->dir_cookie was found on page desc->page_index * and locks the page to prevent removal from the page cache. */ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc) { struct inode *inode = file_inode(desc->file); struct nfs_inode *nfsi = NFS_I(inode); __be32 verf[NFS_DIR_VERIFIER_SIZE]; int res; desc->folio = nfs_readdir_folio_get_cached(desc); if (!desc->folio) return -ENOMEM; if (nfs_readdir_folio_needs_filling(desc->folio)) { /* Grow the dtsize if we had to go back for more pages */ if (desc->folio_index == desc->folio_index_max) nfs_grow_dtsize(desc); desc->folio_index_max = desc->folio_index; trace_nfs_readdir_cache_fill(desc->file, nfsi->cookieverf, desc->last_cookie, desc->folio->index, desc->dtsize); res = nfs_readdir_xdr_to_array(desc, nfsi->cookieverf, verf, &desc->folio, 1); if (res < 0) { nfs_readdir_folio_unlock_and_put_cached(desc); trace_nfs_readdir_cache_fill_done(inode, res); if (res == -EBADCOOKIE || res == -ENOTSYNC) { invalidate_inode_pages2(desc->file->f_mapping); nfs_readdir_rewind_search(desc); trace_nfs_readdir_invalidate_cache_range( inode, 0, MAX_LFS_FILESIZE); return -EAGAIN; } return res; } /* * Set the cookie verifier if the page cache was empty */ if (desc->last_cookie == 0 && memcmp(nfsi->cookieverf, verf, sizeof(nfsi->cookieverf))) { memcpy(nfsi->cookieverf, verf, sizeof(nfsi->cookieverf)); invalidate_inode_pages2_range(desc->file->f_mapping, 1, -1); trace_nfs_readdir_invalidate_cache_range( inode, 1, MAX_LFS_FILESIZE); } desc->clear_cache = false; } res = nfs_readdir_search_array(desc); if (res == 0) return 0; nfs_readdir_folio_unlock_and_put_cached(desc); return res; } /* Search for desc->dir_cookie from the beginning of the page cache */ static int readdir_search_pagecache(struct nfs_readdir_descriptor *desc) { int res; do { res = find_and_lock_cache_page(desc); } while (res == -EAGAIN); return res; } #define NFS_READDIR_CACHE_MISS_THRESHOLD (16UL) /* * Once we've found the start of the dirent within a page: fill 'er up... */ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc, const __be32 *verf) { struct file *file = desc->file; struct nfs_cache_array *array; unsigned int i; bool first_emit = !desc->dir_cookie; array = kmap_local_folio(desc->folio, 0); for (i = desc->cache_entry_index; i < array->size; i++) { struct nfs_cache_array_entry *ent; /* * nfs_readdir_handle_cache_misses return force clear at * (cache_misses > NFS_READDIR_CACHE_MISS_THRESHOLD) for * readdir heuristic, NFS_READDIR_CACHE_MISS_THRESHOLD + 1 * entries need be emitted here. */ if (first_emit && i > NFS_READDIR_CACHE_MISS_THRESHOLD + 2) { desc->eob = true; break; } ent = &array->array[i]; if (!dir_emit(desc->ctx, ent->name, ent->name_len, nfs_compat_user_ino64(ent->ino), ent->d_type)) { desc->eob = true; break; } memcpy(desc->verf, verf, sizeof(desc->verf)); if (i == array->size - 1) { desc->dir_cookie = array->last_cookie; nfs_readdir_seek_next_array(array, desc); } else { desc->dir_cookie = array->array[i + 1].cookie; desc->last_cookie = array->array[0].cookie; } if (nfs_readdir_use_cookie(file)) desc->ctx->pos = desc->dir_cookie; else desc->ctx->pos++; } if (array->folio_is_eof) desc->eof = !desc->eob; kunmap_local(array); dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling ended @ cookie %llu\n", (unsigned long long)desc->dir_cookie); } /* * If we cannot find a cookie in our cache, we suspect that this is * because it points to a deleted file, so we ask the server to return * whatever it thinks is the next entry. We then feed this to filldir. * If all goes well, we should then be able to find our way round the * cache on the next call to readdir_search_pagecache(); * * NOTE: we cannot add the anonymous page to the pagecache because * the data it contains might not be page aligned. Besides, * we should already have a complete representation of the * directory in the page cache by the time we get here. */ static int uncached_readdir(struct nfs_readdir_descriptor *desc) { struct folio **arrays; size_t i, sz = 512; __be32 verf[NFS_DIR_VERIFIER_SIZE]; int status = -ENOMEM; dfprintk(DIRCACHE, "NFS: uncached_readdir() searching for cookie %llu\n", (unsigned long long)desc->dir_cookie); arrays = kcalloc(sz, sizeof(*arrays), GFP_KERNEL); if (!arrays) goto out; arrays[0] = nfs_readdir_folio_array_alloc(desc->dir_cookie, GFP_KERNEL); if (!arrays[0]) goto out; desc->folio_index = 0; desc->cache_entry_index = 0; desc->last_cookie = desc->dir_cookie; desc->folio_index_max = 0; trace_nfs_readdir_uncached(desc->file, desc->verf, desc->last_cookie, -1, desc->dtsize); status = nfs_readdir_xdr_to_array(desc, desc->verf, verf, arrays, sz); if (status < 0) { trace_nfs_readdir_uncached_done(file_inode(desc->file), status); goto out_free; } for (i = 0; !desc->eob && i < sz && arrays[i]; i++) { desc->folio = arrays[i]; nfs_do_filldir(desc, verf); } desc->folio = NULL; /* * Grow the dtsize if we have to go back for more pages, * or shrink it if we're reading too many. */ if (!desc->eof) { if (!desc->eob) nfs_grow_dtsize(desc); else if (desc->buffer_fills == 1 && i < (desc->folio_index_max >> 1)) nfs_shrink_dtsize(desc); } out_free: for (i = 0; i < sz && arrays[i]; i++) nfs_readdir_folio_array_free(arrays[i]); out: if (!nfs_readdir_use_cookie(desc->file)) nfs_readdir_rewind_search(desc); desc->folio_index_max = -1; kfree(arrays); dfprintk(DIRCACHE, "NFS: %s: returns %d\n", __func__, status); return status; } static bool nfs_readdir_handle_cache_misses(struct inode *inode, struct nfs_readdir_descriptor *desc, unsigned int cache_misses, bool force_clear) { if (desc->ctx->pos == 0 || !desc->plus) return false; if (cache_misses <= NFS_READDIR_CACHE_MISS_THRESHOLD && !force_clear) return false; trace_nfs_readdir_force_readdirplus(inode); return true; } /* The file offset position represents the dirent entry number. A last cookie cache takes care of the common case of reading the whole directory. */ static int nfs_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dentry = file_dentry(file); struct inode *inode = d_inode(dentry); struct nfs_inode *nfsi = NFS_I(inode); struct nfs_open_dir_context *dir_ctx = file->private_data; struct nfs_readdir_descriptor *desc; unsigned int cache_hits, cache_misses; bool force_clear; int res; dfprintk(FILE, "NFS: readdir(%pD2) starting at cookie %llu\n", file, (long long)ctx->pos); nfs_inc_stats(inode, NFSIOS_VFSGETDENTS); /* * ctx->pos points to the dirent entry number. * *desc->dir_cookie has the cookie for the next entry. We have * to either find the entry with the appropriate number or * revalidate the cookie. */ nfs_revalidate_mapping(inode, file->f_mapping); res = -ENOMEM; desc = kzalloc(sizeof(*desc), GFP_KERNEL); if (!desc) goto out; desc->file = file; desc->ctx = ctx; desc->folio_index_max = -1; spin_lock(&file->f_lock); desc->dir_cookie = dir_ctx->dir_cookie; desc->folio_index = dir_ctx->page_index; desc->last_cookie = dir_ctx->last_cookie; desc->attr_gencount = dir_ctx->attr_gencount; desc->eof = dir_ctx->eof; nfs_set_dtsize(desc, dir_ctx->dtsize); memcpy(desc->verf, dir_ctx->verf, sizeof(desc->verf)); cache_hits = atomic_xchg(&dir_ctx->cache_hits, 0); cache_misses = atomic_xchg(&dir_ctx->cache_misses, 0); force_clear = dir_ctx->force_clear; spin_unlock(&file->f_lock); if (desc->eof) { res = 0; goto out_free; } desc->plus = nfs_use_readdirplus(inode, ctx, cache_hits, cache_misses); force_clear = nfs_readdir_handle_cache_misses(inode, desc, cache_misses, force_clear); desc->clear_cache = force_clear; do { res = readdir_search_pagecache(desc); if (res == -EBADCOOKIE) { res = 0; /* This means either end of directory */ if (desc->dir_cookie && !desc->eof) { /* Or that the server has 'lost' a cookie */ res = uncached_readdir(desc); if (res == 0) continue; if (res == -EBADCOOKIE || res == -ENOTSYNC) res = 0; } break; } if (res == -ETOOSMALL && desc->plus) { nfs_zap_caches(inode); desc->plus = false; desc->eof = false; continue; } if (res < 0) break; nfs_do_filldir(desc, nfsi->cookieverf); nfs_readdir_folio_unlock_and_put_cached(desc); if (desc->folio_index == desc->folio_index_max) desc->clear_cache = force_clear; } while (!desc->eob && !desc->eof); spin_lock(&file->f_lock); dir_ctx->dir_cookie = desc->dir_cookie; dir_ctx->last_cookie = desc->last_cookie; dir_ctx->attr_gencount = desc->attr_gencount; dir_ctx->page_index = desc->folio_index; dir_ctx->force_clear = force_clear; dir_ctx->eof = desc->eof; dir_ctx->dtsize = desc->dtsize; memcpy(dir_ctx->verf, desc->verf, sizeof(dir_ctx->verf)); spin_unlock(&file->f_lock); out_free: kfree(desc); out: dfprintk(FILE, "NFS: readdir(%pD2) returns %d\n", file, res); return res; } static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence) { struct nfs_open_dir_context *dir_ctx = filp->private_data; dfprintk(FILE, "NFS: llseek dir(%pD2, %lld, %d)\n", filp, offset, whence); switch (whence) { default: return -EINVAL; case SEEK_SET: if (offset < 0) return -EINVAL; spin_lock(&filp->f_lock); break; case SEEK_CUR: if (offset == 0) return filp->f_pos; spin_lock(&filp->f_lock); offset += filp->f_pos; if (offset < 0) { spin_unlock(&filp->f_lock); return -EINVAL; } } if (offset != filp->f_pos) { filp->f_pos = offset; dir_ctx->page_index = 0; if (!nfs_readdir_use_cookie(filp)) { dir_ctx->dir_cookie = 0; dir_ctx->last_cookie = 0; } else { dir_ctx->dir_cookie = offset; dir_ctx->last_cookie = offset; } dir_ctx->eof = false; } spin_unlock(&filp->f_lock); return offset; } /* * All directory operations under NFS are synchronous, so fsync() * is a dummy operation. */ static int nfs_fsync_dir(struct file *filp, loff_t start, loff_t end, int datasync) { dfprintk(FILE, "NFS: fsync dir(%pD2) datasync %d\n", filp, datasync); nfs_inc_stats(file_inode(filp), NFSIOS_VFSFSYNC); return 0; } /** * nfs_force_lookup_revalidate - Mark the directory as having changed * @dir: pointer to directory inode * * This forces the revalidation code in nfs_lookup_revalidate() to do a * full lookup on all child dentries of 'dir' whenever a change occurs * on the server that might have invalidated our dcache. * * Note that we reserve bit '0' as a tag to let us know when a dentry * was revalidated while holding a delegation on its inode. * * The caller should be holding dir->i_lock */ void nfs_force_lookup_revalidate(struct inode *dir) { NFS_I(dir)->cache_change_attribute += 2; } EXPORT_SYMBOL_GPL(nfs_force_lookup_revalidate); /** * nfs_verify_change_attribute - Detects NFS remote directory changes * @dir: pointer to parent directory inode * @verf: previously saved change attribute * * Return "false" if the verifiers doesn't match the change attribute. * This would usually indicate that the directory contents have changed on * the server, and that any dentries need revalidating. */ static bool nfs_verify_change_attribute(struct inode *dir, unsigned long verf) { return (verf & ~1UL) == nfs_save_change_attribute(dir); } static void nfs_set_verifier_delegated(unsigned long *verf) { *verf |= 1UL; } #if IS_ENABLED(CONFIG_NFS_V4) static void nfs_unset_verifier_delegated(unsigned long *verf) { *verf &= ~1UL; } #endif /* IS_ENABLED(CONFIG_NFS_V4) */ static bool nfs_test_verifier_delegated(unsigned long verf) { return verf & 1; } static bool nfs_verifier_is_delegated(struct dentry *dentry) { return nfs_test_verifier_delegated(dentry->d_time); } static void nfs_set_verifier_locked(struct dentry *dentry, unsigned long verf) { struct inode *inode = d_inode(dentry); struct inode *dir = d_inode_rcu(dentry->d_parent); if (!dir || !nfs_verify_change_attribute(dir, verf)) return; if (inode && NFS_PROTO(inode)->have_delegation(inode, FMODE_READ, 0)) nfs_set_verifier_delegated(&verf); dentry->d_time = verf; } /** * nfs_set_verifier - save a parent directory verifier in the dentry * @dentry: pointer to dentry * @verf: verifier to save * * Saves the parent directory verifier in @dentry. If the inode has * a delegation, we also tag the dentry as having been revalidated * while holding a delegation so that we know we don't have to * look it up again after a directory change. */ void nfs_set_verifier(struct dentry *dentry, unsigned long verf) { spin_lock(&dentry->d_lock); nfs_set_verifier_locked(dentry, verf); spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL_GPL(nfs_set_verifier); #if IS_ENABLED(CONFIG_NFS_V4) /** * nfs_clear_verifier_delegated - clear the dir verifier delegation tag * @inode: pointer to inode * * Iterates through the dentries in the inode alias list and clears * the tag used to indicate that the dentry has been revalidated * while holding a delegation. * This function is intended for use when the delegation is being * returned or revoked. */ void nfs_clear_verifier_delegated(struct inode *inode) { struct dentry *alias; if (!inode) return; spin_lock(&inode->i_lock); hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { spin_lock(&alias->d_lock); nfs_unset_verifier_delegated(&alias->d_time); spin_unlock(&alias->d_lock); } spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_clear_verifier_delegated); #endif /* IS_ENABLED(CONFIG_NFS_V4) */ static int nfs_dentry_verify_change(struct inode *dir, struct dentry *dentry) { if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE) && d_really_is_negative(dentry)) return dentry->d_time == inode_peek_iversion_raw(dir); return nfs_verify_change_attribute(dir, dentry->d_time); } /* * A check for whether or not the parent directory has changed. * In the case it has, we assume that the dentries are untrustworthy * and may need to be looked up again. * If rcu_walk prevents us from performing a full check, return 0. */ static int nfs_check_verifier(struct inode *dir, struct dentry *dentry, int rcu_walk) { if (IS_ROOT(dentry)) return 1; if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONE) return 0; if (!nfs_dentry_verify_change(dir, dentry)) return 0; /* Revalidate nfsi->cache_change_attribute before we declare a match */ if (nfs_mapping_need_revalidate_inode(dir)) { if (rcu_walk) return 0; if (__nfs_revalidate_inode(NFS_SERVER(dir), dir) < 0) return 0; } if (!nfs_dentry_verify_change(dir, dentry)) return 0; return 1; } /* * Use intent information to check whether or not we're going to do * an O_EXCL create using this path component. */ static int nfs_is_exclusive_create(struct inode *dir, unsigned int flags) { if (NFS_PROTO(dir)->version == 2) return 0; return (flags & (LOOKUP_CREATE | LOOKUP_EXCL)) == (LOOKUP_CREATE | LOOKUP_EXCL); } /* * Inode and filehandle revalidation for lookups. * * We force revalidation in the cases where the VFS sets LOOKUP_REVAL, * or if the intent information indicates that we're about to open this * particular file and the "nocto" mount flag is not set. * */ static int nfs_lookup_verify_inode(struct inode *inode, unsigned int flags) { struct nfs_server *server = NFS_SERVER(inode); int ret; if (IS_AUTOMOUNT(inode)) return 0; if (flags & LOOKUP_OPEN) { switch (inode->i_mode & S_IFMT) { case S_IFREG: /* A NFSv4 OPEN will revalidate later */ if (server->caps & NFS_CAP_ATOMIC_OPEN) goto out; fallthrough; case S_IFDIR: if (server->flags & NFS_MOUNT_NOCTO) break; /* NFS close-to-open cache consistency validation */ goto out_force; } } /* VFS wants an on-the-wire revalidation */ if (flags & LOOKUP_REVAL) goto out_force; out: if (inode->i_nlink > 0 || (inode->i_nlink == 0 && test_bit(NFS_INO_PRESERVE_UNLINKED, &NFS_I(inode)->flags))) return 0; else return -ESTALE; out_force: if (flags & LOOKUP_RCU) return -ECHILD; ret = __nfs_revalidate_inode(server, inode); if (ret != 0) return ret; goto out; } static void nfs_mark_dir_for_revalidate(struct inode *inode) { spin_lock(&inode->i_lock); nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE); spin_unlock(&inode->i_lock); } /* * We judge how long we want to trust negative * dentries by looking at the parent inode mtime. * * If parent mtime has changed, we revalidate, else we wait for a * period corresponding to the parent's attribute cache timeout value. * * If LOOKUP_RCU prevents us from performing a full check, return 1 * suggesting a reval is needed. * * Note that when creating a new file, or looking up a rename target, * then it shouldn't be necessary to revalidate a negative dentry. */ static inline int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry, unsigned int flags) { if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET)) return 0; if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONEG) return 1; /* Case insensitive server? Revalidate negative dentries */ if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE)) return 1; return !nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU); } static int nfs_lookup_revalidate_done(struct inode *dir, struct dentry *dentry, struct inode *inode, int error) { switch (error) { case 1: break; case -ETIMEDOUT: if (inode && (IS_ROOT(dentry) || NFS_SERVER(inode)->flags & NFS_MOUNT_SOFTREVAL)) error = 1; break; case -ESTALE: case -ENOENT: error = 0; fallthrough; default: /* * We can't d_drop the root of a disconnected tree: * its d_hash is on the s_anon list and d_drop() would hide * it from shrink_dcache_for_unmount(), leading to busy * inodes on unmount and further oopses. */ if (inode && IS_ROOT(dentry)) error = 1; break; } trace_nfs_lookup_revalidate_exit(dir, dentry, 0, error); return error; } static int nfs_lookup_revalidate_negative(struct inode *dir, struct dentry *dentry, unsigned int flags) { int ret = 1; if (nfs_neg_need_reval(dir, dentry, flags)) { if (flags & LOOKUP_RCU) return -ECHILD; ret = 0; } return nfs_lookup_revalidate_done(dir, dentry, NULL, ret); } static int nfs_lookup_revalidate_delegated(struct inode *dir, struct dentry *dentry, struct inode *inode) { nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); return nfs_lookup_revalidate_done(dir, dentry, inode, 1); } static int nfs_lookup_revalidate_dentry(struct inode *dir, const struct qstr *name, struct dentry *dentry, struct inode *inode, unsigned int flags) { struct nfs_fh *fhandle; struct nfs_fattr *fattr; unsigned long dir_verifier; int ret; trace_nfs_lookup_revalidate_enter(dir, dentry, flags); ret = -ENOMEM; fhandle = nfs_alloc_fhandle(); fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); if (fhandle == NULL || fattr == NULL) goto out; dir_verifier = nfs_save_change_attribute(dir); ret = NFS_PROTO(dir)->lookup(dir, dentry, name, fhandle, fattr); if (ret < 0) goto out; /* Request help from readdirplus */ nfs_lookup_advise_force_readdirplus(dir, flags); ret = 0; if (nfs_compare_fh(NFS_FH(inode), fhandle)) goto out; if (nfs_refresh_inode(inode, fattr) < 0) goto out; nfs_setsecurity(inode, fattr); nfs_set_verifier(dentry, dir_verifier); ret = 1; out: nfs_free_fattr(fattr); nfs_free_fhandle(fhandle); /* * If the lookup failed despite the dentry change attribute being * a match, then we should revalidate the directory cache. */ if (!ret && nfs_dentry_verify_change(dir, dentry)) nfs_mark_dir_for_revalidate(dir); return nfs_lookup_revalidate_done(dir, dentry, inode, ret); } /* * This is called every time the dcache has a lookup hit, * and we should check whether we can really trust that * lookup. * * NOTE! The hit can be a negative hit too, don't assume * we have an inode! * * If the parent directory is seen to have changed, we throw out the * cached dentry and do a new lookup. */ static int nfs_do_lookup_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { struct inode *inode; int error = 0; nfs_inc_stats(dir, NFSIOS_DENTRYREVALIDATE); inode = d_inode(dentry); if (!inode) return nfs_lookup_revalidate_negative(dir, dentry, flags); if (is_bad_inode(inode)) { dfprintk(LOOKUPCACHE, "%s: %pd2 has dud inode\n", __func__, dentry); goto out_bad; } if ((flags & LOOKUP_RENAME_TARGET) && d_count(dentry) < 2 && nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE)) goto out_bad; if (nfs_verifier_is_delegated(dentry)) return nfs_lookup_revalidate_delegated(dir, dentry, inode); /* Force a full look up iff the parent directory has changed */ if (!(flags & (LOOKUP_EXCL | LOOKUP_REVAL)) && nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU)) { error = nfs_lookup_verify_inode(inode, flags); if (error) { if (error == -ESTALE) nfs_mark_dir_for_revalidate(dir); goto out_bad; } goto out_valid; } if (flags & LOOKUP_RCU) return -ECHILD; if (NFS_STALE(inode)) goto out_bad; return nfs_lookup_revalidate_dentry(dir, name, dentry, inode, flags); out_valid: return nfs_lookup_revalidate_done(dir, dentry, inode, 1); out_bad: if (flags & LOOKUP_RCU) return -ECHILD; return nfs_lookup_revalidate_done(dir, dentry, inode, error); } static int __nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) { if (flags & LOOKUP_RCU) { if (dentry->d_fsdata == NFS_FSDATA_BLOCKED) return -ECHILD; } else { /* Wait for unlink to complete - see unblock_revalidate() */ wait_var_event(&dentry->d_fsdata, smp_load_acquire(&dentry->d_fsdata) != NFS_FSDATA_BLOCKED); } return 0; } static int nfs_lookup_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { if (__nfs_lookup_revalidate(dentry, flags)) return -ECHILD; return nfs_do_lookup_revalidate(dir, name, dentry, flags); } static void block_revalidate(struct dentry *dentry) { /* old devname - just in case */ kfree(dentry->d_fsdata); /* Any new reference that could lead to an open * will take ->d_lock in lookup_open() -> d_lookup(). * Holding this lock ensures we cannot race with * __nfs_lookup_revalidate() and removes and need * for further barriers. */ lockdep_assert_held(&dentry->d_lock); dentry->d_fsdata = NFS_FSDATA_BLOCKED; } static void unblock_revalidate(struct dentry *dentry) { /* store_release ensures wait_var_event() sees the update */ smp_store_release(&dentry->d_fsdata, NULL); wake_up_var(&dentry->d_fsdata); } /* * A weaker form of d_revalidate for revalidating just the d_inode(dentry) * when we don't really care about the dentry name. This is called when a * pathwalk ends on a dentry that was not found via a normal lookup in the * parent dir (e.g.: ".", "..", procfs symlinks or mountpoint traversals). * * In this situation, we just want to verify that the inode itself is OK * since the dentry might have changed on the server. */ static int nfs_weak_revalidate(struct dentry *dentry, unsigned int flags) { struct inode *inode = d_inode(dentry); int error = 0; /* * I believe we can only get a negative dentry here in the case of a * procfs-style symlink. Just assume it's correct for now, but we may * eventually need to do something more here. */ if (!inode) { dfprintk(LOOKUPCACHE, "%s: %pd2 has negative inode\n", __func__, dentry); return 1; } if (is_bad_inode(inode)) { dfprintk(LOOKUPCACHE, "%s: %pd2 has dud inode\n", __func__, dentry); return 0; } error = nfs_lookup_verify_inode(inode, flags); dfprintk(LOOKUPCACHE, "NFS: %s: inode %lu is %s\n", __func__, inode->i_ino, error ? "invalid" : "valid"); return !error; } /* * This is called from dput() when d_count is going to 0. */ static int nfs_dentry_delete(const struct dentry *dentry) { dfprintk(VFS, "NFS: dentry_delete(%pd2, %x)\n", dentry, dentry->d_flags); /* Unhash any dentry with a stale inode */ if (d_really_is_positive(dentry) && NFS_STALE(d_inode(dentry))) return 1; if (dentry->d_flags & DCACHE_NFSFS_RENAMED) { /* Unhash it, so that ->d_iput() would be called */ return 1; } if (!(dentry->d_sb->s_flags & SB_ACTIVE)) { /* Unhash it, so that ancestors of killed async unlink * files will be cleaned up during umount */ return 1; } return 0; } /* Ensure that we revalidate inode->i_nlink */ static void nfs_drop_nlink(struct inode *inode) { spin_lock(&inode->i_lock); /* drop the inode if we're reasonably sure this is the last link */ if (inode->i_nlink > 0) drop_nlink(inode); NFS_I(inode)->attr_gencount = nfs_inc_attr_generation_counter(); nfs_set_cache_invalid( inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME | NFS_INO_INVALID_NLINK); spin_unlock(&inode->i_lock); } /* * Called when the dentry loses inode. * We use it to clean up silly-renamed files. */ static void nfs_dentry_iput(struct dentry *dentry, struct inode *inode) { if (dentry->d_flags & DCACHE_NFSFS_RENAMED) { nfs_complete_unlink(dentry, inode); nfs_drop_nlink(inode); } iput(inode); } static void nfs_d_release(struct dentry *dentry) { /* free cached devname value, if it survived that far */ if (unlikely(dentry->d_fsdata)) { if (dentry->d_flags & DCACHE_NFSFS_RENAMED) WARN_ON(1); else kfree(dentry->d_fsdata); } } const struct dentry_operations nfs_dentry_operations = { .d_revalidate = nfs_lookup_revalidate, .d_weak_revalidate = nfs_weak_revalidate, .d_delete = nfs_dentry_delete, .d_iput = nfs_dentry_iput, .d_automount = nfs_d_automount, .d_release = nfs_d_release, }; EXPORT_SYMBOL_GPL(nfs_dentry_operations); struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) { struct dentry *res; struct inode *inode = NULL; struct nfs_fh *fhandle = NULL; struct nfs_fattr *fattr = NULL; unsigned long dir_verifier; int error; dfprintk(VFS, "NFS: lookup(%pd2)\n", dentry); nfs_inc_stats(dir, NFSIOS_VFSLOOKUP); if (unlikely(dentry->d_name.len > NFS_SERVER(dir)->namelen)) return ERR_PTR(-ENAMETOOLONG); /* * If we're doing an exclusive create, optimize away the lookup * but don't hash the dentry. */ if (nfs_is_exclusive_create(dir, flags) || flags & LOOKUP_RENAME_TARGET) return NULL; res = ERR_PTR(-ENOMEM); fhandle = nfs_alloc_fhandle(); fattr = nfs_alloc_fattr_with_label(NFS_SERVER(dir)); if (fhandle == NULL || fattr == NULL) goto out; dir_verifier = nfs_save_change_attribute(dir); trace_nfs_lookup_enter(dir, dentry, flags); error = NFS_PROTO(dir)->lookup(dir, dentry, &dentry->d_name, fhandle, fattr); if (error == -ENOENT) { if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE)) dir_verifier = inode_peek_iversion_raw(dir); goto no_entry; } if (error < 0) { res = ERR_PTR(error); goto out; } inode = nfs_fhget(dentry->d_sb, fhandle, fattr); res = ERR_CAST(inode); if (IS_ERR(res)) goto out; /* Notify readdir to use READDIRPLUS */ nfs_lookup_advise_force_readdirplus(dir, flags); no_entry: res = d_splice_alias(inode, dentry); if (res != NULL) { if (IS_ERR(res)) goto out; dentry = res; } nfs_set_verifier(dentry, dir_verifier); out: trace_nfs_lookup_exit(dir, dentry, flags, PTR_ERR_OR_ZERO(res)); nfs_free_fattr(fattr); nfs_free_fhandle(fhandle); return res; } EXPORT_SYMBOL_GPL(nfs_lookup); void nfs_d_prune_case_insensitive_aliases(struct inode *inode) { /* Case insensitive server? Revalidate dentries */ if (inode && nfs_server_capable(inode, NFS_CAP_CASE_INSENSITIVE)) d_prune_aliases(inode); } EXPORT_SYMBOL_GPL(nfs_d_prune_case_insensitive_aliases); #if IS_ENABLED(CONFIG_NFS_V4) static int nfs4_lookup_revalidate(struct inode *, const struct qstr *, struct dentry *, unsigned int); const struct dentry_operations nfs4_dentry_operations = { .d_revalidate = nfs4_lookup_revalidate, .d_weak_revalidate = nfs_weak_revalidate, .d_delete = nfs_dentry_delete, .d_iput = nfs_dentry_iput, .d_automount = nfs_d_automount, .d_release = nfs_d_release, }; EXPORT_SYMBOL_GPL(nfs4_dentry_operations); static struct nfs_open_context *create_nfs_open_context(struct dentry *dentry, int open_flags, struct file *filp) { return alloc_nfs_open_context(dentry, flags_to_mode(open_flags), filp); } static int do_open(struct inode *inode, struct file *filp) { nfs_fscache_open_file(inode, filp); return 0; } static int nfs_finish_open(struct nfs_open_context *ctx, struct dentry *dentry, struct file *file, unsigned open_flags) { int err; err = finish_open(file, dentry, do_open); if (err) goto out; if (S_ISREG(file_inode(file)->i_mode)) nfs_file_set_open_context(file, ctx); else err = -EOPENSTALE; out: return err; } int nfs_atomic_open(struct inode *dir, struct dentry *dentry, struct file *file, unsigned open_flags, umode_t mode) { DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); struct nfs_open_context *ctx; struct dentry *res; struct iattr attr = { .ia_valid = ATTR_OPEN }; struct inode *inode; unsigned int lookup_flags = 0; unsigned long dir_verifier; bool switched = false; int created = 0; int err; /* Expect a negative dentry */ BUG_ON(d_inode(dentry)); dfprintk(VFS, "NFS: atomic_open(%s/%lu), %pd\n", dir->i_sb->s_id, dir->i_ino, dentry); err = nfs_check_flags(open_flags); if (err) return err; /* NFS only supports OPEN on regular files */ if ((open_flags & O_DIRECTORY)) { if (!d_in_lookup(dentry)) { /* * Hashed negative dentry with O_DIRECTORY: dentry was * revalidated and is fine, no need to perform lookup * again */ return -ENOENT; } lookup_flags = LOOKUP_OPEN|LOOKUP_DIRECTORY; goto no_open; } if (dentry->d_name.len > NFS_SERVER(dir)->namelen) return -ENAMETOOLONG; if (open_flags & O_CREAT) { struct nfs_server *server = NFS_SERVER(dir); if (!(server->attr_bitmask[2] & FATTR4_WORD2_MODE_UMASK)) mode &= ~current_umask(); attr.ia_valid |= ATTR_MODE; attr.ia_mode = mode; } if (open_flags & O_TRUNC) { attr.ia_valid |= ATTR_SIZE; attr.ia_size = 0; } if (!(open_flags & O_CREAT) && !d_in_lookup(dentry)) { d_drop(dentry); switched = true; dentry = d_alloc_parallel(dentry->d_parent, &dentry->d_name, &wq); if (IS_ERR(dentry)) return PTR_ERR(dentry); if (unlikely(!d_in_lookup(dentry))) return finish_no_open(file, dentry); } ctx = create_nfs_open_context(dentry, open_flags, file); err = PTR_ERR(ctx); if (IS_ERR(ctx)) goto out; trace_nfs_atomic_open_enter(dir, ctx, open_flags); inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr, &created); if (created) file->f_mode |= FMODE_CREATED; if (IS_ERR(inode)) { err = PTR_ERR(inode); trace_nfs_atomic_open_exit(dir, ctx, open_flags, err); put_nfs_open_context(ctx); d_drop(dentry); switch (err) { case -ENOENT: d_splice_alias(NULL, dentry); if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE)) dir_verifier = inode_peek_iversion_raw(dir); else dir_verifier = nfs_save_change_attribute(dir); nfs_set_verifier(dentry, dir_verifier); break; case -EISDIR: case -ENOTDIR: goto no_open; case -ELOOP: if (!(open_flags & O_NOFOLLOW)) goto no_open; break; /* case -EINVAL: */ default: break; } goto out; } file->f_mode |= FMODE_CAN_ODIRECT; err = nfs_finish_open(ctx, ctx->dentry, file, open_flags); trace_nfs_atomic_open_exit(dir, ctx, open_flags, err); put_nfs_open_context(ctx); out: if (unlikely(switched)) { d_lookup_done(dentry); dput(dentry); } return err; no_open: res = nfs_lookup(dir, dentry, lookup_flags); if (!res) { inode = d_inode(dentry); if ((lookup_flags & LOOKUP_DIRECTORY) && inode && !(S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) res = ERR_PTR(-ENOTDIR); else if (inode && S_ISREG(inode->i_mode)) res = ERR_PTR(-EOPENSTALE); } else if (!IS_ERR(res)) { inode = d_inode(res); if ((lookup_flags & LOOKUP_DIRECTORY) && inode && !(S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) { dput(res); res = ERR_PTR(-ENOTDIR); } else if (inode && S_ISREG(inode->i_mode)) { dput(res); res = ERR_PTR(-EOPENSTALE); } } if (switched) { d_lookup_done(dentry); if (!res) res = dentry; else dput(dentry); } if (IS_ERR(res)) return PTR_ERR(res); return finish_no_open(file, res); } EXPORT_SYMBOL_GPL(nfs_atomic_open); static int nfs4_lookup_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { struct inode *inode; if (__nfs_lookup_revalidate(dentry, flags)) return -ECHILD; trace_nfs_lookup_revalidate_enter(dir, dentry, flags); if (!(flags & LOOKUP_OPEN) || (flags & LOOKUP_DIRECTORY)) goto full_reval; if (d_mountpoint(dentry)) goto full_reval; inode = d_inode(dentry); /* We can't create new files in nfs_open_revalidate(), so we * optimize away revalidation of negative dentries. */ if (inode == NULL) goto full_reval; if (nfs_verifier_is_delegated(dentry)) return nfs_lookup_revalidate_delegated(dir, dentry, inode); /* NFS only supports OPEN on regular files */ if (!S_ISREG(inode->i_mode)) goto full_reval; /* We cannot do exclusive creation on a positive dentry */ if (flags & (LOOKUP_EXCL | LOOKUP_REVAL)) goto reval_dentry; /* Check if the directory changed */ if (!nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU)) goto reval_dentry; /* Let f_op->open() actually open (and revalidate) the file */ return 1; reval_dentry: if (flags & LOOKUP_RCU) return -ECHILD; return nfs_lookup_revalidate_dentry(dir, name, dentry, inode, flags); full_reval: return nfs_do_lookup_revalidate(dir, name, dentry, flags); } #endif /* CONFIG_NFSV4 */ int nfs_atomic_open_v23(struct inode *dir, struct dentry *dentry, struct file *file, unsigned int open_flags, umode_t mode) { /* Same as look+open from lookup_open(), but with different O_TRUNC * handling. */ int error = 0; if (dentry->d_name.len > NFS_SERVER(dir)->namelen) return -ENAMETOOLONG; if (open_flags & O_CREAT) { file->f_mode |= FMODE_CREATED; error = nfs_do_create(dir, dentry, mode, open_flags); if (error) return error; return finish_open(file, dentry, NULL); } else if (d_in_lookup(dentry)) { /* The only flags nfs_lookup considers are * LOOKUP_EXCL and LOOKUP_RENAME_TARGET, and * we want those to be zero so the lookup isn't skipped. */ struct dentry *res = nfs_lookup(dir, dentry, 0); d_lookup_done(dentry); if (unlikely(res)) { if (IS_ERR(res)) return PTR_ERR(res); return finish_no_open(file, res); } } return finish_no_open(file, NULL); } EXPORT_SYMBOL_GPL(nfs_atomic_open_v23); struct dentry * nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fhandle, struct nfs_fattr *fattr) { struct dentry *parent = dget_parent(dentry); struct inode *dir = d_inode(parent); struct inode *inode; struct dentry *d; int error; d_drop(dentry); if (fhandle->size == 0) { error = NFS_PROTO(dir)->lookup(dir, dentry, &dentry->d_name, fhandle, fattr); if (error) goto out_error; } nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); if (!(fattr->valid & NFS_ATTR_FATTR)) { struct nfs_server *server = NFS_SB(dentry->d_sb); error = server->nfs_client->rpc_ops->getattr(server, fhandle, fattr, NULL); if (error < 0) goto out_error; } inode = nfs_fhget(dentry->d_sb, fhandle, fattr); d = d_splice_alias(inode, dentry); out: dput(parent); return d; out_error: d = ERR_PTR(error); goto out; } EXPORT_SYMBOL_GPL(nfs_add_or_obtain); /* * Code common to create, mkdir, and mknod. */ int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle, struct nfs_fattr *fattr) { struct dentry *d; d = nfs_add_or_obtain(dentry, fhandle, fattr); if (IS_ERR(d)) return PTR_ERR(d); /* Callers don't care */ dput(d); return 0; } EXPORT_SYMBOL_GPL(nfs_instantiate); /* * Following a failed create operation, we drop the dentry rather * than retain a negative dentry. This avoids a problem in the event * that the operation succeeded on the server, but an error in the * reply path made it appear to have failed. */ static int nfs_do_create(struct inode *dir, struct dentry *dentry, umode_t mode, int open_flags) { struct iattr attr; int error; open_flags |= O_CREAT; dfprintk(VFS, "NFS: create(%s/%lu), %pd\n", dir->i_sb->s_id, dir->i_ino, dentry); attr.ia_mode = mode; attr.ia_valid = ATTR_MODE; if (open_flags & O_TRUNC) { attr.ia_size = 0; attr.ia_valid |= ATTR_SIZE; } trace_nfs_create_enter(dir, dentry, open_flags); error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags); trace_nfs_create_exit(dir, dentry, open_flags, error); if (error != 0) goto out_err; return 0; out_err: d_drop(dentry); return error; } int nfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { return nfs_do_create(dir, dentry, mode, excl ? O_EXCL : 0); } EXPORT_SYMBOL_GPL(nfs_create); /* * See comments for nfs_proc_create regarding failed operations. */ int nfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { struct iattr attr; int status; dfprintk(VFS, "NFS: mknod(%s/%lu), %pd\n", dir->i_sb->s_id, dir->i_ino, dentry); attr.ia_mode = mode; attr.ia_valid = ATTR_MODE; trace_nfs_mknod_enter(dir, dentry); status = NFS_PROTO(dir)->mknod(dir, dentry, &attr, rdev); trace_nfs_mknod_exit(dir, dentry, status); if (status != 0) goto out_err; return 0; out_err: d_drop(dentry); return status; } EXPORT_SYMBOL_GPL(nfs_mknod); /* * See comments for nfs_proc_create regarding failed operations. */ struct dentry *nfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct iattr attr; struct dentry *ret; dfprintk(VFS, "NFS: mkdir(%s/%lu), %pd\n", dir->i_sb->s_id, dir->i_ino, dentry); attr.ia_valid = ATTR_MODE; attr.ia_mode = mode | S_IFDIR; trace_nfs_mkdir_enter(dir, dentry); ret = NFS_PROTO(dir)->mkdir(dir, dentry, &attr); trace_nfs_mkdir_exit(dir, dentry, PTR_ERR_OR_ZERO(ret)); return ret; } EXPORT_SYMBOL_GPL(nfs_mkdir); static void nfs_dentry_handle_enoent(struct dentry *dentry) { if (simple_positive(dentry)) d_delete(dentry); } static void nfs_dentry_remove_handle_error(struct inode *dir, struct dentry *dentry, int error) { switch (error) { case -ENOENT: if (d_really_is_positive(dentry)) d_delete(dentry); nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); break; case 0: nfs_d_prune_case_insensitive_aliases(d_inode(dentry)); nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); } } int nfs_rmdir(struct inode *dir, struct dentry *dentry) { int error; dfprintk(VFS, "NFS: rmdir(%s/%lu), %pd\n", dir->i_sb->s_id, dir->i_ino, dentry); trace_nfs_rmdir_enter(dir, dentry); if (d_really_is_positive(dentry)) { down_write(&NFS_I(d_inode(dentry))->rmdir_sem); error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name); /* Ensure the VFS deletes this inode */ switch (error) { case 0: clear_nlink(d_inode(dentry)); break; case -ENOENT: nfs_dentry_handle_enoent(dentry); } up_write(&NFS_I(d_inode(dentry))->rmdir_sem); } else error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name); nfs_dentry_remove_handle_error(dir, dentry, error); trace_nfs_rmdir_exit(dir, dentry, error); return error; } EXPORT_SYMBOL_GPL(nfs_rmdir); /* * Remove a file after making sure there are no pending writes, * and after checking that the file has only one user. * * We invalidate the attribute cache and free the inode prior to the operation * to avoid possible races if the server reuses the inode. */ static int nfs_safe_remove(struct dentry *dentry) { struct inode *dir = d_inode(dentry->d_parent); struct inode *inode = d_inode(dentry); int error = -EBUSY; dfprintk(VFS, "NFS: safe_remove(%pd2)\n", dentry); /* If the dentry was sillyrenamed, we simply call d_delete() */ if (dentry->d_flags & DCACHE_NFSFS_RENAMED) { error = 0; goto out; } trace_nfs_remove_enter(dir, dentry); if (inode != NULL) { error = NFS_PROTO(dir)->remove(dir, dentry); if (error == 0) nfs_drop_nlink(inode); } else error = NFS_PROTO(dir)->remove(dir, dentry); if (error == -ENOENT) nfs_dentry_handle_enoent(dentry); trace_nfs_remove_exit(dir, dentry, error); out: return error; } /* We do silly rename. In case sillyrename() returns -EBUSY, the inode * belongs to an active ".nfs..." file and we return -EBUSY. * * If sillyrename() returns 0, we do nothing, otherwise we unlink. */ int nfs_unlink(struct inode *dir, struct dentry *dentry) { int error; dfprintk(VFS, "NFS: unlink(%s/%lu, %pd)\n", dir->i_sb->s_id, dir->i_ino, dentry); trace_nfs_unlink_enter(dir, dentry); spin_lock(&dentry->d_lock); if (d_count(dentry) > 1 && !test_bit(NFS_INO_PRESERVE_UNLINKED, &NFS_I(d_inode(dentry))->flags)) { spin_unlock(&dentry->d_lock); /* Start asynchronous writeout of the inode */ write_inode_now(d_inode(dentry), 0); error = nfs_sillyrename(dir, dentry); goto out; } /* We must prevent any concurrent open until the unlink * completes. ->d_revalidate will wait for ->d_fsdata * to clear. We set it here to ensure no lookup succeeds until * the unlink is complete on the server. */ error = -ETXTBSY; if (WARN_ON(dentry->d_flags & DCACHE_NFSFS_RENAMED) || WARN_ON(dentry->d_fsdata == NFS_FSDATA_BLOCKED)) { spin_unlock(&dentry->d_lock); goto out; } block_revalidate(dentry); spin_unlock(&dentry->d_lock); error = nfs_safe_remove(dentry); nfs_dentry_remove_handle_error(dir, dentry, error); unblock_revalidate(dentry); out: trace_nfs_unlink_exit(dir, dentry, error); return error; } EXPORT_SYMBOL_GPL(nfs_unlink); /* * To create a symbolic link, most file systems instantiate a new inode, * add a page to it containing the path, then write it out to the disk * using prepare_write/commit_write. * * Unfortunately the NFS client can't create the in-core inode first * because it needs a file handle to create an in-core inode (see * fs/nfs/inode.c:nfs_fhget). We only have a file handle *after* the * symlink request has completed on the server. * * So instead we allocate a raw page, copy the symname into it, then do * the SYMLINK request with the page as the buffer. If it succeeds, we * now have a new file handle and can instantiate an in-core NFS inode * and move the raw page into its mapping. */ int nfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { struct folio *folio; char *kaddr; struct iattr attr; unsigned int pathlen = strlen(symname); int error; dfprintk(VFS, "NFS: symlink(%s/%lu, %pd, %s)\n", dir->i_sb->s_id, dir->i_ino, dentry, symname); if (pathlen > PAGE_SIZE) return -ENAMETOOLONG; attr.ia_mode = S_IFLNK | S_IRWXUGO; attr.ia_valid = ATTR_MODE; folio = folio_alloc(GFP_USER, 0); if (!folio) return -ENOMEM; kaddr = folio_address(folio); memcpy(kaddr, symname, pathlen); if (pathlen < PAGE_SIZE) memset(kaddr + pathlen, 0, PAGE_SIZE - pathlen); trace_nfs_symlink_enter(dir, dentry); error = NFS_PROTO(dir)->symlink(dir, dentry, folio, pathlen, &attr); trace_nfs_symlink_exit(dir, dentry, error); if (error != 0) { dfprintk(VFS, "NFS: symlink(%s/%lu, %pd, %s) error %d\n", dir->i_sb->s_id, dir->i_ino, dentry, symname, error); d_drop(dentry); folio_put(folio); return error; } nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); /* * No big deal if we can't add this page to the page cache here. * READLINK will get the missing page from the server if needed. */ if (filemap_add_folio(d_inode(dentry)->i_mapping, folio, 0, GFP_KERNEL) == 0) { folio_mark_uptodate(folio); folio_unlock(folio); } folio_put(folio); return 0; } EXPORT_SYMBOL_GPL(nfs_symlink); int nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(old_dentry); int error; dfprintk(VFS, "NFS: link(%pd2 -> %pd2)\n", old_dentry, dentry); trace_nfs_link_enter(inode, dir, dentry); d_drop(dentry); if (S_ISREG(inode->i_mode)) nfs_sync_inode(inode); error = NFS_PROTO(dir)->link(inode, dir, &dentry->d_name); if (error == 0) { nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); ihold(inode); d_add(dentry, inode); } trace_nfs_link_exit(inode, dir, dentry, error); return error; } EXPORT_SYMBOL_GPL(nfs_link); static void nfs_unblock_rename(struct rpc_task *task, struct nfs_renamedata *data) { struct dentry *new_dentry = data->new_dentry; unblock_revalidate(new_dentry); } /* * RENAME * FIXME: Some nfsds, like the Linux user space nfsd, may generate a * different file handle for the same inode after a rename (e.g. when * moving to a different directory). A fail-safe method to do so would * be to look up old_dir/old_name, create a link to new_dir/new_name and * rename the old file using the sillyrename stuff. This way, the original * file in old_dir will go away when the last process iput()s the inode. * * FIXED. * * It actually works quite well. One needs to have the possibility for * at least one ".nfs..." file in each directory the file ever gets * moved or linked to which happens automagically with the new * implementation that only depends on the dcache stuff instead of * using the inode layer * * Unfortunately, things are a little more complicated than indicated * above. For a cross-directory move, we want to make sure we can get * rid of the old inode after the operation. This means there must be * no pending writes (if it's a file), and the use count must be 1. * If these conditions are met, we can drop the dentries before doing * the rename. */ int nfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { struct inode *old_inode = d_inode(old_dentry); struct inode *new_inode = d_inode(new_dentry); struct dentry *dentry = NULL; struct rpc_task *task; bool must_unblock = false; int error = -EBUSY; if (flags) return -EINVAL; dfprintk(VFS, "NFS: rename(%pd2 -> %pd2, ct=%d)\n", old_dentry, new_dentry, d_count(new_dentry)); trace_nfs_rename_enter(old_dir, old_dentry, new_dir, new_dentry); /* * For non-directories, check whether the target is busy and if so, * make a copy of the dentry and then do a silly-rename. If the * silly-rename succeeds, the copied dentry is hashed and becomes * the new target. */ if (new_inode && !S_ISDIR(new_inode->i_mode)) { /* We must prevent any concurrent open until the unlink * completes. ->d_revalidate will wait for ->d_fsdata * to clear. We set it here to ensure no lookup succeeds until * the unlink is complete on the server. */ error = -ETXTBSY; if (WARN_ON(new_dentry->d_flags & DCACHE_NFSFS_RENAMED) || WARN_ON(new_dentry->d_fsdata == NFS_FSDATA_BLOCKED)) goto out; spin_lock(&new_dentry->d_lock); if (d_count(new_dentry) > 2) { int err; spin_unlock(&new_dentry->d_lock); /* copy the target dentry's name */ dentry = d_alloc(new_dentry->d_parent, &new_dentry->d_name); if (!dentry) goto out; /* silly-rename the existing target ... */ err = nfs_sillyrename(new_dir, new_dentry); if (err) goto out; new_dentry = dentry; new_inode = NULL; } else { block_revalidate(new_dentry); must_unblock = true; spin_unlock(&new_dentry->d_lock); } } if (S_ISREG(old_inode->i_mode)) nfs_sync_inode(old_inode); task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry, must_unblock ? nfs_unblock_rename : NULL); if (IS_ERR(task)) { if (must_unblock) unblock_revalidate(new_dentry); error = PTR_ERR(task); goto out; } error = rpc_wait_for_completion_task(task); if (error != 0) { ((struct nfs_renamedata *)task->tk_calldata)->cancelled = 1; /* Paired with the atomic_dec_and_test() barrier in rpc_do_put_task() */ smp_wmb(); } else error = task->tk_status; rpc_put_task(task); /* Ensure the inode attributes are revalidated */ if (error == 0) { spin_lock(&old_inode->i_lock); NFS_I(old_inode)->attr_gencount = nfs_inc_attr_generation_counter(); nfs_set_cache_invalid(old_inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME | NFS_INO_REVAL_FORCED); spin_unlock(&old_inode->i_lock); } out: trace_nfs_rename_exit(old_dir, old_dentry, new_dir, new_dentry, error); if (!error) { if (new_inode != NULL) nfs_drop_nlink(new_inode); /* * The d_move() should be here instead of in an async RPC completion * handler because we need the proper locks to move the dentry. If * we're interrupted by a signal, the async RPC completion handler * should mark the directories for revalidation. */ d_move(old_dentry, new_dentry); nfs_set_verifier(old_dentry, nfs_save_change_attribute(new_dir)); } else if (error == -ENOENT) nfs_dentry_handle_enoent(old_dentry); /* new dentry created? */ if (dentry) dput(dentry); return error; } EXPORT_SYMBOL_GPL(nfs_rename); static DEFINE_SPINLOCK(nfs_access_lru_lock); static LIST_HEAD(nfs_access_lru_list); static atomic_long_t nfs_access_nr_entries; static unsigned long nfs_access_max_cachesize = 4*1024*1024; module_param(nfs_access_max_cachesize, ulong, 0644); MODULE_PARM_DESC(nfs_access_max_cachesize, "NFS access maximum total cache length"); static void nfs_access_free_entry(struct nfs_access_entry *entry) { put_group_info(entry->group_info); kfree_rcu(entry, rcu_head); smp_mb__before_atomic(); atomic_long_dec(&nfs_access_nr_entries); smp_mb__after_atomic(); } static void nfs_access_free_list(struct list_head *head) { struct nfs_access_entry *cache; while (!list_empty(head)) { cache = list_entry(head->next, struct nfs_access_entry, lru); list_del(&cache->lru); nfs_access_free_entry(cache); } } static unsigned long nfs_do_access_cache_scan(unsigned int nr_to_scan) { LIST_HEAD(head); struct nfs_inode *nfsi, *next; struct nfs_access_entry *cache; long freed = 0; spin_lock(&nfs_access_lru_lock); list_for_each_entry_safe(nfsi, next, &nfs_access_lru_list, access_cache_inode_lru) { struct inode *inode; if (nr_to_scan-- == 0) break; inode = &nfsi->vfs_inode; spin_lock(&inode->i_lock); if (list_empty(&nfsi->access_cache_entry_lru)) goto remove_lru_entry; cache = list_entry(nfsi->access_cache_entry_lru.next, struct nfs_access_entry, lru); list_move(&cache->lru, &head); rb_erase(&cache->rb_node, &nfsi->access_cache); freed++; if (!list_empty(&nfsi->access_cache_entry_lru)) list_move_tail(&nfsi->access_cache_inode_lru, &nfs_access_lru_list); else { remove_lru_entry: list_del_init(&nfsi->access_cache_inode_lru); smp_mb__before_atomic(); clear_bit(NFS_INO_ACL_LRU_SET, &nfsi->flags); smp_mb__after_atomic(); } spin_unlock(&inode->i_lock); } spin_unlock(&nfs_access_lru_lock); nfs_access_free_list(&head); return freed; } unsigned long nfs_access_cache_scan(struct shrinker *shrink, struct shrink_control *sc) { int nr_to_scan = sc->nr_to_scan; gfp_t gfp_mask = sc->gfp_mask; if ((gfp_mask & GFP_KERNEL) != GFP_KERNEL) return SHRINK_STOP; return nfs_do_access_cache_scan(nr_to_scan); } unsigned long nfs_access_cache_count(struct shrinker *shrink, struct shrink_control *sc) { return vfs_pressure_ratio(atomic_long_read(&nfs_access_nr_entries)); } static void nfs_access_cache_enforce_limit(void) { long nr_entries = atomic_long_read(&nfs_access_nr_entries); unsigned long diff; unsigned int nr_to_scan; if (nr_entries < 0 || nr_entries <= nfs_access_max_cachesize) return; nr_to_scan = 100; diff = nr_entries - nfs_access_max_cachesize; if (diff < nr_to_scan) nr_to_scan = diff; nfs_do_access_cache_scan(nr_to_scan); } static void __nfs_access_zap_cache(struct nfs_inode *nfsi, struct list_head *head) { struct rb_root *root_node = &nfsi->access_cache; struct rb_node *n; struct nfs_access_entry *entry; /* Unhook entries from the cache */ while ((n = rb_first(root_node)) != NULL) { entry = rb_entry(n, struct nfs_access_entry, rb_node); rb_erase(n, root_node); list_move(&entry->lru, head); } nfsi->cache_validity &= ~NFS_INO_INVALID_ACCESS; } void nfs_access_zap_cache(struct inode *inode) { LIST_HEAD(head); if (test_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags) == 0) return; /* Remove from global LRU init */ spin_lock(&nfs_access_lru_lock); if (test_and_clear_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags)) list_del_init(&NFS_I(inode)->access_cache_inode_lru); spin_lock(&inode->i_lock); __nfs_access_zap_cache(NFS_I(inode), &head); spin_unlock(&inode->i_lock); spin_unlock(&nfs_access_lru_lock); nfs_access_free_list(&head); } EXPORT_SYMBOL_GPL(nfs_access_zap_cache); static int access_cmp(const struct cred *a, const struct nfs_access_entry *b) { struct group_info *ga, *gb; int g; if (uid_lt(a->fsuid, b->fsuid)) return -1; if (uid_gt(a->fsuid, b->fsuid)) return 1; if (gid_lt(a->fsgid, b->fsgid)) return -1; if (gid_gt(a->fsgid, b->fsgid)) return 1; ga = a->group_info; gb = b->group_info; if (ga == gb) return 0; if (ga == NULL) return -1; if (gb == NULL) return 1; if (ga->ngroups < gb->ngroups) return -1; if (ga->ngroups > gb->ngroups) return 1; for (g = 0; g < ga->ngroups; g++) { if (gid_lt(ga->gid[g], gb->gid[g])) return -1; if (gid_gt(ga->gid[g], gb->gid[g])) return 1; } return 0; } static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, const struct cred *cred) { struct rb_node *n = NFS_I(inode)->access_cache.rb_node; while (n != NULL) { struct nfs_access_entry *entry = rb_entry(n, struct nfs_access_entry, rb_node); int cmp = access_cmp(cred, entry); if (cmp < 0) n = n->rb_left; else if (cmp > 0) n = n->rb_right; else return entry; } return NULL; } static u64 nfs_access_login_time(const struct task_struct *task, const struct cred *cred) { const struct task_struct *parent; const struct cred *pcred; u64 ret; rcu_read_lock(); for (;;) { parent = rcu_dereference(task->real_parent); pcred = __task_cred(parent); if (parent == task || cred_fscmp(pcred, cred) != 0) break; task = parent; } ret = task->start_time; rcu_read_unlock(); return ret; } static int nfs_access_get_cached_locked(struct inode *inode, const struct cred *cred, u32 *mask, bool may_block) { struct nfs_inode *nfsi = NFS_I(inode); u64 login_time = nfs_access_login_time(current, cred); struct nfs_access_entry *cache; bool retry = true; int err; spin_lock(&inode->i_lock); for(;;) { if (nfsi->cache_validity & NFS_INO_INVALID_ACCESS) goto out_zap; cache = nfs_access_search_rbtree(inode, cred); err = -ENOENT; if (cache == NULL) goto out; /* Found an entry, is our attribute cache valid? */ if (!nfs_check_cache_invalid(inode, NFS_INO_INVALID_ACCESS)) break; if (!retry) break; err = -ECHILD; if (!may_block) goto out; spin_unlock(&inode->i_lock); err = __nfs_revalidate_inode(NFS_SERVER(inode), inode); if (err) return err; spin_lock(&inode->i_lock); retry = false; } err = -ENOENT; if ((s64)(login_time - cache->timestamp) > 0) goto out; *mask = cache->mask; list_move_tail(&cache->lru, &nfsi->access_cache_entry_lru); err = 0; out: spin_unlock(&inode->i_lock); return err; out_zap: spin_unlock(&inode->i_lock); nfs_access_zap_cache(inode); return -ENOENT; } static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cred, u32 *mask) { /* Only check the most recently returned cache entry, * but do it without locking. */ struct nfs_inode *nfsi = NFS_I(inode); u64 login_time = nfs_access_login_time(current, cred); struct nfs_access_entry *cache; int err = -ECHILD; struct list_head *lh; rcu_read_lock(); if (nfsi->cache_validity & NFS_INO_INVALID_ACCESS) goto out; lh = rcu_dereference(list_tail_rcu(&nfsi->access_cache_entry_lru)); cache = list_entry(lh, struct nfs_access_entry, lru); if (lh == &nfsi->access_cache_entry_lru || access_cmp(cred, cache) != 0) cache = NULL; if (cache == NULL) goto out; if ((s64)(login_time - cache->timestamp) > 0) goto out; if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_ACCESS)) goto out; *mask = cache->mask; err = 0; out: rcu_read_unlock(); return err; } int nfs_access_get_cached(struct inode *inode, const struct cred *cred, u32 *mask, bool may_block) { int status; status = nfs_access_get_cached_rcu(inode, cred, mask); if (status != 0) status = nfs_access_get_cached_locked(inode, cred, mask, may_block); return status; } EXPORT_SYMBOL_GPL(nfs_access_get_cached); static void nfs_access_add_rbtree(struct inode *inode, struct nfs_access_entry *set, const struct cred *cred) { struct nfs_inode *nfsi = NFS_I(inode); struct rb_root *root_node = &nfsi->access_cache; struct rb_node **p = &root_node->rb_node; struct rb_node *parent = NULL; struct nfs_access_entry *entry; int cmp; spin_lock(&inode->i_lock); while (*p != NULL) { parent = *p; entry = rb_entry(parent, struct nfs_access_entry, rb_node); cmp = access_cmp(cred, entry); if (cmp < 0) p = &parent->rb_left; else if (cmp > 0) p = &parent->rb_right; else goto found; } rb_link_node(&set->rb_node, parent, p); rb_insert_color(&set->rb_node, root_node); list_add_tail(&set->lru, &nfsi->access_cache_entry_lru); spin_unlock(&inode->i_lock); return; found: rb_replace_node(parent, &set->rb_node, root_node); list_add_tail(&set->lru, &nfsi->access_cache_entry_lru); list_del(&entry->lru); spin_unlock(&inode->i_lock); nfs_access_free_entry(entry); } void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set, const struct cred *cred) { struct nfs_access_entry *cache = kmalloc(sizeof(*cache), GFP_KERNEL); if (cache == NULL) return; RB_CLEAR_NODE(&cache->rb_node); cache->fsuid = cred->fsuid; cache->fsgid = cred->fsgid; cache->group_info = get_group_info(cred->group_info); cache->mask = set->mask; cache->timestamp = ktime_get_ns(); /* The above field assignments must be visible * before this item appears on the lru. We cannot easily * use rcu_assign_pointer, so just force the memory barrier. */ smp_wmb(); nfs_access_add_rbtree(inode, cache, cred); /* Update accounting */ smp_mb__before_atomic(); atomic_long_inc(&nfs_access_nr_entries); smp_mb__after_atomic(); /* Add inode to global LRU list */ if (!test_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags)) { spin_lock(&nfs_access_lru_lock); if (!test_and_set_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags)) list_add_tail(&NFS_I(inode)->access_cache_inode_lru, &nfs_access_lru_list); spin_unlock(&nfs_access_lru_lock); } nfs_access_cache_enforce_limit(); } EXPORT_SYMBOL_GPL(nfs_access_add_cache); #define NFS_MAY_READ (NFS_ACCESS_READ) #define NFS_MAY_WRITE (NFS_ACCESS_MODIFY | \ NFS_ACCESS_EXTEND | \ NFS_ACCESS_DELETE) #define NFS_FILE_MAY_WRITE (NFS_ACCESS_MODIFY | \ NFS_ACCESS_EXTEND) #define NFS_DIR_MAY_WRITE NFS_MAY_WRITE #define NFS_MAY_LOOKUP (NFS_ACCESS_LOOKUP) #define NFS_MAY_EXECUTE (NFS_ACCESS_EXECUTE) static int nfs_access_calc_mask(u32 access_result, umode_t umode) { int mask = 0; if (access_result & NFS_MAY_READ) mask |= MAY_READ; if (S_ISDIR(umode)) { if ((access_result & NFS_DIR_MAY_WRITE) == NFS_DIR_MAY_WRITE) mask |= MAY_WRITE; if ((access_result & NFS_MAY_LOOKUP) == NFS_MAY_LOOKUP) mask |= MAY_EXEC; } else if (S_ISREG(umode)) { if ((access_result & NFS_FILE_MAY_WRITE) == NFS_FILE_MAY_WRITE) mask |= MAY_WRITE; if ((access_result & NFS_MAY_EXECUTE) == NFS_MAY_EXECUTE) mask |= MAY_EXEC; } else if (access_result & NFS_MAY_WRITE) mask |= MAY_WRITE; return mask; } void nfs_access_set_mask(struct nfs_access_entry *entry, u32 access_result) { entry->mask = access_result; } EXPORT_SYMBOL_GPL(nfs_access_set_mask); static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask) { struct nfs_access_entry cache; bool may_block = (mask & MAY_NOT_BLOCK) == 0; int cache_mask = -1; int status; trace_nfs_access_enter(inode); status = nfs_access_get_cached(inode, cred, &cache.mask, may_block); if (status == 0) goto out_cached; status = -ECHILD; if (!may_block) goto out; /* * Determine which access bits we want to ask for... */ cache.mask = NFS_ACCESS_READ | NFS_ACCESS_MODIFY | NFS_ACCESS_EXTEND | nfs_access_xattr_mask(NFS_SERVER(inode)); if (S_ISDIR(inode->i_mode)) cache.mask |= NFS_ACCESS_DELETE | NFS_ACCESS_LOOKUP; else cache.mask |= NFS_ACCESS_EXECUTE; status = NFS_PROTO(inode)->access(inode, &cache, cred); if (status != 0) { if (status == -ESTALE) { if (!S_ISDIR(inode->i_mode)) nfs_set_inode_stale(inode); else nfs_zap_caches(inode); } goto out; } nfs_access_add_cache(inode, &cache, cred); out_cached: cache_mask = nfs_access_calc_mask(cache.mask, inode->i_mode); if ((mask & ~cache_mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) != 0) status = -EACCES; out: trace_nfs_access_exit(inode, mask, cache_mask, status); return status; } static int nfs_open_permission_mask(int openflags) { int mask = 0; if (openflags & __FMODE_EXEC) { /* ONLY check exec rights */ mask = MAY_EXEC; } else { if ((openflags & O_ACCMODE) != O_WRONLY) mask |= MAY_READ; if ((openflags & O_ACCMODE) != O_RDONLY) mask |= MAY_WRITE; } return mask; } int nfs_may_open(struct inode *inode, const struct cred *cred, int openflags) { return nfs_do_access(inode, cred, nfs_open_permission_mask(openflags)); } EXPORT_SYMBOL_GPL(nfs_may_open); static int nfs_execute_ok(struct inode *inode, int mask) { struct nfs_server *server = NFS_SERVER(inode); int ret = 0; if (S_ISDIR(inode->i_mode)) return 0; if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_MODE)) { if (mask & MAY_NOT_BLOCK) return -ECHILD; ret = __nfs_revalidate_inode(server, inode); } if (ret == 0 && !execute_ok(inode)) ret = -EACCES; return ret; } int nfs_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { const struct cred *cred = current_cred(); int res = 0; nfs_inc_stats(inode, NFSIOS_VFSACCESS); if ((mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0) goto out; /* Is this sys_access() ? */ if (mask & (MAY_ACCESS | MAY_CHDIR)) goto force_lookup; switch (inode->i_mode & S_IFMT) { case S_IFLNK: goto out; case S_IFREG: if ((mask & MAY_OPEN) && nfs_server_capable(inode, NFS_CAP_ATOMIC_OPEN)) return 0; break; case S_IFDIR: /* * Optimize away all write operations, since the server * will check permissions when we perform the op. */ if ((mask & MAY_WRITE) && !(mask & MAY_READ)) goto out; } force_lookup: if (!NFS_PROTO(inode)->access) goto out_notsup; res = nfs_do_access(inode, cred, mask); out: if (!res && (mask & MAY_EXEC)) res = nfs_execute_ok(inode, mask); dfprintk(VFS, "NFS: permission(%s/%lu), mask=0x%x, res=%d\n", inode->i_sb->s_id, inode->i_ino, mask, res); return res; out_notsup: if (mask & MAY_NOT_BLOCK) return -ECHILD; res = nfs_revalidate_inode(inode, NFS_INO_INVALID_MODE | NFS_INO_INVALID_OTHER); if (res == 0) res = generic_permission(&nop_mnt_idmap, inode, mask); goto out; } EXPORT_SYMBOL_GPL(nfs_permission); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SHARED_IO_H #define _ASM_X86_SHARED_IO_H #include <linux/types.h> #define BUILDIO(bwl, bw, type) \ static __always_inline void __out##bwl(type value, u16 port) \ { \ asm volatile("out" #bwl " %" #bw "0, %w1" \ : : "a"(value), "Nd"(port)); \ } \ \ static __always_inline type __in##bwl(u16 port) \ { \ type value; \ asm volatile("in" #bwl " %w1, %" #bw "0" \ : "=a"(value) : "Nd"(port)); \ return value; \ } BUILDIO(b, b, u8) BUILDIO(w, w, u16) BUILDIO(l, , u32) #undef BUILDIO #define inb __inb #define inw __inw #define inl __inl #define outb __outb #define outw __outw #define outl __outl #endif |
| 993 996 986 999 996 999 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/extable.h> #include <linux/uaccess.h> #include <linux/sched/debug.h> #include <linux/bitfield.h> #include <xen/xen.h> #include <asm/fpu/api.h> #include <asm/fred.h> #include <asm/sev.h> #include <asm/traps.h> #include <asm/kdebug.h> #include <asm/insn-eval.h> #include <asm/sgx.h> static inline unsigned long *pt_regs_nr(struct pt_regs *regs, int nr) { int reg_offset = pt_regs_offset(regs, nr); static unsigned long __dummy; if (WARN_ON_ONCE(reg_offset < 0)) return &__dummy; return (unsigned long *)((unsigned long)regs + reg_offset); } static inline unsigned long ex_fixup_addr(const struct exception_table_entry *x) { return (unsigned long)&x->fixup + x->fixup; } static bool ex_handler_default(const struct exception_table_entry *e, struct pt_regs *regs) { if (e->data & EX_FLAG_CLEAR_AX) regs->ax = 0; if (e->data & EX_FLAG_CLEAR_DX) regs->dx = 0; regs->ip = ex_fixup_addr(e); return true; } /* * This is the *very* rare case where we do a "load_unaligned_zeropad()" * and it's a page crosser into a non-existent page. * * This happens when we optimistically load a pathname a word-at-a-time * and the name is less than the full word and the next page is not * mapped. Typically that only happens for CONFIG_DEBUG_PAGEALLOC. * * NOTE! The faulting address is always a 'mov mem,reg' type instruction * of size 'long', and the exception fixup must always point to right * after the instruction. */ static bool ex_handler_zeropad(const struct exception_table_entry *e, struct pt_regs *regs, unsigned long fault_addr) { struct insn insn; const unsigned long mask = sizeof(long) - 1; unsigned long offset, addr, next_ip, len; unsigned long *reg; next_ip = ex_fixup_addr(e); len = next_ip - regs->ip; if (len > MAX_INSN_SIZE) return false; if (insn_decode(&insn, (void *) regs->ip, len, INSN_MODE_KERN)) return false; if (insn.length != len) return false; if (insn.opcode.bytes[0] != 0x8b) return false; if (insn.opnd_bytes != sizeof(long)) return false; addr = (unsigned long) insn_get_addr_ref(&insn, regs); if (addr == ~0ul) return false; offset = addr & mask; addr = addr & ~mask; if (fault_addr != addr + sizeof(long)) return false; reg = insn_get_modrm_reg_ptr(&insn, regs); if (!reg) return false; *reg = *(unsigned long *)addr >> (offset * 8); return ex_handler_default(e, regs); } static bool ex_handler_fault(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr) { regs->ax = trapnr; return ex_handler_default(fixup, regs); } static bool ex_handler_sgx(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr) { regs->ax = trapnr | SGX_ENCLS_FAULT_FLAG; return ex_handler_default(fixup, regs); } /* * Handler for when we fail to restore a task's FPU state. We should never get * here because the FPU state of a task using the FPU (task->thread.fpu.state) * should always be valid. However, past bugs have allowed userspace to set * reserved bits in the XSAVE area using PTRACE_SETREGSET or sys_rt_sigreturn(). * These caused XRSTOR to fail when switching to the task, leaking the FPU * registers of the task previously executing on the CPU. Mitigate this class * of vulnerability by restoring from the initial state (essentially, zeroing * out all the FPU registers) if we can't restore from the task's FPU state. */ static bool ex_handler_fprestore(const struct exception_table_entry *fixup, struct pt_regs *regs) { regs->ip = ex_fixup_addr(fixup); WARN_ONCE(1, "Bad FPU state detected at %pB, reinitializing FPU registers.", (void *)instruction_pointer(regs)); fpu_reset_from_exception_fixup(); return true; } /* * On x86-64, we end up being imprecise with 'access_ok()', and allow * non-canonical user addresses to make the range comparisons simpler, * and to not have to worry about LAM being enabled. * * In fact, we allow up to one page of "slop" at the sign boundary, * which means that we can do access_ok() by just checking the sign * of the pointer for the common case of having a small access size. */ static bool gp_fault_address_ok(unsigned long fault_address) { #ifdef CONFIG_X86_64 /* Is it in the "user space" part of the non-canonical space? */ if (valid_user_address(fault_address)) return true; /* .. or just above it? */ fault_address -= PAGE_SIZE; if (valid_user_address(fault_address)) return true; #endif return false; } static bool ex_handler_uaccess(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr, unsigned long fault_address) { WARN_ONCE(trapnr == X86_TRAP_GP && !gp_fault_address_ok(fault_address), "General protection fault in user access. Non-canonical address?"); return ex_handler_default(fixup, regs); } static bool ex_handler_msr(const struct exception_table_entry *fixup, struct pt_regs *regs, bool wrmsr, bool safe, int reg) { if (__ONCE_LITE_IF(!safe && wrmsr)) { pr_warn("unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n", (unsigned int)regs->cx, (unsigned int)regs->dx, (unsigned int)regs->ax, regs->ip, (void *)regs->ip); show_stack_regs(regs); } if (__ONCE_LITE_IF(!safe && !wrmsr)) { pr_warn("unchecked MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n", (unsigned int)regs->cx, regs->ip, (void *)regs->ip); show_stack_regs(regs); } if (!wrmsr) { /* Pretend that the read succeeded and returned 0. */ regs->ax = 0; regs->dx = 0; } if (safe) *pt_regs_nr(regs, reg) = -EIO; return ex_handler_default(fixup, regs); } static bool ex_handler_clear_fs(const struct exception_table_entry *fixup, struct pt_regs *regs) { if (static_cpu_has(X86_BUG_NULL_SEG)) asm volatile ("mov %0, %%fs" : : "rm" (__USER_DS)); asm volatile ("mov %0, %%fs" : : "rm" (0)); return ex_handler_default(fixup, regs); } static bool ex_handler_imm_reg(const struct exception_table_entry *fixup, struct pt_regs *regs, int reg, int imm) { *pt_regs_nr(regs, reg) = (long)imm; return ex_handler_default(fixup, regs); } static bool ex_handler_ucopy_len(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr, unsigned long fault_address, int reg, int imm) { regs->cx = imm * regs->cx + *pt_regs_nr(regs, reg); return ex_handler_uaccess(fixup, regs, trapnr, fault_address); } #ifdef CONFIG_X86_FRED static bool ex_handler_eretu(const struct exception_table_entry *fixup, struct pt_regs *regs, unsigned long error_code) { struct pt_regs *uregs = (struct pt_regs *)(regs->sp - offsetof(struct pt_regs, orig_ax)); unsigned short ss = uregs->ss; unsigned short cs = uregs->cs; /* * Move the NMI bit from the invalid stack frame, which caused ERETU * to fault, to the fault handler's stack frame, thus to unblock NMI * with the fault handler's ERETS instruction ASAP if NMI is blocked. */ regs->fred_ss.nmi = uregs->fred_ss.nmi; /* * Sync event information to uregs, i.e., the ERETU return frame, but * is it safe to write to the ERETU return frame which is just above * current event stack frame? * * The RSP used by FRED to push a stack frame is not the value in %rsp, * it is calculated from %rsp with the following 2 steps: * 1) RSP = %rsp - (IA32_FRED_CONFIG & 0x1c0) // Reserve N*64 bytes * 2) RSP = RSP & ~0x3f // Align to a 64-byte cache line * when an event delivery doesn't trigger a stack level change. * * Here is an example with N*64 (N=1) bytes reserved: * * 64-byte cache line ==> ______________ * |___Reserved___| * |__Event_data__| * |_____SS_______| * |_____RSP______| * |_____FLAGS____| * |_____CS_______| * |_____IP_______| * 64-byte cache line ==> |__Error_code__| <== ERETU return frame * |______________| * |______________| * |______________| * |______________| * |______________| * |______________| * |______________| * 64-byte cache line ==> |______________| <== RSP after step 1) and 2) * |___Reserved___| * |__Event_data__| * |_____SS_______| * |_____RSP______| * |_____FLAGS____| * |_____CS_______| * |_____IP_______| * 64-byte cache line ==> |__Error_code__| <== ERETS return frame * * Thus a new FRED stack frame will always be pushed below a previous * FRED stack frame ((N*64) bytes may be reserved between), and it is * safe to write to a previous FRED stack frame as they never overlap. */ fred_info(uregs)->edata = fred_event_data(regs); uregs->ssx = regs->ssx; uregs->fred_ss.ss = ss; /* The NMI bit was moved away above */ uregs->fred_ss.nmi = 0; uregs->csx = regs->csx; uregs->fred_cs.sl = 0; uregs->fred_cs.wfe = 0; uregs->cs = cs; uregs->orig_ax = error_code; return ex_handler_default(fixup, regs); } #endif int ex_get_fixup_type(unsigned long ip) { const struct exception_table_entry *e = search_exception_tables(ip); return e ? FIELD_GET(EX_DATA_TYPE_MASK, e->data) : EX_TYPE_NONE; } int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) { const struct exception_table_entry *e; int type, reg, imm; #ifdef CONFIG_PNPBIOS if (unlikely(SEGMENT_IS_PNP_CODE(regs->cs))) { extern u32 pnp_bios_fault_eip, pnp_bios_fault_esp; extern u32 pnp_bios_is_utter_crap; pnp_bios_is_utter_crap = 1; printk(KERN_CRIT "PNPBIOS fault.. attempting recovery.\n"); __asm__ volatile( "movl %0, %%esp\n\t" "jmp *%1\n\t" : : "g" (pnp_bios_fault_esp), "g" (pnp_bios_fault_eip)); panic("do_trap: can't hit this"); } #endif e = search_exception_tables(regs->ip); if (!e) return 0; type = FIELD_GET(EX_DATA_TYPE_MASK, e->data); reg = FIELD_GET(EX_DATA_REG_MASK, e->data); imm = FIELD_GET(EX_DATA_IMM_MASK, e->data); switch (type) { case EX_TYPE_DEFAULT: case EX_TYPE_DEFAULT_MCE_SAFE: return ex_handler_default(e, regs); case EX_TYPE_FAULT: case EX_TYPE_FAULT_MCE_SAFE: return ex_handler_fault(e, regs, trapnr); case EX_TYPE_UACCESS: return ex_handler_uaccess(e, regs, trapnr, fault_addr); case EX_TYPE_CLEAR_FS: return ex_handler_clear_fs(e, regs); case EX_TYPE_FPU_RESTORE: return ex_handler_fprestore(e, regs); case EX_TYPE_BPF: return ex_handler_bpf(e, regs); case EX_TYPE_WRMSR: return ex_handler_msr(e, regs, true, false, reg); case EX_TYPE_RDMSR: return ex_handler_msr(e, regs, false, false, reg); case EX_TYPE_WRMSR_SAFE: return ex_handler_msr(e, regs, true, true, reg); case EX_TYPE_RDMSR_SAFE: return ex_handler_msr(e, regs, false, true, reg); case EX_TYPE_WRMSR_IN_MCE: ex_handler_msr_mce(regs, true); break; case EX_TYPE_RDMSR_IN_MCE: ex_handler_msr_mce(regs, false); break; case EX_TYPE_POP_REG: regs->sp += sizeof(long); fallthrough; case EX_TYPE_IMM_REG: return ex_handler_imm_reg(e, regs, reg, imm); case EX_TYPE_FAULT_SGX: return ex_handler_sgx(e, regs, trapnr); case EX_TYPE_UCOPY_LEN: return ex_handler_ucopy_len(e, regs, trapnr, fault_addr, reg, imm); case EX_TYPE_ZEROPAD: return ex_handler_zeropad(e, regs, fault_addr); #ifdef CONFIG_X86_FRED case EX_TYPE_ERETU: return ex_handler_eretu(e, regs, error_code); #endif } BUG(); } extern unsigned int early_recursion_flag; /* Restricted version used during very early boot */ void __init early_fixup_exception(struct pt_regs *regs, int trapnr) { /* Ignore early NMIs. */ if (trapnr == X86_TRAP_NMI) return; if (early_recursion_flag > 2) goto halt_loop; /* * Old CPUs leave the high bits of CS on the stack * undefined. I'm not sure which CPUs do this, but at least * the 486 DX works this way. * Xen pv domains are not using the default __KERNEL_CS. */ if (!xen_pv_domain() && regs->cs != __KERNEL_CS) goto fail; /* * The full exception fixup machinery is available as soon as * the early IDT is loaded. This means that it is the * responsibility of extable users to either function correctly * when handlers are invoked early or to simply avoid causing * exceptions before they're ready to handle them. * * This is better than filtering which handlers can be used, * because refusing to call a handler here is guaranteed to * result in a hard-to-debug panic. * * Keep in mind that not all vectors actually get here. Early * page faults, for example, are special. */ if (fixup_exception(regs, trapnr, regs->orig_ax, 0)) return; if (trapnr == X86_TRAP_UD) { if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) { /* Skip the ud2. */ regs->ip += LEN_UD2; return; } /* * If this was a BUG and report_bug returns or if this * was just a normal #UD, we want to continue onward and * crash. */ } fail: early_printk("PANIC: early exception 0x%02x IP %lx:%lx error %lx cr2 0x%lx\n", (unsigned)trapnr, (unsigned long)regs->cs, regs->ip, regs->orig_ax, read_cr2()); show_regs(regs); halt_loop: while (true) halt(); } |
| 2 2 2 15 3 13 10 14 13 10 11 12 9 4 6 2 9 10 2 4 3 1 1 8 1 1 2 4 8 8 8 1 7 3 1 2 4 1 2 1 3 13 2 11 12 6 6 1 5 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 | /* Block- or MTD-based romfs * * Copyright © 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * Derived from: ROMFS file system, Linux implementation * * Copyright © 1997-1999 Janos Farkas <chexum@shadow.banki.hu> * * Using parts of the minix filesystem * Copyright © 1991, 1992 Linus Torvalds * * and parts of the affs filesystem additionally * Copyright © 1993 Ray Burr * Copyright © 1996 Hans-Joachim Widmaier * * Changes * Changed for 2.1.19 modules * Jan 1997 Initial release * Jun 1997 2.1.43+ changes * Proper page locking in read_folio * Changed to work with 2.1.45+ fs * Jul 1997 Fixed follow_link * 2.1.47 * lookup shouldn't return -ENOENT * from Horst von Brand: * fail on wrong checksum * double unlock_super was possible * correct namelen for statfs * spotted by Bill Hawes: * readlink shouldn't iput() * Jun 1998 2.1.106 from Avery Pennarun: glibc scandir() * exposed a problem in readdir * 2.1.107 code-freeze spellchecker run * Aug 1998 2.1.118+ VFS changes * Sep 1998 2.1.122 another VFS change (follow_link) * Apr 1999 2.2.7 no more EBADF checking in * lookup/readdir, use ERR_PTR * Jun 1999 2.3.6 d_alloc_root use changed * 2.3.9 clean up usage of ENOENT/negative * dentries in lookup * clean up page flags setting * (error, uptodate, locking) in * in read_folio * use init_special_inode for * fifos/sockets (and streamline) in * read_inode, fix _ops table order * Aug 1999 2.3.16 __initfunc() => __init change * Oct 1999 2.3.24 page->owner hack obsoleted * Nov 1999 2.3.27 2.3.25+ page->offset => index change * * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public Licence * as published by the Free Software Foundation; either version * 2 of the Licence, or (at your option) any later version. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/string.h> #include <linux/fs.h> #include <linux/time.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/blkdev.h> #include <linux/fs_context.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/statfs.h> #include <linux/mtd/super.h> #include <linux/ctype.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/uaccess.h> #include <linux/major.h> #include "internal.h" static struct kmem_cache *romfs_inode_cachep; static const umode_t romfs_modemap[8] = { 0, /* hard link */ S_IFDIR | 0644, /* directory */ S_IFREG | 0644, /* regular file */ S_IFLNK | 0777, /* symlink */ S_IFBLK | 0600, /* blockdev */ S_IFCHR | 0600, /* chardev */ S_IFSOCK | 0644, /* socket */ S_IFIFO | 0644 /* FIFO */ }; static const unsigned char romfs_dtype_table[] = { DT_UNKNOWN, DT_DIR, DT_REG, DT_LNK, DT_BLK, DT_CHR, DT_SOCK, DT_FIFO }; static struct inode *romfs_iget(struct super_block *sb, unsigned long pos); /* * read a page worth of data from the image */ static int romfs_read_folio(struct file *file, struct folio *folio) { struct inode *inode = folio->mapping->host; loff_t offset, size; unsigned long fillsize, pos; void *buf; int ret; buf = kmap_local_folio(folio, 0); offset = folio_pos(folio); size = i_size_read(inode); fillsize = 0; ret = 0; if (offset < size) { size -= offset; fillsize = size > PAGE_SIZE ? PAGE_SIZE : size; pos = ROMFS_I(inode)->i_dataoffset + offset; ret = romfs_dev_read(inode->i_sb, pos, buf, fillsize); if (ret < 0) { fillsize = 0; ret = -EIO; } } buf = folio_zero_tail(folio, fillsize, buf + fillsize); kunmap_local(buf); folio_end_read(folio, ret == 0); return ret; } static const struct address_space_operations romfs_aops = { .read_folio = romfs_read_folio }; /* * read the entries from a directory */ static int romfs_readdir(struct file *file, struct dir_context *ctx) { struct inode *i = file_inode(file); struct romfs_inode ri; unsigned long offset, maxoff; int j, ino, nextfh; char fsname[ROMFS_MAXFN]; /* XXX dynamic? */ int ret; maxoff = romfs_maxsize(i->i_sb); offset = ctx->pos; if (!offset) { offset = i->i_ino & ROMFH_MASK; ret = romfs_dev_read(i->i_sb, offset, &ri, ROMFH_SIZE); if (ret < 0) goto out; offset = be32_to_cpu(ri.spec) & ROMFH_MASK; } /* Not really failsafe, but we are read-only... */ for (;;) { if (!offset || offset >= maxoff) { offset = maxoff; ctx->pos = offset; goto out; } ctx->pos = offset; /* Fetch inode info */ ret = romfs_dev_read(i->i_sb, offset, &ri, ROMFH_SIZE); if (ret < 0) goto out; j = romfs_dev_strnlen(i->i_sb, offset + ROMFH_SIZE, sizeof(fsname) - 1); if (j < 0) goto out; ret = romfs_dev_read(i->i_sb, offset + ROMFH_SIZE, fsname, j); if (ret < 0) goto out; fsname[j] = '\0'; ino = offset; nextfh = be32_to_cpu(ri.next); if ((nextfh & ROMFH_TYPE) == ROMFH_HRD) ino = be32_to_cpu(ri.spec); if (!dir_emit(ctx, fsname, j, ino, romfs_dtype_table[nextfh & ROMFH_TYPE])) goto out; offset = nextfh & ROMFH_MASK; } out: return 0; } /* * look up an entry in a directory */ static struct dentry *romfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { unsigned long offset, maxoff; struct inode *inode = NULL; struct romfs_inode ri; const char *name; /* got from dentry */ int len, ret; offset = dir->i_ino & ROMFH_MASK; ret = romfs_dev_read(dir->i_sb, offset, &ri, ROMFH_SIZE); if (ret < 0) goto error; /* search all the file entries in the list starting from the one * pointed to by the directory's special data */ maxoff = romfs_maxsize(dir->i_sb); offset = be32_to_cpu(ri.spec) & ROMFH_MASK; name = dentry->d_name.name; len = dentry->d_name.len; for (;;) { if (!offset || offset >= maxoff) break; ret = romfs_dev_read(dir->i_sb, offset, &ri, sizeof(ri)); if (ret < 0) goto error; /* try to match the first 16 bytes of name */ ret = romfs_dev_strcmp(dir->i_sb, offset + ROMFH_SIZE, name, len); if (ret < 0) goto error; if (ret == 1) { /* Hard link handling */ if ((be32_to_cpu(ri.next) & ROMFH_TYPE) == ROMFH_HRD) offset = be32_to_cpu(ri.spec) & ROMFH_MASK; inode = romfs_iget(dir->i_sb, offset); break; } /* next entry */ offset = be32_to_cpu(ri.next) & ROMFH_MASK; } return d_splice_alias(inode, dentry); error: return ERR_PTR(ret); } static const struct file_operations romfs_dir_operations = { .read = generic_read_dir, .iterate_shared = romfs_readdir, .llseek = generic_file_llseek, }; static const struct inode_operations romfs_dir_inode_operations = { .lookup = romfs_lookup, }; /* * get a romfs inode based on its position in the image (which doubles as the * inode number) */ static struct inode *romfs_iget(struct super_block *sb, unsigned long pos) { struct romfs_inode_info *inode; struct romfs_inode ri; struct inode *i; unsigned long nlen; unsigned nextfh; int ret; umode_t mode; /* we might have to traverse a chain of "hard link" file entries to get * to the actual file */ for (;;) { ret = romfs_dev_read(sb, pos, &ri, sizeof(ri)); if (ret < 0) goto error; /* XXX: do romfs_checksum here too (with name) */ nextfh = be32_to_cpu(ri.next); if ((nextfh & ROMFH_TYPE) != ROMFH_HRD) break; pos = be32_to_cpu(ri.spec) & ROMFH_MASK; } /* determine the length of the filename */ nlen = romfs_dev_strnlen(sb, pos + ROMFH_SIZE, ROMFS_MAXFN); if (IS_ERR_VALUE(nlen)) goto eio; /* get an inode for this image position */ i = iget_locked(sb, pos); if (!i) return ERR_PTR(-ENOMEM); if (!(i->i_state & I_NEW)) return i; /* precalculate the data offset */ inode = ROMFS_I(i); inode->i_metasize = (ROMFH_SIZE + nlen + 1 + ROMFH_PAD) & ROMFH_MASK; inode->i_dataoffset = pos + inode->i_metasize; set_nlink(i, 1); /* Hard to decide.. */ i->i_size = be32_to_cpu(ri.size); inode_set_mtime_to_ts(i, inode_set_atime_to_ts(i, inode_set_ctime(i, 0, 0))); /* set up mode and ops */ mode = romfs_modemap[nextfh & ROMFH_TYPE]; switch (nextfh & ROMFH_TYPE) { case ROMFH_DIR: i->i_size = ROMFS_I(i)->i_metasize; i->i_op = &romfs_dir_inode_operations; i->i_fop = &romfs_dir_operations; if (nextfh & ROMFH_EXEC) mode |= S_IXUGO; break; case ROMFH_REG: i->i_fop = &romfs_ro_fops; i->i_data.a_ops = &romfs_aops; if (nextfh & ROMFH_EXEC) mode |= S_IXUGO; break; case ROMFH_SYM: i->i_op = &page_symlink_inode_operations; inode_nohighmem(i); i->i_data.a_ops = &romfs_aops; mode |= S_IRWXUGO; break; default: /* depending on MBZ for sock/fifos */ nextfh = be32_to_cpu(ri.spec); init_special_inode(i, mode, MKDEV(nextfh >> 16, nextfh & 0xffff)); break; } i->i_mode = mode; i->i_blocks = (i->i_size + 511) >> 9; unlock_new_inode(i); return i; eio: ret = -EIO; error: pr_err("read error for inode 0x%lx\n", pos); return ERR_PTR(ret); } /* * allocate a new inode */ static struct inode *romfs_alloc_inode(struct super_block *sb) { struct romfs_inode_info *inode; inode = alloc_inode_sb(sb, romfs_inode_cachep, GFP_KERNEL); return inode ? &inode->vfs_inode : NULL; } /* * return a spent inode to the slab cache */ static void romfs_free_inode(struct inode *inode) { kmem_cache_free(romfs_inode_cachep, ROMFS_I(inode)); } /* * get filesystem statistics */ static int romfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; u64 id = 0; /* When calling huge_encode_dev(), * use sb->s_bdev->bd_dev when, * - CONFIG_ROMFS_ON_BLOCK defined * use sb->s_dev when, * - CONFIG_ROMFS_ON_BLOCK undefined and * - CONFIG_ROMFS_ON_MTD defined * leave id as 0 when, * - CONFIG_ROMFS_ON_BLOCK undefined and * - CONFIG_ROMFS_ON_MTD undefined */ if (sb->s_bdev) id = huge_encode_dev(sb->s_bdev->bd_dev); else if (sb->s_dev) id = huge_encode_dev(sb->s_dev); buf->f_type = ROMFS_MAGIC; buf->f_namelen = ROMFS_MAXFN; buf->f_bsize = ROMBSIZE; buf->f_bfree = buf->f_bavail = buf->f_ffree; buf->f_blocks = (romfs_maxsize(dentry->d_sb) + ROMBSIZE - 1) >> ROMBSBITS; buf->f_fsid = u64_to_fsid(id); return 0; } /* * remounting must involve read-only */ static int romfs_reconfigure(struct fs_context *fc) { sync_filesystem(fc->root->d_sb); fc->sb_flags |= SB_RDONLY; return 0; } static const struct super_operations romfs_super_ops = { .alloc_inode = romfs_alloc_inode, .free_inode = romfs_free_inode, .statfs = romfs_statfs, }; /* * checksum check on part of a romfs filesystem */ static __u32 romfs_checksum(const void *data, int size) { const __be32 *ptr = data; __u32 sum; sum = 0; size >>= 2; while (size > 0) { sum += be32_to_cpu(*ptr++); size--; } return sum; } /* * fill in the superblock */ static int romfs_fill_super(struct super_block *sb, struct fs_context *fc) { struct romfs_super_block *rsb; struct inode *root; unsigned long pos, img_size; const char *storage; size_t len; int ret; #ifdef CONFIG_BLOCK if (!sb->s_mtd) { sb_set_blocksize(sb, ROMBSIZE); } else { sb->s_blocksize = ROMBSIZE; sb->s_blocksize_bits = blksize_bits(ROMBSIZE); } #endif sb->s_maxbytes = 0xFFFFFFFF; sb->s_magic = ROMFS_MAGIC; sb->s_flags |= SB_RDONLY | SB_NOATIME; sb->s_time_min = 0; sb->s_time_max = 0; sb->s_op = &romfs_super_ops; #ifdef CONFIG_ROMFS_ON_MTD /* Use same dev ID from the underlying mtdblock device */ if (sb->s_mtd) sb->s_dev = MKDEV(MTD_BLOCK_MAJOR, sb->s_mtd->index); #endif /* read the image superblock and check it */ rsb = kmalloc(512, GFP_KERNEL); if (!rsb) return -ENOMEM; sb->s_fs_info = (void *) 512; ret = romfs_dev_read(sb, 0, rsb, 512); if (ret < 0) goto error_rsb; img_size = be32_to_cpu(rsb->size); if (sb->s_mtd && img_size > sb->s_mtd->size) goto error_rsb_inval; sb->s_fs_info = (void *) img_size; if (rsb->word0 != ROMSB_WORD0 || rsb->word1 != ROMSB_WORD1 || img_size < ROMFH_SIZE) { if (!(fc->sb_flags & SB_SILENT)) errorf(fc, "VFS: Can't find a romfs filesystem on dev %s.\n", sb->s_id); goto error_rsb_inval; } if (romfs_checksum(rsb, min_t(size_t, img_size, 512))) { pr_err("bad initial checksum on dev %s.\n", sb->s_id); goto error_rsb_inval; } storage = sb->s_mtd ? "MTD" : "the block layer"; len = strnlen(rsb->name, ROMFS_MAXFN); if (!(fc->sb_flags & SB_SILENT)) pr_notice("Mounting image '%*.*s' through %s\n", (unsigned) len, (unsigned) len, rsb->name, storage); kfree(rsb); rsb = NULL; /* find the root directory */ pos = (ROMFH_SIZE + len + 1 + ROMFH_PAD) & ROMFH_MASK; root = romfs_iget(sb, pos); if (IS_ERR(root)) return PTR_ERR(root); sb->s_root = d_make_root(root); if (!sb->s_root) return -ENOMEM; return 0; error_rsb_inval: ret = -EINVAL; error_rsb: kfree(rsb); return ret; } /* * get a superblock for mounting */ static int romfs_get_tree(struct fs_context *fc) { int ret = -EINVAL; #ifdef CONFIG_ROMFS_ON_MTD ret = get_tree_mtd(fc, romfs_fill_super); #endif #ifdef CONFIG_ROMFS_ON_BLOCK if (ret == -EINVAL) ret = get_tree_bdev(fc, romfs_fill_super); #endif return ret; } static const struct fs_context_operations romfs_context_ops = { .get_tree = romfs_get_tree, .reconfigure = romfs_reconfigure, }; /* * Set up the filesystem mount context. */ static int romfs_init_fs_context(struct fs_context *fc) { fc->ops = &romfs_context_ops; return 0; } /* * destroy a romfs superblock in the appropriate manner */ static void romfs_kill_sb(struct super_block *sb) { generic_shutdown_super(sb); #ifdef CONFIG_ROMFS_ON_MTD if (sb->s_mtd) { put_mtd_device(sb->s_mtd); sb->s_mtd = NULL; } #endif #ifdef CONFIG_ROMFS_ON_BLOCK if (sb->s_bdev) { sync_blockdev(sb->s_bdev); bdev_fput(sb->s_bdev_file); } #endif } static struct file_system_type romfs_fs_type = { .owner = THIS_MODULE, .name = "romfs", .init_fs_context = romfs_init_fs_context, .kill_sb = romfs_kill_sb, .fs_flags = FS_REQUIRES_DEV, }; MODULE_ALIAS_FS("romfs"); /* * inode storage initialiser */ static void romfs_i_init_once(void *_inode) { struct romfs_inode_info *inode = _inode; inode_init_once(&inode->vfs_inode); } /* * romfs module initialisation */ static int __init init_romfs_fs(void) { int ret; pr_info("ROMFS MTD (C) 2007 Red Hat, Inc.\n"); romfs_inode_cachep = kmem_cache_create("romfs_i", sizeof(struct romfs_inode_info), 0, SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT, romfs_i_init_once); if (!romfs_inode_cachep) { pr_err("Failed to initialise inode cache\n"); return -ENOMEM; } ret = register_filesystem(&romfs_fs_type); if (ret) { pr_err("Failed to register filesystem\n"); goto error_register; } return 0; error_register: kmem_cache_destroy(romfs_inode_cachep); return ret; } /* * romfs module removal */ static void __exit exit_romfs_fs(void) { unregister_filesystem(&romfs_fs_type); /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(romfs_inode_cachep); } module_init(init_romfs_fs); module_exit(exit_romfs_fs); MODULE_DESCRIPTION("Direct-MTD Capable RomFS"); MODULE_AUTHOR("Red Hat, Inc."); MODULE_LICENSE("GPL"); /* Actually dual-licensed, but it doesn't matter for */ |
| 18 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/fs/pnode.h * * (C) Copyright IBM Corporation 2005. */ #ifndef _LINUX_PNODE_H #define _LINUX_PNODE_H #include <linux/list.h> #include "mount.h" #define IS_MNT_SHARED(m) ((m)->mnt.mnt_flags & MNT_SHARED) #define IS_MNT_SLAVE(m) ((m)->mnt_master) #define IS_MNT_NEW(m) (!(m)->mnt_ns) #define CLEAR_MNT_SHARED(m) ((m)->mnt.mnt_flags &= ~MNT_SHARED) #define IS_MNT_UNBINDABLE(m) ((m)->mnt.mnt_flags & MNT_UNBINDABLE) #define IS_MNT_MARKED(m) ((m)->mnt.mnt_flags & MNT_MARKED) #define SET_MNT_MARK(m) ((m)->mnt.mnt_flags |= MNT_MARKED) #define CLEAR_MNT_MARK(m) ((m)->mnt.mnt_flags &= ~MNT_MARKED) #define IS_MNT_LOCKED(m) ((m)->mnt.mnt_flags & MNT_LOCKED) #define CL_EXPIRE 0x01 #define CL_SLAVE 0x02 #define CL_COPY_UNBINDABLE 0x04 #define CL_MAKE_SHARED 0x08 #define CL_PRIVATE 0x10 #define CL_SHARED_TO_SLAVE 0x20 #define CL_COPY_MNT_NS_FILE 0x40 #define CL_COPY_ALL (CL_COPY_UNBINDABLE | CL_COPY_MNT_NS_FILE) static inline void set_mnt_shared(struct mount *mnt) { mnt->mnt.mnt_flags &= ~MNT_SHARED_MASK; mnt->mnt.mnt_flags |= MNT_SHARED; } void change_mnt_propagation(struct mount *, int); int propagate_mnt(struct mount *, struct mountpoint *, struct mount *, struct hlist_head *); int propagate_umount(struct list_head *); int propagate_mount_busy(struct mount *, int); void propagate_mount_unlock(struct mount *); void mnt_release_group_id(struct mount *); int get_dominating_id(struct mount *mnt, const struct path *root); int mnt_get_count(struct mount *mnt); void mnt_set_mountpoint(struct mount *, struct mountpoint *, struct mount *); void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt); struct mount *copy_tree(struct mount *, struct dentry *, int); bool is_path_reachable(struct mount *, struct dentry *, const struct path *root); int count_mounts(struct mnt_namespace *ns, struct mount *mnt); bool propagation_would_overmount(const struct mount *from, const struct mount *to, const struct mountpoint *mp); #endif /* _LINUX_PNODE_H */ |
| 20 20 23 27 3 3 12 3 15 3 12 15 12 3 23 12 27 27 27 27 27 27 27 13 27 27 22 13 3 3 3 3 6 3 20 6 20 3 3 3 3 3 3 3 3 3 3 3 927 2 925 12 12 2801 2805 2798 20 2802 12 2 12 12 12 12 12 12 12 12 12 12 12 12 23 22 16 10 2784 2782 16 | 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 | // 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); case FSNOTIFY_OBJ_TYPE_MNTNS: return &((struct mnt_namespace *)obj)->n_fsnotify_marks; 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; else if (conn->type == FSNOTIFY_OBJ_TYPE_MNTNS) return &fsnotify_conn_mntns(conn)->n_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; } else if (conn->type == FSNOTIFY_OBJ_TYPE_MNTNS) { fsnotify_conn_mntns(conn)->n_fsnotify_mask = 0; } rcu_assign_pointer(*connp, NULL); conn->obj = NULL; conn->type = FSNOTIFY_OBJ_TYPE_DETACHED; if (sb) 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 (sb && !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: if (sb) 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); |
| 24 25 25 25 24 24 24 25 17 24 25 25 25 25 25 17 24 25 17 17 17 8 17 25 17 25 8 8 8 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Virtio ring implementation. * * Copyright 2007 Rusty Russell IBM Corporation */ #include <linux/virtio.h> #include <linux/virtio_ring.h> #include <linux/virtio_config.h> #include <linux/device.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/hrtimer.h> #include <linux/dma-mapping.h> #include <linux/kmsan.h> #include <linux/spinlock.h> #include <xen/xen.h> #ifdef DEBUG /* For development, we want to crash whenever the ring is screwed. */ #define BAD_RING(_vq, fmt, args...) \ do { \ dev_err(&(_vq)->vq.vdev->dev, \ "%s:"fmt, (_vq)->vq.name, ##args); \ BUG(); \ } while (0) /* Caller is supposed to guarantee no reentry. */ #define START_USE(_vq) \ do { \ if ((_vq)->in_use) \ panic("%s:in_use = %i\n", \ (_vq)->vq.name, (_vq)->in_use); \ (_vq)->in_use = __LINE__; \ } while (0) #define END_USE(_vq) \ do { BUG_ON(!(_vq)->in_use); (_vq)->in_use = 0; } while(0) #define LAST_ADD_TIME_UPDATE(_vq) \ do { \ ktime_t now = ktime_get(); \ \ /* No kick or get, with .1 second between? Warn. */ \ if ((_vq)->last_add_time_valid) \ WARN_ON(ktime_to_ms(ktime_sub(now, \ (_vq)->last_add_time)) > 100); \ (_vq)->last_add_time = now; \ (_vq)->last_add_time_valid = true; \ } while (0) #define LAST_ADD_TIME_CHECK(_vq) \ do { \ if ((_vq)->last_add_time_valid) { \ WARN_ON(ktime_to_ms(ktime_sub(ktime_get(), \ (_vq)->last_add_time)) > 100); \ } \ } while (0) #define LAST_ADD_TIME_INVALID(_vq) \ ((_vq)->last_add_time_valid = false) #else #define BAD_RING(_vq, fmt, args...) \ do { \ dev_err(&_vq->vq.vdev->dev, \ "%s:"fmt, (_vq)->vq.name, ##args); \ (_vq)->broken = true; \ } while (0) #define START_USE(vq) #define END_USE(vq) #define LAST_ADD_TIME_UPDATE(vq) #define LAST_ADD_TIME_CHECK(vq) #define LAST_ADD_TIME_INVALID(vq) #endif struct vring_desc_state_split { void *data; /* Data for callback. */ /* Indirect desc table and extra table, if any. These two will be * allocated together. So we won't stress more to the memory allocator. */ struct vring_desc *indir_desc; }; struct vring_desc_state_packed { void *data; /* Data for callback. */ /* Indirect desc table and extra table, if any. These two will be * allocated together. So we won't stress more to the memory allocator. */ struct vring_packed_desc *indir_desc; u16 num; /* Descriptor list length. */ u16 last; /* The last desc state in a list. */ }; struct vring_desc_extra { dma_addr_t addr; /* Descriptor DMA addr. */ u32 len; /* Descriptor length. */ u16 flags; /* Descriptor flags. */ u16 next; /* The next desc state in a list. */ }; struct vring_virtqueue_split { /* Actual memory layout for this queue. */ struct vring vring; /* Last written value to avail->flags */ u16 avail_flags_shadow; /* * Last written value to avail->idx in * guest byte order. */ u16 avail_idx_shadow; /* Per-descriptor state. */ struct vring_desc_state_split *desc_state; struct vring_desc_extra *desc_extra; /* DMA address and size information */ dma_addr_t queue_dma_addr; size_t queue_size_in_bytes; /* * The parameters for creating vrings are reserved for creating new * vring. */ u32 vring_align; bool may_reduce_num; }; struct vring_virtqueue_packed { /* Actual memory layout for this queue. */ struct { unsigned int num; struct vring_packed_desc *desc; struct vring_packed_desc_event *driver; struct vring_packed_desc_event *device; } vring; /* Driver ring wrap counter. */ bool avail_wrap_counter; /* Avail used flags. */ u16 avail_used_flags; /* Index of the next avail descriptor. */ u16 next_avail_idx; /* * Last written value to driver->flags in * guest byte order. */ u16 event_flags_shadow; /* Per-descriptor state. */ struct vring_desc_state_packed *desc_state; struct vring_desc_extra *desc_extra; /* DMA address and size information */ dma_addr_t ring_dma_addr; dma_addr_t driver_event_dma_addr; dma_addr_t device_event_dma_addr; size_t ring_size_in_bytes; size_t event_size_in_bytes; }; struct vring_virtqueue { struct virtqueue vq; /* Is this a packed ring? */ bool packed_ring; /* Is DMA API used? */ bool use_dma_api; /* Can we use weak barriers? */ bool weak_barriers; /* Other side has made a mess, don't try any more. */ bool broken; /* Host supports indirect buffers */ bool indirect; /* Host publishes avail event idx */ bool event; /* Head of free buffer list. */ unsigned int free_head; /* Number we've added since last sync. */ unsigned int num_added; /* Last used index we've seen. * for split ring, it just contains last used index * for packed ring: * bits up to VRING_PACKED_EVENT_F_WRAP_CTR include the last used index. * bits from VRING_PACKED_EVENT_F_WRAP_CTR include the used wrap counter. */ u16 last_used_idx; /* Hint for event idx: already triggered no need to disable. */ bool event_triggered; union { /* Available for split ring */ struct vring_virtqueue_split split; /* Available for packed ring */ struct vring_virtqueue_packed packed; }; /* How to notify other side. FIXME: commonalize hcalls! */ bool (*notify)(struct virtqueue *vq); /* DMA, allocation, and size information */ bool we_own_ring; /* Device used for doing DMA */ struct device *dma_dev; #ifdef DEBUG /* They're supposed to lock for us. */ unsigned int in_use; /* Figure out if their kicks are too delayed. */ bool last_add_time_valid; ktime_t last_add_time; #endif }; static struct vring_desc_extra *vring_alloc_desc_extra(unsigned int num); static void vring_free(struct virtqueue *_vq); /* * Helpers. */ #define to_vvq(_vq) container_of_const(_vq, struct vring_virtqueue, vq) static bool virtqueue_use_indirect(const struct vring_virtqueue *vq, unsigned int total_sg) { /* * If the host supports indirect descriptor tables, and we have multiple * buffers, then go indirect. FIXME: tune this threshold */ return (vq->indirect && total_sg > 1 && vq->vq.num_free); } /* * Modern virtio devices have feature bits to specify whether they need a * quirk and bypass the IOMMU. If not there, just use the DMA API. * * If there, the interaction between virtio and DMA API is messy. * * On most systems with virtio, physical addresses match bus addresses, * and it doesn't particularly matter whether we use the DMA API. * * On some systems, including Xen and any system with a physical device * that speaks virtio behind a physical IOMMU, we must use the DMA API * for virtio DMA to work at all. * * On other systems, including SPARC and PPC64, virtio-pci devices are * enumerated as though they are behind an IOMMU, but the virtio host * ignores the IOMMU, so we must either pretend that the IOMMU isn't * there or somehow map everything as the identity. * * For the time being, we preserve historic behavior and bypass the DMA * API. * * TODO: install a per-device DMA ops structure that does the right thing * taking into account all the above quirks, and use the DMA API * unconditionally on data path. */ static bool vring_use_dma_api(const struct virtio_device *vdev) { if (!virtio_has_dma_quirk(vdev)) return true; /* Otherwise, we are left to guess. */ /* * In theory, it's possible to have a buggy QEMU-supposed * emulated Q35 IOMMU and Xen enabled at the same time. On * such a configuration, virtio has never worked and will * not work without an even larger kludge. Instead, enable * the DMA API if we're a Xen guest, which at least allows * all of the sensible Xen configurations to work correctly. */ if (xen_domain()) return true; return false; } static bool vring_need_unmap_buffer(const struct vring_virtqueue *vring, const struct vring_desc_extra *extra) { return vring->use_dma_api && (extra->addr != DMA_MAPPING_ERROR); } size_t virtio_max_dma_size(const struct virtio_device *vdev) { size_t max_segment_size = SIZE_MAX; if (vring_use_dma_api(vdev)) max_segment_size = dma_max_mapping_size(vdev->dev.parent); return max_segment_size; } EXPORT_SYMBOL_GPL(virtio_max_dma_size); static void *vring_alloc_queue(struct virtio_device *vdev, size_t size, dma_addr_t *dma_handle, gfp_t flag, struct device *dma_dev) { if (vring_use_dma_api(vdev)) { return dma_alloc_coherent(dma_dev, size, dma_handle, flag); } else { void *queue = alloc_pages_exact(PAGE_ALIGN(size), flag); if (queue) { phys_addr_t phys_addr = virt_to_phys(queue); *dma_handle = (dma_addr_t)phys_addr; /* * Sanity check: make sure we dind't truncate * the address. The only arches I can find that * have 64-bit phys_addr_t but 32-bit dma_addr_t * are certain non-highmem MIPS and x86 * configurations, but these configurations * should never allocate physical pages above 32 * bits, so this is fine. Just in case, throw a * warning and abort if we end up with an * unrepresentable address. */ if (WARN_ON_ONCE(*dma_handle != phys_addr)) { free_pages_exact(queue, PAGE_ALIGN(size)); return NULL; } } return queue; } } static void vring_free_queue(struct virtio_device *vdev, size_t size, void *queue, dma_addr_t dma_handle, struct device *dma_dev) { if (vring_use_dma_api(vdev)) dma_free_coherent(dma_dev, size, queue, dma_handle); else free_pages_exact(queue, PAGE_ALIGN(size)); } /* * The DMA ops on various arches are rather gnarly right now, and * making all of the arch DMA ops work on the vring device itself * is a mess. */ static struct device *vring_dma_dev(const struct vring_virtqueue *vq) { return vq->dma_dev; } /* Map one sg entry. */ static int vring_map_one_sg(const struct vring_virtqueue *vq, struct scatterlist *sg, enum dma_data_direction direction, dma_addr_t *addr, u32 *len, bool premapped) { if (premapped) { *addr = sg_dma_address(sg); *len = sg_dma_len(sg); return 0; } *len = sg->length; if (!vq->use_dma_api) { /* * If DMA is not used, KMSAN doesn't know that the scatterlist * is initialized by the hardware. Explicitly check/unpoison it * depending on the direction. */ kmsan_handle_dma(sg_page(sg), sg->offset, sg->length, direction); *addr = (dma_addr_t)sg_phys(sg); return 0; } /* * We can't use dma_map_sg, because we don't use scatterlists in * the way it expects (we don't guarantee that the scatterlist * will exist for the lifetime of the mapping). */ *addr = dma_map_page(vring_dma_dev(vq), sg_page(sg), sg->offset, sg->length, direction); if (dma_mapping_error(vring_dma_dev(vq), *addr)) return -ENOMEM; return 0; } static dma_addr_t vring_map_single(const struct vring_virtqueue *vq, void *cpu_addr, size_t size, enum dma_data_direction direction) { if (!vq->use_dma_api) return (dma_addr_t)virt_to_phys(cpu_addr); return dma_map_single(vring_dma_dev(vq), cpu_addr, size, direction); } static int vring_mapping_error(const struct vring_virtqueue *vq, dma_addr_t addr) { if (!vq->use_dma_api) return 0; return dma_mapping_error(vring_dma_dev(vq), addr); } static void virtqueue_init(struct vring_virtqueue *vq, u32 num) { vq->vq.num_free = num; if (vq->packed_ring) vq->last_used_idx = 0 | (1 << VRING_PACKED_EVENT_F_WRAP_CTR); else vq->last_used_idx = 0; vq->event_triggered = false; vq->num_added = 0; #ifdef DEBUG vq->in_use = false; vq->last_add_time_valid = false; #endif } /* * Split ring specific functions - *_split(). */ static unsigned int vring_unmap_one_split(const struct vring_virtqueue *vq, struct vring_desc_extra *extra) { u16 flags; flags = extra->flags; if (flags & VRING_DESC_F_INDIRECT) { if (!vq->use_dma_api) goto out; dma_unmap_single(vring_dma_dev(vq), extra->addr, extra->len, (flags & VRING_DESC_F_WRITE) ? DMA_FROM_DEVICE : DMA_TO_DEVICE); } else { if (!vring_need_unmap_buffer(vq, extra)) goto out; dma_unmap_page(vring_dma_dev(vq), extra->addr, extra->len, (flags & VRING_DESC_F_WRITE) ? DMA_FROM_DEVICE : DMA_TO_DEVICE); } out: return extra->next; } static struct vring_desc *alloc_indirect_split(struct virtqueue *_vq, unsigned int total_sg, gfp_t gfp) { struct vring_desc_extra *extra; struct vring_desc *desc; unsigned int i, size; /* * We require lowmem mappings for the descriptors because * otherwise virt_to_phys will give us bogus addresses in the * virtqueue. */ gfp &= ~__GFP_HIGHMEM; size = sizeof(*desc) * total_sg + sizeof(*extra) * total_sg; desc = kmalloc(size, gfp); if (!desc) return NULL; extra = (struct vring_desc_extra *)&desc[total_sg]; for (i = 0; i < total_sg; i++) extra[i].next = i + 1; return desc; } static inline unsigned int virtqueue_add_desc_split(struct virtqueue *vq, struct vring_desc *desc, struct vring_desc_extra *extra, unsigned int i, dma_addr_t addr, unsigned int len, u16 flags, bool premapped) { u16 next; desc[i].flags = cpu_to_virtio16(vq->vdev, flags); desc[i].addr = cpu_to_virtio64(vq->vdev, addr); desc[i].len = cpu_to_virtio32(vq->vdev, len); extra[i].addr = premapped ? DMA_MAPPING_ERROR : addr; extra[i].len = len; extra[i].flags = flags; next = extra[i].next; desc[i].next = cpu_to_virtio16(vq->vdev, next); return next; } static inline int virtqueue_add_split(struct virtqueue *_vq, struct scatterlist *sgs[], unsigned int total_sg, unsigned int out_sgs, unsigned int in_sgs, void *data, void *ctx, bool premapped, gfp_t gfp) { struct vring_virtqueue *vq = to_vvq(_vq); struct vring_desc_extra *extra; struct scatterlist *sg; struct vring_desc *desc; unsigned int i, n, avail, descs_used, prev, err_idx; int head; bool indirect; START_USE(vq); BUG_ON(data == NULL); BUG_ON(ctx && vq->indirect); if (unlikely(vq->broken)) { END_USE(vq); return -EIO; } LAST_ADD_TIME_UPDATE(vq); BUG_ON(total_sg == 0); head = vq->free_head; if (virtqueue_use_indirect(vq, total_sg)) desc = alloc_indirect_split(_vq, total_sg, gfp); else { desc = NULL; WARN_ON_ONCE(total_sg > vq->split.vring.num && !vq->indirect); } if (desc) { /* Use a single buffer which doesn't continue */ indirect = true; /* Set up rest to use this indirect table. */ i = 0; descs_used = 1; extra = (struct vring_desc_extra *)&desc[total_sg]; } else { indirect = false; desc = vq->split.vring.desc; extra = vq->split.desc_extra; i = head; descs_used = total_sg; } if (unlikely(vq->vq.num_free < descs_used)) { pr_debug("Can't add buf len %i - avail = %i\n", descs_used, vq->vq.num_free); /* FIXME: for historical reasons, we force a notify here if * there are outgoing parts to the buffer. Presumably the * host should service the ring ASAP. */ if (out_sgs) vq->notify(&vq->vq); if (indirect) kfree(desc); END_USE(vq); return -ENOSPC; } for (n = 0; n < out_sgs; n++) { for (sg = sgs[n]; sg; sg = sg_next(sg)) { dma_addr_t addr; u32 len; if (vring_map_one_sg(vq, sg, DMA_TO_DEVICE, &addr, &len, premapped)) goto unmap_release; prev = i; /* Note that we trust indirect descriptor * table since it use stream DMA mapping. */ i = virtqueue_add_desc_split(_vq, desc, extra, i, addr, len, VRING_DESC_F_NEXT, premapped); } } for (; n < (out_sgs + in_sgs); n++) { for (sg = sgs[n]; sg; sg = sg_next(sg)) { dma_addr_t addr; u32 len; if (vring_map_one_sg(vq, sg, DMA_FROM_DEVICE, &addr, &len, premapped)) goto unmap_release; prev = i; /* Note that we trust indirect descriptor * table since it use stream DMA mapping. */ i = virtqueue_add_desc_split(_vq, desc, extra, i, addr, len, VRING_DESC_F_NEXT | VRING_DESC_F_WRITE, premapped); } } /* Last one doesn't continue. */ desc[prev].flags &= cpu_to_virtio16(_vq->vdev, ~VRING_DESC_F_NEXT); if (!indirect && vring_need_unmap_buffer(vq, &extra[prev])) vq->split.desc_extra[prev & (vq->split.vring.num - 1)].flags &= ~VRING_DESC_F_NEXT; if (indirect) { /* Now that the indirect table is filled in, map it. */ dma_addr_t addr = vring_map_single( vq, desc, total_sg * sizeof(struct vring_desc), DMA_TO_DEVICE); if (vring_mapping_error(vq, addr)) goto unmap_release; virtqueue_add_desc_split(_vq, vq->split.vring.desc, vq->split.desc_extra, head, addr, total_sg * sizeof(struct vring_desc), VRING_DESC_F_INDIRECT, false); } /* We're using some buffers from the free list. */ vq->vq.num_free -= descs_used; /* Update free pointer */ if (indirect) vq->free_head = vq->split.desc_extra[head].next; else vq->free_head = i; /* Store token and indirect buffer state. */ vq->split.desc_state[head].data = data; if (indirect) vq->split.desc_state[head].indir_desc = desc; else vq->split.desc_state[head].indir_desc = ctx; /* Put entry in available array (but don't update avail->idx until they * do sync). */ avail = vq->split.avail_idx_shadow & (vq->split.vring.num - 1); vq->split.vring.avail->ring[avail] = cpu_to_virtio16(_vq->vdev, head); /* Descriptors and available array need to be set before we expose the * new available array entries. */ virtio_wmb(vq->weak_barriers); vq->split.avail_idx_shadow++; vq->split.vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->split.avail_idx_shadow); vq->num_added++; pr_debug("Added buffer head %i to %p\n", head, vq); END_USE(vq); /* This is very unlikely, but theoretically possible. Kick * just in case. */ if (unlikely(vq->num_added == (1 << 16) - 1)) virtqueue_kick(_vq); return 0; unmap_release: err_idx = i; if (indirect) i = 0; else i = head; for (n = 0; n < total_sg; n++) { if (i == err_idx) break; i = vring_unmap_one_split(vq, &extra[i]); } if (indirect) kfree(desc); END_USE(vq); return -ENOMEM; } static bool virtqueue_kick_prepare_split(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); u16 new, old; bool needs_kick; START_USE(vq); /* We need to expose available array entries before checking avail * event. */ virtio_mb(vq->weak_barriers); old = vq->split.avail_idx_shadow - vq->num_added; new = vq->split.avail_idx_shadow; vq->num_added = 0; LAST_ADD_TIME_CHECK(vq); LAST_ADD_TIME_INVALID(vq); if (vq->event) { needs_kick = vring_need_event(virtio16_to_cpu(_vq->vdev, vring_avail_event(&vq->split.vring)), new, old); } else { needs_kick = !(vq->split.vring.used->flags & cpu_to_virtio16(_vq->vdev, VRING_USED_F_NO_NOTIFY)); } END_USE(vq); return needs_kick; } static void detach_buf_split(struct vring_virtqueue *vq, unsigned int head, void **ctx) { struct vring_desc_extra *extra; unsigned int i, j; __virtio16 nextflag = cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_NEXT); /* Clear data ptr. */ vq->split.desc_state[head].data = NULL; extra = vq->split.desc_extra; /* Put back on free list: unmap first-level descriptors and find end */ i = head; while (vq->split.vring.desc[i].flags & nextflag) { vring_unmap_one_split(vq, &extra[i]); i = vq->split.desc_extra[i].next; vq->vq.num_free++; } vring_unmap_one_split(vq, &extra[i]); vq->split.desc_extra[i].next = vq->free_head; vq->free_head = head; /* Plus final descriptor */ vq->vq.num_free++; if (vq->indirect) { struct vring_desc *indir_desc = vq->split.desc_state[head].indir_desc; u32 len, num; /* Free the indirect table, if any, now that it's unmapped. */ if (!indir_desc) return; len = vq->split.desc_extra[head].len; BUG_ON(!(vq->split.desc_extra[head].flags & VRING_DESC_F_INDIRECT)); BUG_ON(len == 0 || len % sizeof(struct vring_desc)); num = len / sizeof(struct vring_desc); extra = (struct vring_desc_extra *)&indir_desc[num]; if (vq->use_dma_api) { for (j = 0; j < num; j++) vring_unmap_one_split(vq, &extra[j]); } kfree(indir_desc); vq->split.desc_state[head].indir_desc = NULL; } else if (ctx) { *ctx = vq->split.desc_state[head].indir_desc; } } static bool more_used_split(const struct vring_virtqueue *vq) { return vq->last_used_idx != virtio16_to_cpu(vq->vq.vdev, vq->split.vring.used->idx); } static void *virtqueue_get_buf_ctx_split(struct virtqueue *_vq, unsigned int *len, void **ctx) { struct vring_virtqueue *vq = to_vvq(_vq); void *ret; unsigned int i; u16 last_used; START_USE(vq); if (unlikely(vq->broken)) { END_USE(vq); return NULL; } if (!more_used_split(vq)) { pr_debug("No more buffers in queue\n"); END_USE(vq); return NULL; } /* Only get used array entries after they have been exposed by host. */ virtio_rmb(vq->weak_barriers); last_used = (vq->last_used_idx & (vq->split.vring.num - 1)); i = virtio32_to_cpu(_vq->vdev, vq->split.vring.used->ring[last_used].id); *len = virtio32_to_cpu(_vq->vdev, vq->split.vring.used->ring[last_used].len); if (unlikely(i >= vq->split.vring.num)) { BAD_RING(vq, "id %u out of range\n", i); return NULL; } if (unlikely(!vq->split.desc_state[i].data)) { BAD_RING(vq, "id %u is not a head!\n", i); return NULL; } /* detach_buf_split clears data, so grab it now. */ ret = vq->split.desc_state[i].data; detach_buf_split(vq, i, ctx); vq->last_used_idx++; /* If we expect an interrupt for the next entry, tell host * by writing event index and flush out the write before * the read in the next get_buf call. */ if (!(vq->split.avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) virtio_store_mb(vq->weak_barriers, &vring_used_event(&vq->split.vring), cpu_to_virtio16(_vq->vdev, vq->last_used_idx)); LAST_ADD_TIME_INVALID(vq); END_USE(vq); return ret; } static void virtqueue_disable_cb_split(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); if (!(vq->split.avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) { vq->split.avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT; /* * If device triggered an event already it won't trigger one again: * no need to disable. */ if (vq->event_triggered) return; if (vq->event) /* TODO: this is a hack. Figure out a cleaner value to write. */ vring_used_event(&vq->split.vring) = 0x0; else vq->split.vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->split.avail_flags_shadow); } } static unsigned int virtqueue_enable_cb_prepare_split(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); u16 last_used_idx; START_USE(vq); /* We optimistically turn back on interrupts, then check if there was * more to do. */ /* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to * either clear the flags bit or point the event index at the next * entry. Always do both to keep code simple. */ if (vq->split.avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) { vq->split.avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT; if (!vq->event) vq->split.vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->split.avail_flags_shadow); } vring_used_event(&vq->split.vring) = cpu_to_virtio16(_vq->vdev, last_used_idx = vq->last_used_idx); END_USE(vq); return last_used_idx; } static bool virtqueue_poll_split(struct virtqueue *_vq, unsigned int last_used_idx) { struct vring_virtqueue *vq = to_vvq(_vq); return (u16)last_used_idx != virtio16_to_cpu(_vq->vdev, vq->split.vring.used->idx); } static bool virtqueue_enable_cb_delayed_split(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); u16 bufs; START_USE(vq); /* We optimistically turn back on interrupts, then check if there was * more to do. */ /* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to * either clear the flags bit or point the event index at the next * entry. Always update the event index to keep code simple. */ if (vq->split.avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) { vq->split.avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT; if (!vq->event) vq->split.vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->split.avail_flags_shadow); } /* TODO: tune this threshold */ bufs = (u16)(vq->split.avail_idx_shadow - vq->last_used_idx) * 3 / 4; virtio_store_mb(vq->weak_barriers, &vring_used_event(&vq->split.vring), cpu_to_virtio16(_vq->vdev, vq->last_used_idx + bufs)); if (unlikely((u16)(virtio16_to_cpu(_vq->vdev, vq->split.vring.used->idx) - vq->last_used_idx) > bufs)) { END_USE(vq); return false; } END_USE(vq); return true; } static void *virtqueue_detach_unused_buf_split(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); unsigned int i; void *buf; START_USE(vq); for (i = 0; i < vq->split.vring.num; i++) { if (!vq->split.desc_state[i].data) continue; /* detach_buf_split clears data, so grab it now. */ buf = vq->split.desc_state[i].data; detach_buf_split(vq, i, NULL); vq->split.avail_idx_shadow--; vq->split.vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->split.avail_idx_shadow); END_USE(vq); return buf; } /* That should have freed everything. */ BUG_ON(vq->vq.num_free != vq->split.vring.num); END_USE(vq); return NULL; } static void virtqueue_vring_init_split(struct vring_virtqueue_split *vring_split, struct vring_virtqueue *vq) { struct virtio_device *vdev; vdev = vq->vq.vdev; vring_split->avail_flags_shadow = 0; vring_split->avail_idx_shadow = 0; /* No callback? Tell other side not to bother us. */ if (!vq->vq.callback) { vring_split->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT; if (!vq->event) vring_split->vring.avail->flags = cpu_to_virtio16(vdev, vring_split->avail_flags_shadow); } } static void virtqueue_reinit_split(struct vring_virtqueue *vq) { int num; num = vq->split.vring.num; vq->split.vring.avail->flags = 0; vq->split.vring.avail->idx = 0; /* reset avail event */ vq->split.vring.avail->ring[num] = 0; vq->split.vring.used->flags = 0; vq->split.vring.used->idx = 0; /* reset used event */ *(__virtio16 *)&(vq->split.vring.used->ring[num]) = 0; virtqueue_init(vq, num); virtqueue_vring_init_split(&vq->split, vq); } static void virtqueue_vring_attach_split(struct vring_virtqueue *vq, struct vring_virtqueue_split *vring_split) { vq->split = *vring_split; /* Put everything in free lists. */ vq->free_head = 0; } static int vring_alloc_state_extra_split(struct vring_virtqueue_split *vring_split) { struct vring_desc_state_split *state; struct vring_desc_extra *extra; u32 num = vring_split->vring.num; state = kmalloc_array(num, sizeof(struct vring_desc_state_split), GFP_KERNEL); if (!state) goto err_state; extra = vring_alloc_desc_extra(num); if (!extra) goto err_extra; memset(state, 0, num * sizeof(struct vring_desc_state_split)); vring_split->desc_state = state; vring_split->desc_extra = extra; return 0; err_extra: kfree(state); err_state: return -ENOMEM; } static void vring_free_split(struct vring_virtqueue_split *vring_split, struct virtio_device *vdev, struct device *dma_dev) { vring_free_queue(vdev, vring_split->queue_size_in_bytes, vring_split->vring.desc, vring_split->queue_dma_addr, dma_dev); kfree(vring_split->desc_state); kfree(vring_split->desc_extra); } static int vring_alloc_queue_split(struct vring_virtqueue_split *vring_split, struct virtio_device *vdev, u32 num, unsigned int vring_align, bool may_reduce_num, struct device *dma_dev) { void *queue = NULL; dma_addr_t dma_addr; /* We assume num is a power of 2. */ if (!is_power_of_2(num)) { dev_warn(&vdev->dev, "Bad virtqueue length %u\n", num); return -EINVAL; } /* TODO: allocate each queue chunk individually */ for (; num && vring_size(num, vring_align) > PAGE_SIZE; num /= 2) { queue = vring_alloc_queue(vdev, vring_size(num, vring_align), &dma_addr, GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, dma_dev); if (queue) break; if (!may_reduce_num) return -ENOMEM; } if (!num) return -ENOMEM; if (!queue) { /* Try to get a single page. You are my only hope! */ queue = vring_alloc_queue(vdev, vring_size(num, vring_align), &dma_addr, GFP_KERNEL | __GFP_ZERO, dma_dev); } if (!queue) return -ENOMEM; vring_init(&vring_split->vring, num, queue, vring_align); vring_split->queue_dma_addr = dma_addr; vring_split->queue_size_in_bytes = vring_size(num, vring_align); vring_split->vring_align = vring_align; vring_split->may_reduce_num = may_reduce_num; return 0; } static struct virtqueue *__vring_new_virtqueue_split(unsigned int index, struct vring_virtqueue_split *vring_split, struct virtio_device *vdev, bool weak_barriers, bool context, bool (*notify)(struct virtqueue *), void (*callback)(struct virtqueue *), const char *name, struct device *dma_dev) { struct vring_virtqueue *vq; int err; vq = kmalloc(sizeof(*vq), GFP_KERNEL); if (!vq) return NULL; vq->packed_ring = false; vq->vq.callback = callback; vq->vq.vdev = vdev; vq->vq.name = name; vq->vq.index = index; vq->vq.reset = false; vq->we_own_ring = false; vq->notify = notify; vq->weak_barriers = weak_barriers; #ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION vq->broken = true; #else vq->broken = false; #endif vq->dma_dev = dma_dev; vq->use_dma_api = vring_use_dma_api(vdev); vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC) && !context; vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX); if (virtio_has_feature(vdev, VIRTIO_F_ORDER_PLATFORM)) vq->weak_barriers = false; err = vring_alloc_state_extra_split(vring_split); if (err) { kfree(vq); return NULL; } virtqueue_vring_init_split(vring_split, vq); virtqueue_init(vq, vring_split->vring.num); virtqueue_vring_attach_split(vq, vring_split); spin_lock(&vdev->vqs_list_lock); list_add_tail(&vq->vq.list, &vdev->vqs); spin_unlock(&vdev->vqs_list_lock); return &vq->vq; } static struct virtqueue *vring_create_virtqueue_split( unsigned int index, unsigned int num, unsigned int vring_align, struct virtio_device *vdev, bool weak_barriers, bool may_reduce_num, bool context, bool (*notify)(struct virtqueue *), void (*callback)(struct virtqueue *), const char *name, struct device *dma_dev) { struct vring_virtqueue_split vring_split = {}; struct virtqueue *vq; int err; err = vring_alloc_queue_split(&vring_split, vdev, num, vring_align, may_reduce_num, dma_dev); if (err) return NULL; vq = __vring_new_virtqueue_split(index, &vring_split, vdev, weak_barriers, context, notify, callback, name, dma_dev); if (!vq) { vring_free_split(&vring_split, vdev, dma_dev); return NULL; } to_vvq(vq)->we_own_ring = true; return vq; } static int virtqueue_resize_split(struct virtqueue *_vq, u32 num) { struct vring_virtqueue_split vring_split = {}; struct vring_virtqueue *vq = to_vvq(_vq); struct virtio_device *vdev = _vq->vdev; int err; err = vring_alloc_queue_split(&vring_split, vdev, num, vq->split.vring_align, vq->split.may_reduce_num, vring_dma_dev(vq)); if (err) goto err; err = vring_alloc_state_extra_split(&vring_split); if (err) goto err_state_extra; vring_free(&vq->vq); virtqueue_vring_init_split(&vring_split, vq); virtqueue_init(vq, vring_split.vring.num); virtqueue_vring_attach_split(vq, &vring_split); return 0; err_state_extra: vring_free_split(&vring_split, vdev, vring_dma_dev(vq)); err: virtqueue_reinit_split(vq); return -ENOMEM; } /* * Packed ring specific functions - *_packed(). */ static bool packed_used_wrap_counter(u16 last_used_idx) { return !!(last_used_idx & (1 << VRING_PACKED_EVENT_F_WRAP_CTR)); } static u16 packed_last_used(u16 last_used_idx) { return last_used_idx & ~(-(1 << VRING_PACKED_EVENT_F_WRAP_CTR)); } static void vring_unmap_extra_packed(const struct vring_virtqueue *vq, const struct vring_desc_extra *extra) { u16 flags; flags = extra->flags; if (flags & VRING_DESC_F_INDIRECT) { if (!vq->use_dma_api) return; dma_unmap_single(vring_dma_dev(vq), extra->addr, extra->len, (flags & VRING_DESC_F_WRITE) ? DMA_FROM_DEVICE : DMA_TO_DEVICE); } else { if (!vring_need_unmap_buffer(vq, extra)) return; dma_unmap_page(vring_dma_dev(vq), extra->addr, extra->len, (flags & VRING_DESC_F_WRITE) ? DMA_FROM_DEVICE : DMA_TO_DEVICE); } } static struct vring_packed_desc *alloc_indirect_packed(unsigned int total_sg, gfp_t gfp) { struct vring_desc_extra *extra; struct vring_packed_desc *desc; int i, size; /* * We require lowmem mappings for the descriptors because * otherwise virt_to_phys will give us bogus addresses in the * virtqueue. */ gfp &= ~__GFP_HIGHMEM; size = (sizeof(*desc) + sizeof(*extra)) * total_sg; desc = kmalloc(size, gfp); if (!desc) return NULL; extra = (struct vring_desc_extra *)&desc[total_sg]; for (i = 0; i < total_sg; i++) extra[i].next = i + 1; return desc; } static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq, struct scatterlist *sgs[], unsigned int total_sg, unsigned int out_sgs, unsigned int in_sgs, void *data, bool premapped, gfp_t gfp) { struct vring_desc_extra *extra; struct vring_packed_desc *desc; struct scatterlist *sg; unsigned int i, n, err_idx, len; u16 head, id; dma_addr_t addr; head = vq->packed.next_avail_idx; desc = alloc_indirect_packed(total_sg, gfp); if (!desc) return -ENOMEM; extra = (struct vring_desc_extra *)&desc[total_sg]; if (unlikely(vq->vq.num_free < 1)) { pr_debug("Can't add buf len 1 - avail = 0\n"); kfree(desc); END_USE(vq); return -ENOSPC; } i = 0; id = vq->free_head; BUG_ON(id == vq->packed.vring.num); for (n = 0; n < out_sgs + in_sgs; n++) { for (sg = sgs[n]; sg; sg = sg_next(sg)) { if (vring_map_one_sg(vq, sg, n < out_sgs ? DMA_TO_DEVICE : DMA_FROM_DEVICE, &addr, &len, premapped)) goto unmap_release; desc[i].flags = cpu_to_le16(n < out_sgs ? 0 : VRING_DESC_F_WRITE); desc[i].addr = cpu_to_le64(addr); desc[i].len = cpu_to_le32(len); if (unlikely(vq->use_dma_api)) { extra[i].addr = premapped ? DMA_MAPPING_ERROR : addr; extra[i].len = len; extra[i].flags = n < out_sgs ? 0 : VRING_DESC_F_WRITE; } i++; } } /* Now that the indirect table is filled in, map it. */ addr = vring_map_single(vq, desc, total_sg * sizeof(struct vring_packed_desc), DMA_TO_DEVICE); if (vring_mapping_error(vq, addr)) goto unmap_release; vq->packed.vring.desc[head].addr = cpu_to_le64(addr); vq->packed.vring.desc[head].len = cpu_to_le32(total_sg * sizeof(struct vring_packed_desc)); vq->packed.vring.desc[head].id = cpu_to_le16(id); if (vq->use_dma_api) { vq->packed.desc_extra[id].addr = addr; vq->packed.desc_extra[id].len = total_sg * sizeof(struct vring_packed_desc); vq->packed.desc_extra[id].flags = VRING_DESC_F_INDIRECT | vq->packed.avail_used_flags; } /* * A driver MUST NOT make the first descriptor in the list * available before all subsequent descriptors comprising * the list are made available. */ virtio_wmb(vq->weak_barriers); vq->packed.vring.desc[head].flags = cpu_to_le16(VRING_DESC_F_INDIRECT | vq->packed.avail_used_flags); /* We're using some buffers from the free list. */ vq->vq.num_free -= 1; /* Update free pointer */ n = head + 1; if (n >= vq->packed.vring.num) { n = 0; vq->packed.avail_wrap_counter ^= 1; vq->packed.avail_used_flags ^= 1 << VRING_PACKED_DESC_F_AVAIL | 1 << VRING_PACKED_DESC_F_USED; } vq->packed.next_avail_idx = n; vq->free_head = vq->packed.desc_extra[id].next; /* Store token and indirect buffer state. */ vq->packed.desc_state[id].num = 1; vq->packed.desc_state[id].data = data; vq->packed.desc_state[id].indir_desc = desc; vq->packed.desc_state[id].last = id; vq->num_added += 1; pr_debug("Added buffer head %i to %p\n", head, vq); END_USE(vq); return 0; unmap_release: err_idx = i; for (i = 0; i < err_idx; i++) vring_unmap_extra_packed(vq, &extra[i]); kfree(desc); END_USE(vq); return -ENOMEM; } static inline int virtqueue_add_packed(struct virtqueue *_vq, struct scatterlist *sgs[], unsigned int total_sg, unsigned int out_sgs, unsigned int in_sgs, void *data, void *ctx, bool premapped, gfp_t gfp) { struct vring_virtqueue *vq = to_vvq(_vq); struct vring_packed_desc *desc; struct scatterlist *sg; unsigned int i, n, c, descs_used, err_idx, len; __le16 head_flags, flags; u16 head, id, prev, curr, avail_used_flags; int err; START_USE(vq); BUG_ON(data == NULL); BUG_ON(ctx && vq->indirect); if (unlikely(vq->broken)) { END_USE(vq); return -EIO; } LAST_ADD_TIME_UPDATE(vq); BUG_ON(total_sg == 0); if (virtqueue_use_indirect(vq, total_sg)) { err = virtqueue_add_indirect_packed(vq, sgs, total_sg, out_sgs, in_sgs, data, premapped, gfp); if (err != -ENOMEM) { END_USE(vq); return err; } /* fall back on direct */ } head = vq->packed.next_avail_idx; avail_used_flags = vq->packed.avail_used_flags; WARN_ON_ONCE(total_sg > vq->packed.vring.num && !vq->indirect); desc = vq->packed.vring.desc; i = head; descs_used = total_sg; if (unlikely(vq->vq.num_free < descs_used)) { pr_debug("Can't add buf len %i - avail = %i\n", descs_used, vq->vq.num_free); END_USE(vq); return -ENOSPC; } id = vq->free_head; BUG_ON(id == vq->packed.vring.num); curr = id; c = 0; for (n = 0; n < out_sgs + in_sgs; n++) { for (sg = sgs[n]; sg; sg = sg_next(sg)) { dma_addr_t addr; if (vring_map_one_sg(vq, sg, n < out_sgs ? DMA_TO_DEVICE : DMA_FROM_DEVICE, &addr, &len, premapped)) goto unmap_release; flags = cpu_to_le16(vq->packed.avail_used_flags | (++c == total_sg ? 0 : VRING_DESC_F_NEXT) | (n < out_sgs ? 0 : VRING_DESC_F_WRITE)); if (i == head) head_flags = flags; else desc[i].flags = flags; desc[i].addr = cpu_to_le64(addr); desc[i].len = cpu_to_le32(len); desc[i].id = cpu_to_le16(id); if (unlikely(vq->use_dma_api)) { vq->packed.desc_extra[curr].addr = premapped ? DMA_MAPPING_ERROR : addr; vq->packed.desc_extra[curr].len = len; vq->packed.desc_extra[curr].flags = le16_to_cpu(flags); } prev = curr; curr = vq->packed.desc_extra[curr].next; if ((unlikely(++i >= vq->packed.vring.num))) { i = 0; vq->packed.avail_used_flags ^= 1 << VRING_PACKED_DESC_F_AVAIL | 1 << VRING_PACKED_DESC_F_USED; } } } if (i <= head) vq->packed.avail_wrap_counter ^= 1; /* We're using some buffers from the free list. */ vq->vq.num_free -= descs_used; /* Update free pointer */ vq->packed.next_avail_idx = i; vq->free_head = curr; /* Store token. */ vq->packed.desc_state[id].num = descs_used; vq->packed.desc_state[id].data = data; vq->packed.desc_state[id].indir_desc = ctx; vq->packed.desc_state[id].last = prev; /* * A driver MUST NOT make the first descriptor in the list * available before all subsequent descriptors comprising * the list are made available. */ virtio_wmb(vq->weak_barriers); vq->packed.vring.desc[head].flags = head_flags; vq->num_added += descs_used; pr_debug("Added buffer head %i to %p\n", head, vq); END_USE(vq); return 0; unmap_release: err_idx = i; i = head; curr = vq->free_head; vq->packed.avail_used_flags = avail_used_flags; for (n = 0; n < total_sg; n++) { if (i == err_idx) break; vring_unmap_extra_packed(vq, &vq->packed.desc_extra[curr]); curr = vq->packed.desc_extra[curr].next; i++; if (i >= vq->packed.vring.num) i = 0; } END_USE(vq); return -EIO; } static bool virtqueue_kick_prepare_packed(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); u16 new, old, off_wrap, flags, wrap_counter, event_idx; bool needs_kick; union { struct { __le16 off_wrap; __le16 flags; }; u32 u32; } snapshot; START_USE(vq); /* * We need to expose the new flags value before checking notification * suppressions. */ virtio_mb(vq->weak_barriers); old = vq->packed.next_avail_idx - vq->num_added; new = vq->packed.next_avail_idx; vq->num_added = 0; snapshot.u32 = *(u32 *)vq->packed.vring.device; flags = le16_to_cpu(snapshot.flags); LAST_ADD_TIME_CHECK(vq); LAST_ADD_TIME_INVALID(vq); if (flags != VRING_PACKED_EVENT_FLAG_DESC) { needs_kick = (flags != VRING_PACKED_EVENT_FLAG_DISABLE); goto out; } off_wrap = le16_to_cpu(snapshot.off_wrap); wrap_counter = off_wrap >> VRING_PACKED_EVENT_F_WRAP_CTR; event_idx = off_wrap & ~(1 << VRING_PACKED_EVENT_F_WRAP_CTR); if (wrap_counter != vq->packed.avail_wrap_counter) event_idx -= vq->packed.vring.num; needs_kick = vring_need_event(event_idx, new, old); out: END_USE(vq); return needs_kick; } static void detach_buf_packed(struct vring_virtqueue *vq, unsigned int id, void **ctx) { struct vring_desc_state_packed *state = NULL; struct vring_packed_desc *desc; unsigned int i, curr; state = &vq->packed.desc_state[id]; /* Clear data ptr. */ state->data = NULL; vq->packed.desc_extra[state->last].next = vq->free_head; vq->free_head = id; vq->vq.num_free += state->num; if (unlikely(vq->use_dma_api)) { curr = id; for (i = 0; i < state->num; i++) { vring_unmap_extra_packed(vq, &vq->packed.desc_extra[curr]); curr = vq->packed.desc_extra[curr].next; } } if (vq->indirect) { struct vring_desc_extra *extra; u32 len, num; /* Free the indirect table, if any, now that it's unmapped. */ desc = state->indir_desc; if (!desc) return; if (vq->use_dma_api) { len = vq->packed.desc_extra[id].len; num = len / sizeof(struct vring_packed_desc); extra = (struct vring_desc_extra *)&desc[num]; for (i = 0; i < num; i++) vring_unmap_extra_packed(vq, &extra[i]); } kfree(desc); state->indir_desc = NULL; } else if (ctx) { *ctx = state->indir_desc; } } static inline bool is_used_desc_packed(const struct vring_virtqueue *vq, u16 idx, bool used_wrap_counter) { bool avail, used; u16 flags; flags = le16_to_cpu(vq->packed.vring.desc[idx].flags); avail = !!(flags & (1 << VRING_PACKED_DESC_F_AVAIL)); used = !!(flags & (1 << VRING_PACKED_DESC_F_USED)); return avail == used && used == used_wrap_counter; } static bool more_used_packed(const struct vring_virtqueue *vq) { u16 last_used; u16 last_used_idx; bool used_wrap_counter; last_used_idx = READ_ONCE(vq->last_used_idx); last_used = packed_last_used(last_used_idx); used_wrap_counter = packed_used_wrap_counter(last_used_idx); return is_used_desc_packed(vq, last_used, used_wrap_counter); } static void *virtqueue_get_buf_ctx_packed(struct virtqueue *_vq, unsigned int *len, void **ctx) { struct vring_virtqueue *vq = to_vvq(_vq); u16 last_used, id, last_used_idx; bool used_wrap_counter; void *ret; START_USE(vq); if (unlikely(vq->broken)) { END_USE(vq); return NULL; } if (!more_used_packed(vq)) { pr_debug("No more buffers in queue\n"); END_USE(vq); return NULL; } /* Only get used elements after they have been exposed by host. */ virtio_rmb(vq->weak_barriers); last_used_idx = READ_ONCE(vq->last_used_idx); used_wrap_counter = packed_used_wrap_counter(last_used_idx); last_used = packed_last_used(last_used_idx); id = le16_to_cpu(vq->packed.vring.desc[last_used].id); *len = le32_to_cpu(vq->packed.vring.desc[last_used].len); if (unlikely(id >= vq->packed.vring.num)) { BAD_RING(vq, "id %u out of range\n", id); return NULL; } if (unlikely(!vq->packed.desc_state[id].data)) { BAD_RING(vq, "id %u is not a head!\n", id); return NULL; } /* detach_buf_packed clears data, so grab it now. */ ret = vq->packed.desc_state[id].data; detach_buf_packed(vq, id, ctx); last_used += vq->packed.desc_state[id].num; if (unlikely(last_used >= vq->packed.vring.num)) { last_used -= vq->packed.vring.num; used_wrap_counter ^= 1; } last_used = (last_used | (used_wrap_counter << VRING_PACKED_EVENT_F_WRAP_CTR)); WRITE_ONCE(vq->last_used_idx, last_used); /* * If we expect an interrupt for the next entry, tell host * by writing event index and flush out the write before * the read in the next get_buf call. */ if (vq->packed.event_flags_shadow == VRING_PACKED_EVENT_FLAG_DESC) virtio_store_mb(vq->weak_barriers, &vq->packed.vring.driver->off_wrap, cpu_to_le16(vq->last_used_idx)); LAST_ADD_TIME_INVALID(vq); END_USE(vq); return ret; } static void virtqueue_disable_cb_packed(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); if (vq->packed.event_flags_shadow != VRING_PACKED_EVENT_FLAG_DISABLE) { vq->packed.event_flags_shadow = VRING_PACKED_EVENT_FLAG_DISABLE; /* * If device triggered an event already it won't trigger one again: * no need to disable. */ if (vq->event_triggered) return; vq->packed.vring.driver->flags = cpu_to_le16(vq->packed.event_flags_shadow); } } static unsigned int virtqueue_enable_cb_prepare_packed(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); START_USE(vq); /* * We optimistically turn back on interrupts, then check if there was * more to do. */ if (vq->event) { vq->packed.vring.driver->off_wrap = cpu_to_le16(vq->last_used_idx); /* * We need to update event offset and event wrap * counter first before updating event flags. */ virtio_wmb(vq->weak_barriers); } if (vq->packed.event_flags_shadow == VRING_PACKED_EVENT_FLAG_DISABLE) { vq->packed.event_flags_shadow = vq->event ? VRING_PACKED_EVENT_FLAG_DESC : VRING_PACKED_EVENT_FLAG_ENABLE; vq->packed.vring.driver->flags = cpu_to_le16(vq->packed.event_flags_shadow); } END_USE(vq); return vq->last_used_idx; } static bool virtqueue_poll_packed(struct virtqueue *_vq, u16 off_wrap) { struct vring_virtqueue *vq = to_vvq(_vq); bool wrap_counter; u16 used_idx; wrap_counter = off_wrap >> VRING_PACKED_EVENT_F_WRAP_CTR; used_idx = off_wrap & ~(1 << VRING_PACKED_EVENT_F_WRAP_CTR); return is_used_desc_packed(vq, used_idx, wrap_counter); } static bool virtqueue_enable_cb_delayed_packed(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); u16 used_idx, wrap_counter, last_used_idx; u16 bufs; START_USE(vq); /* * We optimistically turn back on interrupts, then check if there was * more to do. */ if (vq->event) { /* TODO: tune this threshold */ bufs = (vq->packed.vring.num - vq->vq.num_free) * 3 / 4; last_used_idx = READ_ONCE(vq->last_used_idx); wrap_counter = packed_used_wrap_counter(last_used_idx); used_idx = packed_last_used(last_used_idx) + bufs; if (used_idx >= vq->packed.vring.num) { used_idx -= vq->packed.vring.num; wrap_counter ^= 1; } vq->packed.vring.driver->off_wrap = cpu_to_le16(used_idx | (wrap_counter << VRING_PACKED_EVENT_F_WRAP_CTR)); /* * We need to update event offset and event wrap * counter first before updating event flags. */ virtio_wmb(vq->weak_barriers); } if (vq->packed.event_flags_shadow == VRING_PACKED_EVENT_FLAG_DISABLE) { vq->packed.event_flags_shadow = vq->event ? VRING_PACKED_EVENT_FLAG_DESC : VRING_PACKED_EVENT_FLAG_ENABLE; vq->packed.vring.driver->flags = cpu_to_le16(vq->packed.event_flags_shadow); } /* * We need to update event suppression structure first * before re-checking for more used buffers. */ virtio_mb(vq->weak_barriers); last_used_idx = READ_ONCE(vq->last_used_idx); wrap_counter = packed_used_wrap_counter(last_used_idx); used_idx = packed_last_used(last_used_idx); if (is_used_desc_packed(vq, used_idx, wrap_counter)) { END_USE(vq); return false; } END_USE(vq); return true; } static void *virtqueue_detach_unused_buf_packed(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); unsigned int i; void *buf; START_USE(vq); for (i = 0; i < vq->packed.vring.num; i++) { if (!vq->packed.desc_state[i].data) continue; /* detach_buf clears data, so grab it now. */ buf = vq->packed.desc_state[i].data; detach_buf_packed(vq, i, NULL); END_USE(vq); return buf; } /* That should have freed everything. */ BUG_ON(vq->vq.num_free != vq->packed.vring.num); END_USE(vq); return NULL; } static struct vring_desc_extra *vring_alloc_desc_extra(unsigned int num) { struct vring_desc_extra *desc_extra; unsigned int i; desc_extra = kmalloc_array(num, sizeof(struct vring_desc_extra), GFP_KERNEL); if (!desc_extra) return NULL; memset(desc_extra, 0, num * sizeof(struct vring_desc_extra)); for (i = 0; i < num - 1; i++) desc_extra[i].next = i + 1; return desc_extra; } static void vring_free_packed(struct vring_virtqueue_packed *vring_packed, struct virtio_device *vdev, struct device *dma_dev) { if (vring_packed->vring.desc) vring_free_queue(vdev, vring_packed->ring_size_in_bytes, vring_packed->vring.desc, vring_packed->ring_dma_addr, dma_dev); if (vring_packed->vring.driver) vring_free_queue(vdev, vring_packed->event_size_in_bytes, vring_packed->vring.driver, vring_packed->driver_event_dma_addr, dma_dev); if (vring_packed->vring.device) vring_free_queue(vdev, vring_packed->event_size_in_bytes, vring_packed->vring.device, vring_packed->device_event_dma_addr, dma_dev); kfree(vring_packed->desc_state); kfree(vring_packed->desc_extra); } static int vring_alloc_queue_packed(struct vring_virtqueue_packed *vring_packed, struct virtio_device *vdev, u32 num, struct device *dma_dev) { struct vring_packed_desc *ring; struct vring_packed_desc_event *driver, *device; dma_addr_t ring_dma_addr, driver_event_dma_addr, device_event_dma_addr; size_t ring_size_in_bytes, event_size_in_bytes; ring_size_in_bytes = num * sizeof(struct vring_packed_desc); ring = vring_alloc_queue(vdev, ring_size_in_bytes, &ring_dma_addr, GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, dma_dev); if (!ring) goto err; vring_packed->vring.desc = ring; vring_packed->ring_dma_addr = ring_dma_addr; vring_packed->ring_size_in_bytes = ring_size_in_bytes; event_size_in_bytes = sizeof(struct vring_packed_desc_event); driver = vring_alloc_queue(vdev, event_size_in_bytes, &driver_event_dma_addr, GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, dma_dev); if (!driver) goto err; vring_packed->vring.driver = driver; vring_packed->event_size_in_bytes = event_size_in_bytes; vring_packed->driver_event_dma_addr = driver_event_dma_addr; device = vring_alloc_queue(vdev, event_size_in_bytes, &device_event_dma_addr, GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, dma_dev); if (!device) goto err; vring_packed->vring.device = device; vring_packed->device_event_dma_addr = device_event_dma_addr; vring_packed->vring.num = num; return 0; err: vring_free_packed(vring_packed, vdev, dma_dev); return -ENOMEM; } static int vring_alloc_state_extra_packed(struct vring_virtqueue_packed *vring_packed) { struct vring_desc_state_packed *state; struct vring_desc_extra *extra; u32 num = vring_packed->vring.num; state = kmalloc_array(num, sizeof(struct vring_desc_state_packed), GFP_KERNEL); if (!state) goto err_desc_state; memset(state, 0, num * sizeof(struct vring_desc_state_packed)); extra = vring_alloc_desc_extra(num); if (!extra) goto err_desc_extra; vring_packed->desc_state = state; vring_packed->desc_extra = extra; return 0; err_desc_extra: kfree(state); err_desc_state: return -ENOMEM; } static void virtqueue_vring_init_packed(struct vring_virtqueue_packed *vring_packed, bool callback) { vring_packed->next_avail_idx = 0; vring_packed->avail_wrap_counter = 1; vring_packed->event_flags_shadow = 0; vring_packed->avail_used_flags = 1 << VRING_PACKED_DESC_F_AVAIL; /* No callback? Tell other side not to bother us. */ if (!callback) { vring_packed->event_flags_shadow = VRING_PACKED_EVENT_FLAG_DISABLE; vring_packed->vring.driver->flags = cpu_to_le16(vring_packed->event_flags_shadow); } } static void virtqueue_vring_attach_packed(struct vring_virtqueue *vq, struct vring_virtqueue_packed *vring_packed) { vq->packed = *vring_packed; /* Put everything in free lists. */ vq->free_head = 0; } static void virtqueue_reinit_packed(struct vring_virtqueue *vq) { memset(vq->packed.vring.device, 0, vq->packed.event_size_in_bytes); memset(vq->packed.vring.driver, 0, vq->packed.event_size_in_bytes); /* we need to reset the desc.flags. For more, see is_used_desc_packed() */ memset(vq->packed.vring.desc, 0, vq->packed.ring_size_in_bytes); virtqueue_init(vq, vq->packed.vring.num); virtqueue_vring_init_packed(&vq->packed, !!vq->vq.callback); } static struct virtqueue *__vring_new_virtqueue_packed(unsigned int index, struct vring_virtqueue_packed *vring_packed, struct virtio_device *vdev, bool weak_barriers, bool context, bool (*notify)(struct virtqueue *), void (*callback)(struct virtqueue *), const char *name, struct device *dma_dev) { struct vring_virtqueue *vq; int err; vq = kmalloc(sizeof(*vq), GFP_KERNEL); if (!vq) return NULL; vq->vq.callback = callback; vq->vq.vdev = vdev; vq->vq.name = name; vq->vq.index = index; vq->vq.reset = false; vq->we_own_ring = false; vq->notify = notify; vq->weak_barriers = weak_barriers; #ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION vq->broken = true; #else vq->broken = false; #endif vq->packed_ring = true; vq->dma_dev = dma_dev; vq->use_dma_api = vring_use_dma_api(vdev); vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC) && !context; vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX); if (virtio_has_feature(vdev, VIRTIO_F_ORDER_PLATFORM)) vq->weak_barriers = false; err = vring_alloc_state_extra_packed(vring_packed); if (err) { kfree(vq); return NULL; } virtqueue_vring_init_packed(vring_packed, !!callback); virtqueue_init(vq, vring_packed->vring.num); virtqueue_vring_attach_packed(vq, vring_packed); spin_lock(&vdev->vqs_list_lock); list_add_tail(&vq->vq.list, &vdev->vqs); spin_unlock(&vdev->vqs_list_lock); return &vq->vq; } static struct virtqueue *vring_create_virtqueue_packed( unsigned int index, unsigned int num, unsigned int vring_align, struct virtio_device *vdev, bool weak_barriers, bool may_reduce_num, bool context, bool (*notify)(struct virtqueue *), void (*callback)(struct virtqueue *), const char *name, struct device *dma_dev) { struct vring_virtqueue_packed vring_packed = {}; struct virtqueue *vq; if (vring_alloc_queue_packed(&vring_packed, vdev, num, dma_dev)) return NULL; vq = __vring_new_virtqueue_packed(index, &vring_packed, vdev, weak_barriers, context, notify, callback, name, dma_dev); if (!vq) { vring_free_packed(&vring_packed, vdev, dma_dev); return NULL; } to_vvq(vq)->we_own_ring = true; return vq; } static int virtqueue_resize_packed(struct virtqueue *_vq, u32 num) { struct vring_virtqueue_packed vring_packed = {}; struct vring_virtqueue *vq = to_vvq(_vq); struct virtio_device *vdev = _vq->vdev; int err; if (vring_alloc_queue_packed(&vring_packed, vdev, num, vring_dma_dev(vq))) goto err_ring; err = vring_alloc_state_extra_packed(&vring_packed); if (err) goto err_state_extra; vring_free(&vq->vq); virtqueue_vring_init_packed(&vring_packed, !!vq->vq.callback); virtqueue_init(vq, vring_packed.vring.num); virtqueue_vring_attach_packed(vq, &vring_packed); return 0; err_state_extra: vring_free_packed(&vring_packed, vdev, vring_dma_dev(vq)); err_ring: virtqueue_reinit_packed(vq); return -ENOMEM; } static int virtqueue_disable_and_recycle(struct virtqueue *_vq, void (*recycle)(struct virtqueue *vq, void *buf)) { struct vring_virtqueue *vq = to_vvq(_vq); struct virtio_device *vdev = vq->vq.vdev; void *buf; int err; if (!vq->we_own_ring) return -EPERM; if (!vdev->config->disable_vq_and_reset) return -ENOENT; if (!vdev->config->enable_vq_after_reset) return -ENOENT; err = vdev->config->disable_vq_and_reset(_vq); if (err) return err; while ((buf = virtqueue_detach_unused_buf(_vq)) != NULL) recycle(_vq, buf); return 0; } static int virtqueue_enable_after_reset(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); struct virtio_device *vdev = vq->vq.vdev; if (vdev->config->enable_vq_after_reset(_vq)) return -EBUSY; return 0; } /* * Generic functions and exported symbols. */ static inline int virtqueue_add(struct virtqueue *_vq, struct scatterlist *sgs[], unsigned int total_sg, unsigned int out_sgs, unsigned int in_sgs, void *data, void *ctx, bool premapped, gfp_t gfp) { struct vring_virtqueue *vq = to_vvq(_vq); return vq->packed_ring ? virtqueue_add_packed(_vq, sgs, total_sg, out_sgs, in_sgs, data, ctx, premapped, gfp) : virtqueue_add_split(_vq, sgs, total_sg, out_sgs, in_sgs, data, ctx, premapped, gfp); } /** * virtqueue_add_sgs - expose buffers to other end * @_vq: the struct virtqueue we're talking about. * @sgs: array of terminated scatterlists. * @out_sgs: the number of scatterlists readable by other side * @in_sgs: the number of scatterlists which are writable (after readable ones) * @data: the token identifying the buffer. * @gfp: how to do memory allocations (if necessary). * * Caller must ensure we don't call this with other virtqueue operations * at the same time (except where noted). * * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO). */ int virtqueue_add_sgs(struct virtqueue *_vq, struct scatterlist *sgs[], unsigned int out_sgs, unsigned int in_sgs, void *data, gfp_t gfp) { unsigned int i, total_sg = 0; /* Count them first. */ for (i = 0; i < out_sgs + in_sgs; i++) { struct scatterlist *sg; for (sg = sgs[i]; sg; sg = sg_next(sg)) total_sg++; } return virtqueue_add(_vq, sgs, total_sg, out_sgs, in_sgs, data, NULL, false, gfp); } EXPORT_SYMBOL_GPL(virtqueue_add_sgs); /** * virtqueue_add_outbuf - expose output buffers to other end * @vq: the struct virtqueue we're talking about. * @sg: scatterlist (must be well-formed and terminated!) * @num: the number of entries in @sg readable by other side * @data: the token identifying the buffer. * @gfp: how to do memory allocations (if necessary). * * Caller must ensure we don't call this with other virtqueue operations * at the same time (except where noted). * * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO). */ int virtqueue_add_outbuf(struct virtqueue *vq, struct scatterlist *sg, unsigned int num, void *data, gfp_t gfp) { return virtqueue_add(vq, &sg, num, 1, 0, data, NULL, false, gfp); } EXPORT_SYMBOL_GPL(virtqueue_add_outbuf); /** * virtqueue_add_outbuf_premapped - expose output buffers to other end * @vq: the struct virtqueue we're talking about. * @sg: scatterlist (must be well-formed and terminated!) * @num: the number of entries in @sg readable by other side * @data: the token identifying the buffer. * @gfp: how to do memory allocations (if necessary). * * Caller must ensure we don't call this with other virtqueue operations * at the same time (except where noted). * * Return: * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO). */ int virtqueue_add_outbuf_premapped(struct virtqueue *vq, struct scatterlist *sg, unsigned int num, void *data, gfp_t gfp) { return virtqueue_add(vq, &sg, num, 1, 0, data, NULL, true, gfp); } EXPORT_SYMBOL_GPL(virtqueue_add_outbuf_premapped); /** * virtqueue_add_inbuf - expose input buffers to other end * @vq: the struct virtqueue we're talking about. * @sg: scatterlist (must be well-formed and terminated!) * @num: the number of entries in @sg writable by other side * @data: the token identifying the buffer. * @gfp: how to do memory allocations (if necessary). * * Caller must ensure we don't call this with other virtqueue operations * at the same time (except where noted). * * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO). */ int virtqueue_add_inbuf(struct virtqueue *vq, struct scatterlist *sg, unsigned int num, void *data, gfp_t gfp) { return virtqueue_add(vq, &sg, num, 0, 1, data, NULL, false, gfp); } EXPORT_SYMBOL_GPL(virtqueue_add_inbuf); /** * virtqueue_add_inbuf_ctx - expose input buffers to other end * @vq: the struct virtqueue we're talking about. * @sg: scatterlist (must be well-formed and terminated!) * @num: the number of entries in @sg writable by other side * @data: the token identifying the buffer. * @ctx: extra context for the token * @gfp: how to do memory allocations (if necessary). * * Caller must ensure we don't call this with other virtqueue operations * at the same time (except where noted). * * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO). */ int virtqueue_add_inbuf_ctx(struct virtqueue *vq, struct scatterlist *sg, unsigned int num, void *data, void *ctx, gfp_t gfp) { return virtqueue_add(vq, &sg, num, 0, 1, data, ctx, false, gfp); } EXPORT_SYMBOL_GPL(virtqueue_add_inbuf_ctx); /** * virtqueue_add_inbuf_premapped - expose input buffers to other end * @vq: the struct virtqueue we're talking about. * @sg: scatterlist (must be well-formed and terminated!) * @num: the number of entries in @sg writable by other side * @data: the token identifying the buffer. * @ctx: extra context for the token * @gfp: how to do memory allocations (if necessary). * * Caller must ensure we don't call this with other virtqueue operations * at the same time (except where noted). * * Return: * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO). */ int virtqueue_add_inbuf_premapped(struct virtqueue *vq, struct scatterlist *sg, unsigned int num, void *data, void *ctx, gfp_t gfp) { return virtqueue_add(vq, &sg, num, 0, 1, data, ctx, true, gfp); } EXPORT_SYMBOL_GPL(virtqueue_add_inbuf_premapped); /** * virtqueue_dma_dev - get the dma dev * @_vq: the struct virtqueue we're talking about. * * Returns the dma dev. That can been used for dma api. */ struct device *virtqueue_dma_dev(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); if (vq->use_dma_api) return vring_dma_dev(vq); else return NULL; } EXPORT_SYMBOL_GPL(virtqueue_dma_dev); /** * virtqueue_kick_prepare - first half of split virtqueue_kick call. * @_vq: the struct virtqueue * * Instead of virtqueue_kick(), you can do: * if (virtqueue_kick_prepare(vq)) * virtqueue_notify(vq); * * This is sometimes useful because the virtqueue_kick_prepare() needs * to be serialized, but the actual virtqueue_notify() call does not. */ bool virtqueue_kick_prepare(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); return vq->packed_ring ? virtqueue_kick_prepare_packed(_vq) : virtqueue_kick_prepare_split(_vq); } EXPORT_SYMBOL_GPL(virtqueue_kick_prepare); /** * virtqueue_notify - second half of split virtqueue_kick call. * @_vq: the struct virtqueue * * This does not need to be serialized. * * Returns false if host notify failed or queue is broken, otherwise true. */ bool virtqueue_notify(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); if (unlikely(vq->broken)) return false; /* Prod other side to tell it about changes. */ if (!vq->notify(_vq)) { vq->broken = true; return false; } return true; } EXPORT_SYMBOL_GPL(virtqueue_notify); /** * virtqueue_kick - update after add_buf * @vq: the struct virtqueue * * After one or more virtqueue_add_* calls, invoke this to kick * the other side. * * Caller must ensure we don't call this with other virtqueue * operations at the same time (except where noted). * * Returns false if kick failed, otherwise true. */ bool virtqueue_kick(struct virtqueue *vq) { if (virtqueue_kick_prepare(vq)) return virtqueue_notify(vq); return true; } EXPORT_SYMBOL_GPL(virtqueue_kick); /** * virtqueue_get_buf_ctx - get the next used buffer * @_vq: the struct virtqueue we're talking about. * @len: the length written into the buffer * @ctx: extra context for the token * * If the device wrote data into the buffer, @len will be set to the * amount written. This means you don't need to clear the buffer * beforehand to ensure there's no data leakage in the case of short * writes. * * Caller must ensure we don't call this with other virtqueue * operations at the same time (except where noted). * * Returns NULL if there are no used buffers, or the "data" token * handed to virtqueue_add_*(). */ void *virtqueue_get_buf_ctx(struct virtqueue *_vq, unsigned int *len, void **ctx) { struct vring_virtqueue *vq = to_vvq(_vq); return vq->packed_ring ? virtqueue_get_buf_ctx_packed(_vq, len, ctx) : virtqueue_get_buf_ctx_split(_vq, len, ctx); } EXPORT_SYMBOL_GPL(virtqueue_get_buf_ctx); void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len) { return virtqueue_get_buf_ctx(_vq, len, NULL); } EXPORT_SYMBOL_GPL(virtqueue_get_buf); /** * virtqueue_disable_cb - disable callbacks * @_vq: the struct virtqueue we're talking about. * * Note that this is not necessarily synchronous, hence unreliable and only * useful as an optimization. * * Unlike other operations, this need not be serialized. */ void virtqueue_disable_cb(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); if (vq->packed_ring) virtqueue_disable_cb_packed(_vq); else virtqueue_disable_cb_split(_vq); } EXPORT_SYMBOL_GPL(virtqueue_disable_cb); /** * virtqueue_enable_cb_prepare - restart callbacks after disable_cb * @_vq: the struct virtqueue we're talking about. * * This re-enables callbacks; it returns current queue state * in an opaque unsigned value. This value should be later tested by * virtqueue_poll, to detect a possible race between the driver checking for * more work, and enabling callbacks. * * Caller must ensure we don't call this with other virtqueue * operations at the same time (except where noted). */ unsigned int virtqueue_enable_cb_prepare(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); if (vq->event_triggered) vq->event_triggered = false; return vq->packed_ring ? virtqueue_enable_cb_prepare_packed(_vq) : virtqueue_enable_cb_prepare_split(_vq); } EXPORT_SYMBOL_GPL(virtqueue_enable_cb_prepare); /** * virtqueue_poll - query pending used buffers * @_vq: the struct virtqueue we're talking about. * @last_used_idx: virtqueue state (from call to virtqueue_enable_cb_prepare). * * Returns "true" if there are pending used buffers in the queue. * * This does not need to be serialized. */ bool virtqueue_poll(struct virtqueue *_vq, unsigned int last_used_idx) { struct vring_virtqueue *vq = to_vvq(_vq); if (unlikely(vq->broken)) return false; virtio_mb(vq->weak_barriers); return vq->packed_ring ? virtqueue_poll_packed(_vq, last_used_idx) : virtqueue_poll_split(_vq, last_used_idx); } EXPORT_SYMBOL_GPL(virtqueue_poll); /** * virtqueue_enable_cb - restart callbacks after disable_cb. * @_vq: the struct virtqueue we're talking about. * * This re-enables callbacks; it returns "false" if there are pending * buffers in the queue, to detect a possible race between the driver * checking for more work, and enabling callbacks. * * Caller must ensure we don't call this with other virtqueue * operations at the same time (except where noted). */ bool virtqueue_enable_cb(struct virtqueue *_vq) { unsigned int last_used_idx = virtqueue_enable_cb_prepare(_vq); return !virtqueue_poll(_vq, last_used_idx); } EXPORT_SYMBOL_GPL(virtqueue_enable_cb); /** * virtqueue_enable_cb_delayed - restart callbacks after disable_cb. * @_vq: the struct virtqueue we're talking about. * * This re-enables callbacks but hints to the other side to delay * interrupts until most of the available buffers have been processed; * it returns "false" if there are many pending buffers in the queue, * to detect a possible race between the driver checking for more work, * and enabling callbacks. * * Caller must ensure we don't call this with other virtqueue * operations at the same time (except where noted). */ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); if (vq->event_triggered) data_race(vq->event_triggered = false); return vq->packed_ring ? virtqueue_enable_cb_delayed_packed(_vq) : virtqueue_enable_cb_delayed_split(_vq); } EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed); /** * virtqueue_detach_unused_buf - detach first unused buffer * @_vq: the struct virtqueue we're talking about. * * Returns NULL or the "data" token handed to virtqueue_add_*(). * This is not valid on an active queue; it is useful for device * shutdown or the reset queue. */ void *virtqueue_detach_unused_buf(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); return vq->packed_ring ? virtqueue_detach_unused_buf_packed(_vq) : virtqueue_detach_unused_buf_split(_vq); } EXPORT_SYMBOL_GPL(virtqueue_detach_unused_buf); static inline bool more_used(const struct vring_virtqueue *vq) { return vq->packed_ring ? more_used_packed(vq) : more_used_split(vq); } /** * vring_interrupt - notify a virtqueue on an interrupt * @irq: the IRQ number (ignored) * @_vq: the struct virtqueue to notify * * Calls the callback function of @_vq to process the virtqueue * notification. */ irqreturn_t vring_interrupt(int irq, void *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); if (!more_used(vq)) { pr_debug("virtqueue interrupt with no work for %p\n", vq); return IRQ_NONE; } if (unlikely(vq->broken)) { #ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION dev_warn_once(&vq->vq.vdev->dev, "virtio vring IRQ raised before DRIVER_OK"); return IRQ_NONE; #else return IRQ_HANDLED; #endif } /* Just a hint for performance: so it's ok that this can be racy! */ if (vq->event) data_race(vq->event_triggered = true); pr_debug("virtqueue callback for %p (%p)\n", vq, vq->vq.callback); if (vq->vq.callback) vq->vq.callback(&vq->vq); return IRQ_HANDLED; } EXPORT_SYMBOL_GPL(vring_interrupt); struct virtqueue *vring_create_virtqueue( unsigned int index, unsigned int num, unsigned int vring_align, struct virtio_device *vdev, bool weak_barriers, bool may_reduce_num, bool context, bool (*notify)(struct virtqueue *), void (*callback)(struct virtqueue *), const char *name) { if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED)) return vring_create_virtqueue_packed(index, num, vring_align, vdev, weak_barriers, may_reduce_num, context, notify, callback, name, vdev->dev.parent); return vring_create_virtqueue_split(index, num, vring_align, vdev, weak_barriers, may_reduce_num, context, notify, callback, name, vdev->dev.parent); } EXPORT_SYMBOL_GPL(vring_create_virtqueue); struct virtqueue *vring_create_virtqueue_dma( unsigned int index, unsigned int num, unsigned int vring_align, struct virtio_device *vdev, bool weak_barriers, bool may_reduce_num, bool context, bool (*notify)(struct virtqueue *), void (*callback)(struct virtqueue *), const char *name, struct device *dma_dev) { if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED)) return vring_create_virtqueue_packed(index, num, vring_align, vdev, weak_barriers, may_reduce_num, context, notify, callback, name, dma_dev); return vring_create_virtqueue_split(index, num, vring_align, vdev, weak_barriers, may_reduce_num, context, notify, callback, name, dma_dev); } EXPORT_SYMBOL_GPL(vring_create_virtqueue_dma); /** * virtqueue_resize - resize the vring of vq * @_vq: the struct virtqueue we're talking about. * @num: new ring num * @recycle: callback to recycle unused buffers * @recycle_done: callback to be invoked when recycle for all unused buffers done * * When it is really necessary to create a new vring, it will set the current vq * into the reset state. Then call the passed callback to recycle the buffer * that is no longer used. Only after the new vring is successfully created, the * old vring will be released. * * Caller must ensure we don't call this with other virtqueue operations * at the same time (except where noted). * * Returns zero or a negative error. * 0: success. * -ENOMEM: Failed to allocate a new ring, fall back to the original ring size. * vq can still work normally * -EBUSY: Failed to sync with device, vq may not work properly * -ENOENT: Transport or device not supported * -E2BIG/-EINVAL: num error * -EPERM: Operation not permitted * */ int virtqueue_resize(struct virtqueue *_vq, u32 num, void (*recycle)(struct virtqueue *vq, void *buf), void (*recycle_done)(struct virtqueue *vq)) { struct vring_virtqueue *vq = to_vvq(_vq); int err; if (num > vq->vq.num_max) return -E2BIG; if (!num) return -EINVAL; if ((vq->packed_ring ? vq->packed.vring.num : vq->split.vring.num) == num) return 0; err = virtqueue_disable_and_recycle(_vq, recycle); if (err) return err; if (recycle_done) recycle_done(_vq); if (vq->packed_ring) err = virtqueue_resize_packed(_vq, num); else err = virtqueue_resize_split(_vq, num); return virtqueue_enable_after_reset(_vq); } EXPORT_SYMBOL_GPL(virtqueue_resize); /** * virtqueue_reset - detach and recycle all unused buffers * @_vq: the struct virtqueue we're talking about. * @recycle: callback to recycle unused buffers * @recycle_done: callback to be invoked when recycle for all unused buffers done * * Caller must ensure we don't call this with other virtqueue operations * at the same time (except where noted). * * Returns zero or a negative error. * 0: success. * -EBUSY: Failed to sync with device, vq may not work properly * -ENOENT: Transport or device not supported * -EPERM: Operation not permitted */ int virtqueue_reset(struct virtqueue *_vq, void (*recycle)(struct virtqueue *vq, void *buf), void (*recycle_done)(struct virtqueue *vq)) { struct vring_virtqueue *vq = to_vvq(_vq); int err; err = virtqueue_disable_and_recycle(_vq, recycle); if (err) return err; if (recycle_done) recycle_done(_vq); if (vq->packed_ring) virtqueue_reinit_packed(vq); else virtqueue_reinit_split(vq); return virtqueue_enable_after_reset(_vq); } EXPORT_SYMBOL_GPL(virtqueue_reset); struct virtqueue *vring_new_virtqueue(unsigned int index, unsigned int num, unsigned int vring_align, struct virtio_device *vdev, bool weak_barriers, bool context, void *pages, bool (*notify)(struct virtqueue *vq), void (*callback)(struct virtqueue *vq), const char *name) { struct vring_virtqueue_split vring_split = {}; if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED)) { struct vring_virtqueue_packed vring_packed = {}; vring_packed.vring.num = num; vring_packed.vring.desc = pages; return __vring_new_virtqueue_packed(index, &vring_packed, vdev, weak_barriers, context, notify, callback, name, vdev->dev.parent); } vring_init(&vring_split.vring, num, pages, vring_align); return __vring_new_virtqueue_split(index, &vring_split, vdev, weak_barriers, context, notify, callback, name, vdev->dev.parent); } EXPORT_SYMBOL_GPL(vring_new_virtqueue); static void vring_free(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); if (vq->we_own_ring) { if (vq->packed_ring) { vring_free_queue(vq->vq.vdev, vq->packed.ring_size_in_bytes, vq->packed.vring.desc, vq->packed.ring_dma_addr, vring_dma_dev(vq)); vring_free_queue(vq->vq.vdev, vq->packed.event_size_in_bytes, vq->packed.vring.driver, vq->packed.driver_event_dma_addr, vring_dma_dev(vq)); vring_free_queue(vq->vq.vdev, vq->packed.event_size_in_bytes, vq->packed.vring.device, vq->packed.device_event_dma_addr, vring_dma_dev(vq)); kfree(vq->packed.desc_state); kfree(vq->packed.desc_extra); } else { vring_free_queue(vq->vq.vdev, vq->split.queue_size_in_bytes, vq->split.vring.desc, vq->split.queue_dma_addr, vring_dma_dev(vq)); } } if (!vq->packed_ring) { kfree(vq->split.desc_state); kfree(vq->split.desc_extra); } } void vring_del_virtqueue(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); spin_lock(&vq->vq.vdev->vqs_list_lock); list_del(&_vq->list); spin_unlock(&vq->vq.vdev->vqs_list_lock); vring_free(_vq); kfree(vq); } EXPORT_SYMBOL_GPL(vring_del_virtqueue); u32 vring_notification_data(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); u16 next; if (vq->packed_ring) next = (vq->packed.next_avail_idx & ~(-(1 << VRING_PACKED_EVENT_F_WRAP_CTR))) | vq->packed.avail_wrap_counter << VRING_PACKED_EVENT_F_WRAP_CTR; else next = vq->split.avail_idx_shadow; return next << 16 | _vq->index; } EXPORT_SYMBOL_GPL(vring_notification_data); /* Manipulates transport-specific feature bits. */ void vring_transport_features(struct virtio_device *vdev) { unsigned int i; for (i = VIRTIO_TRANSPORT_F_START; i < VIRTIO_TRANSPORT_F_END; i++) { switch (i) { case VIRTIO_RING_F_INDIRECT_DESC: break; case VIRTIO_RING_F_EVENT_IDX: break; case VIRTIO_F_VERSION_1: break; case VIRTIO_F_ACCESS_PLATFORM: break; case VIRTIO_F_RING_PACKED: break; case VIRTIO_F_ORDER_PLATFORM: break; case VIRTIO_F_NOTIFICATION_DATA: break; default: /* We don't understand this bit. */ __virtio_clear_bit(vdev, i); } } } EXPORT_SYMBOL_GPL(vring_transport_features); /** * virtqueue_get_vring_size - return the size of the virtqueue's vring * @_vq: the struct virtqueue containing the vring of interest. * * Returns the size of the vring. This is mainly used for boasting to * userspace. Unlike other operations, this need not be serialized. */ unsigned int virtqueue_get_vring_size(const struct virtqueue *_vq) { const struct vring_virtqueue *vq = to_vvq(_vq); return vq->packed_ring ? vq->packed.vring.num : vq->split.vring.num; } EXPORT_SYMBOL_GPL(virtqueue_get_vring_size); /* * This function should only be called by the core, not directly by the driver. */ void __virtqueue_break(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); /* Pairs with READ_ONCE() in virtqueue_is_broken(). */ WRITE_ONCE(vq->broken, true); } EXPORT_SYMBOL_GPL(__virtqueue_break); /* * This function should only be called by the core, not directly by the driver. */ void __virtqueue_unbreak(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); /* Pairs with READ_ONCE() in virtqueue_is_broken(). */ WRITE_ONCE(vq->broken, false); } EXPORT_SYMBOL_GPL(__virtqueue_unbreak); bool virtqueue_is_broken(const struct virtqueue *_vq) { const struct vring_virtqueue *vq = to_vvq(_vq); return READ_ONCE(vq->broken); } EXPORT_SYMBOL_GPL(virtqueue_is_broken); /* * This should prevent the device from being used, allowing drivers to * recover. You may need to grab appropriate locks to flush. */ void virtio_break_device(struct virtio_device *dev) { struct virtqueue *_vq; spin_lock(&dev->vqs_list_lock); list_for_each_entry(_vq, &dev->vqs, list) { struct vring_virtqueue *vq = to_vvq(_vq); /* Pairs with READ_ONCE() in virtqueue_is_broken(). */ WRITE_ONCE(vq->broken, true); } spin_unlock(&dev->vqs_list_lock); } EXPORT_SYMBOL_GPL(virtio_break_device); /* * This should allow the device to be used by the driver. You may * need to grab appropriate locks to flush the write to * vq->broken. This should only be used in some specific case e.g * (probing and restoring). This function should only be called by the * core, not directly by the driver. */ void __virtio_unbreak_device(struct virtio_device *dev) { struct virtqueue *_vq; spin_lock(&dev->vqs_list_lock); list_for_each_entry(_vq, &dev->vqs, list) { struct vring_virtqueue *vq = to_vvq(_vq); /* Pairs with READ_ONCE() in virtqueue_is_broken(). */ WRITE_ONCE(vq->broken, false); } spin_unlock(&dev->vqs_list_lock); } EXPORT_SYMBOL_GPL(__virtio_unbreak_device); dma_addr_t virtqueue_get_desc_addr(const struct virtqueue *_vq) { const struct vring_virtqueue *vq = to_vvq(_vq); BUG_ON(!vq->we_own_ring); if (vq->packed_ring) return vq->packed.ring_dma_addr; return vq->split.queue_dma_addr; } EXPORT_SYMBOL_GPL(virtqueue_get_desc_addr); dma_addr_t virtqueue_get_avail_addr(const struct virtqueue *_vq) { const struct vring_virtqueue *vq = to_vvq(_vq); BUG_ON(!vq->we_own_ring); if (vq->packed_ring) return vq->packed.driver_event_dma_addr; return vq->split.queue_dma_addr + ((char *)vq->split.vring.avail - (char *)vq->split.vring.desc); } EXPORT_SYMBOL_GPL(virtqueue_get_avail_addr); dma_addr_t virtqueue_get_used_addr(const struct virtqueue *_vq) { const struct vring_virtqueue *vq = to_vvq(_vq); BUG_ON(!vq->we_own_ring); if (vq->packed_ring) return vq->packed.device_event_dma_addr; return vq->split.queue_dma_addr + ((char *)vq->split.vring.used - (char *)vq->split.vring.desc); } EXPORT_SYMBOL_GPL(virtqueue_get_used_addr); /* Only available for split ring */ const struct vring *virtqueue_get_vring(const struct virtqueue *vq) { return &to_vvq(vq)->split.vring; } EXPORT_SYMBOL_GPL(virtqueue_get_vring); /** * virtqueue_dma_map_single_attrs - map DMA for _vq * @_vq: the struct virtqueue we're talking about. * @ptr: the pointer of the buffer to do dma * @size: the size of the buffer to do dma * @dir: DMA direction * @attrs: DMA Attrs * * The caller calls this to do dma mapping in advance. The DMA address can be * passed to this _vq when it is in pre-mapped mode. * * return DMA address. Caller should check that by virtqueue_dma_mapping_error(). */ dma_addr_t virtqueue_dma_map_single_attrs(struct virtqueue *_vq, void *ptr, size_t size, enum dma_data_direction dir, unsigned long attrs) { struct vring_virtqueue *vq = to_vvq(_vq); if (!vq->use_dma_api) { kmsan_handle_dma(virt_to_page(ptr), offset_in_page(ptr), size, dir); return (dma_addr_t)virt_to_phys(ptr); } return dma_map_single_attrs(vring_dma_dev(vq), ptr, size, dir, attrs); } EXPORT_SYMBOL_GPL(virtqueue_dma_map_single_attrs); /** * virtqueue_dma_unmap_single_attrs - unmap DMA for _vq * @_vq: the struct virtqueue we're talking about. * @addr: the dma address to unmap * @size: the size of the buffer * @dir: DMA direction * @attrs: DMA Attrs * * Unmap the address that is mapped by the virtqueue_dma_map_* APIs. * */ void virtqueue_dma_unmap_single_attrs(struct virtqueue *_vq, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { struct vring_virtqueue *vq = to_vvq(_vq); if (!vq->use_dma_api) return; dma_unmap_single_attrs(vring_dma_dev(vq), addr, size, dir, attrs); } EXPORT_SYMBOL_GPL(virtqueue_dma_unmap_single_attrs); /** * virtqueue_dma_mapping_error - check dma address * @_vq: the struct virtqueue we're talking about. * @addr: DMA address * * Returns 0 means dma valid. Other means invalid dma address. */ int virtqueue_dma_mapping_error(struct virtqueue *_vq, dma_addr_t addr) { struct vring_virtqueue *vq = to_vvq(_vq); if (!vq->use_dma_api) return 0; return dma_mapping_error(vring_dma_dev(vq), addr); } EXPORT_SYMBOL_GPL(virtqueue_dma_mapping_error); /** * virtqueue_dma_need_sync - check a dma address needs sync * @_vq: the struct virtqueue we're talking about. * @addr: DMA address * * Check if the dma address mapped by the virtqueue_dma_map_* APIs needs to be * synchronized * * return bool */ bool virtqueue_dma_need_sync(struct virtqueue *_vq, dma_addr_t addr) { struct vring_virtqueue *vq = to_vvq(_vq); if (!vq->use_dma_api) return false; return dma_need_sync(vring_dma_dev(vq), addr); } EXPORT_SYMBOL_GPL(virtqueue_dma_need_sync); /** * virtqueue_dma_sync_single_range_for_cpu - dma sync for cpu * @_vq: the struct virtqueue we're talking about. * @addr: DMA address * @offset: DMA address offset * @size: buf size for sync * @dir: DMA direction * * Before calling this function, use virtqueue_dma_need_sync() to confirm that * the DMA address really needs to be synchronized * */ void virtqueue_dma_sync_single_range_for_cpu(struct virtqueue *_vq, dma_addr_t addr, unsigned long offset, size_t size, enum dma_data_direction dir) { struct vring_virtqueue *vq = to_vvq(_vq); struct device *dev = vring_dma_dev(vq); if (!vq->use_dma_api) return; dma_sync_single_range_for_cpu(dev, addr, offset, size, dir); } EXPORT_SYMBOL_GPL(virtqueue_dma_sync_single_range_for_cpu); /** * virtqueue_dma_sync_single_range_for_device - dma sync for device * @_vq: the struct virtqueue we're talking about. * @addr: DMA address * @offset: DMA address offset * @size: buf size for sync * @dir: DMA direction * * Before calling this function, use virtqueue_dma_need_sync() to confirm that * the DMA address really needs to be synchronized */ void virtqueue_dma_sync_single_range_for_device(struct virtqueue *_vq, dma_addr_t addr, unsigned long offset, size_t size, enum dma_data_direction dir) { struct vring_virtqueue *vq = to_vvq(_vq); struct device *dev = vring_dma_dev(vq); if (!vq->use_dma_api) return; dma_sync_single_range_for_device(dev, addr, offset, size, dir); } EXPORT_SYMBOL_GPL(virtqueue_dma_sync_single_range_for_device); MODULE_DESCRIPTION("Virtio ring implementation"); MODULE_LICENSE("GPL"); |
| 2 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 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 | /* * net/tipc/bearer.c: TIPC bearer code * * Copyright (c) 1996-2006, 2013-2016, Ericsson AB * Copyright (c) 2004-2006, 2010-2013, Wind River Systems * 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 names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * 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 <net/sock.h> #include "core.h" #include "bearer.h" #include "link.h" #include "discover.h" #include "monitor.h" #include "bcast.h" #include "netlink.h" #include "udp_media.h" #include "trace.h" #include "crypto.h" #define MAX_ADDR_STR 60 static struct tipc_media * const media_info_array[] = { ð_media_info, #ifdef CONFIG_TIPC_MEDIA_IB &ib_media_info, #endif #ifdef CONFIG_TIPC_MEDIA_UDP &udp_media_info, #endif NULL }; static struct tipc_bearer *bearer_get(struct net *net, int bearer_id) { struct tipc_net *tn = tipc_net(net); return rcu_dereference(tn->bearer_list[bearer_id]); } static void bearer_disable(struct net *net, struct tipc_bearer *b); static int tipc_l2_rcv_msg(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); /** * tipc_media_find - locates specified media object by name * @name: name to locate */ struct tipc_media *tipc_media_find(const char *name) { u32 i; for (i = 0; media_info_array[i] != NULL; i++) { if (!strcmp(media_info_array[i]->name, name)) break; } return media_info_array[i]; } /** * media_find_id - locates specified media object by type identifier * @type: type identifier to locate */ static struct tipc_media *media_find_id(u8 type) { u32 i; for (i = 0; media_info_array[i] != NULL; i++) { if (media_info_array[i]->type_id == type) break; } return media_info_array[i]; } /** * tipc_media_addr_printf - record media address in print buffer * @buf: output buffer * @len: output buffer size remaining * @a: input media address */ int tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a) { char addr_str[MAX_ADDR_STR]; struct tipc_media *m; int ret; m = media_find_id(a->media_id); if (m && !m->addr2str(a, addr_str, sizeof(addr_str))) ret = scnprintf(buf, len, "%s(%s)", m->name, addr_str); else { u32 i; ret = scnprintf(buf, len, "UNKNOWN(%u)", a->media_id); for (i = 0; i < sizeof(a->value); i++) ret += scnprintf(buf + ret, len - ret, "-%x", a->value[i]); } return ret; } /** * bearer_name_validate - validate & (optionally) deconstruct bearer name * @name: ptr to bearer name string * @name_parts: ptr to area for bearer name components (or NULL if not needed) * * Return: 1 if bearer name is valid, otherwise 0. */ static int bearer_name_validate(const char *name, struct tipc_bearer_names *name_parts) { char name_copy[TIPC_MAX_BEARER_NAME]; char *media_name; char *if_name; u32 media_len; u32 if_len; /* copy bearer name & ensure length is OK */ if (strscpy(name_copy, name, TIPC_MAX_BEARER_NAME) < 0) return 0; /* ensure all component parts of bearer name are present */ media_name = name_copy; if_name = strchr(media_name, ':'); if (if_name == NULL) return 0; *(if_name++) = 0; media_len = if_name - media_name; if_len = strlen(if_name) + 1; /* validate component parts of bearer name */ if ((media_len <= 1) || (media_len > TIPC_MAX_MEDIA_NAME) || (if_len <= 1) || (if_len > TIPC_MAX_IF_NAME)) return 0; /* return bearer name components, if necessary */ if (name_parts) { if (strscpy(name_parts->media_name, media_name, TIPC_MAX_MEDIA_NAME) < 0) return 0; if (strscpy(name_parts->if_name, if_name, TIPC_MAX_IF_NAME) < 0) return 0; } return 1; } /** * tipc_bearer_find - locates bearer object with matching bearer name * @net: the applicable net namespace * @name: bearer name to locate */ struct tipc_bearer *tipc_bearer_find(struct net *net, const char *name) { struct tipc_net *tn = tipc_net(net); struct tipc_bearer *b; u32 i; for (i = 0; i < MAX_BEARERS; i++) { b = rtnl_dereference(tn->bearer_list[i]); if (b && (!strcmp(b->name, name))) return b; } return NULL; } /* tipc_bearer_get_name - get the bearer name from its id. * @net: network namespace * @name: a pointer to the buffer where the name will be stored. * @bearer_id: the id to get the name from. */ int tipc_bearer_get_name(struct net *net, char *name, u32 bearer_id) { struct tipc_net *tn = tipc_net(net); struct tipc_bearer *b; if (bearer_id >= MAX_BEARERS) return -EINVAL; b = rtnl_dereference(tn->bearer_list[bearer_id]); if (!b) return -EINVAL; strcpy(name, b->name); return 0; } void tipc_bearer_add_dest(struct net *net, u32 bearer_id, u32 dest) { struct tipc_bearer *b; rcu_read_lock(); b = bearer_get(net, bearer_id); if (b) tipc_disc_add_dest(b->disc); rcu_read_unlock(); } void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest) { struct tipc_bearer *b; rcu_read_lock(); b = bearer_get(net, bearer_id); if (b) tipc_disc_remove_dest(b->disc); rcu_read_unlock(); } /** * tipc_enable_bearer - enable bearer with the given name * @net: the applicable net namespace * @name: bearer name to enable * @disc_domain: bearer domain * @prio: bearer priority * @attr: nlattr array * @extack: netlink extended ack */ static int tipc_enable_bearer(struct net *net, const char *name, u32 disc_domain, u32 prio, struct nlattr *attr[], struct netlink_ext_ack *extack) { struct tipc_net *tn = tipc_net(net); struct tipc_bearer_names b_names; int with_this_prio = 1; struct tipc_bearer *b; struct tipc_media *m; struct sk_buff *skb; int bearer_id = 0; int res = -EINVAL; char *errstr = ""; u32 i; if (!bearer_name_validate(name, &b_names)) { NL_SET_ERR_MSG(extack, "Illegal name"); return res; } if (prio > TIPC_MAX_LINK_PRI && prio != TIPC_MEDIA_LINK_PRI) { errstr = "illegal priority"; NL_SET_ERR_MSG(extack, "Illegal priority"); goto rejected; } m = tipc_media_find(b_names.media_name); if (!m) { errstr = "media not registered"; NL_SET_ERR_MSG(extack, "Media not registered"); goto rejected; } if (prio == TIPC_MEDIA_LINK_PRI) prio = m->priority; /* Check new bearer vs existing ones and find free bearer id if any */ bearer_id = MAX_BEARERS; i = MAX_BEARERS; while (i-- != 0) { b = rtnl_dereference(tn->bearer_list[i]); if (!b) { bearer_id = i; continue; } if (!strcmp(name, b->name)) { errstr = "already enabled"; NL_SET_ERR_MSG(extack, "Already enabled"); goto rejected; } if (b->priority == prio && (++with_this_prio > 2)) { pr_warn("Bearer <%s>: already 2 bearers with priority %u\n", name, prio); if (prio == TIPC_MIN_LINK_PRI) { errstr = "cannot adjust to lower"; NL_SET_ERR_MSG(extack, "Cannot adjust to lower"); goto rejected; } pr_warn("Bearer <%s>: trying with adjusted priority\n", name); prio--; bearer_id = MAX_BEARERS; i = MAX_BEARERS; with_this_prio = 1; } } if (bearer_id >= MAX_BEARERS) { errstr = "max 3 bearers permitted"; NL_SET_ERR_MSG(extack, "Max 3 bearers permitted"); goto rejected; } b = kzalloc(sizeof(*b), GFP_ATOMIC); if (!b) return -ENOMEM; strscpy(b->name, name); b->media = m; res = m->enable_media(net, b, attr); if (res) { kfree(b); errstr = "failed to enable media"; NL_SET_ERR_MSG(extack, "Failed to enable media"); goto rejected; } b->identity = bearer_id; b->tolerance = m->tolerance; b->min_win = m->min_win; b->max_win = m->max_win; b->domain = disc_domain; b->net_plane = bearer_id + 'A'; b->priority = prio; refcount_set(&b->refcnt, 1); res = tipc_disc_create(net, b, &b->bcast_addr, &skb); if (res) { bearer_disable(net, b); errstr = "failed to create discoverer"; NL_SET_ERR_MSG(extack, "Failed to create discoverer"); goto rejected; } /* Create monitoring data before accepting activate messages */ if (tipc_mon_create(net, bearer_id)) { bearer_disable(net, b); kfree_skb(skb); return -ENOMEM; } test_and_set_bit_lock(0, &b->up); rcu_assign_pointer(tn->bearer_list[bearer_id], b); if (skb) tipc_bearer_xmit_skb(net, bearer_id, skb, &b->bcast_addr); pr_info("Enabled bearer <%s>, priority %u\n", name, prio); return res; rejected: pr_warn("Enabling of bearer <%s> rejected, %s\n", name, errstr); return res; } /** * tipc_reset_bearer - Reset all links established over this bearer * @net: the applicable net namespace * @b: the target bearer */ static int tipc_reset_bearer(struct net *net, struct tipc_bearer *b) { pr_info("Resetting bearer <%s>\n", b->name); tipc_node_delete_links(net, b->identity); tipc_disc_reset(net, b); return 0; } bool tipc_bearer_hold(struct tipc_bearer *b) { return (b && refcount_inc_not_zero(&b->refcnt)); } void tipc_bearer_put(struct tipc_bearer *b) { if (b && refcount_dec_and_test(&b->refcnt)) kfree_rcu(b, rcu); } /** * bearer_disable - disable this bearer * @net: the applicable net namespace * @b: the bearer to disable * * Note: This routine assumes caller holds RTNL lock. */ static void bearer_disable(struct net *net, struct tipc_bearer *b) { struct tipc_net *tn = tipc_net(net); int bearer_id = b->identity; pr_info("Disabling bearer <%s>\n", b->name); clear_bit_unlock(0, &b->up); tipc_node_delete_links(net, bearer_id); b->media->disable_media(b); RCU_INIT_POINTER(b->media_ptr, NULL); if (b->disc) tipc_disc_delete(b->disc); RCU_INIT_POINTER(tn->bearer_list[bearer_id], NULL); tipc_bearer_put(b); tipc_mon_delete(net, bearer_id); } int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b, struct nlattr *attr[]) { char *dev_name = strchr((const char *)b->name, ':') + 1; int hwaddr_len = b->media->hwaddr_len; u8 node_id[NODE_ID_LEN] = {0,}; struct net_device *dev; /* Find device with specified name */ dev = dev_get_by_name(net, dev_name); if (!dev) return -ENODEV; if (tipc_mtu_bad(dev)) { dev_put(dev); return -EINVAL; } if (dev == net->loopback_dev) { dev_put(dev); pr_info("Enabling <%s> not permitted\n", b->name); return -EINVAL; } /* Autoconfigure own node identity if needed */ if (!tipc_own_id(net) && hwaddr_len <= NODE_ID_LEN) { memcpy(node_id, dev->dev_addr, hwaddr_len); tipc_net_init(net, node_id, 0); } if (!tipc_own_id(net)) { dev_put(dev); pr_warn("Failed to obtain node identity\n"); return -EINVAL; } /* Associate TIPC bearer with L2 bearer */ rcu_assign_pointer(b->media_ptr, dev); b->pt.dev = dev; b->pt.type = htons(ETH_P_TIPC); b->pt.func = tipc_l2_rcv_msg; dev_add_pack(&b->pt); memset(&b->bcast_addr, 0, sizeof(b->bcast_addr)); memcpy(b->bcast_addr.value, dev->broadcast, hwaddr_len); b->bcast_addr.media_id = b->media->type_id; b->bcast_addr.broadcast = TIPC_BROADCAST_SUPPORT; b->mtu = dev->mtu; b->media->raw2addr(b, &b->addr, (const char *)dev->dev_addr); rcu_assign_pointer(dev->tipc_ptr, b); return 0; } /* tipc_disable_l2_media - detach TIPC bearer from an L2 interface * @b: the target bearer * * Mark L2 bearer as inactive so that incoming buffers are thrown away */ void tipc_disable_l2_media(struct tipc_bearer *b) { struct net_device *dev; dev = (struct net_device *)rtnl_dereference(b->media_ptr); dev_remove_pack(&b->pt); RCU_INIT_POINTER(dev->tipc_ptr, NULL); synchronize_net(); dev_put(dev); } /** * tipc_l2_send_msg - send a TIPC packet out over an L2 interface * @net: the associated network namespace * @skb: the packet to be sent * @b: the bearer through which the packet is to be sent * @dest: peer destination address */ int tipc_l2_send_msg(struct net *net, struct sk_buff *skb, struct tipc_bearer *b, struct tipc_media_addr *dest) { struct net_device *dev; int delta; dev = (struct net_device *)rcu_dereference(b->media_ptr); if (!dev) return 0; delta = SKB_DATA_ALIGN(dev->hard_header_len - skb_headroom(skb)); if ((delta > 0) && pskb_expand_head(skb, delta, 0, GFP_ATOMIC)) { kfree_skb(skb); return 0; } skb_reset_network_header(skb); skb->dev = dev; skb->protocol = htons(ETH_P_TIPC); dev_hard_header(skb, dev, ETH_P_TIPC, dest->value, dev->dev_addr, skb->len); dev_queue_xmit(skb); return 0; } bool tipc_bearer_bcast_support(struct net *net, u32 bearer_id) { bool supp = false; struct tipc_bearer *b; rcu_read_lock(); b = bearer_get(net, bearer_id); if (b) supp = (b->bcast_addr.broadcast == TIPC_BROADCAST_SUPPORT); rcu_read_unlock(); return supp; } int tipc_bearer_mtu(struct net *net, u32 bearer_id) { int mtu = 0; struct tipc_bearer *b; rcu_read_lock(); b = bearer_get(net, bearer_id); if (b) mtu = b->mtu; rcu_read_unlock(); return mtu; } int tipc_bearer_min_mtu(struct net *net, u32 bearer_id) { int mtu = TIPC_MIN_BEARER_MTU; struct tipc_bearer *b; rcu_read_lock(); b = bearer_get(net, bearer_id); if (b) mtu += b->encap_hlen; rcu_read_unlock(); return mtu; } /* tipc_bearer_xmit_skb - sends buffer to destination over bearer */ void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id, struct sk_buff *skb, struct tipc_media_addr *dest) { struct tipc_msg *hdr = buf_msg(skb); struct tipc_bearer *b; rcu_read_lock(); b = bearer_get(net, bearer_id); if (likely(b && (test_bit(0, &b->up) || msg_is_reset(hdr)))) { #ifdef CONFIG_TIPC_CRYPTO tipc_crypto_xmit(net, &skb, b, dest, NULL); if (skb) #endif b->media->send_msg(net, skb, b, dest); } else { kfree_skb(skb); } rcu_read_unlock(); } /* tipc_bearer_xmit() -send buffer to destination over bearer */ void tipc_bearer_xmit(struct net *net, u32 bearer_id, struct sk_buff_head *xmitq, struct tipc_media_addr *dst, struct tipc_node *__dnode) { struct tipc_bearer *b; struct sk_buff *skb, *tmp; if (skb_queue_empty(xmitq)) return; rcu_read_lock(); b = bearer_get(net, bearer_id); if (unlikely(!b)) __skb_queue_purge(xmitq); skb_queue_walk_safe(xmitq, skb, tmp) { __skb_dequeue(xmitq); if (likely(test_bit(0, &b->up) || msg_is_reset(buf_msg(skb)))) { #ifdef CONFIG_TIPC_CRYPTO tipc_crypto_xmit(net, &skb, b, dst, __dnode); if (skb) #endif b->media->send_msg(net, skb, b, dst); } else { kfree_skb(skb); } } rcu_read_unlock(); } /* tipc_bearer_bc_xmit() - broadcast buffers to all destinations */ void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id, struct sk_buff_head *xmitq) { struct tipc_net *tn = tipc_net(net); struct tipc_media_addr *dst; int net_id = tn->net_id; struct tipc_bearer *b; struct sk_buff *skb, *tmp; struct tipc_msg *hdr; rcu_read_lock(); b = bearer_get(net, bearer_id); if (unlikely(!b || !test_bit(0, &b->up))) __skb_queue_purge(xmitq); skb_queue_walk_safe(xmitq, skb, tmp) { hdr = buf_msg(skb); msg_set_non_seq(hdr, 1); msg_set_mc_netid(hdr, net_id); __skb_dequeue(xmitq); dst = &b->bcast_addr; #ifdef CONFIG_TIPC_CRYPTO tipc_crypto_xmit(net, &skb, b, dst, NULL); if (skb) #endif b->media->send_msg(net, skb, b, dst); } rcu_read_unlock(); } /** * tipc_l2_rcv_msg - handle incoming TIPC message from an interface * @skb: the received message * @dev: the net device that the packet was received on * @pt: the packet_type structure which was used to register this handler * @orig_dev: the original receive net device in case the device is a bond * * Accept only packets explicitly sent to this node, or broadcast packets; * ignores packets sent using interface multicast, and traffic sent to other * nodes (which can happen if interface is running in promiscuous mode). */ static int tipc_l2_rcv_msg(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct tipc_bearer *b; rcu_read_lock(); b = rcu_dereference(dev->tipc_ptr) ?: rcu_dereference(orig_dev->tipc_ptr); if (likely(b && test_bit(0, &b->up) && (skb->pkt_type <= PACKET_MULTICAST))) { skb_mark_not_on_list(skb); TIPC_SKB_CB(skb)->flags = 0; tipc_rcv(dev_net(b->pt.dev), skb, b); rcu_read_unlock(); return NET_RX_SUCCESS; } rcu_read_unlock(); kfree_skb(skb); return NET_RX_DROP; } /** * tipc_l2_device_event - handle device events from network device * @nb: the context of the notification * @evt: the type of event * @ptr: the net device that the event was on * * This function is called by the Ethernet driver in case of link * change event. */ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct tipc_bearer *b; b = rtnl_dereference(dev->tipc_ptr); if (!b) return NOTIFY_DONE; trace_tipc_l2_device_event(dev, b, evt); switch (evt) { case NETDEV_CHANGE: if (netif_carrier_ok(dev) && netif_oper_up(dev)) { test_and_set_bit_lock(0, &b->up); break; } fallthrough; case NETDEV_GOING_DOWN: clear_bit_unlock(0, &b->up); tipc_reset_bearer(net, b); break; case NETDEV_UP: test_and_set_bit_lock(0, &b->up); break; case NETDEV_CHANGEMTU: if (tipc_mtu_bad(dev)) { bearer_disable(net, b); break; } b->mtu = dev->mtu; tipc_reset_bearer(net, b); break; case NETDEV_CHANGEADDR: b->media->raw2addr(b, &b->addr, (const char *)dev->dev_addr); tipc_reset_bearer(net, b); break; case NETDEV_UNREGISTER: case NETDEV_CHANGENAME: bearer_disable(net, b); break; } return NOTIFY_OK; } static struct notifier_block notifier = { .notifier_call = tipc_l2_device_event, .priority = 0, }; int tipc_bearer_setup(void) { return register_netdevice_notifier(¬ifier); } void tipc_bearer_cleanup(void) { unregister_netdevice_notifier(¬ifier); } void tipc_bearer_stop(struct net *net) { struct tipc_net *tn = tipc_net(net); struct tipc_bearer *b; u32 i; for (i = 0; i < MAX_BEARERS; i++) { b = rtnl_dereference(tn->bearer_list[i]); if (b) { bearer_disable(net, b); tn->bearer_list[i] = NULL; } } } void tipc_clone_to_loopback(struct net *net, struct sk_buff_head *pkts) { struct net_device *dev = net->loopback_dev; struct sk_buff *skb, *_skb; int exp; skb_queue_walk(pkts, _skb) { skb = pskb_copy(_skb, GFP_ATOMIC); if (!skb) continue; exp = SKB_DATA_ALIGN(dev->hard_header_len - skb_headroom(skb)); if (exp > 0 && pskb_expand_head(skb, exp, 0, GFP_ATOMIC)) { kfree_skb(skb); continue; } skb_reset_network_header(skb); dev_hard_header(skb, dev, ETH_P_TIPC, dev->dev_addr, dev->dev_addr, skb->len); skb->dev = dev; skb->pkt_type = PACKET_HOST; skb->ip_summed = CHECKSUM_UNNECESSARY; skb->protocol = eth_type_trans(skb, dev); netif_rx(skb); } } static int tipc_loopback_rcv_pkt(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *od) { consume_skb(skb); return NET_RX_SUCCESS; } int tipc_attach_loopback(struct net *net) { struct net_device *dev = net->loopback_dev; struct tipc_net *tn = tipc_net(net); if (!dev) return -ENODEV; netdev_hold(dev, &tn->loopback_pt.dev_tracker, GFP_KERNEL); tn->loopback_pt.dev = dev; tn->loopback_pt.type = htons(ETH_P_TIPC); tn->loopback_pt.func = tipc_loopback_rcv_pkt; dev_add_pack(&tn->loopback_pt); return 0; } void tipc_detach_loopback(struct net *net) { struct tipc_net *tn = tipc_net(net); dev_remove_pack(&tn->loopback_pt); netdev_put(net->loopback_dev, &tn->loopback_pt.dev_tracker); } /* Caller should hold rtnl_lock to protect the bearer */ static int __tipc_nl_add_bearer(struct tipc_nl_msg *msg, struct tipc_bearer *bearer, int nlflags) { void *hdr; struct nlattr *attrs; struct nlattr *prop; hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, nlflags, TIPC_NL_BEARER_GET); if (!hdr) return -EMSGSIZE; attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_BEARER); if (!attrs) goto msg_full; if (nla_put_string(msg->skb, TIPC_NLA_BEARER_NAME, bearer->name)) goto attr_msg_full; prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_BEARER_PROP); if (!prop) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, bearer->priority)) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_TOL, bearer->tolerance)) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bearer->max_win)) goto prop_msg_full; if (bearer->media->type_id == TIPC_MEDIA_TYPE_UDP) if (nla_put_u32(msg->skb, TIPC_NLA_PROP_MTU, bearer->mtu)) goto prop_msg_full; nla_nest_end(msg->skb, prop); #ifdef CONFIG_TIPC_MEDIA_UDP if (bearer->media->type_id == TIPC_MEDIA_TYPE_UDP) { if (tipc_udp_nl_add_bearer_data(msg, bearer)) goto attr_msg_full; } #endif nla_nest_end(msg->skb, attrs); genlmsg_end(msg->skb, hdr); return 0; prop_msg_full: nla_nest_cancel(msg->skb, prop); attr_msg_full: nla_nest_cancel(msg->skb, attrs); msg_full: genlmsg_cancel(msg->skb, hdr); return -EMSGSIZE; } int tipc_nl_bearer_dump(struct sk_buff *skb, struct netlink_callback *cb) { int err; int i = cb->args[0]; struct tipc_bearer *bearer; struct tipc_nl_msg msg; struct net *net = sock_net(skb->sk); struct tipc_net *tn = tipc_net(net); if (i == MAX_BEARERS) return 0; msg.skb = skb; msg.portid = NETLINK_CB(cb->skb).portid; msg.seq = cb->nlh->nlmsg_seq; rtnl_lock(); for (i = 0; i < MAX_BEARERS; i++) { bearer = rtnl_dereference(tn->bearer_list[i]); if (!bearer) continue; err = __tipc_nl_add_bearer(&msg, bearer, NLM_F_MULTI); if (err) break; } rtnl_unlock(); cb->args[0] = i; return skb->len; } int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info) { int err; char *name; struct sk_buff *rep; struct tipc_bearer *bearer; struct tipc_nl_msg msg; struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; struct net *net = genl_info_net(info); if (!info->attrs[TIPC_NLA_BEARER]) return -EINVAL; err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX, info->attrs[TIPC_NLA_BEARER], tipc_nl_bearer_policy, info->extack); if (err) return err; if (!attrs[TIPC_NLA_BEARER_NAME]) return -EINVAL; name = nla_data(attrs[TIPC_NLA_BEARER_NAME]); rep = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (!rep) return -ENOMEM; msg.skb = rep; msg.portid = info->snd_portid; msg.seq = info->snd_seq; rtnl_lock(); bearer = tipc_bearer_find(net, name); if (!bearer) { err = -EINVAL; NL_SET_ERR_MSG(info->extack, "Bearer not found"); goto err_out; } err = __tipc_nl_add_bearer(&msg, bearer, 0); if (err) goto err_out; rtnl_unlock(); return genlmsg_reply(rep, info); err_out: rtnl_unlock(); nlmsg_free(rep); return err; } int __tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info) { int err; char *name; struct tipc_bearer *bearer; struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; struct net *net = sock_net(skb->sk); if (!info->attrs[TIPC_NLA_BEARER]) return -EINVAL; err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX, info->attrs[TIPC_NLA_BEARER], tipc_nl_bearer_policy, info->extack); if (err) return err; if (!attrs[TIPC_NLA_BEARER_NAME]) return -EINVAL; name = nla_data(attrs[TIPC_NLA_BEARER_NAME]); bearer = tipc_bearer_find(net, name); if (!bearer) { NL_SET_ERR_MSG(info->extack, "Bearer not found"); return -EINVAL; } bearer_disable(net, bearer); return 0; } int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info) { int err; rtnl_lock(); err = __tipc_nl_bearer_disable(skb, info); rtnl_unlock(); return err; } int __tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info) { int err; char *bearer; struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; struct net *net = sock_net(skb->sk); u32 domain = 0; u32 prio; prio = TIPC_MEDIA_LINK_PRI; if (!info->attrs[TIPC_NLA_BEARER]) return -EINVAL; err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX, info->attrs[TIPC_NLA_BEARER], tipc_nl_bearer_policy, info->extack); if (err) return err; if (!attrs[TIPC_NLA_BEARER_NAME]) return -EINVAL; bearer = nla_data(attrs[TIPC_NLA_BEARER_NAME]); if (attrs[TIPC_NLA_BEARER_DOMAIN]) domain = nla_get_u32(attrs[TIPC_NLA_BEARER_DOMAIN]); if (attrs[TIPC_NLA_BEARER_PROP]) { struct nlattr *props[TIPC_NLA_PROP_MAX + 1]; err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_BEARER_PROP], props); if (err) return err; if (props[TIPC_NLA_PROP_PRIO]) prio = nla_get_u32(props[TIPC_NLA_PROP_PRIO]); } return tipc_enable_bearer(net, bearer, domain, prio, attrs, info->extack); } int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info) { int err; rtnl_lock(); err = __tipc_nl_bearer_enable(skb, info); rtnl_unlock(); return err; } int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info) { int err; char *name; struct tipc_bearer *b; struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; struct net *net = sock_net(skb->sk); if (!info->attrs[TIPC_NLA_BEARER]) return -EINVAL; err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX, info->attrs[TIPC_NLA_BEARER], tipc_nl_bearer_policy, info->extack); if (err) return err; if (!attrs[TIPC_NLA_BEARER_NAME]) return -EINVAL; name = nla_data(attrs[TIPC_NLA_BEARER_NAME]); rtnl_lock(); b = tipc_bearer_find(net, name); if (!b) { NL_SET_ERR_MSG(info->extack, "Bearer not found"); err = -EINVAL; goto out; } #ifdef CONFIG_TIPC_MEDIA_UDP if (attrs[TIPC_NLA_BEARER_UDP_OPTS]) { if (b->media->type_id != TIPC_MEDIA_TYPE_UDP) { NL_SET_ERR_MSG(info->extack, "UDP option is unsupported"); err = -EINVAL; goto out; } err = tipc_udp_nl_bearer_add(b, attrs[TIPC_NLA_BEARER_UDP_OPTS]); } #endif out: rtnl_unlock(); return err; } int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) { struct tipc_bearer *b; struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; struct net *net = sock_net(skb->sk); char *name; int err; if (!info->attrs[TIPC_NLA_BEARER]) return -EINVAL; err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX, info->attrs[TIPC_NLA_BEARER], tipc_nl_bearer_policy, info->extack); if (err) return err; if (!attrs[TIPC_NLA_BEARER_NAME]) return -EINVAL; name = nla_data(attrs[TIPC_NLA_BEARER_NAME]); b = tipc_bearer_find(net, name); if (!b) { NL_SET_ERR_MSG(info->extack, "Bearer not found"); return -EINVAL; } if (attrs[TIPC_NLA_BEARER_PROP]) { struct nlattr *props[TIPC_NLA_PROP_MAX + 1]; err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_BEARER_PROP], props); if (err) return err; if (props[TIPC_NLA_PROP_TOL]) { b->tolerance = nla_get_u32(props[TIPC_NLA_PROP_TOL]); tipc_node_apply_property(net, b, TIPC_NLA_PROP_TOL); } if (props[TIPC_NLA_PROP_PRIO]) b->priority = nla_get_u32(props[TIPC_NLA_PROP_PRIO]); if (props[TIPC_NLA_PROP_WIN]) b->max_win = nla_get_u32(props[TIPC_NLA_PROP_WIN]); if (props[TIPC_NLA_PROP_MTU]) { if (b->media->type_id != TIPC_MEDIA_TYPE_UDP) { NL_SET_ERR_MSG(info->extack, "MTU property is unsupported"); return -EINVAL; } #ifdef CONFIG_TIPC_MEDIA_UDP if (nla_get_u32(props[TIPC_NLA_PROP_MTU]) < b->encap_hlen + TIPC_MIN_BEARER_MTU) { NL_SET_ERR_MSG(info->extack, "MTU value is out-of-range"); return -EINVAL; } b->mtu = nla_get_u32(props[TIPC_NLA_PROP_MTU]); tipc_node_apply_property(net, b, TIPC_NLA_PROP_MTU); #endif } } return 0; } int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) { int err; rtnl_lock(); err = __tipc_nl_bearer_set(skb, info); rtnl_unlock(); return err; } static int __tipc_nl_add_media(struct tipc_nl_msg *msg, struct tipc_media *media, int nlflags) { void *hdr; struct nlattr *attrs; struct nlattr *prop; hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, nlflags, TIPC_NL_MEDIA_GET); if (!hdr) return -EMSGSIZE; attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_MEDIA); if (!attrs) goto msg_full; if (nla_put_string(msg->skb, TIPC_NLA_MEDIA_NAME, media->name)) goto attr_msg_full; prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_MEDIA_PROP); if (!prop) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, media->priority)) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_TOL, media->tolerance)) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, media->max_win)) goto prop_msg_full; if (media->type_id == TIPC_MEDIA_TYPE_UDP) if (nla_put_u32(msg->skb, TIPC_NLA_PROP_MTU, media->mtu)) goto prop_msg_full; nla_nest_end(msg->skb, prop); nla_nest_end(msg->skb, attrs); genlmsg_end(msg->skb, hdr); return 0; prop_msg_full: nla_nest_cancel(msg->skb, prop); attr_msg_full: nla_nest_cancel(msg->skb, attrs); msg_full: genlmsg_cancel(msg->skb, hdr); return -EMSGSIZE; } int tipc_nl_media_dump(struct sk_buff *skb, struct netlink_callback *cb) { int err; int i = cb->args[0]; struct tipc_nl_msg msg; if (i == MAX_MEDIA) return 0; msg.skb = skb; msg.portid = NETLINK_CB(cb->skb).portid; msg.seq = cb->nlh->nlmsg_seq; rtnl_lock(); for (; media_info_array[i] != NULL; i++) { err = __tipc_nl_add_media(&msg, media_info_array[i], NLM_F_MULTI); if (err) break; } rtnl_unlock(); cb->args[0] = i; return skb->len; } int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info) { int err; char *name; struct tipc_nl_msg msg; struct tipc_media *media; struct sk_buff *rep; struct nlattr *attrs[TIPC_NLA_MEDIA_MAX + 1]; if (!info->attrs[TIPC_NLA_MEDIA]) return -EINVAL; err = nla_parse_nested_deprecated(attrs, TIPC_NLA_MEDIA_MAX, info->attrs[TIPC_NLA_MEDIA], tipc_nl_media_policy, info->extack); if (err) return err; if (!attrs[TIPC_NLA_MEDIA_NAME]) return -EINVAL; name = nla_data(attrs[TIPC_NLA_MEDIA_NAME]); rep = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (!rep) return -ENOMEM; msg.skb = rep; msg.portid = info->snd_portid; msg.seq = info->snd_seq; rtnl_lock(); media = tipc_media_find(name); if (!media) { NL_SET_ERR_MSG(info->extack, "Media not found"); err = -EINVAL; goto err_out; } err = __tipc_nl_add_media(&msg, media, 0); if (err) goto err_out; rtnl_unlock(); return genlmsg_reply(rep, info); err_out: rtnl_unlock(); nlmsg_free(rep); return err; } int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info) { int err; char *name; struct tipc_media *m; struct nlattr *attrs[TIPC_NLA_MEDIA_MAX + 1]; if (!info->attrs[TIPC_NLA_MEDIA]) return -EINVAL; err = nla_parse_nested_deprecated(attrs, TIPC_NLA_MEDIA_MAX, info->attrs[TIPC_NLA_MEDIA], tipc_nl_media_policy, info->extack); if (!attrs[TIPC_NLA_MEDIA_NAME]) return -EINVAL; name = nla_data(attrs[TIPC_NLA_MEDIA_NAME]); m = tipc_media_find(name); if (!m) { NL_SET_ERR_MSG(info->extack, "Media not found"); return -EINVAL; } if (attrs[TIPC_NLA_MEDIA_PROP]) { struct nlattr *props[TIPC_NLA_PROP_MAX + 1]; err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_MEDIA_PROP], props); if (err) return err; if (props[TIPC_NLA_PROP_TOL]) m->tolerance = nla_get_u32(props[TIPC_NLA_PROP_TOL]); if (props[TIPC_NLA_PROP_PRIO]) m->priority = nla_get_u32(props[TIPC_NLA_PROP_PRIO]); if (props[TIPC_NLA_PROP_WIN]) m->max_win = nla_get_u32(props[TIPC_NLA_PROP_WIN]); if (props[TIPC_NLA_PROP_MTU]) { if (m->type_id != TIPC_MEDIA_TYPE_UDP) { NL_SET_ERR_MSG(info->extack, "MTU property is unsupported"); return -EINVAL; } #ifdef CONFIG_TIPC_MEDIA_UDP if (tipc_udp_mtu_bad(nla_get_u32 (props[TIPC_NLA_PROP_MTU]))) { NL_SET_ERR_MSG(info->extack, "MTU value is out-of-range"); return -EINVAL; } m->mtu = nla_get_u32(props[TIPC_NLA_PROP_MTU]); #endif } } return 0; } int tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info) { int err; rtnl_lock(); err = __tipc_nl_media_set(skb, info); rtnl_unlock(); return err; } |
| 20 14 18 22 | 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 | /* * linux/fs/nls/nls_cp863.c * * Charset cp863 translation tables. * Generated automatically from the Unicode and charset * tables from the Unicode Organization (www.unicode.org). * The Unicode to charset table has only exact mappings. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00*/ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10*/ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20*/ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30*/ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40*/ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50*/ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60*/ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70*/ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80*/ 0x00c7, 0x00fc, 0x00e9, 0x00e2, 0x00c2, 0x00e0, 0x00b6, 0x00e7, 0x00ea, 0x00eb, 0x00e8, 0x00ef, 0x00ee, 0x2017, 0x00c0, 0x00a7, /* 0x90*/ 0x00c9, 0x00c8, 0x00ca, 0x00f4, 0x00cb, 0x00cf, 0x00fb, 0x00f9, 0x00a4, 0x00d4, 0x00dc, 0x00a2, 0x00a3, 0x00d9, 0x00db, 0x0192, /* 0xa0*/ 0x00a6, 0x00b4, 0x00f3, 0x00fa, 0x00a8, 0x00b8, 0x00b3, 0x00af, 0x00ce, 0x2310, 0x00ac, 0x00bd, 0x00bc, 0x00be, 0x00ab, 0x00bb, /* 0xb0*/ 0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x2561, 0x2562, 0x2556, 0x2555, 0x2563, 0x2551, 0x2557, 0x255d, 0x255c, 0x255b, 0x2510, /* 0xc0*/ 0x2514, 0x2534, 0x252c, 0x251c, 0x2500, 0x253c, 0x255e, 0x255f, 0x255a, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256c, 0x2567, /* 0xd0*/ 0x2568, 0x2564, 0x2565, 0x2559, 0x2558, 0x2552, 0x2553, 0x256b, 0x256a, 0x2518, 0x250c, 0x2588, 0x2584, 0x258c, 0x2590, 0x2580, /* 0xe0*/ 0x03b1, 0x00df, 0x0393, 0x03c0, 0x03a3, 0x03c3, 0x00b5, 0x03c4, 0x03a6, 0x0398, 0x03a9, 0x03b4, 0x221e, 0x03c6, 0x03b5, 0x2229, /* 0xf0*/ 0x2261, 0x00b1, 0x2265, 0x2264, 0x2320, 0x2321, 0x00f7, 0x2248, 0x00b0, 0x2219, 0x00b7, 0x221a, 0x207f, 0x00b2, 0x25a0, 0x00a0, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xff, 0x00, 0x9b, 0x9c, 0x98, 0x00, 0xa0, 0x8f, /* 0xa0-0xa7 */ 0xa4, 0x00, 0x00, 0xae, 0xaa, 0x00, 0x00, 0xa7, /* 0xa8-0xaf */ 0xf8, 0xf1, 0xfd, 0xa6, 0xa1, 0xe6, 0x86, 0xfa, /* 0xb0-0xb7 */ 0xa5, 0x00, 0x00, 0xaf, 0xac, 0xab, 0xad, 0x00, /* 0xb8-0xbf */ 0x8e, 0x00, 0x84, 0x00, 0x00, 0x00, 0x00, 0x80, /* 0xc0-0xc7 */ 0x91, 0x90, 0x92, 0x94, 0x00, 0x00, 0xa8, 0x95, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x99, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x9d, 0x00, 0x9e, 0x9a, 0x00, 0x00, 0xe1, /* 0xd8-0xdf */ 0x85, 0x00, 0x83, 0x00, 0x00, 0x00, 0x00, 0x87, /* 0xe0-0xe7 */ 0x8a, 0x82, 0x88, 0x89, 0x00, 0x00, 0x8c, 0x8b, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0xa2, 0x93, 0x00, 0x00, 0xf6, /* 0xf0-0xf7 */ 0x00, 0x97, 0xa3, 0x96, 0x81, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page01[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x9f, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ }; static const unsigned char page03[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0xe2, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0xe9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0xe4, 0x00, 0x00, 0xe8, 0x00, /* 0xa0-0xa7 */ 0x00, 0xea, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0xe0, 0x00, 0x00, 0xeb, 0xee, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0xe3, 0x00, 0x00, 0xe5, 0xe7, 0x00, 0xed, 0x00, /* 0xc0-0xc7 */ }; static const unsigned char page20[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x8d, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfc, /* 0x78-0x7f */ }; static const unsigned char page22[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0xf9, 0xfb, 0x00, 0x00, 0x00, 0xec, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0xef, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0xf7, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0xf0, 0x00, 0x00, 0xf3, 0xf2, 0x00, 0x00, /* 0x60-0x67 */ }; static const unsigned char page23[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0xa9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0xf4, 0xf5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ }; static const unsigned char page25[256] = { 0xc4, 0x00, 0xb3, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0xda, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0xbf, 0x00, 0x00, 0x00, 0xc0, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0xd9, 0x00, 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0xb4, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0xc2, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0xc1, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0xc5, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0xcd, 0xba, 0xd5, 0xd6, 0xc9, 0xb8, 0xb7, 0xbb, /* 0x50-0x57 */ 0xd4, 0xd3, 0xc8, 0xbe, 0xbd, 0xbc, 0xc6, 0xc7, /* 0x58-0x5f */ 0xcc, 0xb5, 0xb6, 0xb9, 0xd1, 0xd2, 0xcb, 0xcf, /* 0x60-0x67 */ 0xd0, 0xca, 0xd8, 0xd7, 0xce, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0xdf, 0x00, 0x00, 0x00, 0xdc, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0xdb, 0x00, 0x00, 0x00, 0xdd, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0xde, 0xb0, 0xb1, 0xb2, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ }; static const unsigned char *const page_uni2charset[256] = { page00, page01, NULL, page03, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, page20, NULL, page22, page23, NULL, page25, NULL, NULL, }; static const unsigned char charset2lower[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */ 0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x87, 0x81, 0x82, 0x83, 0x83, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x85, 0x8f, /* 0x88-0x8f */ 0x82, 0x8a, 0x88, 0x93, 0x89, 0x8b, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x93, 0x81, 0x9b, 0x9c, 0x97, 0x96, 0x9f, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0x8c, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe1, 0x00, 0xe3, 0xe5, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xed, 0x00, 0x00, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x9a, 0x90, 0x84, 0x84, 0x8e, 0x86, 0x80, /* 0x80-0x87 */ 0x92, 0x94, 0x91, 0x95, 0xa8, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x99, 0x94, 0x95, 0x9e, 0x9d, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x00, /* 0x98-0x9f */ 0xa0, 0xa1, 0x00, 0x00, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0x00, 0xe1, 0xe2, 0x00, 0xe4, 0xe4, 0x00, 0x00, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0x00, 0xec, 0xe8, 0x00, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "cp863", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_cp863(void) { return register_nls(&table); } static void __exit exit_nls_cp863(void) { unregister_nls(&table); } module_init(init_nls_cp863) module_exit(exit_nls_cp863) MODULE_DESCRIPTION("NLS Codepage 863 (Canadian French)"); MODULE_LICENSE("Dual BSD/GPL"); |
| 11 11 11 17 16 11 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/init.h> #include <linux/scatterlist.h> #include <linux/mempool.h> #include <linux/slab.h> #define SG_MEMPOOL_NR ARRAY_SIZE(sg_pools) #define SG_MEMPOOL_SIZE 2 struct sg_pool { size_t size; char *name; struct kmem_cache *slab; mempool_t *pool; }; #define SP(x) { .size = x, "sgpool-" __stringify(x) } #if (SG_CHUNK_SIZE < 32) #error SG_CHUNK_SIZE is too small (must be 32 or greater) #endif static struct sg_pool sg_pools[] = { SP(8), SP(16), #if (SG_CHUNK_SIZE > 32) SP(32), #if (SG_CHUNK_SIZE > 64) SP(64), #if (SG_CHUNK_SIZE > 128) SP(128), #if (SG_CHUNK_SIZE > 256) #error SG_CHUNK_SIZE is too large (256 MAX) #endif #endif #endif #endif SP(SG_CHUNK_SIZE) }; #undef SP static inline unsigned int sg_pool_index(unsigned short nents) { unsigned int index; BUG_ON(nents > SG_CHUNK_SIZE); if (nents <= 8) index = 0; else index = get_count_order(nents) - 3; return index; } static void sg_pool_free(struct scatterlist *sgl, unsigned int nents) { struct sg_pool *sgp; sgp = sg_pools + sg_pool_index(nents); mempool_free(sgl, sgp->pool); } static struct scatterlist *sg_pool_alloc(unsigned int nents, gfp_t gfp_mask) { struct sg_pool *sgp; sgp = sg_pools + sg_pool_index(nents); return mempool_alloc(sgp->pool, gfp_mask); } /** * sg_free_table_chained - Free a previously mapped sg table * @table: The sg table header to use * @nents_first_chunk: size of the first_chunk SGL passed to * sg_alloc_table_chained * * Description: * Free an sg table previously allocated and setup with * sg_alloc_table_chained(). * * @nents_first_chunk has to be same with that same parameter passed * to sg_alloc_table_chained(). * **/ void sg_free_table_chained(struct sg_table *table, unsigned nents_first_chunk) { if (table->orig_nents <= nents_first_chunk) return; if (nents_first_chunk == 1) nents_first_chunk = 0; __sg_free_table(table, SG_CHUNK_SIZE, nents_first_chunk, sg_pool_free, table->orig_nents); } EXPORT_SYMBOL_GPL(sg_free_table_chained); /** * sg_alloc_table_chained - Allocate and chain SGLs in an sg table * @table: The sg table header to use * @nents: Number of entries in sg list * @first_chunk: first SGL * @nents_first_chunk: number of the SGL of @first_chunk * * Description: * Allocate and chain SGLs in an sg table. If @nents@ is larger than * @nents_first_chunk a chained sg table will be setup. @first_chunk is * ignored if nents_first_chunk <= 1 because user expects the SGL points * non-chain SGL. * **/ int sg_alloc_table_chained(struct sg_table *table, int nents, struct scatterlist *first_chunk, unsigned nents_first_chunk) { int ret; BUG_ON(!nents); if (first_chunk && nents_first_chunk) { if (nents <= nents_first_chunk) { table->nents = table->orig_nents = nents; sg_init_table(table->sgl, nents); return 0; } } /* User supposes that the 1st SGL includes real entry */ if (nents_first_chunk <= 1) { first_chunk = NULL; nents_first_chunk = 0; } ret = __sg_alloc_table(table, nents, SG_CHUNK_SIZE, first_chunk, nents_first_chunk, GFP_ATOMIC, sg_pool_alloc); if (unlikely(ret)) sg_free_table_chained(table, nents_first_chunk); return ret; } EXPORT_SYMBOL_GPL(sg_alloc_table_chained); static __init int sg_pool_init(void) { int i; for (i = 0; i < SG_MEMPOOL_NR; i++) { struct sg_pool *sgp = sg_pools + i; int size = sgp->size * sizeof(struct scatterlist); sgp->slab = kmem_cache_create(sgp->name, size, 0, SLAB_HWCACHE_ALIGN, NULL); if (!sgp->slab) { printk(KERN_ERR "SG_POOL: can't init sg slab %s\n", sgp->name); goto cleanup_sdb; } sgp->pool = mempool_create_slab_pool(SG_MEMPOOL_SIZE, sgp->slab); if (!sgp->pool) { printk(KERN_ERR "SG_POOL: can't init sg mempool %s\n", sgp->name); goto cleanup_sdb; } } return 0; cleanup_sdb: for (i = 0; i < SG_MEMPOOL_NR; i++) { struct sg_pool *sgp = sg_pools + i; mempool_destroy(sgp->pool); kmem_cache_destroy(sgp->slab); } return -ENOMEM; } subsys_initcall(sg_pool_init); |
| 16 16 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _SCSI_DISK_H #define _SCSI_DISK_H /* * More than enough for everybody ;) The huge number of majors * is a leftover from 16bit dev_t days, we don't really need that * much numberspace. */ #define SD_MAJORS 16 /* * Time out in seconds for disks and Magneto-opticals (which are slower). */ #define SD_TIMEOUT (30 * HZ) #define SD_MOD_TIMEOUT (75 * HZ) /* * Flush timeout is a multiplier over the standard device timeout which is * user modifiable via sysfs but initially set to SD_TIMEOUT */ #define SD_FLUSH_TIMEOUT_MULTIPLIER 2 #define SD_WRITE_SAME_TIMEOUT (120 * HZ) /* * Number of allowed retries */ #define SD_MAX_RETRIES 5 #define SD_PASSTHROUGH_RETRIES 1 #define SD_MAX_MEDIUM_TIMEOUTS 2 /* * Size of the initial data buffer for mode and read capacity data */ #define SD_BUF_SIZE 512 /* * Number of sectors at the end of the device to avoid multi-sector * accesses to in the case of last_sector_bug */ #define SD_LAST_BUGGY_SECTORS 8 enum { SD_EXT_CDB_SIZE = 32, /* Extended CDB size */ SD_MEMPOOL_SIZE = 2, /* CDB pool size */ }; enum { SD_DEF_XFER_BLOCKS = 0xffff, SD_MAX_XFER_BLOCKS = 0xffffffff, SD_MAX_WS10_BLOCKS = 0xffff, SD_MAX_WS16_BLOCKS = 0x7fffff, }; enum { SD_LBP_FULL = 0, /* Full logical block provisioning */ SD_LBP_UNMAP, /* Use UNMAP command */ SD_LBP_WS16, /* Use WRITE SAME(16) with UNMAP bit */ SD_LBP_WS10, /* Use WRITE SAME(10) with UNMAP bit */ SD_LBP_ZERO, /* Use WRITE SAME(10) with zero payload */ SD_LBP_DISABLE, /* Discard disabled due to failed cmd */ }; enum { SD_ZERO_WRITE = 0, /* Use WRITE(10/16) command */ SD_ZERO_WS, /* Use WRITE SAME(10/16) command */ SD_ZERO_WS16_UNMAP, /* Use WRITE SAME(16) with UNMAP */ SD_ZERO_WS10_UNMAP, /* Use WRITE SAME(10) with UNMAP */ }; /** * struct zoned_disk_info - Specific properties of a ZBC SCSI device. * @nr_zones: number of zones. * @zone_blocks: number of logical blocks per zone. * * This data structure holds the ZBC SCSI device properties that are retrieved * twice: a first time before the gendisk capacity is known and a second time * after the gendisk capacity is known. */ struct zoned_disk_info { u32 nr_zones; u32 zone_blocks; }; struct scsi_disk { struct scsi_device *device; /* * disk_dev is used to show attributes in /sys/class/scsi_disk/, * but otherwise not really needed. Do not use for refcounting. */ struct device disk_dev; struct gendisk *disk; struct opal_dev *opal_dev; #ifdef CONFIG_BLK_DEV_ZONED /* Updated during revalidation before the gendisk capacity is known. */ struct zoned_disk_info early_zone_info; /* Updated during revalidation after the gendisk capacity is known. */ struct zoned_disk_info zone_info; u32 zones_optimal_open; u32 zones_optimal_nonseq; u32 zones_max_open; /* * Either zero or a power of two. If not zero it means that the offset * between zone starting LBAs is constant. */ u32 zone_starting_lba_gran; #endif atomic_t openers; sector_t capacity; /* size in logical blocks */ int max_retries; u32 min_xfer_blocks; u32 max_xfer_blocks; u32 opt_xfer_blocks; u32 max_ws_blocks; u32 max_unmap_blocks; u32 unmap_granularity; u32 unmap_alignment; u32 max_atomic; u32 atomic_alignment; u32 atomic_granularity; u32 max_atomic_with_boundary; u32 max_atomic_boundary; u32 index; unsigned int physical_block_size; unsigned int max_medium_access_timeouts; unsigned int medium_access_timed_out; /* number of permanent streams */ u16 permanent_stream_count; u8 media_present; u8 write_prot; u8 protection_type;/* Data Integrity Field */ u8 provisioning_mode; u8 zeroing_mode; u8 nr_actuators; /* Number of actuators */ bool suspended; /* Disk is suspended (stopped) */ unsigned ATO : 1; /* state of disk ATO bit */ unsigned cache_override : 1; /* temp override of WCE,RCD */ unsigned WCE : 1; /* state of disk WCE bit */ unsigned RCD : 1; /* state of disk RCD bit, unused */ unsigned DPOFUA : 1; /* state of disk DPOFUA bit */ unsigned first_scan : 1; unsigned lbpme : 1; unsigned lbprz : 1; unsigned lbpu : 1; unsigned lbpws : 1; unsigned lbpws10 : 1; unsigned lbpvpd : 1; unsigned ws10 : 1; unsigned ws16 : 1; unsigned rc_basis: 2; unsigned zoned: 2; unsigned urswrz : 1; unsigned security : 1; unsigned ignore_medium_access_errors : 1; unsigned rscs : 1; /* reduced stream control support */ unsigned use_atomic_write_boundary : 1; }; #define to_scsi_disk(obj) container_of(obj, struct scsi_disk, disk_dev) static inline struct scsi_disk *scsi_disk(struct gendisk *disk) { return disk->private_data; } #define sd_printk(prefix, sdsk, fmt, a...) \ (sdsk)->disk ? \ sdev_prefix_printk(prefix, (sdsk)->device, \ (sdsk)->disk->disk_name, fmt, ##a) : \ sdev_printk(prefix, (sdsk)->device, fmt, ##a) #define sd_first_printk(prefix, sdsk, fmt, a...) \ do { \ if ((sdsk)->first_scan) \ sd_printk(prefix, sdsk, fmt, ##a); \ } while (0) static inline int scsi_medium_access_command(struct scsi_cmnd *scmd) { switch (scmd->cmnd[0]) { case READ_6: case READ_10: case READ_12: case READ_16: case SYNCHRONIZE_CACHE: case VERIFY: case VERIFY_12: case VERIFY_16: case WRITE_6: case WRITE_10: case WRITE_12: case WRITE_16: case WRITE_SAME: case WRITE_SAME_16: case UNMAP: return 1; case VARIABLE_LENGTH_CMD: switch (scmd->cmnd[9]) { case READ_32: case VERIFY_32: case WRITE_32: case WRITE_SAME_32: return 1; } } return 0; } static inline sector_t logical_to_sectors(struct scsi_device *sdev, sector_t blocks) { return blocks << (ilog2(sdev->sector_size) - 9); } static inline unsigned int logical_to_bytes(struct scsi_device *sdev, sector_t blocks) { return blocks * sdev->sector_size; } static inline sector_t bytes_to_logical(struct scsi_device *sdev, unsigned int bytes) { return bytes >> ilog2(sdev->sector_size); } static inline sector_t sectors_to_logical(struct scsi_device *sdev, sector_t sector) { return sector >> (ilog2(sdev->sector_size) - 9); } void sd_dif_config_host(struct scsi_disk *sdkp, struct queue_limits *lim); #ifdef CONFIG_BLK_DEV_ZONED int sd_zbc_read_zones(struct scsi_disk *sdkp, struct queue_limits *lim, u8 buf[SD_BUF_SIZE]); int sd_zbc_revalidate_zones(struct scsi_disk *sdkp); blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd, unsigned char op, bool all); unsigned int sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes, struct scsi_sense_hdr *sshdr); int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); #else /* CONFIG_BLK_DEV_ZONED */ static inline int sd_zbc_read_zones(struct scsi_disk *sdkp, struct queue_limits *lim, u8 buf[SD_BUF_SIZE]) { return 0; } static inline int sd_zbc_revalidate_zones(struct scsi_disk *sdkp) { return 0; } static inline blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd, unsigned char op, bool all) { return BLK_STS_TARGET; } static inline unsigned int sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes, struct scsi_sense_hdr *sshdr) { return good_bytes; } #define sd_zbc_report_zones NULL #endif /* CONFIG_BLK_DEV_ZONED */ void sd_print_sense_hdr(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr); void sd_print_result(const struct scsi_disk *sdkp, const char *msg, int result); #endif /* _SCSI_DISK_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_RT_H #define _LINUX_SCHED_RT_H #include <linux/sched.h> struct task_struct; static inline bool rt_prio(int prio) { return unlikely(prio < MAX_RT_PRIO && prio >= MAX_DL_PRIO); } static inline bool rt_or_dl_prio(int prio) { return unlikely(prio < MAX_RT_PRIO); } /* * Returns true if a task has a priority that belongs to RT class. PI-boosted * tasks will return true. Use rt_policy() to ignore PI-boosted tasks. */ static inline bool rt_task(struct task_struct *p) { return rt_prio(p->prio); } /* * Returns true if a task has a priority that belongs to RT or DL classes. * PI-boosted tasks will return true. Use rt_or_dl_task_policy() to ignore * PI-boosted tasks. */ static inline bool rt_or_dl_task(struct task_struct *p) { return rt_or_dl_prio(p->prio); } /* * Returns true if a task has a policy that belongs to RT or DL classes. * PI-boosted tasks will return false. */ static inline bool rt_or_dl_task_policy(struct task_struct *tsk) { int policy = tsk->policy; if (policy == SCHED_FIFO || policy == SCHED_RR) return true; if (policy == SCHED_DEADLINE) return true; return false; } #ifdef CONFIG_RT_MUTEXES extern void rt_mutex_pre_schedule(void); extern void rt_mutex_schedule(void); extern void rt_mutex_post_schedule(void); /* * Must hold either p->pi_lock or task_rq(p)->lock. */ static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *p) { return p->pi_top_task; } extern void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task); extern void rt_mutex_adjust_pi(struct task_struct *p); #else static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task) { return NULL; } # define rt_mutex_adjust_pi(p) do { } while (0) #endif extern void normalize_rt_tasks(void); /* * default timeslice is 100 msecs (used only for SCHED_RR tasks). * Timeslices get refilled after they expire. */ #define RR_TIMESLICE (100 * HZ / 1000) #endif /* _LINUX_SCHED_RT_H */ |
| 5 1 5 6 6 2 5 5 5 5 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 | // SPDX-License-Identifier: GPL-2.0 /* * fs/sysfs/symlink.c - operations for initializing and mounting sysfs * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007 Tejun Heo <teheo@suse.de> * * Please see Documentation/filesystems/sysfs.rst for more information. */ #include <linux/fs.h> #include <linux/magic.h> #include <linux/mount.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/user_namespace.h> #include <linux/fs_context.h> #include <net/net_namespace.h> #include "sysfs.h" static struct kernfs_root *sysfs_root; struct kernfs_node *sysfs_root_kn; static int sysfs_get_tree(struct fs_context *fc) { struct kernfs_fs_context *kfc = fc->fs_private; int ret; ret = kernfs_get_tree(fc); if (ret) return ret; if (kfc->new_sb_created) fc->root->d_sb->s_iflags |= SB_I_USERNS_VISIBLE; return 0; } static void sysfs_fs_context_free(struct fs_context *fc) { struct kernfs_fs_context *kfc = fc->fs_private; if (kfc->ns_tag) kobj_ns_drop(KOBJ_NS_TYPE_NET, kfc->ns_tag); kernfs_free_fs_context(fc); kfree(kfc); } static const struct fs_context_operations sysfs_fs_context_ops = { .free = sysfs_fs_context_free, .get_tree = sysfs_get_tree, }; static int sysfs_init_fs_context(struct fs_context *fc) { struct kernfs_fs_context *kfc; struct net *netns; if (!(fc->sb_flags & SB_KERNMOUNT)) { if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET)) return -EPERM; } kfc = kzalloc(sizeof(struct kernfs_fs_context), GFP_KERNEL); if (!kfc) return -ENOMEM; kfc->ns_tag = netns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET); kfc->root = sysfs_root; kfc->magic = SYSFS_MAGIC; fc->fs_private = kfc; fc->ops = &sysfs_fs_context_ops; if (netns) { put_user_ns(fc->user_ns); fc->user_ns = get_user_ns(netns->user_ns); } fc->global = true; return 0; } static void sysfs_kill_sb(struct super_block *sb) { void *ns = (void *)kernfs_super_ns(sb); kernfs_kill_sb(sb); kobj_ns_drop(KOBJ_NS_TYPE_NET, ns); } static struct file_system_type sysfs_fs_type = { .name = "sysfs", .init_fs_context = sysfs_init_fs_context, .kill_sb = sysfs_kill_sb, .fs_flags = FS_USERNS_MOUNT, }; int __init sysfs_init(void) { int err; sysfs_root = kernfs_create_root(NULL, KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK, NULL); if (IS_ERR(sysfs_root)) return PTR_ERR(sysfs_root); sysfs_root_kn = kernfs_root_to_node(sysfs_root); err = register_filesystem(&sysfs_fs_type); if (err) { kernfs_destroy_root(sysfs_root); return err; } return 0; } |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 | // SPDX-License-Identifier: GPL-2.0 /* * io_uring opcode handling table */ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/io_uring.h> #include <linux/io_uring/cmd.h> #include "io_uring.h" #include "opdef.h" #include "refs.h" #include "tctx.h" #include "sqpoll.h" #include "fdinfo.h" #include "kbuf.h" #include "rsrc.h" #include "xattr.h" #include "nop.h" #include "fs.h" #include "splice.h" #include "sync.h" #include "advise.h" #include "openclose.h" #include "uring_cmd.h" #include "epoll.h" #include "statx.h" #include "net.h" #include "msg_ring.h" #include "timeout.h" #include "poll.h" #include "cancel.h" #include "rw.h" #include "waitid.h" #include "futex.h" #include "truncate.h" #include "zcrx.h" static int io_no_issue(struct io_kiocb *req, unsigned int issue_flags) { WARN_ON_ONCE(1); return -ECANCELED; } static __maybe_unused int io_eopnotsupp_prep(struct io_kiocb *kiocb, const struct io_uring_sqe *sqe) { return -EOPNOTSUPP; } const struct io_issue_def io_issue_defs[] = { [IORING_OP_NOP] = { .audit_skip = 1, .iopoll = 1, .prep = io_nop_prep, .issue = io_nop, }, [IORING_OP_READV] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .buffer_select = 1, .plug = 1, .audit_skip = 1, .ioprio = 1, .iopoll = 1, .iopoll_queue = 1, .vectored = 1, .async_size = sizeof(struct io_async_rw), .prep = io_prep_readv, .issue = io_read, }, [IORING_OP_WRITEV] = { .needs_file = 1, .hash_reg_file = 1, .unbound_nonreg_file = 1, .pollout = 1, .plug = 1, .audit_skip = 1, .ioprio = 1, .iopoll = 1, .iopoll_queue = 1, .vectored = 1, .async_size = sizeof(struct io_async_rw), .prep = io_prep_writev, .issue = io_write, }, [IORING_OP_FSYNC] = { .needs_file = 1, .audit_skip = 1, .prep = io_fsync_prep, .issue = io_fsync, }, [IORING_OP_READ_FIXED] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .plug = 1, .audit_skip = 1, .ioprio = 1, .iopoll = 1, .iopoll_queue = 1, .async_size = sizeof(struct io_async_rw), .prep = io_prep_read_fixed, .issue = io_read_fixed, }, [IORING_OP_WRITE_FIXED] = { .needs_file = 1, .hash_reg_file = 1, .unbound_nonreg_file = 1, .pollout = 1, .plug = 1, .audit_skip = 1, .ioprio = 1, .iopoll = 1, .iopoll_queue = 1, .async_size = sizeof(struct io_async_rw), .prep = io_prep_write_fixed, .issue = io_write_fixed, }, [IORING_OP_POLL_ADD] = { .needs_file = 1, .unbound_nonreg_file = 1, .audit_skip = 1, .prep = io_poll_add_prep, .issue = io_poll_add, }, [IORING_OP_POLL_REMOVE] = { .audit_skip = 1, .prep = io_poll_remove_prep, .issue = io_poll_remove, }, [IORING_OP_SYNC_FILE_RANGE] = { .needs_file = 1, .audit_skip = 1, .prep = io_sfr_prep, .issue = io_sync_file_range, }, [IORING_OP_SENDMSG] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollout = 1, .ioprio = 1, #if defined(CONFIG_NET) .async_size = sizeof(struct io_async_msghdr), .prep = io_sendmsg_prep, .issue = io_sendmsg, #else .prep = io_eopnotsupp_prep, #endif }, [IORING_OP_RECVMSG] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .buffer_select = 1, .ioprio = 1, #if defined(CONFIG_NET) .async_size = sizeof(struct io_async_msghdr), .prep = io_recvmsg_prep, .issue = io_recvmsg, #else .prep = io_eopnotsupp_prep, #endif }, [IORING_OP_TIMEOUT] = { .audit_skip = 1, .async_size = sizeof(struct io_timeout_data), .prep = io_timeout_prep, .issue = io_timeout, }, [IORING_OP_TIMEOUT_REMOVE] = { /* used by timeout updates' prep() */ .audit_skip = 1, .prep = io_timeout_remove_prep, .issue = io_timeout_remove, }, [IORING_OP_ACCEPT] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .poll_exclusive = 1, .ioprio = 1, /* used for flags */ #if defined(CONFIG_NET) .prep = io_accept_prep, .issue = io_accept, #else .prep = io_eopnotsupp_prep, #endif }, [IORING_OP_ASYNC_CANCEL] = { .audit_skip = 1, .prep = io_async_cancel_prep, .issue = io_async_cancel, }, [IORING_OP_LINK_TIMEOUT] = { .audit_skip = 1, .async_size = sizeof(struct io_timeout_data), .prep = io_link_timeout_prep, .issue = io_no_issue, }, [IORING_OP_CONNECT] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollout = 1, #if defined(CONFIG_NET) .async_size = sizeof(struct io_async_msghdr), .prep = io_connect_prep, .issue = io_connect, #else .prep = io_eopnotsupp_prep, #endif }, [IORING_OP_FALLOCATE] = { .needs_file = 1, .prep = io_fallocate_prep, .issue = io_fallocate, }, [IORING_OP_OPENAT] = { .prep = io_openat_prep, .issue = io_openat, }, [IORING_OP_CLOSE] = { .prep = io_close_prep, .issue = io_close, }, [IORING_OP_FILES_UPDATE] = { .audit_skip = 1, .iopoll = 1, .prep = io_files_update_prep, .issue = io_files_update, }, [IORING_OP_STATX] = { .audit_skip = 1, .prep = io_statx_prep, .issue = io_statx, }, [IORING_OP_READ] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .buffer_select = 1, .plug = 1, .audit_skip = 1, .ioprio = 1, .iopoll = 1, .iopoll_queue = 1, .async_size = sizeof(struct io_async_rw), .prep = io_prep_read, .issue = io_read, }, [IORING_OP_WRITE] = { .needs_file = 1, .hash_reg_file = 1, .unbound_nonreg_file = 1, .pollout = 1, .plug = 1, .audit_skip = 1, .ioprio = 1, .iopoll = 1, .iopoll_queue = 1, .async_size = sizeof(struct io_async_rw), .prep = io_prep_write, .issue = io_write, }, [IORING_OP_FADVISE] = { .needs_file = 1, .audit_skip = 1, .prep = io_fadvise_prep, .issue = io_fadvise, }, [IORING_OP_MADVISE] = { .audit_skip = 1, .prep = io_madvise_prep, .issue = io_madvise, }, [IORING_OP_SEND] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollout = 1, .audit_skip = 1, .ioprio = 1, .buffer_select = 1, #if defined(CONFIG_NET) .async_size = sizeof(struct io_async_msghdr), .prep = io_sendmsg_prep, .issue = io_send, #else .prep = io_eopnotsupp_prep, #endif }, [IORING_OP_RECV] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .buffer_select = 1, .audit_skip = 1, .ioprio = 1, #if defined(CONFIG_NET) .async_size = sizeof(struct io_async_msghdr), .prep = io_recvmsg_prep, .issue = io_recv, #else .prep = io_eopnotsupp_prep, #endif }, [IORING_OP_OPENAT2] = { .prep = io_openat2_prep, .issue = io_openat2, }, [IORING_OP_EPOLL_CTL] = { .unbound_nonreg_file = 1, .audit_skip = 1, #if defined(CONFIG_EPOLL) .prep = io_epoll_ctl_prep, .issue = io_epoll_ctl, #else .prep = io_eopnotsupp_prep, #endif }, [IORING_OP_SPLICE] = { .needs_file = 1, .hash_reg_file = 1, .unbound_nonreg_file = 1, .audit_skip = 1, .prep = io_splice_prep, .issue = io_splice, }, [IORING_OP_PROVIDE_BUFFERS] = { .audit_skip = 1, .iopoll = 1, .prep = io_provide_buffers_prep, .issue = io_provide_buffers, }, [IORING_OP_REMOVE_BUFFERS] = { .audit_skip = 1, .iopoll = 1, .prep = io_remove_buffers_prep, .issue = io_remove_buffers, }, [IORING_OP_TEE] = { .needs_file = 1, .hash_reg_file = 1, .unbound_nonreg_file = 1, .audit_skip = 1, .prep = io_tee_prep, .issue = io_tee, }, [IORING_OP_SHUTDOWN] = { .needs_file = 1, #if defined(CONFIG_NET) .prep = io_shutdown_prep, .issue = io_shutdown, #else .prep = io_eopnotsupp_prep, #endif }, [IORING_OP_RENAMEAT] = { .prep = io_renameat_prep, .issue = io_renameat, }, [IORING_OP_UNLINKAT] = { .prep = io_unlinkat_prep, .issue = io_unlinkat, }, [IORING_OP_MKDIRAT] = { .prep = io_mkdirat_prep, .issue = io_mkdirat, }, [IORING_OP_SYMLINKAT] = { .prep = io_symlinkat_prep, .issue = io_symlinkat, }, [IORING_OP_LINKAT] = { .prep = io_linkat_prep, .issue = io_linkat, }, [IORING_OP_MSG_RING] = { .needs_file = 1, .iopoll = 1, .prep = io_msg_ring_prep, .issue = io_msg_ring, }, [IORING_OP_FSETXATTR] = { .needs_file = 1, .prep = io_fsetxattr_prep, .issue = io_fsetxattr, }, [IORING_OP_SETXATTR] = { .prep = io_setxattr_prep, .issue = io_setxattr, }, [IORING_OP_FGETXATTR] = { .needs_file = 1, .prep = io_fgetxattr_prep, .issue = io_fgetxattr, }, [IORING_OP_GETXATTR] = { .prep = io_getxattr_prep, .issue = io_getxattr, }, [IORING_OP_SOCKET] = { .audit_skip = 1, #if defined(CONFIG_NET) .prep = io_socket_prep, .issue = io_socket, #else .prep = io_eopnotsupp_prep, #endif }, [IORING_OP_URING_CMD] = { .needs_file = 1, .plug = 1, .iopoll = 1, .iopoll_queue = 1, .async_size = sizeof(struct io_async_cmd), .prep = io_uring_cmd_prep, .issue = io_uring_cmd, }, [IORING_OP_SEND_ZC] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollout = 1, .audit_skip = 1, .ioprio = 1, #if defined(CONFIG_NET) .async_size = sizeof(struct io_async_msghdr), .prep = io_send_zc_prep, .issue = io_send_zc, #else .prep = io_eopnotsupp_prep, #endif }, [IORING_OP_SENDMSG_ZC] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollout = 1, .ioprio = 1, #if defined(CONFIG_NET) .async_size = sizeof(struct io_async_msghdr), .prep = io_send_zc_prep, .issue = io_sendmsg_zc, #else .prep = io_eopnotsupp_prep, #endif }, [IORING_OP_READ_MULTISHOT] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .buffer_select = 1, .audit_skip = 1, .async_size = sizeof(struct io_async_rw), .prep = io_read_mshot_prep, .issue = io_read_mshot, }, [IORING_OP_WAITID] = { .async_size = sizeof(struct io_waitid_async), .prep = io_waitid_prep, .issue = io_waitid, }, [IORING_OP_FUTEX_WAIT] = { #if defined(CONFIG_FUTEX) .prep = io_futex_prep, .issue = io_futex_wait, #else .prep = io_eopnotsupp_prep, #endif }, [IORING_OP_FUTEX_WAKE] = { #if defined(CONFIG_FUTEX) .prep = io_futex_prep, .issue = io_futex_wake, #else .prep = io_eopnotsupp_prep, #endif }, [IORING_OP_FUTEX_WAITV] = { #if defined(CONFIG_FUTEX) .prep = io_futexv_prep, .issue = io_futexv_wait, #else .prep = io_eopnotsupp_prep, #endif }, [IORING_OP_FIXED_FD_INSTALL] = { .needs_file = 1, .prep = io_install_fixed_fd_prep, .issue = io_install_fixed_fd, }, [IORING_OP_FTRUNCATE] = { .needs_file = 1, .hash_reg_file = 1, .prep = io_ftruncate_prep, .issue = io_ftruncate, }, [IORING_OP_BIND] = { #if defined(CONFIG_NET) .needs_file = 1, .prep = io_bind_prep, .issue = io_bind, .async_size = sizeof(struct io_async_msghdr), #else .prep = io_eopnotsupp_prep, #endif }, [IORING_OP_LISTEN] = { #if defined(CONFIG_NET) .needs_file = 1, .prep = io_listen_prep, .issue = io_listen, .async_size = sizeof(struct io_async_msghdr), #else .prep = io_eopnotsupp_prep, #endif }, [IORING_OP_RECV_ZC] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .ioprio = 1, #if defined(CONFIG_NET) .prep = io_recvzc_prep, .issue = io_recvzc, #else .prep = io_eopnotsupp_prep, #endif }, [IORING_OP_EPOLL_WAIT] = { .needs_file = 1, .audit_skip = 1, .pollin = 1, #if defined(CONFIG_EPOLL) .prep = io_epoll_wait_prep, .issue = io_epoll_wait, #else .prep = io_eopnotsupp_prep, #endif }, [IORING_OP_READV_FIXED] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .plug = 1, .audit_skip = 1, .ioprio = 1, .iopoll = 1, .iopoll_queue = 1, .vectored = 1, .async_size = sizeof(struct io_async_rw), .prep = io_prep_readv_fixed, .issue = io_read, }, [IORING_OP_WRITEV_FIXED] = { .needs_file = 1, .hash_reg_file = 1, .unbound_nonreg_file = 1, .pollout = 1, .plug = 1, .audit_skip = 1, .ioprio = 1, .iopoll = 1, .iopoll_queue = 1, .vectored = 1, .async_size = sizeof(struct io_async_rw), .prep = io_prep_writev_fixed, .issue = io_write, }, }; const struct io_cold_def io_cold_defs[] = { [IORING_OP_NOP] = { .name = "NOP", }, [IORING_OP_READV] = { .name = "READV", .cleanup = io_readv_writev_cleanup, .fail = io_rw_fail, }, [IORING_OP_WRITEV] = { .name = "WRITEV", .cleanup = io_readv_writev_cleanup, .fail = io_rw_fail, }, [IORING_OP_FSYNC] = { .name = "FSYNC", }, [IORING_OP_READ_FIXED] = { .name = "READ_FIXED", .cleanup = io_readv_writev_cleanup, .fail = io_rw_fail, }, [IORING_OP_WRITE_FIXED] = { .name = "WRITE_FIXED", .cleanup = io_readv_writev_cleanup, .fail = io_rw_fail, }, [IORING_OP_POLL_ADD] = { .name = "POLL_ADD", }, [IORING_OP_POLL_REMOVE] = { .name = "POLL_REMOVE", }, [IORING_OP_SYNC_FILE_RANGE] = { .name = "SYNC_FILE_RANGE", }, [IORING_OP_SENDMSG] = { .name = "SENDMSG", #if defined(CONFIG_NET) .cleanup = io_sendmsg_recvmsg_cleanup, .fail = io_sendrecv_fail, #endif }, [IORING_OP_RECVMSG] = { .name = "RECVMSG", #if defined(CONFIG_NET) .cleanup = io_sendmsg_recvmsg_cleanup, .fail = io_sendrecv_fail, #endif }, [IORING_OP_TIMEOUT] = { .name = "TIMEOUT", }, [IORING_OP_TIMEOUT_REMOVE] = { .name = "TIMEOUT_REMOVE", }, [IORING_OP_ACCEPT] = { .name = "ACCEPT", }, [IORING_OP_ASYNC_CANCEL] = { .name = "ASYNC_CANCEL", }, [IORING_OP_LINK_TIMEOUT] = { .name = "LINK_TIMEOUT", }, [IORING_OP_CONNECT] = { .name = "CONNECT", }, [IORING_OP_FALLOCATE] = { .name = "FALLOCATE", }, [IORING_OP_OPENAT] = { .name = "OPENAT", .cleanup = io_open_cleanup, }, [IORING_OP_CLOSE] = { .name = "CLOSE", }, [IORING_OP_FILES_UPDATE] = { .name = "FILES_UPDATE", }, [IORING_OP_STATX] = { .name = "STATX", .cleanup = io_statx_cleanup, }, [IORING_OP_READ] = { .name = "READ", .cleanup = io_readv_writev_cleanup, .fail = io_rw_fail, }, [IORING_OP_WRITE] = { .name = "WRITE", .cleanup = io_readv_writev_cleanup, .fail = io_rw_fail, }, [IORING_OP_FADVISE] = { .name = "FADVISE", }, [IORING_OP_MADVISE] = { .name = "MADVISE", }, [IORING_OP_SEND] = { .name = "SEND", #if defined(CONFIG_NET) .cleanup = io_sendmsg_recvmsg_cleanup, .fail = io_sendrecv_fail, #endif }, [IORING_OP_RECV] = { .name = "RECV", #if defined(CONFIG_NET) .cleanup = io_sendmsg_recvmsg_cleanup, .fail = io_sendrecv_fail, #endif }, [IORING_OP_OPENAT2] = { .name = "OPENAT2", .cleanup = io_open_cleanup, }, [IORING_OP_EPOLL_CTL] = { .name = "EPOLL", }, [IORING_OP_SPLICE] = { .name = "SPLICE", .cleanup = io_splice_cleanup, }, [IORING_OP_PROVIDE_BUFFERS] = { .name = "PROVIDE_BUFFERS", }, [IORING_OP_REMOVE_BUFFERS] = { .name = "REMOVE_BUFFERS", }, [IORING_OP_TEE] = { .name = "TEE", .cleanup = io_splice_cleanup, }, [IORING_OP_SHUTDOWN] = { .name = "SHUTDOWN", }, [IORING_OP_RENAMEAT] = { .name = "RENAMEAT", .cleanup = io_renameat_cleanup, }, [IORING_OP_UNLINKAT] = { .name = "UNLINKAT", .cleanup = io_unlinkat_cleanup, }, [IORING_OP_MKDIRAT] = { .name = "MKDIRAT", .cleanup = io_mkdirat_cleanup, }, [IORING_OP_SYMLINKAT] = { .name = "SYMLINKAT", .cleanup = io_link_cleanup, }, [IORING_OP_LINKAT] = { .name = "LINKAT", .cleanup = io_link_cleanup, }, [IORING_OP_MSG_RING] = { .name = "MSG_RING", .cleanup = io_msg_ring_cleanup, }, [IORING_OP_FSETXATTR] = { .name = "FSETXATTR", .cleanup = io_xattr_cleanup, }, [IORING_OP_SETXATTR] = { .name = "SETXATTR", .cleanup = io_xattr_cleanup, }, [IORING_OP_FGETXATTR] = { .name = "FGETXATTR", .cleanup = io_xattr_cleanup, }, [IORING_OP_GETXATTR] = { .name = "GETXATTR", .cleanup = io_xattr_cleanup, }, [IORING_OP_SOCKET] = { .name = "SOCKET", }, [IORING_OP_URING_CMD] = { .name = "URING_CMD", .cleanup = io_uring_cmd_cleanup, }, [IORING_OP_SEND_ZC] = { .name = "SEND_ZC", #if defined(CONFIG_NET) .cleanup = io_send_zc_cleanup, .fail = io_sendrecv_fail, #endif }, [IORING_OP_SENDMSG_ZC] = { .name = "SENDMSG_ZC", #if defined(CONFIG_NET) .cleanup = io_send_zc_cleanup, .fail = io_sendrecv_fail, #endif }, [IORING_OP_READ_MULTISHOT] = { .name = "READ_MULTISHOT", .cleanup = io_readv_writev_cleanup, }, [IORING_OP_WAITID] = { .name = "WAITID", }, [IORING_OP_FUTEX_WAIT] = { .name = "FUTEX_WAIT", }, [IORING_OP_FUTEX_WAKE] = { .name = "FUTEX_WAKE", }, [IORING_OP_FUTEX_WAITV] = { .name = "FUTEX_WAITV", }, [IORING_OP_FIXED_FD_INSTALL] = { .name = "FIXED_FD_INSTALL", }, [IORING_OP_FTRUNCATE] = { .name = "FTRUNCATE", }, [IORING_OP_BIND] = { .name = "BIND", }, [IORING_OP_LISTEN] = { .name = "LISTEN", }, [IORING_OP_RECV_ZC] = { .name = "RECV_ZC", }, [IORING_OP_EPOLL_WAIT] = { .name = "EPOLL_WAIT", }, [IORING_OP_READV_FIXED] = { .name = "READV_FIXED", .cleanup = io_readv_writev_cleanup, .fail = io_rw_fail, }, [IORING_OP_WRITEV_FIXED] = { .name = "WRITEV_FIXED", .cleanup = io_readv_writev_cleanup, .fail = io_rw_fail, }, }; const char *io_uring_get_opcode(u8 opcode) { if (opcode < IORING_OP_LAST) return io_cold_defs[opcode].name; return "INVALID"; } bool io_uring_op_supported(u8 opcode) { if (opcode < IORING_OP_LAST && io_issue_defs[opcode].prep != io_eopnotsupp_prep) return true; return false; } void __init io_uring_optable_init(void) { int i; BUILD_BUG_ON(ARRAY_SIZE(io_cold_defs) != IORING_OP_LAST); BUILD_BUG_ON(ARRAY_SIZE(io_issue_defs) != IORING_OP_LAST); for (i = 0; i < ARRAY_SIZE(io_issue_defs); i++) { BUG_ON(!io_issue_defs[i].prep); if (io_issue_defs[i].prep != io_eopnotsupp_prep) BUG_ON(!io_issue_defs[i].issue); WARN_ON_ONCE(!io_cold_defs[i].name); } } |
| 262 14 266 29 262 261 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2008 Oracle. All rights reserved. */ #ifndef BTRFS_DELAYED_REF_H #define BTRFS_DELAYED_REF_H #include <linux/types.h> #include <linux/refcount.h> #include <linux/list.h> #include <linux/rbtree.h> #include <linux/mutex.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <uapi/linux/btrfs_tree.h> #include "fs.h" #include "messages.h" struct btrfs_trans_handle; struct btrfs_fs_info; /* these are the possible values of struct btrfs_delayed_ref_node->action */ enum btrfs_delayed_ref_action { /* Add one backref to the tree */ BTRFS_ADD_DELAYED_REF = 1, /* Delete one backref from the tree */ BTRFS_DROP_DELAYED_REF, /* Record a full extent allocation */ BTRFS_ADD_DELAYED_EXTENT, /* Not changing ref count on head ref */ BTRFS_UPDATE_DELAYED_HEAD, } __packed; struct btrfs_data_ref { /* For EXTENT_DATA_REF */ /* Inode which refers to this data extent */ u64 objectid; /* * file_offset - extent_offset * * file_offset is the key.offset of the EXTENT_DATA key. * extent_offset is btrfs_file_extent_offset() of the EXTENT_DATA data. */ u64 offset; }; struct btrfs_tree_ref { /* * Level of this tree block. * * Shared for skinny (TREE_BLOCK_REF) and normal tree ref. */ int level; /* For non-skinny metadata, no special member needed */ }; struct btrfs_delayed_ref_node { struct rb_node ref_node; /* * If action is BTRFS_ADD_DELAYED_REF, also link this node to * ref_head->ref_add_list, then we do not need to iterate the * refs rbtree in the corresponding delayed ref head * (struct btrfs_delayed_ref_head::ref_tree). */ struct list_head add_list; /* the starting bytenr of the extent */ u64 bytenr; /* the size of the extent */ u64 num_bytes; /* seq number to keep track of insertion order */ u64 seq; /* The ref_root for this ref */ u64 ref_root; /* * The parent for this ref, if this isn't set the ref_root is the * reference owner. */ u64 parent; /* ref count on this data structure */ refcount_t refs; /* * how many refs is this entry adding or deleting. For * head refs, this may be a negative number because it is keeping * track of the total mods done to the reference count. * For individual refs, this will always be a positive number * * It may be more than one, since it is possible for a single * parent to have more than one ref on an extent */ int ref_mod; unsigned int action:8; unsigned int type:8; union { struct btrfs_tree_ref tree_ref; struct btrfs_data_ref data_ref; }; }; struct btrfs_delayed_extent_op { struct btrfs_disk_key key; bool update_key; bool update_flags; u64 flags_to_set; }; /* * the head refs are used to hold a lock on a given extent, which allows us * to make sure that only one process is running the delayed refs * at a time for a single extent. They also store the sum of all the * reference count modifications we've queued up. */ struct btrfs_delayed_ref_head { u64 bytenr; u64 num_bytes; /* * the mutex is held while running the refs, and it is also * held when checking the sum of reference modifications. */ struct mutex mutex; refcount_t refs; /* Protects 'ref_tree' and 'ref_add_list'. */ spinlock_t lock; struct rb_root_cached ref_tree; /* accumulate add BTRFS_ADD_DELAYED_REF nodes to this ref_add_list. */ struct list_head ref_add_list; struct btrfs_delayed_extent_op *extent_op; /* * This is used to track the final ref_mod from all the refs associated * with this head ref, this is not adjusted as delayed refs are run, * this is meant to track if we need to do the csum accounting or not. */ int total_ref_mod; /* * This is the current outstanding mod references for this bytenr. This * is used with lookup_extent_info to get an accurate reference count * for a bytenr, so it is adjusted as delayed refs are run so that any * on disk reference count + ref_mod is accurate. */ int ref_mod; /* * The root that triggered the allocation when must_insert_reserved is * set to true. */ u64 owning_root; /* * Track reserved bytes when setting must_insert_reserved. On success * or cleanup, we will need to free the reservation. */ u64 reserved_bytes; /* Tree block level, for metadata only. */ u8 level; /* * when a new extent is allocated, it is just reserved in memory * The actual extent isn't inserted into the extent allocation tree * until the delayed ref is processed. must_insert_reserved is * used to flag a delayed ref so the accounting can be updated * when a full insert is done. * * It is possible the extent will be freed before it is ever * inserted into the extent allocation tree. In this case * we need to update the in ram accounting to properly reflect * the free has happened. */ bool must_insert_reserved; bool is_data; bool is_system; bool processing; /* * Indicate if it's currently in the data structure that tracks head * refs (struct btrfs_delayed_ref_root::head_refs). */ bool tracked; }; enum btrfs_delayed_ref_flags { /* Indicate that we are flushing delayed refs for the commit */ BTRFS_DELAYED_REFS_FLUSHING, }; struct btrfs_delayed_ref_root { /* * Track head references. * The keys correspond to the logical address of the extent ("bytenr") * right shifted by fs_info->sectorsize_bits. This is both to get a more * dense index space (optimizes xarray structure) and because indexes in * xarrays are of "unsigned long" type, meaning they are 32 bits wide on * 32 bits platforms, limiting the extent range to 4G which is too low * and makes it unusable (truncated index values) on 32 bits platforms. * Protected by the spinlock 'lock' defined below. */ struct xarray head_refs; /* * Track dirty extent records. * The keys correspond to the logical address of the extent ("bytenr") * right shifted by fs_info->sectorsize_bits, for same reasons as above. */ struct xarray dirty_extents; /* * Protects the xarray head_refs, its entries and the following fields: * num_heads, num_heads_ready, pending_csums and run_delayed_start. */ spinlock_t lock; /* Total number of head refs, protected by the spinlock 'lock'. */ unsigned long num_heads; /* * Total number of head refs ready for processing, protected by the * spinlock 'lock'. */ unsigned long num_heads_ready; /* * Track space reserved for deleting csums of data extents. * Protected by the spinlock 'lock'. */ u64 pending_csums; unsigned long flags; /* * Track from which bytenr to start searching ref heads. * Protected by the spinlock 'lock'. */ u64 run_delayed_start; /* * To make qgroup to skip given root. * This is for snapshot, as btrfs_qgroup_inherit() will manually * modify counters for snapshot and its source, so we should skip * the snapshot in new_root/old_roots or it will get calculated twice */ u64 qgroup_to_skip; }; enum btrfs_ref_type { BTRFS_REF_NOT_SET, BTRFS_REF_DATA, BTRFS_REF_METADATA, BTRFS_REF_LAST, } __packed; struct btrfs_ref { enum btrfs_ref_type type; enum btrfs_delayed_ref_action action; /* * Whether this extent should go through qgroup record. * * Normally false, but for certain cases like delayed subtree scan, * setting this flag can hugely reduce qgroup overhead. */ bool skip_qgroup; #ifdef CONFIG_BTRFS_FS_REF_VERIFY /* Through which root is this modification. */ u64 real_root; #endif u64 bytenr; u64 num_bytes; u64 owning_root; /* * The root that owns the reference for this reference, this will be set * or ->parent will be set, depending on what type of reference this is. */ u64 ref_root; /* Bytenr of the parent tree block */ u64 parent; union { struct btrfs_data_ref data_ref; struct btrfs_tree_ref tree_ref; }; }; extern struct kmem_cache *btrfs_delayed_ref_head_cachep; extern struct kmem_cache *btrfs_delayed_ref_node_cachep; extern struct kmem_cache *btrfs_delayed_extent_op_cachep; int __init btrfs_delayed_ref_init(void); void __cold btrfs_delayed_ref_exit(void); static inline u64 btrfs_calc_delayed_ref_bytes(const struct btrfs_fs_info *fs_info, int num_delayed_refs) { u64 num_bytes; num_bytes = btrfs_calc_insert_metadata_size(fs_info, num_delayed_refs); /* * We have to check the mount option here because we could be enabling * the free space tree for the first time and don't have the compat_ro * option set yet. * * We need extra reservations if we have the free space tree because * we'll have to modify that tree as well. */ if (btrfs_test_opt(fs_info, FREE_SPACE_TREE)) num_bytes *= 2; return num_bytes; } static inline u64 btrfs_calc_delayed_ref_csum_bytes(const struct btrfs_fs_info *fs_info, int num_csum_items) { /* * Deleting csum items does not result in new nodes/leaves and does not * require changing the free space tree, only the csum tree, so this is * all we need. */ return btrfs_calc_metadata_size(fs_info, num_csum_items); } void btrfs_init_tree_ref(struct btrfs_ref *generic_ref, int level, u64 mod_root, bool skip_qgroup); void btrfs_init_data_ref(struct btrfs_ref *generic_ref, u64 ino, u64 offset, u64 mod_root, bool skip_qgroup); static inline struct btrfs_delayed_extent_op * btrfs_alloc_delayed_extent_op(void) { return kmem_cache_alloc(btrfs_delayed_extent_op_cachep, GFP_NOFS); } static inline void btrfs_free_delayed_extent_op(struct btrfs_delayed_extent_op *op) { if (op) kmem_cache_free(btrfs_delayed_extent_op_cachep, op); } void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref); static inline u64 btrfs_ref_head_to_space_flags( struct btrfs_delayed_ref_head *head_ref) { if (head_ref->is_data) return BTRFS_BLOCK_GROUP_DATA; else if (head_ref->is_system) return BTRFS_BLOCK_GROUP_SYSTEM; return BTRFS_BLOCK_GROUP_METADATA; } static inline void btrfs_put_delayed_ref_head(struct btrfs_delayed_ref_head *head) { if (refcount_dec_and_test(&head->refs)) kmem_cache_free(btrfs_delayed_ref_head_cachep, head); } int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, struct btrfs_ref *generic_ref, struct btrfs_delayed_extent_op *extent_op); int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, struct btrfs_ref *generic_ref, u64 reserved); int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u8 level, struct btrfs_delayed_extent_op *extent_op); void btrfs_merge_delayed_refs(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_root *delayed_refs, struct btrfs_delayed_ref_head *head); struct btrfs_delayed_ref_head * btrfs_find_delayed_ref_head(const struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_root *delayed_refs, u64 bytenr); static inline void btrfs_delayed_ref_unlock(struct btrfs_delayed_ref_head *head) { mutex_unlock(&head->mutex); } void btrfs_delete_ref_head(const struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_root *delayed_refs, struct btrfs_delayed_ref_head *head); struct btrfs_delayed_ref_head *btrfs_select_ref_head( const struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_root *delayed_refs); void btrfs_unselect_ref_head(struct btrfs_delayed_ref_root *delayed_refs, struct btrfs_delayed_ref_head *head); struct btrfs_delayed_ref_node *btrfs_select_delayed_ref(struct btrfs_delayed_ref_head *head); int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info, u64 seq); void btrfs_delayed_refs_rsv_release(struct btrfs_fs_info *fs_info, int nr_refs, int nr_csums); void btrfs_update_delayed_refs_rsv(struct btrfs_trans_handle *trans); void btrfs_inc_delayed_refs_rsv_bg_inserts(struct btrfs_fs_info *fs_info); void btrfs_dec_delayed_refs_rsv_bg_inserts(struct btrfs_fs_info *fs_info); void btrfs_inc_delayed_refs_rsv_bg_updates(struct btrfs_fs_info *fs_info); void btrfs_dec_delayed_refs_rsv_bg_updates(struct btrfs_fs_info *fs_info); int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info, enum btrfs_reserve_flush_enum flush); bool btrfs_check_space_for_delayed_refs(struct btrfs_fs_info *fs_info); bool btrfs_find_delayed_tree_ref(struct btrfs_delayed_ref_head *head, u64 root, u64 parent); void btrfs_destroy_delayed_refs(struct btrfs_transaction *trans); static inline u64 btrfs_delayed_ref_owner(struct btrfs_delayed_ref_node *node) { if (node->type == BTRFS_EXTENT_DATA_REF_KEY || node->type == BTRFS_SHARED_DATA_REF_KEY) return node->data_ref.objectid; return node->tree_ref.level; } static inline u64 btrfs_delayed_ref_offset(struct btrfs_delayed_ref_node *node) { if (node->type == BTRFS_EXTENT_DATA_REF_KEY || node->type == BTRFS_SHARED_DATA_REF_KEY) return node->data_ref.offset; return 0; } static inline u8 btrfs_ref_type(struct btrfs_ref *ref) { ASSERT(ref->type == BTRFS_REF_DATA || ref->type == BTRFS_REF_METADATA); if (ref->type == BTRFS_REF_DATA) { if (ref->parent) return BTRFS_SHARED_DATA_REF_KEY; else return BTRFS_EXTENT_DATA_REF_KEY; } else { if (ref->parent) return BTRFS_SHARED_BLOCK_REF_KEY; else return BTRFS_TREE_BLOCK_REF_KEY; } return 0; } #endif |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 11 5 3 3 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 1 1 1 2 2 1 1 1 10 10 10 9 10 2 2 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 2 2 2 3 4 4 2 2 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Timers abstract layer * Copyright (c) by Jaroslav Kysela <perex@perex.cz> */ #include <linux/delay.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/time.h> #include <linux/mutex.h> #include <linux/device.h> #include <linux/module.h> #include <linux/string.h> #include <linux/sched/signal.h> #include <linux/anon_inodes.h> #include <linux/idr.h> #include <sound/core.h> #include <sound/timer.h> #include <sound/control.h> #include <sound/info.h> #include <sound/minors.h> #include <sound/initval.h> #include <linux/kmod.h> /* internal flags */ #define SNDRV_TIMER_IFLG_PAUSED 0x00010000 #define SNDRV_TIMER_IFLG_DEAD 0x00020000 #if IS_ENABLED(CONFIG_SND_HRTIMER) #define DEFAULT_TIMER_LIMIT 4 #else #define DEFAULT_TIMER_LIMIT 1 #endif static int timer_limit = DEFAULT_TIMER_LIMIT; static int timer_tstamp_monotonic = 1; MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>, Takashi Iwai <tiwai@suse.de>"); MODULE_DESCRIPTION("ALSA timer interface"); MODULE_LICENSE("GPL"); module_param(timer_limit, int, 0444); MODULE_PARM_DESC(timer_limit, "Maximum global timers in system."); module_param(timer_tstamp_monotonic, int, 0444); MODULE_PARM_DESC(timer_tstamp_monotonic, "Use posix monotonic clock source for timestamps (default)."); MODULE_ALIAS_CHARDEV(CONFIG_SND_MAJOR, SNDRV_MINOR_TIMER); MODULE_ALIAS("devname:snd/timer"); enum timer_tread_format { TREAD_FORMAT_NONE = 0, TREAD_FORMAT_TIME64, TREAD_FORMAT_TIME32, }; struct snd_timer_tread32 { int event; s32 tstamp_sec; s32 tstamp_nsec; unsigned int val; }; struct snd_timer_tread64 { int event; u8 pad1[4]; s64 tstamp_sec; s64 tstamp_nsec; unsigned int val; u8 pad2[4]; }; struct snd_timer_user { struct snd_timer_instance *timeri; int tread; /* enhanced read with timestamps and events */ unsigned long ticks; unsigned long overrun; int qhead; int qtail; int qused; int queue_size; bool disconnected; struct snd_timer_read *queue; struct snd_timer_tread64 *tqueue; spinlock_t qlock; unsigned long last_resolution; unsigned int filter; struct timespec64 tstamp; /* trigger tstamp */ wait_queue_head_t qchange_sleep; struct snd_fasync *fasync; struct mutex ioctl_lock; }; struct snd_timer_status32 { s32 tstamp_sec; /* Timestamp - last update */ s32 tstamp_nsec; unsigned int resolution; /* current period resolution in ns */ unsigned int lost; /* counter of master tick lost */ unsigned int overrun; /* count of read queue overruns */ unsigned int queue; /* used queue size */ unsigned char reserved[64]; /* reserved */ }; #define SNDRV_TIMER_IOCTL_STATUS32 _IOR('T', 0x14, struct snd_timer_status32) struct snd_timer_status64 { s64 tstamp_sec; /* Timestamp - last update */ s64 tstamp_nsec; unsigned int resolution; /* current period resolution in ns */ unsigned int lost; /* counter of master tick lost */ unsigned int overrun; /* count of read queue overruns */ unsigned int queue; /* used queue size */ unsigned char reserved[64]; /* reserved */ }; #ifdef CONFIG_SND_UTIMER #define SNDRV_UTIMERS_MAX_COUNT 128 /* Internal data structure for keeping the state of the userspace-driven timer */ struct snd_utimer { char *name; struct snd_timer *timer; unsigned int id; }; #endif #define SNDRV_TIMER_IOCTL_STATUS64 _IOR('T', 0x14, struct snd_timer_status64) /* list of timers */ static LIST_HEAD(snd_timer_list); /* list of slave instances */ static LIST_HEAD(snd_timer_slave_list); /* lock for slave active lists */ static DEFINE_SPINLOCK(slave_active_lock); #define MAX_SLAVE_INSTANCES 1000 static int num_slaves; static DEFINE_MUTEX(register_mutex); static int snd_timer_free(struct snd_timer *timer); static int snd_timer_dev_free(struct snd_device *device); static int snd_timer_dev_register(struct snd_device *device); static int snd_timer_dev_disconnect(struct snd_device *device); static void snd_timer_reschedule(struct snd_timer * timer, unsigned long ticks_left); /* * create a timer instance with the given owner string. */ struct snd_timer_instance *snd_timer_instance_new(const char *owner) { struct snd_timer_instance *timeri; timeri = kzalloc(sizeof(*timeri), GFP_KERNEL); if (timeri == NULL) return NULL; timeri->owner = kstrdup(owner, GFP_KERNEL); if (! timeri->owner) { kfree(timeri); return NULL; } INIT_LIST_HEAD(&timeri->open_list); INIT_LIST_HEAD(&timeri->active_list); INIT_LIST_HEAD(&timeri->ack_list); INIT_LIST_HEAD(&timeri->slave_list_head); INIT_LIST_HEAD(&timeri->slave_active_head); return timeri; } EXPORT_SYMBOL(snd_timer_instance_new); void snd_timer_instance_free(struct snd_timer_instance *timeri) { if (timeri) { if (timeri->private_free) timeri->private_free(timeri); kfree(timeri->owner); kfree(timeri); } } EXPORT_SYMBOL(snd_timer_instance_free); /* * find a timer instance from the given timer id */ static struct snd_timer *snd_timer_find(struct snd_timer_id *tid) { struct snd_timer *timer; list_for_each_entry(timer, &snd_timer_list, device_list) { if (timer->tmr_class != tid->dev_class) continue; if ((timer->tmr_class == SNDRV_TIMER_CLASS_CARD || timer->tmr_class == SNDRV_TIMER_CLASS_PCM) && (timer->card == NULL || timer->card->number != tid->card)) continue; if (timer->tmr_device != tid->device) continue; if (timer->tmr_subdevice != tid->subdevice) continue; return timer; } return NULL; } #ifdef CONFIG_MODULES static void snd_timer_request(struct snd_timer_id *tid) { switch (tid->dev_class) { case SNDRV_TIMER_CLASS_GLOBAL: if (tid->device < timer_limit) request_module("snd-timer-%i", tid->device); break; case SNDRV_TIMER_CLASS_CARD: case SNDRV_TIMER_CLASS_PCM: if (tid->card < snd_ecards_limit) request_module("snd-card-%i", tid->card); break; default: break; } } #endif /* move the slave if it belongs to the master; return 1 if match */ static int check_matching_master_slave(struct snd_timer_instance *master, struct snd_timer_instance *slave) { if (slave->slave_class != master->slave_class || slave->slave_id != master->slave_id) return 0; if (master->timer->num_instances >= master->timer->max_instances) return -EBUSY; list_move_tail(&slave->open_list, &master->slave_list_head); master->timer->num_instances++; guard(spinlock_irq)(&slave_active_lock); guard(spinlock)(&master->timer->lock); slave->master = master; slave->timer = master->timer; if (slave->flags & SNDRV_TIMER_IFLG_RUNNING) list_add_tail(&slave->active_list, &master->slave_active_head); return 1; } /* * look for a master instance matching with the slave id of the given slave. * when found, relink the open_link of the slave. * * call this with register_mutex down. */ static int snd_timer_check_slave(struct snd_timer_instance *slave) { struct snd_timer *timer; struct snd_timer_instance *master; int err = 0; /* FIXME: it's really dumb to look up all entries.. */ list_for_each_entry(timer, &snd_timer_list, device_list) { list_for_each_entry(master, &timer->open_list_head, open_list) { err = check_matching_master_slave(master, slave); if (err != 0) /* match found or error */ goto out; } } out: return err < 0 ? err : 0; } /* * look for slave instances matching with the slave id of the given master. * when found, relink the open_link of slaves. * * call this with register_mutex down. */ static int snd_timer_check_master(struct snd_timer_instance *master) { struct snd_timer_instance *slave, *tmp; int err = 0; /* check all pending slaves */ list_for_each_entry_safe(slave, tmp, &snd_timer_slave_list, open_list) { err = check_matching_master_slave(master, slave); if (err < 0) break; } return err < 0 ? err : 0; } static void snd_timer_close_locked(struct snd_timer_instance *timeri, struct device **card_devp_to_put); /* * open a timer instance * when opening a master, the slave id must be here given. */ int snd_timer_open(struct snd_timer_instance *timeri, struct snd_timer_id *tid, unsigned int slave_id) { struct snd_timer *timer; struct device *card_dev_to_put = NULL; int err; mutex_lock(®ister_mutex); if (tid->dev_class == SNDRV_TIMER_CLASS_SLAVE) { /* open a slave instance */ if (tid->dev_sclass <= SNDRV_TIMER_SCLASS_NONE || tid->dev_sclass > SNDRV_TIMER_SCLASS_OSS_SEQUENCER) { pr_debug("ALSA: timer: invalid slave class %i\n", tid->dev_sclass); err = -EINVAL; goto unlock; } if (num_slaves >= MAX_SLAVE_INSTANCES) { err = -EBUSY; goto unlock; } timeri->slave_class = tid->dev_sclass; timeri->slave_id = tid->device; timeri->flags |= SNDRV_TIMER_IFLG_SLAVE; list_add_tail(&timeri->open_list, &snd_timer_slave_list); num_slaves++; err = snd_timer_check_slave(timeri); goto list_added; } /* open a master instance */ timer = snd_timer_find(tid); #ifdef CONFIG_MODULES if (!timer) { mutex_unlock(®ister_mutex); snd_timer_request(tid); mutex_lock(®ister_mutex); timer = snd_timer_find(tid); } #endif if (!timer) { err = -ENODEV; goto unlock; } if (!list_empty(&timer->open_list_head)) { struct snd_timer_instance *t = list_entry(timer->open_list_head.next, struct snd_timer_instance, open_list); if (t->flags & SNDRV_TIMER_IFLG_EXCLUSIVE) { err = -EBUSY; goto unlock; } } if (timer->num_instances >= timer->max_instances) { err = -EBUSY; goto unlock; } if (!try_module_get(timer->module)) { err = -EBUSY; goto unlock; } /* take a card refcount for safe disconnection */ if (timer->card) { get_device(&timer->card->card_dev); card_dev_to_put = &timer->card->card_dev; } if (list_empty(&timer->open_list_head) && timer->hw.open) { err = timer->hw.open(timer); if (err) { module_put(timer->module); goto unlock; } } timeri->timer = timer; timeri->slave_class = tid->dev_sclass; timeri->slave_id = slave_id; list_add_tail(&timeri->open_list, &timer->open_list_head); timer->num_instances++; err = snd_timer_check_master(timeri); list_added: if (err < 0) snd_timer_close_locked(timeri, &card_dev_to_put); unlock: mutex_unlock(®ister_mutex); /* put_device() is called after unlock for avoiding deadlock */ if (err < 0 && card_dev_to_put) put_device(card_dev_to_put); return err; } EXPORT_SYMBOL(snd_timer_open); /* remove slave links, called from snd_timer_close_locked() below */ static void remove_slave_links(struct snd_timer_instance *timeri, struct snd_timer *timer) { struct snd_timer_instance *slave, *tmp; guard(spinlock_irq)(&slave_active_lock); guard(spinlock)(&timer->lock); timeri->timer = NULL; list_for_each_entry_safe(slave, tmp, &timeri->slave_list_head, open_list) { list_move_tail(&slave->open_list, &snd_timer_slave_list); timer->num_instances--; slave->master = NULL; slave->timer = NULL; list_del_init(&slave->ack_list); list_del_init(&slave->active_list); } } /* * close a timer instance * call this with register_mutex down. */ static void snd_timer_close_locked(struct snd_timer_instance *timeri, struct device **card_devp_to_put) { struct snd_timer *timer = timeri->timer; if (timer) { guard(spinlock_irq)(&timer->lock); timeri->flags |= SNDRV_TIMER_IFLG_DEAD; } if (!list_empty(&timeri->open_list)) { list_del_init(&timeri->open_list); if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) num_slaves--; } /* force to stop the timer */ snd_timer_stop(timeri); if (timer) { timer->num_instances--; /* wait, until the active callback is finished */ spin_lock_irq(&timer->lock); while (timeri->flags & SNDRV_TIMER_IFLG_CALLBACK) { spin_unlock_irq(&timer->lock); udelay(10); spin_lock_irq(&timer->lock); } spin_unlock_irq(&timer->lock); remove_slave_links(timeri, timer); /* slave doesn't need to release timer resources below */ if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) timer = NULL; } if (timer) { if (list_empty(&timer->open_list_head) && timer->hw.close) timer->hw.close(timer); /* release a card refcount for safe disconnection */ if (timer->card) *card_devp_to_put = &timer->card->card_dev; module_put(timer->module); } } /* * close a timer instance */ void snd_timer_close(struct snd_timer_instance *timeri) { struct device *card_dev_to_put = NULL; if (snd_BUG_ON(!timeri)) return; scoped_guard(mutex, ®ister_mutex) snd_timer_close_locked(timeri, &card_dev_to_put); /* put_device() is called after unlock for avoiding deadlock */ if (card_dev_to_put) put_device(card_dev_to_put); } EXPORT_SYMBOL(snd_timer_close); static unsigned long snd_timer_hw_resolution(struct snd_timer *timer) { if (timer->hw.c_resolution) return timer->hw.c_resolution(timer); else return timer->hw.resolution; } unsigned long snd_timer_resolution(struct snd_timer_instance *timeri) { struct snd_timer * timer; unsigned long ret = 0; if (timeri == NULL) return 0; timer = timeri->timer; if (timer) { guard(spinlock_irqsave)(&timer->lock); ret = snd_timer_hw_resolution(timer); } return ret; } EXPORT_SYMBOL(snd_timer_resolution); static void snd_timer_notify1(struct snd_timer_instance *ti, int event) { struct snd_timer *timer = ti->timer; unsigned long resolution = 0; struct snd_timer_instance *ts; struct timespec64 tstamp; if (timer_tstamp_monotonic) ktime_get_ts64(&tstamp); else ktime_get_real_ts64(&tstamp); if (snd_BUG_ON(event < SNDRV_TIMER_EVENT_START || event > SNDRV_TIMER_EVENT_PAUSE)) return; if (timer && (event == SNDRV_TIMER_EVENT_START || event == SNDRV_TIMER_EVENT_CONTINUE)) resolution = snd_timer_hw_resolution(timer); if (ti->ccallback) ti->ccallback(ti, event, &tstamp, resolution); if (ti->flags & SNDRV_TIMER_IFLG_SLAVE) return; if (timer == NULL) return; if (timer->hw.flags & SNDRV_TIMER_HW_SLAVE) return; event += 10; /* convert to SNDRV_TIMER_EVENT_MXXX */ list_for_each_entry(ts, &ti->slave_active_head, active_list) if (ts->ccallback) ts->ccallback(ts, event, &tstamp, resolution); } /* start/continue a master timer */ static int snd_timer_start1(struct snd_timer_instance *timeri, bool start, unsigned long ticks) { struct snd_timer *timer; int result; timer = timeri->timer; if (!timer) return -EINVAL; guard(spinlock_irqsave)(&timer->lock); if (timeri->flags & SNDRV_TIMER_IFLG_DEAD) return -EINVAL; if (timer->card && timer->card->shutdown) return -ENODEV; if (timeri->flags & (SNDRV_TIMER_IFLG_RUNNING | SNDRV_TIMER_IFLG_START)) return -EBUSY; /* check the actual time for the start tick; * bail out as error if it's way too low (< 100us) */ if (start && !(timer->hw.flags & SNDRV_TIMER_HW_SLAVE)) { if ((u64)snd_timer_hw_resolution(timer) * ticks < 100000) return -EINVAL; } if (start) timeri->ticks = timeri->cticks = ticks; else if (!timeri->cticks) timeri->cticks = 1; timeri->pticks = 0; list_move_tail(&timeri->active_list, &timer->active_list_head); if (timer->running) { if (timer->hw.flags & SNDRV_TIMER_HW_SLAVE) goto __start_now; timer->flags |= SNDRV_TIMER_FLG_RESCHED; timeri->flags |= SNDRV_TIMER_IFLG_START; result = 1; /* delayed start */ } else { if (start) timer->sticks = ticks; timer->hw.start(timer); __start_now: timer->running++; timeri->flags |= SNDRV_TIMER_IFLG_RUNNING; result = 0; } snd_timer_notify1(timeri, start ? SNDRV_TIMER_EVENT_START : SNDRV_TIMER_EVENT_CONTINUE); return result; } /* start/continue a slave timer */ static int snd_timer_start_slave(struct snd_timer_instance *timeri, bool start) { guard(spinlock_irqsave)(&slave_active_lock); if (timeri->flags & SNDRV_TIMER_IFLG_DEAD) return -EINVAL; if (timeri->flags & SNDRV_TIMER_IFLG_RUNNING) return -EBUSY; timeri->flags |= SNDRV_TIMER_IFLG_RUNNING; if (timeri->master && timeri->timer) { guard(spinlock)(&timeri->timer->lock); list_add_tail(&timeri->active_list, &timeri->master->slave_active_head); snd_timer_notify1(timeri, start ? SNDRV_TIMER_EVENT_START : SNDRV_TIMER_EVENT_CONTINUE); } return 1; /* delayed start */ } /* stop/pause a master timer */ static int snd_timer_stop1(struct snd_timer_instance *timeri, bool stop) { struct snd_timer *timer; timer = timeri->timer; if (!timer) return -EINVAL; guard(spinlock_irqsave)(&timer->lock); list_del_init(&timeri->ack_list); list_del_init(&timeri->active_list); if (!(timeri->flags & (SNDRV_TIMER_IFLG_RUNNING | SNDRV_TIMER_IFLG_START))) return -EBUSY; if (timer->card && timer->card->shutdown) return 0; if (stop) { timeri->cticks = timeri->ticks; timeri->pticks = 0; } if ((timeri->flags & SNDRV_TIMER_IFLG_RUNNING) && !(--timer->running)) { timer->hw.stop(timer); if (timer->flags & SNDRV_TIMER_FLG_RESCHED) { timer->flags &= ~SNDRV_TIMER_FLG_RESCHED; snd_timer_reschedule(timer, 0); if (timer->flags & SNDRV_TIMER_FLG_CHANGE) { timer->flags &= ~SNDRV_TIMER_FLG_CHANGE; timer->hw.start(timer); } } } timeri->flags &= ~(SNDRV_TIMER_IFLG_RUNNING | SNDRV_TIMER_IFLG_START); if (stop) timeri->flags &= ~SNDRV_TIMER_IFLG_PAUSED; else timeri->flags |= SNDRV_TIMER_IFLG_PAUSED; snd_timer_notify1(timeri, stop ? SNDRV_TIMER_EVENT_STOP : SNDRV_TIMER_EVENT_PAUSE); return 0; } /* stop/pause a slave timer */ static int snd_timer_stop_slave(struct snd_timer_instance *timeri, bool stop) { bool running; guard(spinlock_irqsave)(&slave_active_lock); running = timeri->flags & SNDRV_TIMER_IFLG_RUNNING; timeri->flags &= ~SNDRV_TIMER_IFLG_RUNNING; if (timeri->timer) { guard(spinlock)(&timeri->timer->lock); list_del_init(&timeri->ack_list); list_del_init(&timeri->active_list); if (running) snd_timer_notify1(timeri, stop ? SNDRV_TIMER_EVENT_STOP : SNDRV_TIMER_EVENT_PAUSE); } return running ? 0 : -EBUSY; } /* * start the timer instance */ int snd_timer_start(struct snd_timer_instance *timeri, unsigned int ticks) { if (timeri == NULL || ticks < 1) return -EINVAL; if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) return snd_timer_start_slave(timeri, true); else return snd_timer_start1(timeri, true, ticks); } EXPORT_SYMBOL(snd_timer_start); /* * stop the timer instance. * * do not call this from the timer callback! */ int snd_timer_stop(struct snd_timer_instance *timeri) { if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) return snd_timer_stop_slave(timeri, true); else return snd_timer_stop1(timeri, true); } EXPORT_SYMBOL(snd_timer_stop); /* * start again.. the tick is kept. */ int snd_timer_continue(struct snd_timer_instance *timeri) { /* timer can continue only after pause */ if (!(timeri->flags & SNDRV_TIMER_IFLG_PAUSED)) return -EINVAL; if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) return snd_timer_start_slave(timeri, false); else return snd_timer_start1(timeri, false, 0); } EXPORT_SYMBOL(snd_timer_continue); /* * pause.. remember the ticks left */ int snd_timer_pause(struct snd_timer_instance * timeri) { if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) return snd_timer_stop_slave(timeri, false); else return snd_timer_stop1(timeri, false); } EXPORT_SYMBOL(snd_timer_pause); /* * reschedule the timer * * start pending instances and check the scheduling ticks. * when the scheduling ticks is changed set CHANGE flag to reprogram the timer. */ static void snd_timer_reschedule(struct snd_timer * timer, unsigned long ticks_left) { struct snd_timer_instance *ti; unsigned long ticks = ~0UL; list_for_each_entry(ti, &timer->active_list_head, active_list) { if (ti->flags & SNDRV_TIMER_IFLG_START) { ti->flags &= ~SNDRV_TIMER_IFLG_START; ti->flags |= SNDRV_TIMER_IFLG_RUNNING; timer->running++; } if (ti->flags & SNDRV_TIMER_IFLG_RUNNING) { if (ticks > ti->cticks) ticks = ti->cticks; } } if (ticks == ~0UL) { timer->flags &= ~SNDRV_TIMER_FLG_RESCHED; return; } if (ticks > timer->hw.ticks) ticks = timer->hw.ticks; if (ticks_left != ticks) timer->flags |= SNDRV_TIMER_FLG_CHANGE; timer->sticks = ticks; } /* call callbacks in timer ack list */ static void snd_timer_process_callbacks(struct snd_timer *timer, struct list_head *head) { struct snd_timer_instance *ti; unsigned long resolution, ticks; while (!list_empty(head)) { ti = list_first_entry(head, struct snd_timer_instance, ack_list); /* remove from ack_list and make empty */ list_del_init(&ti->ack_list); if (!(ti->flags & SNDRV_TIMER_IFLG_DEAD)) { ticks = ti->pticks; ti->pticks = 0; resolution = ti->resolution; ti->flags |= SNDRV_TIMER_IFLG_CALLBACK; spin_unlock(&timer->lock); if (ti->callback) ti->callback(ti, resolution, ticks); spin_lock(&timer->lock); ti->flags &= ~SNDRV_TIMER_IFLG_CALLBACK; } } } /* clear pending instances from ack list */ static void snd_timer_clear_callbacks(struct snd_timer *timer, struct list_head *head) { guard(spinlock_irqsave)(&timer->lock); while (!list_empty(head)) list_del_init(head->next); } /* * timer work * */ static void snd_timer_work(struct work_struct *work) { struct snd_timer *timer = container_of(work, struct snd_timer, task_work); if (timer->card && timer->card->shutdown) { snd_timer_clear_callbacks(timer, &timer->sack_list_head); return; } guard(spinlock_irqsave)(&timer->lock); snd_timer_process_callbacks(timer, &timer->sack_list_head); } /* * timer interrupt * * ticks_left is usually equal to timer->sticks. * */ void snd_timer_interrupt(struct snd_timer * timer, unsigned long ticks_left) { struct snd_timer_instance *ti, *ts, *tmp; unsigned long resolution; struct list_head *ack_list_head; if (timer == NULL) return; if (timer->card && timer->card->shutdown) { snd_timer_clear_callbacks(timer, &timer->ack_list_head); return; } guard(spinlock_irqsave)(&timer->lock); /* remember the current resolution */ resolution = snd_timer_hw_resolution(timer); /* loop for all active instances * Here we cannot use list_for_each_entry because the active_list of a * processed instance is relinked to done_list_head before the callback * is called. */ list_for_each_entry_safe(ti, tmp, &timer->active_list_head, active_list) { if (ti->flags & SNDRV_TIMER_IFLG_DEAD) continue; if (!(ti->flags & SNDRV_TIMER_IFLG_RUNNING)) continue; ti->pticks += ticks_left; ti->resolution = resolution; if (ti->cticks < ticks_left) ti->cticks = 0; else ti->cticks -= ticks_left; if (ti->cticks) /* not expired */ continue; if (ti->flags & SNDRV_TIMER_IFLG_AUTO) { ti->cticks = ti->ticks; } else { ti->flags &= ~SNDRV_TIMER_IFLG_RUNNING; --timer->running; list_del_init(&ti->active_list); } if ((timer->hw.flags & SNDRV_TIMER_HW_WORK) || (ti->flags & SNDRV_TIMER_IFLG_FAST)) ack_list_head = &timer->ack_list_head; else ack_list_head = &timer->sack_list_head; if (list_empty(&ti->ack_list)) list_add_tail(&ti->ack_list, ack_list_head); list_for_each_entry(ts, &ti->slave_active_head, active_list) { ts->pticks = ti->pticks; ts->resolution = resolution; if (list_empty(&ts->ack_list)) list_add_tail(&ts->ack_list, ack_list_head); } } if (timer->flags & SNDRV_TIMER_FLG_RESCHED) snd_timer_reschedule(timer, timer->sticks); if (timer->running) { if (timer->hw.flags & SNDRV_TIMER_HW_STOP) { timer->hw.stop(timer); timer->flags |= SNDRV_TIMER_FLG_CHANGE; } if (!(timer->hw.flags & SNDRV_TIMER_HW_AUTO) || (timer->flags & SNDRV_TIMER_FLG_CHANGE)) { /* restart timer */ timer->flags &= ~SNDRV_TIMER_FLG_CHANGE; timer->hw.start(timer); } } else { timer->hw.stop(timer); } /* now process all fast callbacks */ snd_timer_process_callbacks(timer, &timer->ack_list_head); /* do we have any slow callbacks? */ if (!list_empty(&timer->sack_list_head)) queue_work(system_highpri_wq, &timer->task_work); } EXPORT_SYMBOL(snd_timer_interrupt); /* */ int snd_timer_new(struct snd_card *card, char *id, struct snd_timer_id *tid, struct snd_timer **rtimer) { struct snd_timer *timer; int err; static const struct snd_device_ops ops = { .dev_free = snd_timer_dev_free, .dev_register = snd_timer_dev_register, .dev_disconnect = snd_timer_dev_disconnect, }; if (snd_BUG_ON(!tid)) return -EINVAL; if (tid->dev_class == SNDRV_TIMER_CLASS_CARD || tid->dev_class == SNDRV_TIMER_CLASS_PCM) { if (WARN_ON(!card)) return -EINVAL; } if (rtimer) *rtimer = NULL; timer = kzalloc(sizeof(*timer), GFP_KERNEL); if (!timer) return -ENOMEM; timer->tmr_class = tid->dev_class; timer->card = card; timer->tmr_device = tid->device; timer->tmr_subdevice = tid->subdevice; if (id) strscpy(timer->id, id, sizeof(timer->id)); timer->sticks = 1; INIT_LIST_HEAD(&timer->device_list); INIT_LIST_HEAD(&timer->open_list_head); INIT_LIST_HEAD(&timer->active_list_head); INIT_LIST_HEAD(&timer->ack_list_head); INIT_LIST_HEAD(&timer->sack_list_head); spin_lock_init(&timer->lock); INIT_WORK(&timer->task_work, snd_timer_work); timer->max_instances = 1000; /* default limit per timer */ if (card != NULL) { timer->module = card->module; err = snd_device_new(card, SNDRV_DEV_TIMER, timer, &ops); if (err < 0) { snd_timer_free(timer); return err; } } if (rtimer) *rtimer = timer; return 0; } EXPORT_SYMBOL(snd_timer_new); static int snd_timer_free(struct snd_timer *timer) { if (!timer) return 0; guard(mutex)(®ister_mutex); if (! list_empty(&timer->open_list_head)) { struct list_head *p, *n; struct snd_timer_instance *ti; pr_warn("ALSA: timer %p is busy?\n", timer); list_for_each_safe(p, n, &timer->open_list_head) { list_del_init(p); ti = list_entry(p, struct snd_timer_instance, open_list); ti->timer = NULL; } } list_del(&timer->device_list); if (timer->private_free) timer->private_free(timer); kfree(timer); return 0; } static int snd_timer_dev_free(struct snd_device *device) { struct snd_timer *timer = device->device_data; return snd_timer_free(timer); } static int snd_timer_dev_register(struct snd_device *dev) { struct snd_timer *timer = dev->device_data; struct snd_timer *timer1; if (snd_BUG_ON(!timer || !timer->hw.start || !timer->hw.stop)) return -ENXIO; if (!(timer->hw.flags & SNDRV_TIMER_HW_SLAVE) && !timer->hw.resolution && timer->hw.c_resolution == NULL) return -EINVAL; guard(mutex)(®ister_mutex); list_for_each_entry(timer1, &snd_timer_list, device_list) { if (timer1->tmr_class > timer->tmr_class) break; if (timer1->tmr_class < timer->tmr_class) continue; if (timer1->card && timer->card) { if (timer1->card->number > timer->card->number) break; if (timer1->card->number < timer->card->number) continue; } if (timer1->tmr_device > timer->tmr_device) break; if (timer1->tmr_device < timer->tmr_device) continue; if (timer1->tmr_subdevice > timer->tmr_subdevice) break; if (timer1->tmr_subdevice < timer->tmr_subdevice) continue; /* conflicts.. */ return -EBUSY; } list_add_tail(&timer->device_list, &timer1->device_list); return 0; } static int snd_timer_dev_disconnect(struct snd_device *device) { struct snd_timer *timer = device->device_data; struct snd_timer_instance *ti; guard(mutex)(®ister_mutex); list_del_init(&timer->device_list); /* wake up pending sleepers */ list_for_each_entry(ti, &timer->open_list_head, open_list) { if (ti->disconnect) ti->disconnect(ti); } return 0; } void snd_timer_notify(struct snd_timer *timer, int event, struct timespec64 *tstamp) { unsigned long resolution = 0; struct snd_timer_instance *ti, *ts; if (timer->card && timer->card->shutdown) return; if (! (timer->hw.flags & SNDRV_TIMER_HW_SLAVE)) return; if (snd_BUG_ON(event < SNDRV_TIMER_EVENT_MSTART || event > SNDRV_TIMER_EVENT_MRESUME)) return; guard(spinlock_irqsave)(&timer->lock); if (event == SNDRV_TIMER_EVENT_MSTART || event == SNDRV_TIMER_EVENT_MCONTINUE || event == SNDRV_TIMER_EVENT_MRESUME) resolution = snd_timer_hw_resolution(timer); list_for_each_entry(ti, &timer->active_list_head, active_list) { if (ti->ccallback) ti->ccallback(ti, event, tstamp, resolution); list_for_each_entry(ts, &ti->slave_active_head, active_list) if (ts->ccallback) ts->ccallback(ts, event, tstamp, resolution); } } EXPORT_SYMBOL(snd_timer_notify); /* * exported functions for global timers */ int snd_timer_global_new(char *id, int device, struct snd_timer **rtimer) { struct snd_timer_id tid; tid.dev_class = SNDRV_TIMER_CLASS_GLOBAL; tid.dev_sclass = SNDRV_TIMER_SCLASS_NONE; tid.card = -1; tid.device = device; tid.subdevice = 0; return snd_timer_new(NULL, id, &tid, rtimer); } EXPORT_SYMBOL(snd_timer_global_new); int snd_timer_global_free(struct snd_timer *timer) { return snd_timer_free(timer); } EXPORT_SYMBOL(snd_timer_global_free); int snd_timer_global_register(struct snd_timer *timer) { struct snd_device dev; memset(&dev, 0, sizeof(dev)); dev.device_data = timer; return snd_timer_dev_register(&dev); } EXPORT_SYMBOL(snd_timer_global_register); /* * System timer */ struct snd_timer_system_private { struct timer_list tlist; struct snd_timer *snd_timer; unsigned long last_expires; unsigned long last_jiffies; unsigned long correction; }; static void snd_timer_s_function(struct timer_list *t) { struct snd_timer_system_private *priv = from_timer(priv, t, tlist); struct snd_timer *timer = priv->snd_timer; unsigned long jiff = jiffies; if (time_after(jiff, priv->last_expires)) priv->correction += (long)jiff - (long)priv->last_expires; snd_timer_interrupt(timer, (long)jiff - (long)priv->last_jiffies); } static int snd_timer_s_start(struct snd_timer * timer) { struct snd_timer_system_private *priv; unsigned long njiff; priv = (struct snd_timer_system_private *) timer->private_data; njiff = (priv->last_jiffies = jiffies); if (priv->correction > timer->sticks - 1) { priv->correction -= timer->sticks - 1; njiff++; } else { njiff += timer->sticks - priv->correction; priv->correction = 0; } priv->last_expires = njiff; mod_timer(&priv->tlist, njiff); return 0; } static int snd_timer_s_stop(struct snd_timer * timer) { struct snd_timer_system_private *priv; unsigned long jiff; priv = (struct snd_timer_system_private *) timer->private_data; timer_delete(&priv->tlist); jiff = jiffies; if (time_before(jiff, priv->last_expires)) timer->sticks = priv->last_expires - jiff; else timer->sticks = 1; priv->correction = 0; return 0; } static int snd_timer_s_close(struct snd_timer *timer) { struct snd_timer_system_private *priv; priv = (struct snd_timer_system_private *)timer->private_data; timer_delete_sync(&priv->tlist); return 0; } static const struct snd_timer_hardware snd_timer_system = { .flags = SNDRV_TIMER_HW_FIRST | SNDRV_TIMER_HW_WORK, .resolution = NSEC_PER_SEC / HZ, .ticks = 10000000L, .close = snd_timer_s_close, .start = snd_timer_s_start, .stop = snd_timer_s_stop }; static void snd_timer_free_system(struct snd_timer *timer) { kfree(timer->private_data); } static int snd_timer_register_system(void) { struct snd_timer *timer; struct snd_timer_system_private *priv; int err; err = snd_timer_global_new("system", SNDRV_TIMER_GLOBAL_SYSTEM, &timer); if (err < 0) return err; strcpy(timer->name, "system timer"); timer->hw = snd_timer_system; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (priv == NULL) { snd_timer_free(timer); return -ENOMEM; } priv->snd_timer = timer; timer_setup(&priv->tlist, snd_timer_s_function, 0); timer->private_data = priv; timer->private_free = snd_timer_free_system; return snd_timer_global_register(timer); } #ifdef CONFIG_SND_PROC_FS /* * Info interface */ static void snd_timer_proc_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_timer *timer; struct snd_timer_instance *ti; unsigned long resolution; guard(mutex)(®ister_mutex); list_for_each_entry(timer, &snd_timer_list, device_list) { if (timer->card && timer->card->shutdown) continue; switch (timer->tmr_class) { case SNDRV_TIMER_CLASS_GLOBAL: snd_iprintf(buffer, "G%i: ", timer->tmr_device); break; case SNDRV_TIMER_CLASS_CARD: snd_iprintf(buffer, "C%i-%i: ", timer->card->number, timer->tmr_device); break; case SNDRV_TIMER_CLASS_PCM: snd_iprintf(buffer, "P%i-%i-%i: ", timer->card->number, timer->tmr_device, timer->tmr_subdevice); break; default: snd_iprintf(buffer, "?%i-%i-%i-%i: ", timer->tmr_class, timer->card ? timer->card->number : -1, timer->tmr_device, timer->tmr_subdevice); } snd_iprintf(buffer, "%s :", timer->name); scoped_guard(spinlock_irq, &timer->lock) resolution = snd_timer_hw_resolution(timer); if (resolution) snd_iprintf(buffer, " %lu.%03luus (%lu ticks)", resolution / 1000, resolution % 1000, timer->hw.ticks); if (timer->hw.flags & SNDRV_TIMER_HW_SLAVE) snd_iprintf(buffer, " SLAVE"); snd_iprintf(buffer, "\n"); list_for_each_entry(ti, &timer->open_list_head, open_list) snd_iprintf(buffer, " Client %s : %s\n", ti->owner ? ti->owner : "unknown", (ti->flags & (SNDRV_TIMER_IFLG_START | SNDRV_TIMER_IFLG_RUNNING)) ? "running" : "stopped"); } } static struct snd_info_entry *snd_timer_proc_entry; static void __init snd_timer_proc_init(void) { struct snd_info_entry *entry; entry = snd_info_create_module_entry(THIS_MODULE, "timers", NULL); if (entry != NULL) { entry->c.text.read = snd_timer_proc_read; if (snd_info_register(entry) < 0) { snd_info_free_entry(entry); entry = NULL; } } snd_timer_proc_entry = entry; } static void __exit snd_timer_proc_done(void) { snd_info_free_entry(snd_timer_proc_entry); } #else /* !CONFIG_SND_PROC_FS */ #define snd_timer_proc_init() #define snd_timer_proc_done() #endif /* * USER SPACE interface */ static void snd_timer_user_interrupt(struct snd_timer_instance *timeri, unsigned long resolution, unsigned long ticks) { struct snd_timer_user *tu = timeri->callback_data; struct snd_timer_read *r; int prev; guard(spinlock)(&tu->qlock); if (tu->qused > 0) { prev = tu->qtail == 0 ? tu->queue_size - 1 : tu->qtail - 1; r = &tu->queue[prev]; if (r->resolution == resolution) { r->ticks += ticks; goto __wake; } } if (tu->qused >= tu->queue_size) { tu->overrun++; } else { r = &tu->queue[tu->qtail++]; tu->qtail %= tu->queue_size; r->resolution = resolution; r->ticks = ticks; tu->qused++; } __wake: snd_kill_fasync(tu->fasync, SIGIO, POLL_IN); wake_up(&tu->qchange_sleep); } static void snd_timer_user_append_to_tqueue(struct snd_timer_user *tu, struct snd_timer_tread64 *tread) { if (tu->qused >= tu->queue_size) { tu->overrun++; } else { memcpy(&tu->tqueue[tu->qtail++], tread, sizeof(*tread)); tu->qtail %= tu->queue_size; tu->qused++; } } static void snd_timer_user_ccallback(struct snd_timer_instance *timeri, int event, struct timespec64 *tstamp, unsigned long resolution) { struct snd_timer_user *tu = timeri->callback_data; struct snd_timer_tread64 r1; if (event >= SNDRV_TIMER_EVENT_START && event <= SNDRV_TIMER_EVENT_PAUSE) tu->tstamp = *tstamp; if ((tu->filter & (1 << event)) == 0 || !tu->tread) return; memset(&r1, 0, sizeof(r1)); r1.event = event; r1.tstamp_sec = tstamp->tv_sec; r1.tstamp_nsec = tstamp->tv_nsec; r1.val = resolution; scoped_guard(spinlock_irqsave, &tu->qlock) snd_timer_user_append_to_tqueue(tu, &r1); snd_kill_fasync(tu->fasync, SIGIO, POLL_IN); wake_up(&tu->qchange_sleep); } static void snd_timer_user_disconnect(struct snd_timer_instance *timeri) { struct snd_timer_user *tu = timeri->callback_data; tu->disconnected = true; wake_up(&tu->qchange_sleep); } static void snd_timer_user_tinterrupt(struct snd_timer_instance *timeri, unsigned long resolution, unsigned long ticks) { struct snd_timer_user *tu = timeri->callback_data; struct snd_timer_tread64 *r, r1; struct timespec64 tstamp; int prev, append = 0; memset(&r1, 0, sizeof(r1)); memset(&tstamp, 0, sizeof(tstamp)); scoped_guard(spinlock, &tu->qlock) { if ((tu->filter & ((1 << SNDRV_TIMER_EVENT_RESOLUTION) | (1 << SNDRV_TIMER_EVENT_TICK))) == 0) return; if (tu->last_resolution != resolution || ticks > 0) { if (timer_tstamp_monotonic) ktime_get_ts64(&tstamp); else ktime_get_real_ts64(&tstamp); } if ((tu->filter & (1 << SNDRV_TIMER_EVENT_RESOLUTION)) && tu->last_resolution != resolution) { r1.event = SNDRV_TIMER_EVENT_RESOLUTION; r1.tstamp_sec = tstamp.tv_sec; r1.tstamp_nsec = tstamp.tv_nsec; r1.val = resolution; snd_timer_user_append_to_tqueue(tu, &r1); tu->last_resolution = resolution; append++; } if ((tu->filter & (1 << SNDRV_TIMER_EVENT_TICK)) == 0) break; if (ticks == 0) break; if (tu->qused > 0) { prev = tu->qtail == 0 ? tu->queue_size - 1 : tu->qtail - 1; r = &tu->tqueue[prev]; if (r->event == SNDRV_TIMER_EVENT_TICK) { r->tstamp_sec = tstamp.tv_sec; r->tstamp_nsec = tstamp.tv_nsec; r->val += ticks; append++; break; } } r1.event = SNDRV_TIMER_EVENT_TICK; r1.tstamp_sec = tstamp.tv_sec; r1.tstamp_nsec = tstamp.tv_nsec; r1.val = ticks; snd_timer_user_append_to_tqueue(tu, &r1); append++; } if (append == 0) return; snd_kill_fasync(tu->fasync, SIGIO, POLL_IN); wake_up(&tu->qchange_sleep); } static int realloc_user_queue(struct snd_timer_user *tu, int size) { struct snd_timer_read *queue = NULL; struct snd_timer_tread64 *tqueue = NULL; if (tu->tread) { tqueue = kcalloc(size, sizeof(*tqueue), GFP_KERNEL); if (!tqueue) return -ENOMEM; } else { queue = kcalloc(size, sizeof(*queue), GFP_KERNEL); if (!queue) return -ENOMEM; } guard(spinlock_irq)(&tu->qlock); kfree(tu->queue); kfree(tu->tqueue); tu->queue_size = size; tu->queue = queue; tu->tqueue = tqueue; tu->qhead = tu->qtail = tu->qused = 0; return 0; } static int snd_timer_user_open(struct inode *inode, struct file *file) { struct snd_timer_user *tu; int err; err = stream_open(inode, file); if (err < 0) return err; tu = kzalloc(sizeof(*tu), GFP_KERNEL); if (tu == NULL) return -ENOMEM; spin_lock_init(&tu->qlock); init_waitqueue_head(&tu->qchange_sleep); mutex_init(&tu->ioctl_lock); tu->ticks = 1; if (realloc_user_queue(tu, 128) < 0) { kfree(tu); return -ENOMEM; } file->private_data = tu; return 0; } static int snd_timer_user_release(struct inode *inode, struct file *file) { struct snd_timer_user *tu; if (file->private_data) { tu = file->private_data; file->private_data = NULL; scoped_guard(mutex, &tu->ioctl_lock) { if (tu->timeri) { snd_timer_close(tu->timeri); snd_timer_instance_free(tu->timeri); } } snd_fasync_free(tu->fasync); kfree(tu->queue); kfree(tu->tqueue); kfree(tu); } return 0; } static void snd_timer_user_zero_id(struct snd_timer_id *id) { id->dev_class = SNDRV_TIMER_CLASS_NONE; id->dev_sclass = SNDRV_TIMER_SCLASS_NONE; id->card = -1; id->device = -1; id->subdevice = -1; } static void snd_timer_user_copy_id(struct snd_timer_id *id, struct snd_timer *timer) { id->dev_class = timer->tmr_class; id->dev_sclass = SNDRV_TIMER_SCLASS_NONE; id->card = timer->card ? timer->card->number : -1; id->device = timer->tmr_device; id->subdevice = timer->tmr_subdevice; } static void get_next_device(struct snd_timer_id *id) { struct snd_timer *timer; struct list_head *p; if (id->dev_class < 0) { /* first item */ if (list_empty(&snd_timer_list)) snd_timer_user_zero_id(id); else { timer = list_entry(snd_timer_list.next, struct snd_timer, device_list); snd_timer_user_copy_id(id, timer); } } else { switch (id->dev_class) { case SNDRV_TIMER_CLASS_GLOBAL: id->device = id->device < 0 ? 0 : id->device + 1; list_for_each(p, &snd_timer_list) { timer = list_entry(p, struct snd_timer, device_list); if (timer->tmr_class > SNDRV_TIMER_CLASS_GLOBAL) { snd_timer_user_copy_id(id, timer); break; } if (timer->tmr_device >= id->device) { snd_timer_user_copy_id(id, timer); break; } } if (p == &snd_timer_list) snd_timer_user_zero_id(id); break; case SNDRV_TIMER_CLASS_CARD: case SNDRV_TIMER_CLASS_PCM: if (id->card < 0) { id->card = 0; } else { if (id->device < 0) { id->device = 0; } else { if (id->subdevice < 0) id->subdevice = 0; else if (id->subdevice < INT_MAX) id->subdevice++; } } list_for_each(p, &snd_timer_list) { timer = list_entry(p, struct snd_timer, device_list); if (timer->tmr_class > id->dev_class) { snd_timer_user_copy_id(id, timer); break; } if (timer->tmr_class < id->dev_class) continue; if (timer->card->number > id->card) { snd_timer_user_copy_id(id, timer); break; } if (timer->card->number < id->card) continue; if (timer->tmr_device > id->device) { snd_timer_user_copy_id(id, timer); break; } if (timer->tmr_device < id->device) continue; if (timer->tmr_subdevice > id->subdevice) { snd_timer_user_copy_id(id, timer); break; } if (timer->tmr_subdevice < id->subdevice) continue; snd_timer_user_copy_id(id, timer); break; } if (p == &snd_timer_list) snd_timer_user_zero_id(id); break; default: snd_timer_user_zero_id(id); } } } static int snd_timer_user_next_device(struct snd_timer_id __user *_tid) { struct snd_timer_id id; if (copy_from_user(&id, _tid, sizeof(id))) return -EFAULT; scoped_guard(mutex, ®ister_mutex) get_next_device(&id); if (copy_to_user(_tid, &id, sizeof(*_tid))) return -EFAULT; return 0; } static int snd_timer_user_ginfo(struct file *file, struct snd_timer_ginfo __user *_ginfo) { struct snd_timer_ginfo *ginfo __free(kfree) = NULL; struct snd_timer_id tid; struct snd_timer *t; struct list_head *p; ginfo = memdup_user(_ginfo, sizeof(*ginfo)); if (IS_ERR(ginfo)) return PTR_ERR(ginfo); tid = ginfo->tid; memset(ginfo, 0, sizeof(*ginfo)); ginfo->tid = tid; scoped_guard(mutex, ®ister_mutex) { t = snd_timer_find(&tid); if (!t) return -ENODEV; ginfo->card = t->card ? t->card->number : -1; if (t->hw.flags & SNDRV_TIMER_HW_SLAVE) ginfo->flags |= SNDRV_TIMER_FLG_SLAVE; strscpy(ginfo->id, t->id, sizeof(ginfo->id)); strscpy(ginfo->name, t->name, sizeof(ginfo->name)); scoped_guard(spinlock_irq, &t->lock) ginfo->resolution = snd_timer_hw_resolution(t); if (t->hw.resolution_min > 0) { ginfo->resolution_min = t->hw.resolution_min; ginfo->resolution_max = t->hw.resolution_max; } list_for_each(p, &t->open_list_head) { ginfo->clients++; } } if (copy_to_user(_ginfo, ginfo, sizeof(*ginfo))) return -EFAULT; return 0; } static int timer_set_gparams(struct snd_timer_gparams *gparams) { struct snd_timer *t; guard(mutex)(®ister_mutex); t = snd_timer_find(&gparams->tid); if (!t) return -ENODEV; if (!list_empty(&t->open_list_head)) return -EBUSY; if (!t->hw.set_period) return -ENOSYS; return t->hw.set_period(t, gparams->period_num, gparams->period_den); } static int snd_timer_user_gparams(struct file *file, struct snd_timer_gparams __user *_gparams) { struct snd_timer_gparams gparams; if (copy_from_user(&gparams, _gparams, sizeof(gparams))) return -EFAULT; return timer_set_gparams(&gparams); } static int snd_timer_user_gstatus(struct file *file, struct snd_timer_gstatus __user *_gstatus) { struct snd_timer_gstatus gstatus; struct snd_timer_id tid; struct snd_timer *t; if (copy_from_user(&gstatus, _gstatus, sizeof(gstatus))) return -EFAULT; tid = gstatus.tid; memset(&gstatus, 0, sizeof(gstatus)); gstatus.tid = tid; scoped_guard(mutex, ®ister_mutex) { t = snd_timer_find(&tid); if (t != NULL) { guard(spinlock_irq)(&t->lock); gstatus.resolution = snd_timer_hw_resolution(t); if (t->hw.precise_resolution) { t->hw.precise_resolution(t, &gstatus.resolution_num, &gstatus.resolution_den); } else { gstatus.resolution_num = gstatus.resolution; gstatus.resolution_den = 1000000000uL; } } else { return -ENODEV; } } if (copy_to_user(_gstatus, &gstatus, sizeof(gstatus))) return -EFAULT; return 0; } static int snd_timer_user_tselect(struct file *file, struct snd_timer_select __user *_tselect) { struct snd_timer_user *tu; struct snd_timer_select tselect; char str[32]; int err = 0; tu = file->private_data; if (tu->timeri) { snd_timer_close(tu->timeri); snd_timer_instance_free(tu->timeri); tu->timeri = NULL; } if (copy_from_user(&tselect, _tselect, sizeof(tselect))) { err = -EFAULT; goto __err; } sprintf(str, "application %i", current->pid); if (tselect.id.dev_class != SNDRV_TIMER_CLASS_SLAVE) tselect.id.dev_sclass = SNDRV_TIMER_SCLASS_APPLICATION; tu->timeri = snd_timer_instance_new(str); if (!tu->timeri) { err = -ENOMEM; goto __err; } tu->timeri->flags |= SNDRV_TIMER_IFLG_FAST; tu->timeri->callback = tu->tread ? snd_timer_user_tinterrupt : snd_timer_user_interrupt; tu->timeri->ccallback = snd_timer_user_ccallback; tu->timeri->callback_data = (void *)tu; tu->timeri->disconnect = snd_timer_user_disconnect; err = snd_timer_open(tu->timeri, &tselect.id, current->pid); if (err < 0) { snd_timer_instance_free(tu->timeri); tu->timeri = NULL; } __err: return err; } static int snd_timer_user_info(struct file *file, struct snd_timer_info __user *_info) { struct snd_timer_user *tu; struct snd_timer_info *info __free(kfree) = NULL; struct snd_timer *t; tu = file->private_data; if (!tu->timeri) return -EBADFD; t = tu->timeri->timer; if (!t) return -EBADFD; info = kzalloc(sizeof(*info), GFP_KERNEL); if (! info) return -ENOMEM; info->card = t->card ? t->card->number : -1; if (t->hw.flags & SNDRV_TIMER_HW_SLAVE) info->flags |= SNDRV_TIMER_FLG_SLAVE; strscpy(info->id, t->id, sizeof(info->id)); strscpy(info->name, t->name, sizeof(info->name)); scoped_guard(spinlock_irq, &t->lock) info->resolution = snd_timer_hw_resolution(t); if (copy_to_user(_info, info, sizeof(*_info))) return -EFAULT; return 0; } static int snd_timer_user_params(struct file *file, struct snd_timer_params __user *_params) { struct snd_timer_user *tu; struct snd_timer_params params; struct snd_timer *t; int err; tu = file->private_data; if (!tu->timeri) return -EBADFD; t = tu->timeri->timer; if (!t) return -EBADFD; if (copy_from_user(¶ms, _params, sizeof(params))) return -EFAULT; if (!(t->hw.flags & SNDRV_TIMER_HW_SLAVE)) { u64 resolution; if (params.ticks < 1) { err = -EINVAL; goto _end; } /* Don't allow resolution less than 1ms */ resolution = snd_timer_resolution(tu->timeri); resolution *= params.ticks; if (resolution < 1000000) { err = -EINVAL; goto _end; } } if (params.queue_size > 0 && (params.queue_size < 32 || params.queue_size > 1024)) { err = -EINVAL; goto _end; } if (params.filter & ~((1<<SNDRV_TIMER_EVENT_RESOLUTION)| (1<<SNDRV_TIMER_EVENT_TICK)| (1<<SNDRV_TIMER_EVENT_START)| (1<<SNDRV_TIMER_EVENT_STOP)| (1<<SNDRV_TIMER_EVENT_CONTINUE)| (1<<SNDRV_TIMER_EVENT_PAUSE)| (1<<SNDRV_TIMER_EVENT_SUSPEND)| (1<<SNDRV_TIMER_EVENT_RESUME)| (1<<SNDRV_TIMER_EVENT_MSTART)| (1<<SNDRV_TIMER_EVENT_MSTOP)| (1<<SNDRV_TIMER_EVENT_MCONTINUE)| (1<<SNDRV_TIMER_EVENT_MPAUSE)| (1<<SNDRV_TIMER_EVENT_MSUSPEND)| (1<<SNDRV_TIMER_EVENT_MRESUME))) { err = -EINVAL; goto _end; } snd_timer_stop(tu->timeri); scoped_guard(spinlock_irq, &t->lock) { tu->timeri->flags &= ~(SNDRV_TIMER_IFLG_AUTO| SNDRV_TIMER_IFLG_EXCLUSIVE| SNDRV_TIMER_IFLG_EARLY_EVENT); if (params.flags & SNDRV_TIMER_PSFLG_AUTO) tu->timeri->flags |= SNDRV_TIMER_IFLG_AUTO; if (params.flags & SNDRV_TIMER_PSFLG_EXCLUSIVE) tu->timeri->flags |= SNDRV_TIMER_IFLG_EXCLUSIVE; if (params.flags & SNDRV_TIMER_PSFLG_EARLY_EVENT) tu->timeri->flags |= SNDRV_TIMER_IFLG_EARLY_EVENT; } if (params.queue_size > 0 && (unsigned int)tu->queue_size != params.queue_size) { err = realloc_user_queue(tu, params.queue_size); if (err < 0) goto _end; } scoped_guard(spinlock_irq, &tu->qlock) { tu->qhead = tu->qtail = tu->qused = 0; if (tu->timeri->flags & SNDRV_TIMER_IFLG_EARLY_EVENT) { if (tu->tread) { struct snd_timer_tread64 tread; memset(&tread, 0, sizeof(tread)); tread.event = SNDRV_TIMER_EVENT_EARLY; tread.tstamp_sec = 0; tread.tstamp_nsec = 0; tread.val = 0; snd_timer_user_append_to_tqueue(tu, &tread); } else { struct snd_timer_read *r = &tu->queue[0]; r->resolution = 0; r->ticks = 0; tu->qused++; tu->qtail++; } } tu->filter = params.filter; tu->ticks = params.ticks; } err = 0; _end: if (copy_to_user(_params, ¶ms, sizeof(params))) return -EFAULT; return err; } static int snd_timer_user_status32(struct file *file, struct snd_timer_status32 __user *_status) { struct snd_timer_user *tu; struct snd_timer_status32 status; tu = file->private_data; if (!tu->timeri) return -EBADFD; memset(&status, 0, sizeof(status)); status.tstamp_sec = tu->tstamp.tv_sec; status.tstamp_nsec = tu->tstamp.tv_nsec; status.resolution = snd_timer_resolution(tu->timeri); status.lost = tu->timeri->lost; status.overrun = tu->overrun; scoped_guard(spinlock_irq, &tu->qlock) status.queue = tu->qused; if (copy_to_user(_status, &status, sizeof(status))) return -EFAULT; return 0; } static int snd_timer_user_status64(struct file *file, struct snd_timer_status64 __user *_status) { struct snd_timer_user *tu; struct snd_timer_status64 status; tu = file->private_data; if (!tu->timeri) return -EBADFD; memset(&status, 0, sizeof(status)); status.tstamp_sec = tu->tstamp.tv_sec; status.tstamp_nsec = tu->tstamp.tv_nsec; status.resolution = snd_timer_resolution(tu->timeri); status.lost = tu->timeri->lost; status.overrun = tu->overrun; scoped_guard(spinlock_irq, &tu->qlock) status.queue = tu->qused; if (copy_to_user(_status, &status, sizeof(status))) return -EFAULT; return 0; } static int snd_timer_user_start(struct file *file) { int err; struct snd_timer_user *tu; tu = file->private_data; if (!tu->timeri) return -EBADFD; snd_timer_stop(tu->timeri); tu->timeri->lost = 0; tu->last_resolution = 0; err = snd_timer_start(tu->timeri, tu->ticks); if (err < 0) return err; return 0; } static int snd_timer_user_stop(struct file *file) { int err; struct snd_timer_user *tu; tu = file->private_data; if (!tu->timeri) return -EBADFD; err = snd_timer_stop(tu->timeri); if (err < 0) return err; return 0; } static int snd_timer_user_continue(struct file *file) { int err; struct snd_timer_user *tu; tu = file->private_data; if (!tu->timeri) return -EBADFD; /* start timer instead of continue if it's not used before */ if (!(tu->timeri->flags & SNDRV_TIMER_IFLG_PAUSED)) return snd_timer_user_start(file); tu->timeri->lost = 0; err = snd_timer_continue(tu->timeri); if (err < 0) return err; return 0; } static int snd_timer_user_pause(struct file *file) { int err; struct snd_timer_user *tu; tu = file->private_data; if (!tu->timeri) return -EBADFD; err = snd_timer_pause(tu->timeri); if (err < 0) return err; return 0; } static int snd_timer_user_tread(void __user *argp, struct snd_timer_user *tu, unsigned int cmd, bool compat) { int __user *p = argp; int xarg, old_tread; if (tu->timeri) /* too late */ return -EBUSY; if (get_user(xarg, p)) return -EFAULT; old_tread = tu->tread; if (!xarg) tu->tread = TREAD_FORMAT_NONE; else if (cmd == SNDRV_TIMER_IOCTL_TREAD64 || (IS_ENABLED(CONFIG_64BIT) && !compat)) tu->tread = TREAD_FORMAT_TIME64; else tu->tread = TREAD_FORMAT_TIME32; if (tu->tread != old_tread && realloc_user_queue(tu, tu->queue_size) < 0) { tu->tread = old_tread; return -ENOMEM; } return 0; } enum { SNDRV_TIMER_IOCTL_START_OLD = _IO('T', 0x20), SNDRV_TIMER_IOCTL_STOP_OLD = _IO('T', 0x21), SNDRV_TIMER_IOCTL_CONTINUE_OLD = _IO('T', 0x22), SNDRV_TIMER_IOCTL_PAUSE_OLD = _IO('T', 0x23), }; #ifdef CONFIG_SND_UTIMER /* * Since userspace-driven timers are passed to userspace, we need to have an identifier * which will allow us to use them (basically, the subdevice number of udriven timer). */ static DEFINE_IDA(snd_utimer_ids); static void snd_utimer_put_id(struct snd_utimer *utimer) { int timer_id = utimer->id; snd_BUG_ON(timer_id < 0 || timer_id >= SNDRV_UTIMERS_MAX_COUNT); ida_free(&snd_utimer_ids, timer_id); } static int snd_utimer_take_id(void) { return ida_alloc_max(&snd_utimer_ids, SNDRV_UTIMERS_MAX_COUNT - 1, GFP_KERNEL); } static void snd_utimer_free(struct snd_utimer *utimer) { snd_timer_free(utimer->timer); snd_utimer_put_id(utimer); kfree(utimer->name); kfree(utimer); } static int snd_utimer_release(struct inode *inode, struct file *file) { struct snd_utimer *utimer = (struct snd_utimer *)file->private_data; snd_utimer_free(utimer); return 0; } static int snd_utimer_trigger(struct file *file) { struct snd_utimer *utimer = (struct snd_utimer *)file->private_data; snd_timer_interrupt(utimer->timer, utimer->timer->sticks); return 0; } static long snd_utimer_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) { switch (ioctl) { case SNDRV_TIMER_IOCTL_TRIGGER: return snd_utimer_trigger(file); } return -ENOTTY; } static const struct file_operations snd_utimer_fops = { .llseek = noop_llseek, .release = snd_utimer_release, .unlocked_ioctl = snd_utimer_ioctl, }; static int snd_utimer_start(struct snd_timer *t) { return 0; } static int snd_utimer_stop(struct snd_timer *t) { return 0; } static int snd_utimer_open(struct snd_timer *t) { return 0; } static int snd_utimer_close(struct snd_timer *t) { return 0; } static const struct snd_timer_hardware timer_hw = { .flags = SNDRV_TIMER_HW_AUTO | SNDRV_TIMER_HW_WORK, .open = snd_utimer_open, .close = snd_utimer_close, .start = snd_utimer_start, .stop = snd_utimer_stop, }; static int snd_utimer_create(struct snd_timer_uinfo *utimer_info, struct snd_utimer **r_utimer) { struct snd_utimer *utimer; struct snd_timer *timer; struct snd_timer_id tid; int utimer_id; int err = 0; if (!utimer_info || utimer_info->resolution == 0) return -EINVAL; utimer = kzalloc(sizeof(*utimer), GFP_KERNEL); if (!utimer) return -ENOMEM; /* We hold the ioctl lock here so we won't get a race condition when allocating id */ utimer_id = snd_utimer_take_id(); if (utimer_id < 0) { err = utimer_id; goto err_take_id; } utimer->name = kasprintf(GFP_KERNEL, "snd-utimer%d", utimer_id); if (!utimer->name) { err = -ENOMEM; goto err_get_name; } utimer->id = utimer_id; tid.dev_sclass = SNDRV_TIMER_SCLASS_APPLICATION; tid.dev_class = SNDRV_TIMER_CLASS_GLOBAL; tid.card = -1; tid.device = SNDRV_TIMER_GLOBAL_UDRIVEN; tid.subdevice = utimer_id; err = snd_timer_new(NULL, utimer->name, &tid, &timer); if (err < 0) { pr_err("Can't create userspace-driven timer\n"); goto err_timer_new; } timer->module = THIS_MODULE; timer->hw = timer_hw; timer->hw.resolution = utimer_info->resolution; timer->hw.ticks = 1; timer->max_instances = MAX_SLAVE_INSTANCES; utimer->timer = timer; err = snd_timer_global_register(timer); if (err < 0) { pr_err("Can't register a userspace-driven timer\n"); goto err_timer_reg; } *r_utimer = utimer; return 0; err_timer_reg: snd_timer_free(timer); err_timer_new: kfree(utimer->name); err_get_name: snd_utimer_put_id(utimer); err_take_id: kfree(utimer); return err; } static int snd_utimer_ioctl_create(struct file *file, struct snd_timer_uinfo __user *_utimer_info) { struct snd_utimer *utimer; struct snd_timer_uinfo *utimer_info __free(kfree) = NULL; int err, timer_fd; utimer_info = memdup_user(_utimer_info, sizeof(*utimer_info)); if (IS_ERR(utimer_info)) return PTR_ERR(utimer_info); err = snd_utimer_create(utimer_info, &utimer); if (err < 0) return err; utimer_info->id = utimer->id; timer_fd = anon_inode_getfd(utimer->name, &snd_utimer_fops, utimer, O_RDWR | O_CLOEXEC); if (timer_fd < 0) { snd_utimer_free(utimer); return timer_fd; } utimer_info->fd = timer_fd; err = copy_to_user(_utimer_info, utimer_info, sizeof(*utimer_info)); if (err) { /* * "Leak" the fd, as there is nothing we can do about it. * It might have been closed already since anon_inode_getfd * makes it available for userspace. * * We have to rely on the process exit path to do any * necessary cleanup (e.g. releasing the file). */ return -EFAULT; } return 0; } #else static int snd_utimer_ioctl_create(struct file *file, struct snd_timer_uinfo __user *_utimer_info) { return -ENOTTY; } #endif static long __snd_timer_user_ioctl(struct file *file, unsigned int cmd, unsigned long arg, bool compat) { struct snd_timer_user *tu; void __user *argp = (void __user *)arg; int __user *p = argp; tu = file->private_data; switch (cmd) { case SNDRV_TIMER_IOCTL_PVERSION: return put_user(SNDRV_TIMER_VERSION, p) ? -EFAULT : 0; case SNDRV_TIMER_IOCTL_NEXT_DEVICE: return snd_timer_user_next_device(argp); case SNDRV_TIMER_IOCTL_TREAD_OLD: case SNDRV_TIMER_IOCTL_TREAD64: return snd_timer_user_tread(argp, tu, cmd, compat); case SNDRV_TIMER_IOCTL_GINFO: return snd_timer_user_ginfo(file, argp); case SNDRV_TIMER_IOCTL_GPARAMS: return snd_timer_user_gparams(file, argp); case SNDRV_TIMER_IOCTL_GSTATUS: return snd_timer_user_gstatus(file, argp); case SNDRV_TIMER_IOCTL_SELECT: return snd_timer_user_tselect(file, argp); case SNDRV_TIMER_IOCTL_INFO: return snd_timer_user_info(file, argp); case SNDRV_TIMER_IOCTL_PARAMS: return snd_timer_user_params(file, argp); case SNDRV_TIMER_IOCTL_STATUS32: return snd_timer_user_status32(file, argp); case SNDRV_TIMER_IOCTL_STATUS64: return snd_timer_user_status64(file, argp); case SNDRV_TIMER_IOCTL_START: case SNDRV_TIMER_IOCTL_START_OLD: return snd_timer_user_start(file); case SNDRV_TIMER_IOCTL_STOP: case SNDRV_TIMER_IOCTL_STOP_OLD: return snd_timer_user_stop(file); case SNDRV_TIMER_IOCTL_CONTINUE: case SNDRV_TIMER_IOCTL_CONTINUE_OLD: return snd_timer_user_continue(file); case SNDRV_TIMER_IOCTL_PAUSE: case SNDRV_TIMER_IOCTL_PAUSE_OLD: return snd_timer_user_pause(file); case SNDRV_TIMER_IOCTL_CREATE: return snd_utimer_ioctl_create(file, argp); } return -ENOTTY; } static long snd_timer_user_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct snd_timer_user *tu = file->private_data; guard(mutex)(&tu->ioctl_lock); return __snd_timer_user_ioctl(file, cmd, arg, false); } static int snd_timer_user_fasync(int fd, struct file * file, int on) { struct snd_timer_user *tu; tu = file->private_data; return snd_fasync_helper(fd, file, on, &tu->fasync); } static ssize_t snd_timer_user_read(struct file *file, char __user *buffer, size_t count, loff_t *offset) { struct snd_timer_tread64 *tread; struct snd_timer_tread32 tread32; struct snd_timer_user *tu; long result = 0, unit; int qhead; int err = 0; tu = file->private_data; switch (tu->tread) { case TREAD_FORMAT_TIME64: unit = sizeof(struct snd_timer_tread64); break; case TREAD_FORMAT_TIME32: unit = sizeof(struct snd_timer_tread32); break; case TREAD_FORMAT_NONE: unit = sizeof(struct snd_timer_read); break; default: WARN_ONCE(1, "Corrupt snd_timer_user\n"); return -ENOTSUPP; } mutex_lock(&tu->ioctl_lock); spin_lock_irq(&tu->qlock); while ((long)count - result >= unit) { while (!tu->qused) { wait_queue_entry_t wait; if ((file->f_flags & O_NONBLOCK) != 0 || result > 0) { err = -EAGAIN; goto _error; } set_current_state(TASK_INTERRUPTIBLE); init_waitqueue_entry(&wait, current); add_wait_queue(&tu->qchange_sleep, &wait); spin_unlock_irq(&tu->qlock); mutex_unlock(&tu->ioctl_lock); schedule(); mutex_lock(&tu->ioctl_lock); spin_lock_irq(&tu->qlock); remove_wait_queue(&tu->qchange_sleep, &wait); if (tu->disconnected) { err = -ENODEV; goto _error; } if (signal_pending(current)) { err = -ERESTARTSYS; goto _error; } } qhead = tu->qhead++; tu->qhead %= tu->queue_size; tu->qused--; spin_unlock_irq(&tu->qlock); tread = &tu->tqueue[qhead]; switch (tu->tread) { case TREAD_FORMAT_TIME64: if (copy_to_user(buffer, tread, sizeof(struct snd_timer_tread64))) err = -EFAULT; break; case TREAD_FORMAT_TIME32: memset(&tread32, 0, sizeof(tread32)); tread32 = (struct snd_timer_tread32) { .event = tread->event, .tstamp_sec = tread->tstamp_sec, .tstamp_nsec = tread->tstamp_nsec, .val = tread->val, }; if (copy_to_user(buffer, &tread32, sizeof(tread32))) err = -EFAULT; break; case TREAD_FORMAT_NONE: if (copy_to_user(buffer, &tu->queue[qhead], sizeof(struct snd_timer_read))) err = -EFAULT; break; default: err = -ENOTSUPP; break; } spin_lock_irq(&tu->qlock); if (err < 0) goto _error; result += unit; buffer += unit; } _error: spin_unlock_irq(&tu->qlock); mutex_unlock(&tu->ioctl_lock); return result > 0 ? result : err; } static __poll_t snd_timer_user_poll(struct file *file, poll_table * wait) { __poll_t mask; struct snd_timer_user *tu; tu = file->private_data; poll_wait(file, &tu->qchange_sleep, wait); mask = 0; guard(spinlock_irq)(&tu->qlock); if (tu->qused) mask |= EPOLLIN | EPOLLRDNORM; if (tu->disconnected) mask |= EPOLLERR; return mask; } #ifdef CONFIG_COMPAT #include "timer_compat.c" #else #define snd_timer_user_ioctl_compat NULL #endif static const struct file_operations snd_timer_f_ops = { .owner = THIS_MODULE, .read = snd_timer_user_read, .open = snd_timer_user_open, .release = snd_timer_user_release, .poll = snd_timer_user_poll, .unlocked_ioctl = snd_timer_user_ioctl, .compat_ioctl = snd_timer_user_ioctl_compat, .fasync = snd_timer_user_fasync, }; /* unregister the system timer */ static void snd_timer_free_all(void) { struct snd_timer *timer, *n; list_for_each_entry_safe(timer, n, &snd_timer_list, device_list) snd_timer_free(timer); } static struct device *timer_dev; /* * ENTRY functions */ static int __init alsa_timer_init(void) { int err; err = snd_device_alloc(&timer_dev, NULL); if (err < 0) return err; dev_set_name(timer_dev, "timer"); #ifdef SNDRV_OSS_INFO_DEV_TIMERS snd_oss_info_register(SNDRV_OSS_INFO_DEV_TIMERS, SNDRV_CARDS - 1, "system timer"); #endif err = snd_timer_register_system(); if (err < 0) { pr_err("ALSA: unable to register system timer (%i)\n", err); goto put_timer; } err = snd_register_device(SNDRV_DEVICE_TYPE_TIMER, NULL, 0, &snd_timer_f_ops, NULL, timer_dev); if (err < 0) { pr_err("ALSA: unable to register timer device (%i)\n", err); snd_timer_free_all(); goto put_timer; } snd_timer_proc_init(); return 0; put_timer: put_device(timer_dev); return err; } static void __exit alsa_timer_exit(void) { snd_unregister_device(timer_dev); snd_timer_free_all(); put_device(timer_dev); snd_timer_proc_done(); #ifdef SNDRV_OSS_INFO_DEV_TIMERS snd_oss_info_unregister(SNDRV_OSS_INFO_DEV_TIMERS, SNDRV_CARDS - 1); #endif } module_init(alsa_timer_init) module_exit(alsa_timer_exit) |
| 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Interface handling * * Copyright 2002-2005, Instant802 Networks, Inc. * Copyright 2005-2006, Devicescape Software, Inc. * Copyright (c) 2006 Jiri Benc <jbenc@suse.cz> * Copyright 2008, Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (c) 2016 Intel Deutschland GmbH * Copyright (C) 2018-2025 Intel Corporation */ #include <linux/slab.h> #include <linux/kernel.h> #include <linux/if_arp.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/kcov.h> #include <net/mac80211.h> #include <net/ieee80211_radiotap.h> #include "ieee80211_i.h" #include "sta_info.h" #include "debugfs_netdev.h" #include "mesh.h" #include "led.h" #include "driver-ops.h" #include "wme.h" #include "rate.h" /** * DOC: Interface list locking * * The interface list in each struct ieee80211_local is protected * three-fold: * * (1) modifications may only be done under the RTNL *and* wiphy mutex * *and* iflist_mtx * (2) modifications are done in an RCU manner so atomic readers * can traverse the list in RCU-safe blocks. * * As a consequence, reads (traversals) of the list can be protected * by either the RTNL, the wiphy mutex, the iflist_mtx or RCU. */ static void ieee80211_iface_work(struct wiphy *wiphy, struct wiphy_work *work); bool __ieee80211_recalc_txpower(struct ieee80211_link_data *link) { struct ieee80211_chanctx_conf *chanctx_conf; int power; rcu_read_lock(); chanctx_conf = rcu_dereference(link->conf->chanctx_conf); if (!chanctx_conf) { rcu_read_unlock(); return false; } power = ieee80211_chandef_max_power(&chanctx_conf->def); rcu_read_unlock(); if (link->user_power_level != IEEE80211_UNSET_POWER_LEVEL) power = min(power, link->user_power_level); if (link->ap_power_level != IEEE80211_UNSET_POWER_LEVEL) power = min(power, link->ap_power_level); if (power != link->conf->txpower) { link->conf->txpower = power; return true; } return false; } void ieee80211_recalc_txpower(struct ieee80211_link_data *link, bool update_bss) { if (__ieee80211_recalc_txpower(link) || (update_bss && ieee80211_sdata_running(link->sdata))) ieee80211_link_info_change_notify(link->sdata, link, BSS_CHANGED_TXPOWER); } static u32 __ieee80211_idle_off(struct ieee80211_local *local) { if (!(local->hw.conf.flags & IEEE80211_CONF_IDLE)) return 0; local->hw.conf.flags &= ~IEEE80211_CONF_IDLE; return IEEE80211_CONF_CHANGE_IDLE; } static u32 __ieee80211_idle_on(struct ieee80211_local *local) { if (local->hw.conf.flags & IEEE80211_CONF_IDLE) return 0; ieee80211_flush_queues(local, NULL, false); local->hw.conf.flags |= IEEE80211_CONF_IDLE; return IEEE80211_CONF_CHANGE_IDLE; } static u32 __ieee80211_recalc_idle(struct ieee80211_local *local, bool force_active) { bool working, scanning, active; unsigned int led_trig_start = 0, led_trig_stop = 0; lockdep_assert_wiphy(local->hw.wiphy); active = force_active || !list_empty(&local->chanctx_list) || local->monitors; working = !local->ops->remain_on_channel && !list_empty(&local->roc_list); scanning = test_bit(SCAN_SW_SCANNING, &local->scanning) || test_bit(SCAN_ONCHANNEL_SCANNING, &local->scanning); if (working || scanning) led_trig_start |= IEEE80211_TPT_LEDTRIG_FL_WORK; else led_trig_stop |= IEEE80211_TPT_LEDTRIG_FL_WORK; if (active) led_trig_start |= IEEE80211_TPT_LEDTRIG_FL_CONNECTED; else led_trig_stop |= IEEE80211_TPT_LEDTRIG_FL_CONNECTED; ieee80211_mod_tpt_led_trig(local, led_trig_start, led_trig_stop); if (working || scanning || active) return __ieee80211_idle_off(local); return __ieee80211_idle_on(local); } u32 ieee80211_idle_off(struct ieee80211_local *local) { return __ieee80211_recalc_idle(local, true); } void ieee80211_recalc_idle(struct ieee80211_local *local) { u32 change = __ieee80211_recalc_idle(local, false); if (change) ieee80211_hw_config(local, change); } static int ieee80211_verify_mac(struct ieee80211_sub_if_data *sdata, u8 *addr, bool check_dup) { struct ieee80211_local *local = sdata->local; struct ieee80211_sub_if_data *iter; u64 new, mask, tmp; u8 *m; int ret = 0; lockdep_assert_wiphy(local->hw.wiphy); if (is_zero_ether_addr(local->hw.wiphy->addr_mask)) return 0; m = addr; new = ((u64)m[0] << 5*8) | ((u64)m[1] << 4*8) | ((u64)m[2] << 3*8) | ((u64)m[3] << 2*8) | ((u64)m[4] << 1*8) | ((u64)m[5] << 0*8); m = local->hw.wiphy->addr_mask; mask = ((u64)m[0] << 5*8) | ((u64)m[1] << 4*8) | ((u64)m[2] << 3*8) | ((u64)m[3] << 2*8) | ((u64)m[4] << 1*8) | ((u64)m[5] << 0*8); if (!check_dup) return ret; list_for_each_entry(iter, &local->interfaces, list) { if (iter == sdata) continue; if (iter->vif.type == NL80211_IFTYPE_MONITOR && !(iter->u.mntr.flags & MONITOR_FLAG_ACTIVE)) continue; m = iter->vif.addr; tmp = ((u64)m[0] << 5*8) | ((u64)m[1] << 4*8) | ((u64)m[2] << 3*8) | ((u64)m[3] << 2*8) | ((u64)m[4] << 1*8) | ((u64)m[5] << 0*8); if ((new & ~mask) != (tmp & ~mask)) { ret = -EINVAL; break; } } return ret; } static int ieee80211_can_powered_addr_change(struct ieee80211_sub_if_data *sdata) { struct ieee80211_roc_work *roc; struct ieee80211_local *local = sdata->local; struct ieee80211_sub_if_data *scan_sdata; int ret = 0; lockdep_assert_wiphy(local->hw.wiphy); /* To be the most flexible here we want to only limit changing the * address if the specific interface is doing offchannel work or * scanning. */ if (netif_carrier_ok(sdata->dev)) return -EBUSY; /* First check no ROC work is happening on this iface */ list_for_each_entry(roc, &local->roc_list, list) { if (roc->sdata != sdata) continue; if (roc->started) { ret = -EBUSY; goto unlock; } } /* And if this iface is scanning */ if (local->scanning) { scan_sdata = rcu_dereference_protected(local->scan_sdata, lockdep_is_held(&local->hw.wiphy->mtx)); if (sdata == scan_sdata) ret = -EBUSY; } switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: /* More interface types could be added here but changing the * address while powered makes the most sense in client modes. */ break; default: ret = -EOPNOTSUPP; } unlock: return ret; } static int _ieee80211_change_mac(struct ieee80211_sub_if_data *sdata, void *addr) { struct ieee80211_local *local = sdata->local; struct sockaddr *sa = addr; bool check_dup = true; bool live = false; int ret; if (ieee80211_sdata_running(sdata)) { ret = ieee80211_can_powered_addr_change(sdata); if (ret) return ret; live = true; } if (sdata->vif.type == NL80211_IFTYPE_MONITOR && !(sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE)) check_dup = false; ret = ieee80211_verify_mac(sdata, sa->sa_data, check_dup); if (ret) return ret; if (live) drv_remove_interface(local, sdata); ret = eth_mac_addr(sdata->dev, sa); if (ret == 0) { memcpy(sdata->vif.addr, sa->sa_data, ETH_ALEN); ether_addr_copy(sdata->vif.bss_conf.addr, sdata->vif.addr); } /* Regardless of eth_mac_addr() return we still want to add the * interface back. This should not fail... */ if (live) WARN_ON(drv_add_interface(local, sdata)); return ret; } static int ieee80211_change_mac(struct net_device *dev, void *addr) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; /* * This happens during unregistration if there's a bond device * active (maybe other cases?) and we must get removed from it. * But we really don't care anymore if it's not registered now. */ if (!dev->ieee80211_ptr->registered) return 0; guard(wiphy)(local->hw.wiphy); return _ieee80211_change_mac(sdata, addr); } static inline int identical_mac_addr_allowed(int type1, int type2) { return type1 == NL80211_IFTYPE_MONITOR || type2 == NL80211_IFTYPE_MONITOR || type1 == NL80211_IFTYPE_P2P_DEVICE || type2 == NL80211_IFTYPE_P2P_DEVICE || (type1 == NL80211_IFTYPE_AP && type2 == NL80211_IFTYPE_AP_VLAN) || (type1 == NL80211_IFTYPE_AP_VLAN && (type2 == NL80211_IFTYPE_AP || type2 == NL80211_IFTYPE_AP_VLAN)); } static int ieee80211_check_concurrent_iface(struct ieee80211_sub_if_data *sdata, enum nl80211_iftype iftype) { struct ieee80211_local *local = sdata->local; struct ieee80211_sub_if_data *nsdata; ASSERT_RTNL(); lockdep_assert_wiphy(local->hw.wiphy); /* we hold the RTNL here so can safely walk the list */ list_for_each_entry(nsdata, &local->interfaces, list) { if (nsdata != sdata && ieee80211_sdata_running(nsdata)) { /* * Only OCB and monitor mode may coexist */ if ((sdata->vif.type == NL80211_IFTYPE_OCB && nsdata->vif.type != NL80211_IFTYPE_MONITOR) || (sdata->vif.type != NL80211_IFTYPE_MONITOR && nsdata->vif.type == NL80211_IFTYPE_OCB)) return -EBUSY; /* * Allow only a single IBSS interface to be up at any * time. This is restricted because beacon distribution * cannot work properly if both are in the same IBSS. * * To remove this restriction we'd have to disallow them * from setting the same SSID on different IBSS interfaces * belonging to the same hardware. Then, however, we're * faced with having to adopt two different TSF timers... */ if (iftype == NL80211_IFTYPE_ADHOC && nsdata->vif.type == NL80211_IFTYPE_ADHOC) return -EBUSY; /* * will not add another interface while any channel * switch is active. */ if (nsdata->vif.bss_conf.csa_active) return -EBUSY; /* * The remaining checks are only performed for interfaces * with the same MAC address. */ if (!ether_addr_equal(sdata->vif.addr, nsdata->vif.addr)) continue; /* * check whether it may have the same address */ if (!identical_mac_addr_allowed(iftype, nsdata->vif.type)) return -ENOTUNIQ; /* No support for VLAN with MLO yet */ if (iftype == NL80211_IFTYPE_AP_VLAN && sdata->wdev.use_4addr && nsdata->vif.type == NL80211_IFTYPE_AP && nsdata->vif.valid_links) return -EOPNOTSUPP; /* * can only add VLANs to enabled APs */ if (iftype == NL80211_IFTYPE_AP_VLAN && nsdata->vif.type == NL80211_IFTYPE_AP) sdata->bss = &nsdata->u.ap; } } return ieee80211_check_combinations(sdata, NULL, 0, 0, -1); } static int ieee80211_check_queues(struct ieee80211_sub_if_data *sdata, enum nl80211_iftype iftype) { int n_queues = sdata->local->hw.queues; int i; if (iftype == NL80211_IFTYPE_NAN) return 0; if (iftype != NL80211_IFTYPE_P2P_DEVICE) { for (i = 0; i < IEEE80211_NUM_ACS; i++) { if (WARN_ON_ONCE(sdata->vif.hw_queue[i] == IEEE80211_INVAL_HW_QUEUE)) return -EINVAL; if (WARN_ON_ONCE(sdata->vif.hw_queue[i] >= n_queues)) return -EINVAL; } } if ((iftype != NL80211_IFTYPE_AP && iftype != NL80211_IFTYPE_P2P_GO && iftype != NL80211_IFTYPE_MESH_POINT) || !ieee80211_hw_check(&sdata->local->hw, QUEUE_CONTROL)) { sdata->vif.cab_queue = IEEE80211_INVAL_HW_QUEUE; return 0; } if (WARN_ON_ONCE(sdata->vif.cab_queue == IEEE80211_INVAL_HW_QUEUE)) return -EINVAL; if (WARN_ON_ONCE(sdata->vif.cab_queue >= n_queues)) return -EINVAL; return 0; } static int ieee80211_open(struct net_device *dev) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); int err; /* fail early if user set an invalid address */ if (!is_valid_ether_addr(dev->dev_addr)) return -EADDRNOTAVAIL; guard(wiphy)(sdata->local->hw.wiphy); err = ieee80211_check_concurrent_iface(sdata, sdata->vif.type); if (err) return err; return ieee80211_do_open(&sdata->wdev, true); } static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_down) { struct ieee80211_local *local = sdata->local; unsigned long flags; struct sk_buff_head freeq; struct sk_buff *skb, *tmp; u32 hw_reconf_flags = 0; int i, flushed; struct ps_data *ps; struct cfg80211_chan_def chandef; bool cancel_scan; struct cfg80211_nan_func *func; lockdep_assert_wiphy(local->hw.wiphy); clear_bit(SDATA_STATE_RUNNING, &sdata->state); synchronize_rcu(); /* flush _ieee80211_wake_txqs() */ cancel_scan = rcu_access_pointer(local->scan_sdata) == sdata; if (cancel_scan) ieee80211_scan_cancel(local); ieee80211_roc_purge(local, sdata); switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: ieee80211_mgd_stop(sdata); break; case NL80211_IFTYPE_ADHOC: ieee80211_ibss_stop(sdata); break; case NL80211_IFTYPE_MONITOR: list_del_rcu(&sdata->u.mntr.list); break; default: break; } /* * Remove all stations associated with this interface. * * This must be done before calling ops->remove_interface() * because otherwise we can later invoke ops->sta_notify() * whenever the STAs are removed, and that invalidates driver * assumptions about always getting a vif pointer that is valid * (because if we remove a STA after ops->remove_interface() * the driver will have removed the vif info already!) * * For AP_VLANs stations may exist since there's nothing else that * would have removed them, but in other modes there shouldn't * be any stations. */ flushed = sta_info_flush(sdata, -1); WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_AP_VLAN && flushed > 0); /* don't count this interface for allmulti while it is down */ if (sdata->flags & IEEE80211_SDATA_ALLMULTI) atomic_dec(&local->iff_allmultis); if (sdata->vif.type == NL80211_IFTYPE_AP) { local->fif_pspoll--; local->fif_probe_req--; } else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) { local->fif_probe_req--; } if (sdata->dev) { netif_addr_lock_bh(sdata->dev); spin_lock_bh(&local->filter_lock); __hw_addr_unsync(&local->mc_list, &sdata->dev->mc, sdata->dev->addr_len); spin_unlock_bh(&local->filter_lock); netif_addr_unlock_bh(sdata->dev); } timer_delete_sync(&local->dynamic_ps_timer); wiphy_work_cancel(local->hw.wiphy, &local->dynamic_ps_enable_work); WARN(ieee80211_vif_is_mld(&sdata->vif), "destroying interface with valid links 0x%04x\n", sdata->vif.valid_links); sdata->vif.bss_conf.csa_active = false; if (sdata->vif.type == NL80211_IFTYPE_STATION) sdata->deflink.u.mgd.csa.waiting_bcn = false; ieee80211_vif_unblock_queues_csa(sdata); wiphy_work_cancel(local->hw.wiphy, &sdata->deflink.csa.finalize_work); wiphy_work_cancel(local->hw.wiphy, &sdata->deflink.color_change_finalize_work); wiphy_delayed_work_cancel(local->hw.wiphy, &sdata->deflink.dfs_cac_timer_work); if (sdata->wdev.links[0].cac_started) { chandef = sdata->vif.bss_conf.chanreq.oper; WARN_ON(local->suspended); ieee80211_link_release_channel(&sdata->deflink); cfg80211_cac_event(sdata->dev, &chandef, NL80211_RADAR_CAC_ABORTED, GFP_KERNEL, 0); } if (sdata->vif.type == NL80211_IFTYPE_AP) { WARN_ON(!list_empty(&sdata->u.ap.vlans)); } else if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { /* remove all packets in parent bc_buf pointing to this dev */ ps = &sdata->bss->ps; spin_lock_irqsave(&ps->bc_buf.lock, flags); skb_queue_walk_safe(&ps->bc_buf, skb, tmp) { if (skb->dev == sdata->dev) { __skb_unlink(skb, &ps->bc_buf); local->total_ps_buffered--; ieee80211_free_txskb(&local->hw, skb); } } spin_unlock_irqrestore(&ps->bc_buf.lock, flags); } if (going_down) local->open_count--; switch (sdata->vif.type) { case NL80211_IFTYPE_AP_VLAN: list_del(&sdata->u.vlan.list); RCU_INIT_POINTER(sdata->vif.bss_conf.chanctx_conf, NULL); /* see comment in the default case below */ ieee80211_free_keys(sdata, true); /* no need to tell driver */ break; case NL80211_IFTYPE_MONITOR: local->monitors--; if (!(sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE) && !ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) { local->virt_monitors--; if (local->virt_monitors == 0) { local->hw.conf.flags &= ~IEEE80211_CONF_MONITOR; hw_reconf_flags |= IEEE80211_CONF_CHANGE_MONITOR; } ieee80211_adjust_monitor_flags(sdata, -1); } break; case NL80211_IFTYPE_NAN: /* clean all the functions */ spin_lock_bh(&sdata->u.nan.func_lock); idr_for_each_entry(&sdata->u.nan.function_inst_ids, func, i) { idr_remove(&sdata->u.nan.function_inst_ids, i); cfg80211_free_nan_func(func); } idr_destroy(&sdata->u.nan.function_inst_ids); spin_unlock_bh(&sdata->u.nan.func_lock); break; case NL80211_IFTYPE_P2P_DEVICE: /* relies on synchronize_rcu() below */ RCU_INIT_POINTER(local->p2p_sdata, NULL); fallthrough; default: wiphy_work_cancel(sdata->local->hw.wiphy, &sdata->work); /* * When we get here, the interface is marked down. * Free the remaining keys, if there are any * (which can happen in AP mode if userspace sets * keys before the interface is operating) * * Force the key freeing to always synchronize_net() * to wait for the RX path in case it is using this * interface enqueuing frames at this very time on * another CPU. */ ieee80211_free_keys(sdata, true); skb_queue_purge(&sdata->skb_queue); skb_queue_purge(&sdata->status_queue); } /* * Since ieee80211_free_txskb() may issue __dev_queue_xmit() * which should be called with interrupts enabled, reclamation * is done in two phases: */ __skb_queue_head_init(&freeq); /* unlink from local queues... */ spin_lock_irqsave(&local->queue_stop_reason_lock, flags); for (i = 0; i < IEEE80211_MAX_QUEUES; i++) { skb_queue_walk_safe(&local->pending[i], skb, tmp) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); if (info->control.vif == &sdata->vif) { __skb_unlink(skb, &local->pending[i]); __skb_queue_tail(&freeq, skb); } } } spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); /* ... and perform actual reclamation with interrupts enabled. */ skb_queue_walk_safe(&freeq, skb, tmp) { __skb_unlink(skb, &freeq); ieee80211_free_txskb(&local->hw, skb); } if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) ieee80211_txq_remove_vlan(local, sdata); if (sdata->vif.txq) ieee80211_txq_purge(sdata->local, to_txq_info(sdata->vif.txq)); sdata->bss = NULL; if (local->open_count == 0) ieee80211_clear_tx_pending(local); sdata->vif.bss_conf.beacon_int = 0; /* * If the interface goes down while suspended, presumably because * the device was unplugged and that happens before our resume, * then the driver is already unconfigured and the remainder of * this function isn't needed. * XXX: what about WoWLAN? If the device has software state, e.g. * memory allocated, it might expect teardown commands from * mac80211 here? */ if (local->suspended) { WARN_ON(local->wowlan); WARN_ON(rcu_access_pointer(local->monitor_sdata)); return; } switch (sdata->vif.type) { case NL80211_IFTYPE_AP_VLAN: break; case NL80211_IFTYPE_MONITOR: if (local->virt_monitors == 0) ieee80211_del_virtual_monitor(local); ieee80211_recalc_idle(local); ieee80211_recalc_offload(local); if (!(sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE) && !ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) break; ieee80211_link_release_channel(&sdata->deflink); fallthrough; default: if (!going_down) break; drv_remove_interface(local, sdata); /* Clear private driver data to prevent reuse */ memset(sdata->vif.drv_priv, 0, local->hw.vif_data_size); } ieee80211_recalc_ps(local); if (cancel_scan) wiphy_delayed_work_flush(local->hw.wiphy, &local->scan_work); if (local->open_count == 0) { ieee80211_stop_device(local, false); /* no reconfiguring after stop! */ return; } /* do after stop to avoid reconfiguring when we stop anyway */ ieee80211_configure_filter(local); ieee80211_hw_config(local, hw_reconf_flags); if (local->virt_monitors == local->open_count) ieee80211_add_virtual_monitor(local); } static void ieee80211_stop_mbssid(struct ieee80211_sub_if_data *sdata) { struct ieee80211_sub_if_data *tx_sdata, *non_tx_sdata, *tmp_sdata; struct ieee80211_vif *tx_vif = sdata->vif.mbssid_tx_vif; if (!tx_vif) return; tx_sdata = vif_to_sdata(tx_vif); sdata->vif.mbssid_tx_vif = NULL; list_for_each_entry_safe(non_tx_sdata, tmp_sdata, &tx_sdata->local->interfaces, list) { if (non_tx_sdata != sdata && non_tx_sdata != tx_sdata && non_tx_sdata->vif.mbssid_tx_vif == tx_vif && ieee80211_sdata_running(non_tx_sdata)) { non_tx_sdata->vif.mbssid_tx_vif = NULL; dev_close(non_tx_sdata->wdev.netdev); } } if (sdata != tx_sdata && ieee80211_sdata_running(tx_sdata)) { tx_sdata->vif.mbssid_tx_vif = NULL; dev_close(tx_sdata->wdev.netdev); } } static int ieee80211_stop(struct net_device *dev) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); /* close dependent VLAN and MBSSID interfaces before locking wiphy */ if (sdata->vif.type == NL80211_IFTYPE_AP) { struct ieee80211_sub_if_data *vlan, *tmpsdata; list_for_each_entry_safe(vlan, tmpsdata, &sdata->u.ap.vlans, u.vlan.list) dev_close(vlan->dev); ieee80211_stop_mbssid(sdata); } guard(wiphy)(sdata->local->hw.wiphy); wiphy_work_cancel(sdata->local->hw.wiphy, &sdata->activate_links_work); ieee80211_do_stop(sdata, true); return 0; } static void ieee80211_set_multicast_list(struct net_device *dev) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; int allmulti, sdata_allmulti; allmulti = !!(dev->flags & IFF_ALLMULTI); sdata_allmulti = !!(sdata->flags & IEEE80211_SDATA_ALLMULTI); if (allmulti != sdata_allmulti) { if (dev->flags & IFF_ALLMULTI) atomic_inc(&local->iff_allmultis); else atomic_dec(&local->iff_allmultis); sdata->flags ^= IEEE80211_SDATA_ALLMULTI; } spin_lock_bh(&local->filter_lock); __hw_addr_sync(&local->mc_list, &dev->mc, dev->addr_len); spin_unlock_bh(&local->filter_lock); wiphy_work_queue(local->hw.wiphy, &local->reconfig_filter); } /* * Called when the netdev is removed or, by the code below, before * the interface type changes. */ static void ieee80211_teardown_sdata(struct ieee80211_sub_if_data *sdata) { if (WARN_ON(!list_empty(&sdata->work.entry))) wiphy_work_cancel(sdata->local->hw.wiphy, &sdata->work); /* free extra data */ ieee80211_free_keys(sdata, false); ieee80211_debugfs_remove_netdev(sdata); ieee80211_destroy_frag_cache(&sdata->frags); if (ieee80211_vif_is_mesh(&sdata->vif)) ieee80211_mesh_teardown_sdata(sdata); ieee80211_vif_clear_links(sdata); ieee80211_link_stop(&sdata->deflink); } static void ieee80211_uninit(struct net_device *dev) { ieee80211_teardown_sdata(IEEE80211_DEV_TO_SUB_IF(dev)); } static int ieee80211_netdev_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; return drv_net_setup_tc(local, sdata, dev, type, type_data); } static const struct net_device_ops ieee80211_dataif_ops = { .ndo_open = ieee80211_open, .ndo_stop = ieee80211_stop, .ndo_uninit = ieee80211_uninit, .ndo_start_xmit = ieee80211_subif_start_xmit, .ndo_set_rx_mode = ieee80211_set_multicast_list, .ndo_set_mac_address = ieee80211_change_mac, .ndo_setup_tc = ieee80211_netdev_setup_tc, }; static u16 ieee80211_monitor_select_queue(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr; int len_rthdr; if (local->hw.queues < IEEE80211_NUM_ACS) return 0; /* reset flags and info before parsing radiotap header */ memset(info, 0, sizeof(*info)); if (!ieee80211_parse_tx_radiotap(skb, dev)) return 0; /* doesn't matter, frame will be dropped */ len_rthdr = ieee80211_get_radiotap_len(skb->data); hdr = (struct ieee80211_hdr *)(skb->data + len_rthdr); if (skb->len < len_rthdr + 2 || skb->len < len_rthdr + ieee80211_hdrlen(hdr->frame_control)) return 0; /* doesn't matter, frame will be dropped */ return ieee80211_select_queue_80211(sdata, skb, hdr); } static const struct net_device_ops ieee80211_monitorif_ops = { .ndo_open = ieee80211_open, .ndo_stop = ieee80211_stop, .ndo_uninit = ieee80211_uninit, .ndo_start_xmit = ieee80211_monitor_start_xmit, .ndo_set_rx_mode = ieee80211_set_multicast_list, .ndo_set_mac_address = ieee80211_change_mac, .ndo_select_queue = ieee80211_monitor_select_queue, }; static int ieee80211_netdev_fill_forward_path(struct net_device_path_ctx *ctx, struct net_device_path *path) { struct ieee80211_sub_if_data *sdata; struct ieee80211_local *local; struct sta_info *sta; int ret = -ENOENT; sdata = IEEE80211_DEV_TO_SUB_IF(ctx->dev); local = sdata->local; if (!local->ops->net_fill_forward_path) return -EOPNOTSUPP; rcu_read_lock(); switch (sdata->vif.type) { case NL80211_IFTYPE_AP_VLAN: sta = rcu_dereference(sdata->u.vlan.sta); if (sta) break; if (sdata->wdev.use_4addr) goto out; if (is_multicast_ether_addr(ctx->daddr)) goto out; sta = sta_info_get_bss(sdata, ctx->daddr); break; case NL80211_IFTYPE_AP: if (is_multicast_ether_addr(ctx->daddr)) goto out; sta = sta_info_get(sdata, ctx->daddr); break; case NL80211_IFTYPE_STATION: if (sdata->wdev.wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS) { sta = sta_info_get(sdata, ctx->daddr); if (sta && test_sta_flag(sta, WLAN_STA_TDLS_PEER)) { if (!test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH)) goto out; break; } } sta = sta_info_get(sdata, sdata->deflink.u.mgd.bssid); break; default: goto out; } if (!sta) goto out; ret = drv_net_fill_forward_path(local, sdata, &sta->sta, ctx, path); out: rcu_read_unlock(); return ret; } static const struct net_device_ops ieee80211_dataif_8023_ops = { .ndo_open = ieee80211_open, .ndo_stop = ieee80211_stop, .ndo_uninit = ieee80211_uninit, .ndo_start_xmit = ieee80211_subif_start_xmit_8023, .ndo_set_rx_mode = ieee80211_set_multicast_list, .ndo_set_mac_address = ieee80211_change_mac, .ndo_fill_forward_path = ieee80211_netdev_fill_forward_path, .ndo_setup_tc = ieee80211_netdev_setup_tc, }; static bool ieee80211_iftype_supports_hdr_offload(enum nl80211_iftype iftype) { switch (iftype) { /* P2P GO and client are mapped to AP/STATION types */ case NL80211_IFTYPE_AP: case NL80211_IFTYPE_STATION: return true; default: return false; } } static bool ieee80211_set_sdata_offload_flags(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; u32 flags; flags = sdata->vif.offload_flags; if (ieee80211_hw_check(&local->hw, SUPPORTS_TX_ENCAP_OFFLOAD) && ieee80211_iftype_supports_hdr_offload(sdata->vif.type)) { flags |= IEEE80211_OFFLOAD_ENCAP_ENABLED; if (!ieee80211_hw_check(&local->hw, SUPPORTS_TX_FRAG) && local->hw.wiphy->frag_threshold != (u32)-1) flags &= ~IEEE80211_OFFLOAD_ENCAP_ENABLED; if (local->virt_monitors) flags &= ~IEEE80211_OFFLOAD_ENCAP_ENABLED; } else { flags &= ~IEEE80211_OFFLOAD_ENCAP_ENABLED; } if (ieee80211_hw_check(&local->hw, SUPPORTS_RX_DECAP_OFFLOAD) && ieee80211_iftype_supports_hdr_offload(sdata->vif.type)) { flags |= IEEE80211_OFFLOAD_DECAP_ENABLED; if (local->virt_monitors && !ieee80211_hw_check(&local->hw, SUPPORTS_CONC_MON_RX_DECAP)) flags &= ~IEEE80211_OFFLOAD_DECAP_ENABLED; } else { flags &= ~IEEE80211_OFFLOAD_DECAP_ENABLED; } if (sdata->vif.offload_flags == flags) return false; sdata->vif.offload_flags = flags; ieee80211_check_fast_rx_iface(sdata); return true; } static void ieee80211_set_vif_encap_ops(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; struct ieee80211_sub_if_data *bss = sdata; bool enabled; if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { if (!sdata->bss) return; bss = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap); } if (!ieee80211_hw_check(&local->hw, SUPPORTS_TX_ENCAP_OFFLOAD) || !ieee80211_iftype_supports_hdr_offload(bss->vif.type)) return; enabled = bss->vif.offload_flags & IEEE80211_OFFLOAD_ENCAP_ENABLED; if (sdata->wdev.use_4addr && !(bss->vif.offload_flags & IEEE80211_OFFLOAD_ENCAP_4ADDR)) enabled = false; sdata->dev->netdev_ops = enabled ? &ieee80211_dataif_8023_ops : &ieee80211_dataif_ops; } static void ieee80211_recalc_sdata_offload(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; struct ieee80211_sub_if_data *vsdata; if (ieee80211_set_sdata_offload_flags(sdata)) { drv_update_vif_offload(local, sdata); ieee80211_set_vif_encap_ops(sdata); } list_for_each_entry(vsdata, &local->interfaces, list) { if (vsdata->vif.type != NL80211_IFTYPE_AP_VLAN || vsdata->bss != &sdata->u.ap) continue; ieee80211_set_vif_encap_ops(vsdata); } } void ieee80211_recalc_offload(struct ieee80211_local *local) { struct ieee80211_sub_if_data *sdata; if (!ieee80211_hw_check(&local->hw, SUPPORTS_TX_ENCAP_OFFLOAD)) return; lockdep_assert_wiphy(local->hw.wiphy); list_for_each_entry(sdata, &local->interfaces, list) { if (!ieee80211_sdata_running(sdata)) continue; ieee80211_recalc_sdata_offload(sdata); } } void ieee80211_adjust_monitor_flags(struct ieee80211_sub_if_data *sdata, const int offset) { struct ieee80211_local *local = sdata->local; u32 flags = sdata->u.mntr.flags; #define ADJUST(_f, _s) do { \ if (flags & MONITOR_FLAG_##_f) \ local->fif_##_s += offset; \ } while (0) ADJUST(FCSFAIL, fcsfail); ADJUST(PLCPFAIL, plcpfail); ADJUST(CONTROL, control); ADJUST(CONTROL, pspoll); ADJUST(OTHER_BSS, other_bss); if (!(flags & MONITOR_FLAG_SKIP_TX)) local->tx_mntrs += offset; #undef ADJUST } static void ieee80211_set_default_queues(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; int i; for (i = 0; i < IEEE80211_NUM_ACS; i++) { if (ieee80211_hw_check(&local->hw, QUEUE_CONTROL)) sdata->vif.hw_queue[i] = IEEE80211_INVAL_HW_QUEUE; else if (local->hw.queues >= IEEE80211_NUM_ACS) sdata->vif.hw_queue[i] = i; else sdata->vif.hw_queue[i] = 0; } sdata->vif.cab_queue = IEEE80211_INVAL_HW_QUEUE; } static void ieee80211_sdata_init(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata) { sdata->local = local; /* * Initialize the default link, so we can use link_id 0 for non-MLD, * and that continues to work for non-MLD-aware drivers that use just * vif.bss_conf instead of vif.link_conf. * * Note that we never change this, so if link ID 0 isn't used in an * MLD connection, we get a separate allocation for it. */ ieee80211_link_init(sdata, -1, &sdata->deflink, &sdata->vif.bss_conf); } int ieee80211_add_virtual_monitor(struct ieee80211_local *local) { struct ieee80211_sub_if_data *sdata; int ret; ASSERT_RTNL(); lockdep_assert_wiphy(local->hw.wiphy); if (local->monitor_sdata || ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) return 0; sdata = kzalloc(sizeof(*sdata) + local->hw.vif_data_size, GFP_KERNEL); if (!sdata) return -ENOMEM; /* set up data */ sdata->vif.type = NL80211_IFTYPE_MONITOR; snprintf(sdata->name, IFNAMSIZ, "%s-monitor", wiphy_name(local->hw.wiphy)); sdata->wdev.iftype = NL80211_IFTYPE_MONITOR; sdata->wdev.wiphy = local->hw.wiphy; ieee80211_sdata_init(local, sdata); ieee80211_set_default_queues(sdata); if (ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) { ret = drv_add_interface(local, sdata); if (WARN_ON(ret)) { /* ok .. stupid driver, it asked for this! */ kfree(sdata); return ret; } } set_bit(SDATA_STATE_RUNNING, &sdata->state); ret = ieee80211_check_queues(sdata, NL80211_IFTYPE_MONITOR); if (ret) { kfree(sdata); return ret; } mutex_lock(&local->iflist_mtx); rcu_assign_pointer(local->monitor_sdata, sdata); mutex_unlock(&local->iflist_mtx); ret = ieee80211_link_use_channel(&sdata->deflink, &local->monitor_chanreq, IEEE80211_CHANCTX_EXCLUSIVE); if (ret) { mutex_lock(&local->iflist_mtx); RCU_INIT_POINTER(local->monitor_sdata, NULL); mutex_unlock(&local->iflist_mtx); synchronize_net(); drv_remove_interface(local, sdata); kfree(sdata); return ret; } skb_queue_head_init(&sdata->skb_queue); skb_queue_head_init(&sdata->status_queue); wiphy_work_init(&sdata->work, ieee80211_iface_work); return 0; } void ieee80211_del_virtual_monitor(struct ieee80211_local *local) { struct ieee80211_sub_if_data *sdata; if (ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) return; ASSERT_RTNL(); lockdep_assert_wiphy(local->hw.wiphy); mutex_lock(&local->iflist_mtx); sdata = rcu_dereference_protected(local->monitor_sdata, lockdep_is_held(&local->iflist_mtx)); if (!sdata) { mutex_unlock(&local->iflist_mtx); return; } clear_bit(SDATA_STATE_RUNNING, &sdata->state); ieee80211_link_release_channel(&sdata->deflink); if (ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) drv_remove_interface(local, sdata); RCU_INIT_POINTER(local->monitor_sdata, NULL); mutex_unlock(&local->iflist_mtx); synchronize_net(); kfree(sdata); } /* * NOTE: Be very careful when changing this function, it must NOT return * an error on interface type changes that have been pre-checked, so most * checks should be in ieee80211_check_concurrent_iface. */ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); struct net_device *dev = wdev->netdev; struct ieee80211_local *local = sdata->local; u64 changed = 0; int res; u32 hw_reconf_flags = 0; lockdep_assert_wiphy(local->hw.wiphy); switch (sdata->vif.type) { case NL80211_IFTYPE_AP_VLAN: { struct ieee80211_sub_if_data *master; if (!sdata->bss) return -ENOLINK; list_add(&sdata->u.vlan.list, &sdata->bss->vlans); master = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap); sdata->control_port_protocol = master->control_port_protocol; sdata->control_port_no_encrypt = master->control_port_no_encrypt; sdata->control_port_over_nl80211 = master->control_port_over_nl80211; sdata->control_port_no_preauth = master->control_port_no_preauth; sdata->vif.cab_queue = master->vif.cab_queue; memcpy(sdata->vif.hw_queue, master->vif.hw_queue, sizeof(sdata->vif.hw_queue)); sdata->vif.bss_conf.chanreq = master->vif.bss_conf.chanreq; sdata->crypto_tx_tailroom_needed_cnt += master->crypto_tx_tailroom_needed_cnt; break; } case NL80211_IFTYPE_AP: sdata->bss = &sdata->u.ap; break; case NL80211_IFTYPE_MESH_POINT: case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_MONITOR: case NL80211_IFTYPE_ADHOC: case NL80211_IFTYPE_P2P_DEVICE: case NL80211_IFTYPE_OCB: case NL80211_IFTYPE_NAN: /* no special treatment */ break; case NL80211_IFTYPE_UNSPECIFIED: case NUM_NL80211_IFTYPES: case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_P2P_GO: case NL80211_IFTYPE_WDS: /* cannot happen */ WARN_ON(1); break; } if (local->open_count == 0) { /* here we can consider everything in good order (again) */ local->reconfig_failure = false; res = drv_start(local); if (res) goto err_del_bss; ieee80211_led_radio(local, true); ieee80211_mod_tpt_led_trig(local, IEEE80211_TPT_LEDTRIG_FL_RADIO, 0); } /* * Copy the hopefully now-present MAC address to * this interface, if it has the special null one. */ if (dev && is_zero_ether_addr(dev->dev_addr)) { eth_hw_addr_set(dev, local->hw.wiphy->perm_addr); memcpy(dev->perm_addr, dev->dev_addr, ETH_ALEN); if (!is_valid_ether_addr(dev->dev_addr)) { res = -EADDRNOTAVAIL; goto err_stop; } } sdata->vif.addr_valid = sdata->vif.type != NL80211_IFTYPE_MONITOR || (sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE); switch (sdata->vif.type) { case NL80211_IFTYPE_AP_VLAN: /* no need to tell driver, but set carrier and chanctx */ if (sdata->bss->active) { ieee80211_link_vlan_copy_chanctx(&sdata->deflink); netif_carrier_on(dev); ieee80211_set_vif_encap_ops(sdata); } else { netif_carrier_off(dev); } break; case NL80211_IFTYPE_MONITOR: if ((sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE) || ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) { res = drv_add_interface(local, sdata); if (res) goto err_stop; } else { if (local->virt_monitors == 0 && local->open_count == 0) { res = ieee80211_add_virtual_monitor(local); if (res) goto err_stop; } local->virt_monitors++; /* must be before the call to ieee80211_configure_filter */ if (local->virt_monitors == 1) { local->hw.conf.flags |= IEEE80211_CONF_MONITOR; hw_reconf_flags |= IEEE80211_CONF_CHANGE_MONITOR; } } local->monitors++; ieee80211_adjust_monitor_flags(sdata, 1); ieee80211_configure_filter(local); ieee80211_recalc_offload(local); ieee80211_recalc_idle(local); netif_carrier_on(dev); break; default: if (coming_up) { ieee80211_del_virtual_monitor(local); ieee80211_set_sdata_offload_flags(sdata); res = drv_add_interface(local, sdata); if (res) goto err_stop; ieee80211_set_vif_encap_ops(sdata); res = ieee80211_check_queues(sdata, ieee80211_vif_type_p2p(&sdata->vif)); if (res) goto err_del_interface; } if (sdata->vif.type == NL80211_IFTYPE_AP) { local->fif_pspoll++; local->fif_probe_req++; ieee80211_configure_filter(local); } else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) { local->fif_probe_req++; } if (sdata->vif.probe_req_reg) drv_config_iface_filter(local, sdata, FIF_PROBE_REQ, FIF_PROBE_REQ); if (sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE && sdata->vif.type != NL80211_IFTYPE_NAN) changed |= ieee80211_reset_erp_info(sdata); ieee80211_link_info_change_notify(sdata, &sdata->deflink, changed); switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_ADHOC: case NL80211_IFTYPE_AP: case NL80211_IFTYPE_MESH_POINT: case NL80211_IFTYPE_OCB: netif_carrier_off(dev); break; case NL80211_IFTYPE_P2P_DEVICE: case NL80211_IFTYPE_NAN: break; default: /* not reached */ WARN_ON(1); } /* * Set default queue parameters so drivers don't * need to initialise the hardware if the hardware * doesn't start up with sane defaults. * Enable QoS for anything but station interfaces. */ ieee80211_set_wmm_default(&sdata->deflink, true, sdata->vif.type != NL80211_IFTYPE_STATION); } switch (sdata->vif.type) { case NL80211_IFTYPE_P2P_DEVICE: rcu_assign_pointer(local->p2p_sdata, sdata); break; case NL80211_IFTYPE_MONITOR: list_add_tail_rcu(&sdata->u.mntr.list, &local->mon_list); break; default: break; } /* * set_multicast_list will be invoked by the networking core * which will check whether any increments here were done in * error and sync them down to the hardware as filter flags. */ if (sdata->flags & IEEE80211_SDATA_ALLMULTI) atomic_inc(&local->iff_allmultis); if (coming_up) local->open_count++; if (local->open_count == 1) ieee80211_hw_conf_init(local); else if (hw_reconf_flags) ieee80211_hw_config(local, hw_reconf_flags); ieee80211_recalc_ps(local); set_bit(SDATA_STATE_RUNNING, &sdata->state); return 0; err_del_interface: drv_remove_interface(local, sdata); err_stop: if (!local->open_count) drv_stop(local, false); err_del_bss: sdata->bss = NULL; if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) list_del(&sdata->u.vlan.list); /* might already be clear but that doesn't matter */ clear_bit(SDATA_STATE_RUNNING, &sdata->state); return res; } static void ieee80211_if_setup(struct net_device *dev) { ether_setup(dev); dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_NO_QUEUE; dev->netdev_ops = &ieee80211_dataif_ops; dev->needs_free_netdev = true; } static void ieee80211_iface_process_skb(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { struct ieee80211_mgmt *mgmt = (void *)skb->data; lockdep_assert_wiphy(local->hw.wiphy); if (ieee80211_is_action(mgmt->frame_control) && mgmt->u.action.category == WLAN_CATEGORY_BACK) { struct sta_info *sta; int len = skb->len; sta = sta_info_get_bss(sdata, mgmt->sa); if (sta) { switch (mgmt->u.action.u.addba_req.action_code) { case WLAN_ACTION_ADDBA_REQ: ieee80211_process_addba_request(local, sta, mgmt, len); break; case WLAN_ACTION_ADDBA_RESP: ieee80211_process_addba_resp(local, sta, mgmt, len); break; case WLAN_ACTION_DELBA: ieee80211_process_delba(sdata, sta, mgmt, len); break; default: WARN_ON(1); break; } } } else if (ieee80211_is_action(mgmt->frame_control) && mgmt->u.action.category == WLAN_CATEGORY_VHT) { switch (mgmt->u.action.u.vht_group_notif.action_code) { case WLAN_VHT_ACTION_OPMODE_NOTIF: { struct ieee80211_rx_status *status; enum nl80211_band band; struct sta_info *sta; u8 opmode; status = IEEE80211_SKB_RXCB(skb); band = status->band; opmode = mgmt->u.action.u.vht_opmode_notif.operating_mode; sta = sta_info_get_bss(sdata, mgmt->sa); if (sta) ieee80211_vht_handle_opmode(sdata, &sta->deflink, opmode, band); break; } case WLAN_VHT_ACTION_GROUPID_MGMT: ieee80211_process_mu_groups(sdata, &sdata->deflink, mgmt); break; default: WARN_ON(1); break; } } else if (ieee80211_is_action(mgmt->frame_control) && mgmt->u.action.category == WLAN_CATEGORY_S1G) { switch (mgmt->u.action.u.s1g.action_code) { case WLAN_S1G_TWT_TEARDOWN: case WLAN_S1G_TWT_SETUP: ieee80211_s1g_rx_twt_action(sdata, skb); break; default: break; } } else if (ieee80211_is_action(mgmt->frame_control) && mgmt->u.action.category == WLAN_CATEGORY_PROTECTED_EHT) { if (sdata->vif.type == NL80211_IFTYPE_STATION) { switch (mgmt->u.action.u.ttlm_req.action_code) { case WLAN_PROTECTED_EHT_ACTION_TTLM_REQ: ieee80211_process_neg_ttlm_req(sdata, mgmt, skb->len); break; case WLAN_PROTECTED_EHT_ACTION_TTLM_RES: ieee80211_process_neg_ttlm_res(sdata, mgmt, skb->len); break; case WLAN_PROTECTED_EHT_ACTION_TTLM_TEARDOWN: ieee80211_process_ttlm_teardown(sdata); break; case WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_RESP: ieee80211_process_ml_reconf_resp(sdata, mgmt, skb->len); break; case WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_RESP: ieee80211_process_epcs_ena_resp(sdata, mgmt, skb->len); break; case WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_TEARDOWN: ieee80211_process_epcs_teardown(sdata, mgmt, skb->len); break; default: break; } } } else if (ieee80211_is_ext(mgmt->frame_control)) { if (sdata->vif.type == NL80211_IFTYPE_STATION) ieee80211_sta_rx_queued_ext(sdata, skb); else WARN_ON(1); } else if (ieee80211_is_data_qos(mgmt->frame_control)) { struct ieee80211_hdr *hdr = (void *)mgmt; struct sta_info *sta; /* * So the frame isn't mgmt, but frame_control * is at the right place anyway, of course, so * the if statement is correct. * * Warn if we have other data frame types here, * they must not get here. */ WARN_ON(hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_NULLFUNC)); WARN_ON(!(hdr->seq_ctrl & cpu_to_le16(IEEE80211_SCTL_FRAG))); /* * This was a fragment of a frame, received while * a block-ack session was active. That cannot be * right, so terminate the session. */ sta = sta_info_get_bss(sdata, mgmt->sa); if (sta) { u16 tid = ieee80211_get_tid(hdr); __ieee80211_stop_rx_ba_session( sta, tid, WLAN_BACK_RECIPIENT, WLAN_REASON_QSTA_REQUIRE_SETUP, true); } } else switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: ieee80211_sta_rx_queued_mgmt(sdata, skb); break; case NL80211_IFTYPE_ADHOC: ieee80211_ibss_rx_queued_mgmt(sdata, skb); break; case NL80211_IFTYPE_MESH_POINT: if (!ieee80211_vif_is_mesh(&sdata->vif)) break; ieee80211_mesh_rx_queued_mgmt(sdata, skb); break; default: WARN(1, "frame for unexpected interface type"); break; } } static void ieee80211_iface_process_status(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { struct ieee80211_mgmt *mgmt = (void *)skb->data; if (ieee80211_is_action(mgmt->frame_control) && mgmt->u.action.category == WLAN_CATEGORY_S1G) { switch (mgmt->u.action.u.s1g.action_code) { case WLAN_S1G_TWT_TEARDOWN: case WLAN_S1G_TWT_SETUP: ieee80211_s1g_status_twt_action(sdata, skb); break; default: break; } } } static void ieee80211_iface_work(struct wiphy *wiphy, struct wiphy_work *work) { struct ieee80211_sub_if_data *sdata = container_of(work, struct ieee80211_sub_if_data, work); struct ieee80211_local *local = sdata->local; struct sk_buff *skb; if (!ieee80211_sdata_running(sdata)) return; if (test_bit(SCAN_SW_SCANNING, &local->scanning)) return; if (!ieee80211_can_run_worker(local)) return; /* first process frames */ while ((skb = skb_dequeue(&sdata->skb_queue))) { kcov_remote_start_common(skb_get_kcov_handle(skb)); if (skb->protocol == cpu_to_be16(ETH_P_TDLS)) ieee80211_process_tdls_channel_switch(sdata, skb); else ieee80211_iface_process_skb(local, sdata, skb); kfree_skb(skb); kcov_remote_stop(); } /* process status queue */ while ((skb = skb_dequeue(&sdata->status_queue))) { kcov_remote_start_common(skb_get_kcov_handle(skb)); ieee80211_iface_process_status(sdata, skb); kfree_skb(skb); kcov_remote_stop(); } /* then other type-dependent work */ switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: ieee80211_sta_work(sdata); break; case NL80211_IFTYPE_ADHOC: ieee80211_ibss_work(sdata); break; case NL80211_IFTYPE_MESH_POINT: if (!ieee80211_vif_is_mesh(&sdata->vif)) break; ieee80211_mesh_work(sdata); break; case NL80211_IFTYPE_OCB: ieee80211_ocb_work(sdata); break; default: break; } } static void ieee80211_activate_links_work(struct wiphy *wiphy, struct wiphy_work *work) { struct ieee80211_sub_if_data *sdata = container_of(work, struct ieee80211_sub_if_data, activate_links_work); struct ieee80211_local *local = wiphy_priv(wiphy); if (local->in_reconfig) return; ieee80211_set_active_links(&sdata->vif, sdata->desired_active_links); sdata->desired_active_links = 0; } /* * Helper function to initialise an interface to a specific type. */ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata, enum nl80211_iftype type) { static const u8 bssid_wildcard[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; /* clear type-dependent unions */ memset(&sdata->u, 0, sizeof(sdata->u)); memset(&sdata->deflink.u, 0, sizeof(sdata->deflink.u)); /* and set some type-dependent values */ sdata->vif.type = type; sdata->vif.p2p = false; sdata->wdev.iftype = type; sdata->control_port_protocol = cpu_to_be16(ETH_P_PAE); sdata->control_port_no_encrypt = false; sdata->control_port_over_nl80211 = false; sdata->control_port_no_preauth = false; sdata->vif.cfg.idle = true; sdata->vif.bss_conf.txpower = INT_MIN; /* unset */ sdata->noack_map = 0; /* only monitor/p2p-device differ */ if (sdata->dev) { sdata->dev->netdev_ops = &ieee80211_dataif_ops; sdata->dev->type = ARPHRD_ETHER; } skb_queue_head_init(&sdata->skb_queue); skb_queue_head_init(&sdata->status_queue); wiphy_work_init(&sdata->work, ieee80211_iface_work); wiphy_work_init(&sdata->activate_links_work, ieee80211_activate_links_work); switch (type) { case NL80211_IFTYPE_P2P_GO: type = NL80211_IFTYPE_AP; sdata->vif.type = type; sdata->vif.p2p = true; fallthrough; case NL80211_IFTYPE_AP: skb_queue_head_init(&sdata->u.ap.ps.bc_buf); INIT_LIST_HEAD(&sdata->u.ap.vlans); sdata->vif.bss_conf.bssid = sdata->vif.addr; break; case NL80211_IFTYPE_P2P_CLIENT: type = NL80211_IFTYPE_STATION; sdata->vif.type = type; sdata->vif.p2p = true; fallthrough; case NL80211_IFTYPE_STATION: sdata->vif.bss_conf.bssid = sdata->deflink.u.mgd.bssid; ieee80211_sta_setup_sdata(sdata); break; case NL80211_IFTYPE_OCB: sdata->vif.bss_conf.bssid = bssid_wildcard; ieee80211_ocb_setup_sdata(sdata); break; case NL80211_IFTYPE_ADHOC: sdata->vif.bss_conf.bssid = sdata->u.ibss.bssid; ieee80211_ibss_setup_sdata(sdata); break; case NL80211_IFTYPE_MESH_POINT: if (ieee80211_vif_is_mesh(&sdata->vif)) ieee80211_mesh_init_sdata(sdata); break; case NL80211_IFTYPE_MONITOR: sdata->dev->type = ARPHRD_IEEE80211_RADIOTAP; sdata->dev->netdev_ops = &ieee80211_monitorif_ops; sdata->u.mntr.flags = MONITOR_FLAG_CONTROL | MONITOR_FLAG_OTHER_BSS; break; case NL80211_IFTYPE_NAN: idr_init(&sdata->u.nan.function_inst_ids); spin_lock_init(&sdata->u.nan.func_lock); sdata->vif.bss_conf.bssid = sdata->vif.addr; break; case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_P2P_DEVICE: sdata->vif.bss_conf.bssid = sdata->vif.addr; break; case NL80211_IFTYPE_UNSPECIFIED: case NL80211_IFTYPE_WDS: case NUM_NL80211_IFTYPES: WARN_ON(1); break; } /* need to do this after the switch so vif.type is correct */ ieee80211_link_setup(&sdata->deflink); ieee80211_debugfs_recreate_netdev(sdata, false); } static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata, enum nl80211_iftype type) { struct ieee80211_local *local = sdata->local; int ret, err; enum nl80211_iftype internal_type = type; bool p2p = false; ASSERT_RTNL(); if (!local->ops->change_interface) return -EBUSY; /* for now, don't support changing while links exist */ if (ieee80211_vif_is_mld(&sdata->vif)) return -EBUSY; switch (sdata->vif.type) { case NL80211_IFTYPE_AP: if (!list_empty(&sdata->u.ap.vlans)) return -EBUSY; break; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_ADHOC: case NL80211_IFTYPE_OCB: /* * Could maybe also all others here? * Just not sure how that interacts * with the RX/config path e.g. for * mesh. */ break; default: return -EBUSY; } switch (type) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_ADHOC: case NL80211_IFTYPE_OCB: /* * Could probably support everything * but here. */ break; case NL80211_IFTYPE_P2P_CLIENT: p2p = true; internal_type = NL80211_IFTYPE_STATION; break; case NL80211_IFTYPE_P2P_GO: p2p = true; internal_type = NL80211_IFTYPE_AP; break; default: return -EBUSY; } ret = ieee80211_check_concurrent_iface(sdata, internal_type); if (ret) return ret; ieee80211_stop_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_IFTYPE_CHANGE); /* do_stop will synchronize_rcu() first thing */ ieee80211_do_stop(sdata, false); ieee80211_teardown_sdata(sdata); ieee80211_set_sdata_offload_flags(sdata); ret = drv_change_interface(local, sdata, internal_type, p2p); if (ret) type = ieee80211_vif_type_p2p(&sdata->vif); /* * Ignore return value here, there's not much we can do since * the driver changed the interface type internally already. * The warnings will hopefully make driver authors fix it :-) */ ieee80211_check_queues(sdata, type); ieee80211_setup_sdata(sdata, type); ieee80211_set_vif_encap_ops(sdata); err = ieee80211_do_open(&sdata->wdev, false); WARN(err, "type change: do_open returned %d", err); ieee80211_wake_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_IFTYPE_CHANGE); return ret; } int ieee80211_if_change_type(struct ieee80211_sub_if_data *sdata, enum nl80211_iftype type) { int ret; ASSERT_RTNL(); if (type == ieee80211_vif_type_p2p(&sdata->vif)) return 0; if (ieee80211_sdata_running(sdata)) { ret = ieee80211_runtime_change_iftype(sdata, type); if (ret) return ret; } else { /* Purge and reset type-dependent state. */ ieee80211_teardown_sdata(sdata); ieee80211_setup_sdata(sdata, type); } /* reset some values that shouldn't be kept across type changes */ if (type == NL80211_IFTYPE_STATION) sdata->u.mgd.use_4addr = false; return 0; } static void ieee80211_assign_perm_addr(struct ieee80211_local *local, u8 *perm_addr, enum nl80211_iftype type) { struct ieee80211_sub_if_data *sdata; u64 mask, start, addr, val, inc; u8 *m; u8 tmp_addr[ETH_ALEN]; int i; lockdep_assert_wiphy(local->hw.wiphy); /* default ... something at least */ memcpy(perm_addr, local->hw.wiphy->perm_addr, ETH_ALEN); if (is_zero_ether_addr(local->hw.wiphy->addr_mask) && local->hw.wiphy->n_addresses <= 1) return; switch (type) { case NL80211_IFTYPE_MONITOR: /* doesn't matter */ break; case NL80211_IFTYPE_AP_VLAN: /* match up with an AP interface */ list_for_each_entry(sdata, &local->interfaces, list) { if (sdata->vif.type != NL80211_IFTYPE_AP) continue; memcpy(perm_addr, sdata->vif.addr, ETH_ALEN); break; } /* keep default if no AP interface present */ break; case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_P2P_GO: if (ieee80211_hw_check(&local->hw, P2P_DEV_ADDR_FOR_INTF)) { list_for_each_entry(sdata, &local->interfaces, list) { if (sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE) continue; if (!ieee80211_sdata_running(sdata)) continue; memcpy(perm_addr, sdata->vif.addr, ETH_ALEN); return; } } fallthrough; default: /* assign a new address if possible -- try n_addresses first */ for (i = 0; i < local->hw.wiphy->n_addresses; i++) { bool used = false; list_for_each_entry(sdata, &local->interfaces, list) { if (ether_addr_equal(local->hw.wiphy->addresses[i].addr, sdata->vif.addr)) { used = true; break; } } if (!used) { memcpy(perm_addr, local->hw.wiphy->addresses[i].addr, ETH_ALEN); break; } } /* try mask if available */ if (is_zero_ether_addr(local->hw.wiphy->addr_mask)) break; m = local->hw.wiphy->addr_mask; mask = ((u64)m[0] << 5*8) | ((u64)m[1] << 4*8) | ((u64)m[2] << 3*8) | ((u64)m[3] << 2*8) | ((u64)m[4] << 1*8) | ((u64)m[5] << 0*8); if (__ffs64(mask) + hweight64(mask) != fls64(mask)) { /* not a contiguous mask ... not handled now! */ pr_info("not contiguous\n"); break; } /* * Pick address of existing interface in case user changed * MAC address manually, default to perm_addr. */ m = local->hw.wiphy->perm_addr; list_for_each_entry(sdata, &local->interfaces, list) { if (sdata->vif.type == NL80211_IFTYPE_MONITOR) continue; m = sdata->vif.addr; break; } start = ((u64)m[0] << 5*8) | ((u64)m[1] << 4*8) | ((u64)m[2] << 3*8) | ((u64)m[3] << 2*8) | ((u64)m[4] << 1*8) | ((u64)m[5] << 0*8); inc = 1ULL<<__ffs64(mask); val = (start & mask); addr = (start & ~mask) | (val & mask); do { bool used = false; tmp_addr[5] = addr >> 0*8; tmp_addr[4] = addr >> 1*8; tmp_addr[3] = addr >> 2*8; tmp_addr[2] = addr >> 3*8; tmp_addr[1] = addr >> 4*8; tmp_addr[0] = addr >> 5*8; val += inc; list_for_each_entry(sdata, &local->interfaces, list) { if (ether_addr_equal(tmp_addr, sdata->vif.addr)) { used = true; break; } } if (!used) { memcpy(perm_addr, tmp_addr, ETH_ALEN); break; } addr = (start & ~mask) | (val & mask); } while (addr != start); break; } } int ieee80211_if_add(struct ieee80211_local *local, const char *name, unsigned char name_assign_type, struct wireless_dev **new_wdev, enum nl80211_iftype type, struct vif_params *params) { struct net_device *ndev = NULL; struct ieee80211_sub_if_data *sdata = NULL; struct txq_info *txqi; int ret, i; ASSERT_RTNL(); lockdep_assert_wiphy(local->hw.wiphy); if (type == NL80211_IFTYPE_P2P_DEVICE || type == NL80211_IFTYPE_NAN) { struct wireless_dev *wdev; sdata = kzalloc(sizeof(*sdata) + local->hw.vif_data_size, GFP_KERNEL); if (!sdata) return -ENOMEM; wdev = &sdata->wdev; sdata->dev = NULL; strscpy(sdata->name, name, IFNAMSIZ); ieee80211_assign_perm_addr(local, wdev->address, type); memcpy(sdata->vif.addr, wdev->address, ETH_ALEN); ether_addr_copy(sdata->vif.bss_conf.addr, sdata->vif.addr); } else { int size = ALIGN(sizeof(*sdata) + local->hw.vif_data_size, sizeof(void *)); int txq_size = 0; if (type != NL80211_IFTYPE_AP_VLAN && (type != NL80211_IFTYPE_MONITOR || (params->flags & MONITOR_FLAG_ACTIVE))) txq_size += sizeof(struct txq_info) + local->hw.txq_data_size; ndev = alloc_netdev_mqs(size + txq_size, name, name_assign_type, ieee80211_if_setup, 1, 1); if (!ndev) return -ENOMEM; dev_net_set(ndev, wiphy_net(local->hw.wiphy)); ndev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; ndev->needed_headroom = local->tx_headroom + 4*6 /* four MAC addresses */ + 2 + 2 + 2 + 2 /* ctl, dur, seq, qos */ + 6 /* mesh */ + 8 /* rfc1042/bridge tunnel */ - ETH_HLEN /* ethernet hard_header_len */ + IEEE80211_ENCRYPT_HEADROOM; ndev->needed_tailroom = IEEE80211_ENCRYPT_TAILROOM; ret = dev_alloc_name(ndev, ndev->name); if (ret < 0) { free_netdev(ndev); return ret; } ieee80211_assign_perm_addr(local, ndev->perm_addr, type); if (is_valid_ether_addr(params->macaddr)) eth_hw_addr_set(ndev, params->macaddr); else eth_hw_addr_set(ndev, ndev->perm_addr); SET_NETDEV_DEV(ndev, wiphy_dev(local->hw.wiphy)); /* don't use IEEE80211_DEV_TO_SUB_IF -- it checks too much */ sdata = netdev_priv(ndev); ndev->ieee80211_ptr = &sdata->wdev; memcpy(sdata->vif.addr, ndev->dev_addr, ETH_ALEN); ether_addr_copy(sdata->vif.bss_conf.addr, sdata->vif.addr); memcpy(sdata->name, ndev->name, IFNAMSIZ); if (txq_size) { txqi = netdev_priv(ndev) + size; ieee80211_txq_init(sdata, NULL, txqi, 0); } sdata->dev = ndev; } /* initialise type-independent data */ sdata->wdev.wiphy = local->hw.wiphy; ieee80211_sdata_init(local, sdata); ieee80211_init_frag_cache(&sdata->frags); INIT_LIST_HEAD(&sdata->key_list); wiphy_delayed_work_init(&sdata->dec_tailroom_needed_wk, ieee80211_delayed_tailroom_dec); for (i = 0; i < NUM_NL80211_BANDS; i++) { struct ieee80211_supported_band *sband; sband = local->hw.wiphy->bands[i]; sdata->rc_rateidx_mask[i] = sband ? (1 << sband->n_bitrates) - 1 : 0; if (sband) { __le16 cap; u16 *vht_rate_mask; memcpy(sdata->rc_rateidx_mcs_mask[i], sband->ht_cap.mcs.rx_mask, sizeof(sdata->rc_rateidx_mcs_mask[i])); cap = sband->vht_cap.vht_mcs.rx_mcs_map; vht_rate_mask = sdata->rc_rateidx_vht_mcs_mask[i]; ieee80211_get_vht_mask_from_cap(cap, vht_rate_mask); } else { memset(sdata->rc_rateidx_mcs_mask[i], 0, sizeof(sdata->rc_rateidx_mcs_mask[i])); memset(sdata->rc_rateidx_vht_mcs_mask[i], 0, sizeof(sdata->rc_rateidx_vht_mcs_mask[i])); } } ieee80211_set_default_queues(sdata); /* setup type-dependent data */ ieee80211_setup_sdata(sdata, type); if (ndev) { ndev->ieee80211_ptr->use_4addr = params->use_4addr; if (type == NL80211_IFTYPE_STATION) sdata->u.mgd.use_4addr = params->use_4addr; ndev->features |= local->hw.netdev_features; ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ndev->hw_features |= ndev->features & MAC80211_SUPPORTED_FEATURES_TX; sdata->vif.netdev_features = local->hw.netdev_features; netdev_set_default_ethtool_ops(ndev, &ieee80211_ethtool_ops); /* MTU range is normally 256 - 2304, where the upper limit is * the maximum MSDU size. Monitor interfaces send and receive * MPDU and A-MSDU frames which may be much larger so we do * not impose an upper limit in that case. */ ndev->min_mtu = 256; if (type == NL80211_IFTYPE_MONITOR) ndev->max_mtu = 0; else ndev->max_mtu = local->hw.max_mtu; ret = cfg80211_register_netdevice(ndev); if (ret) { free_netdev(ndev); return ret; } } mutex_lock(&local->iflist_mtx); list_add_tail_rcu(&sdata->list, &local->interfaces); mutex_unlock(&local->iflist_mtx); if (new_wdev) *new_wdev = &sdata->wdev; return 0; } void ieee80211_if_remove(struct ieee80211_sub_if_data *sdata) { ASSERT_RTNL(); lockdep_assert_wiphy(sdata->local->hw.wiphy); mutex_lock(&sdata->local->iflist_mtx); list_del_rcu(&sdata->list); mutex_unlock(&sdata->local->iflist_mtx); if (sdata->vif.txq) ieee80211_txq_purge(sdata->local, to_txq_info(sdata->vif.txq)); synchronize_rcu(); cfg80211_unregister_wdev(&sdata->wdev); if (!sdata->dev) { ieee80211_teardown_sdata(sdata); kfree(sdata); } } void ieee80211_sdata_stop(struct ieee80211_sub_if_data *sdata) { if (WARN_ON_ONCE(!test_bit(SDATA_STATE_RUNNING, &sdata->state))) return; ieee80211_do_stop(sdata, true); } void ieee80211_remove_interfaces(struct ieee80211_local *local) { struct ieee80211_sub_if_data *sdata, *tmp; LIST_HEAD(unreg_list); ASSERT_RTNL(); /* Before destroying the interfaces, make sure they're all stopped so * that the hardware is stopped. Otherwise, the driver might still be * iterating the interfaces during the shutdown, e.g. from a worker * or from RX processing or similar, and if it does so (using atomic * iteration) while we're manipulating the list, the iteration will * crash. * * After this, the hardware should be stopped and the driver should * have stopped all of its activities, so that we can do RCU-unaware * manipulations of the interface list below. */ cfg80211_shutdown_all_interfaces(local->hw.wiphy); guard(wiphy)(local->hw.wiphy); WARN(local->open_count, "%s: open count remains %d\n", wiphy_name(local->hw.wiphy), local->open_count); mutex_lock(&local->iflist_mtx); list_splice_init(&local->interfaces, &unreg_list); mutex_unlock(&local->iflist_mtx); list_for_each_entry_safe(sdata, tmp, &unreg_list, list) { bool netdev = sdata->dev; /* * Remove IP addresses explicitly, since the notifier will * skip the callbacks if wdev->registered is false, since * we can't acquire the wiphy_lock() again there if already * inside this locked section. */ sdata->vif.cfg.arp_addr_cnt = 0; if (sdata->vif.type == NL80211_IFTYPE_STATION && sdata->u.mgd.associated) ieee80211_vif_cfg_change_notify(sdata, BSS_CHANGED_ARP_FILTER); list_del(&sdata->list); cfg80211_unregister_wdev(&sdata->wdev); if (!netdev) kfree(sdata); } } static int netdev_notify(struct notifier_block *nb, unsigned long state, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct ieee80211_sub_if_data *sdata; if (state != NETDEV_CHANGENAME) return NOTIFY_DONE; if (!dev->ieee80211_ptr || !dev->ieee80211_ptr->wiphy) return NOTIFY_DONE; if (dev->ieee80211_ptr->wiphy->privid != mac80211_wiphy_privid) return NOTIFY_DONE; sdata = IEEE80211_DEV_TO_SUB_IF(dev); memcpy(sdata->name, dev->name, IFNAMSIZ); ieee80211_debugfs_rename_netdev(sdata); return NOTIFY_OK; } static struct notifier_block mac80211_netdev_notifier = { .notifier_call = netdev_notify, }; int ieee80211_iface_init(void) { return register_netdevice_notifier(&mac80211_netdev_notifier); } void ieee80211_iface_exit(void) { unregister_netdevice_notifier(&mac80211_netdev_notifier); } void ieee80211_vif_inc_num_mcast(struct ieee80211_sub_if_data *sdata) { if (sdata->vif.type == NL80211_IFTYPE_AP) atomic_inc(&sdata->u.ap.num_mcast_sta); else if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) atomic_inc(&sdata->u.vlan.num_mcast_sta); } void ieee80211_vif_dec_num_mcast(struct ieee80211_sub_if_data *sdata) { if (sdata->vif.type == NL80211_IFTYPE_AP) atomic_dec(&sdata->u.ap.num_mcast_sta); else if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) atomic_dec(&sdata->u.vlan.num_mcast_sta); } void ieee80211_vif_block_queues_csa(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; if (ieee80211_hw_check(&local->hw, HANDLES_QUIET_CSA)) return; ieee80211_stop_vif_queues_norefcount(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); } void ieee80211_vif_unblock_queues_csa(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; ieee80211_wake_vif_queues_norefcount(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); } |
| 775 777 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * ACPI device specific properties support. * * Copyright (C) 2014 - 2023, Intel Corporation * All rights reserved. * * Authors: Mika Westerberg <mika.westerberg@linux.intel.com> * Darren Hart <dvhart@linux.intel.com> * Rafael J. Wysocki <rafael.j.wysocki@intel.com> * Sakari Ailus <sakari.ailus@linux.intel.com> */ #define pr_fmt(fmt) "ACPI: " fmt #include <linux/acpi.h> #include <linux/device.h> #include <linux/export.h> #include "internal.h" static int acpi_data_get_property_array(const struct acpi_device_data *data, const char *name, acpi_object_type type, const union acpi_object **obj); /* * The GUIDs here are made equivalent to each other in order to avoid extra * complexity in the properties handling code, with the caveat that the * kernel will accept certain combinations of GUID and properties that are * not defined without a warning. For instance if any of the properties * from different GUID appear in a property list of another, it will be * accepted by the kernel. Firmware validation tools should catch these. * * References: * * [1] UEFI DSD Guide. * https://github.com/UEFI/DSD-Guide/blob/main/src/dsd-guide.adoc */ static const guid_t prp_guids[] = { /* ACPI _DSD device properties GUID [1]: daffd814-6eba-4d8c-8a91-bc9bbf4aa301 */ GUID_INIT(0xdaffd814, 0x6eba, 0x4d8c, 0x8a, 0x91, 0xbc, 0x9b, 0xbf, 0x4a, 0xa3, 0x01), /* Hotplug in D3 GUID: 6211e2c0-58a3-4af3-90e1-927a4e0c55a4 */ GUID_INIT(0x6211e2c0, 0x58a3, 0x4af3, 0x90, 0xe1, 0x92, 0x7a, 0x4e, 0x0c, 0x55, 0xa4), /* External facing port GUID: efcc06cc-73ac-4bc3-bff0-76143807c389 */ GUID_INIT(0xefcc06cc, 0x73ac, 0x4bc3, 0xbf, 0xf0, 0x76, 0x14, 0x38, 0x07, 0xc3, 0x89), /* Thunderbolt GUID for IMR_VALID: c44d002f-69f9-4e7d-a904-a7baabdf43f7 */ GUID_INIT(0xc44d002f, 0x69f9, 0x4e7d, 0xa9, 0x04, 0xa7, 0xba, 0xab, 0xdf, 0x43, 0xf7), /* Thunderbolt GUID for WAKE_SUPPORTED: 6c501103-c189-4296-ba72-9bf5a26ebe5d */ GUID_INIT(0x6c501103, 0xc189, 0x4296, 0xba, 0x72, 0x9b, 0xf5, 0xa2, 0x6e, 0xbe, 0x5d), /* Storage device needs D3 GUID: 5025030f-842f-4ab4-a561-99a5189762d0 */ GUID_INIT(0x5025030f, 0x842f, 0x4ab4, 0xa5, 0x61, 0x99, 0xa5, 0x18, 0x97, 0x62, 0xd0), }; /* ACPI _DSD data subnodes GUID [1]: dbb8e3e6-5886-4ba6-8795-1319f52a966b */ static const guid_t ads_guid = GUID_INIT(0xdbb8e3e6, 0x5886, 0x4ba6, 0x87, 0x95, 0x13, 0x19, 0xf5, 0x2a, 0x96, 0x6b); /* ACPI _DSD data buffer GUID [1]: edb12dd0-363d-4085-a3d2-49522ca160c4 */ static const guid_t buffer_prop_guid = GUID_INIT(0xedb12dd0, 0x363d, 0x4085, 0xa3, 0xd2, 0x49, 0x52, 0x2c, 0xa1, 0x60, 0xc4); static bool acpi_enumerate_nondev_subnodes(acpi_handle scope, union acpi_object *desc, struct acpi_device_data *data, struct fwnode_handle *parent); static bool acpi_extract_properties(acpi_handle handle, union acpi_object *desc, struct acpi_device_data *data); static bool acpi_nondev_subnode_extract(union acpi_object *desc, acpi_handle handle, const union acpi_object *link, struct list_head *list, struct fwnode_handle *parent) { struct acpi_data_node *dn; bool result; if (acpi_graph_ignore_port(handle)) return false; dn = kzalloc(sizeof(*dn), GFP_KERNEL); if (!dn) return false; dn->name = link->package.elements[0].string.pointer; fwnode_init(&dn->fwnode, &acpi_data_fwnode_ops); dn->parent = parent; INIT_LIST_HEAD(&dn->data.properties); INIT_LIST_HEAD(&dn->data.subnodes); result = acpi_extract_properties(handle, desc, &dn->data); if (handle) { acpi_handle scope; acpi_status status; /* * The scope for the subnode object lookup is the one of the * namespace node (device) containing the object that has * returned the package. That is, it's the scope of that * object's parent. */ status = acpi_get_parent(handle, &scope); if (ACPI_SUCCESS(status) && acpi_enumerate_nondev_subnodes(scope, desc, &dn->data, &dn->fwnode)) result = true; } else if (acpi_enumerate_nondev_subnodes(NULL, desc, &dn->data, &dn->fwnode)) { result = true; } if (result) { dn->handle = handle; dn->data.pointer = desc; list_add_tail(&dn->sibling, list); return true; } kfree(dn); acpi_handle_debug(handle, "Invalid properties/subnodes data, skipping\n"); return false; } static bool acpi_nondev_subnode_data_ok(acpi_handle handle, const union acpi_object *link, struct list_head *list, struct fwnode_handle *parent) { struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER }; acpi_status status; status = acpi_evaluate_object_typed(handle, NULL, NULL, &buf, ACPI_TYPE_PACKAGE); if (ACPI_FAILURE(status)) return false; if (acpi_nondev_subnode_extract(buf.pointer, handle, link, list, parent)) return true; ACPI_FREE(buf.pointer); return false; } static bool acpi_nondev_subnode_ok(acpi_handle scope, const union acpi_object *link, struct list_head *list, struct fwnode_handle *parent) { acpi_handle handle; acpi_status status; if (!scope) return false; status = acpi_get_handle(scope, link->package.elements[1].string.pointer, &handle); if (ACPI_FAILURE(status)) return false; return acpi_nondev_subnode_data_ok(handle, link, list, parent); } static bool acpi_add_nondev_subnodes(acpi_handle scope, union acpi_object *links, struct list_head *list, struct fwnode_handle *parent) { bool ret = false; int i; for (i = 0; i < links->package.count; i++) { union acpi_object *link, *desc; acpi_handle handle; bool result; link = &links->package.elements[i]; /* Only two elements allowed. */ if (link->package.count != 2) continue; /* The first one must be a string. */ if (link->package.elements[0].type != ACPI_TYPE_STRING) continue; /* The second one may be a string, a reference or a package. */ switch (link->package.elements[1].type) { case ACPI_TYPE_STRING: result = acpi_nondev_subnode_ok(scope, link, list, parent); break; case ACPI_TYPE_LOCAL_REFERENCE: handle = link->package.elements[1].reference.handle; result = acpi_nondev_subnode_data_ok(handle, link, list, parent); break; case ACPI_TYPE_PACKAGE: desc = &link->package.elements[1]; result = acpi_nondev_subnode_extract(desc, NULL, link, list, parent); break; default: result = false; break; } ret = ret || result; } return ret; } static bool acpi_enumerate_nondev_subnodes(acpi_handle scope, union acpi_object *desc, struct acpi_device_data *data, struct fwnode_handle *parent) { int i; /* Look for the ACPI data subnodes GUID. */ for (i = 0; i < desc->package.count; i += 2) { const union acpi_object *guid; union acpi_object *links; guid = &desc->package.elements[i]; links = &desc->package.elements[i + 1]; /* * The first element must be a GUID and the second one must be * a package. */ if (guid->type != ACPI_TYPE_BUFFER || guid->buffer.length != 16 || links->type != ACPI_TYPE_PACKAGE) break; if (!guid_equal((guid_t *)guid->buffer.pointer, &ads_guid)) continue; return acpi_add_nondev_subnodes(scope, links, &data->subnodes, parent); } return false; } static bool acpi_property_value_ok(const union acpi_object *value) { int j; /* * The value must be an integer, a string, a reference, or a package * whose every element must be an integer, a string, or a reference. */ switch (value->type) { case ACPI_TYPE_INTEGER: case ACPI_TYPE_STRING: case ACPI_TYPE_LOCAL_REFERENCE: return true; case ACPI_TYPE_PACKAGE: for (j = 0; j < value->package.count; j++) switch (value->package.elements[j].type) { case ACPI_TYPE_INTEGER: case ACPI_TYPE_STRING: case ACPI_TYPE_LOCAL_REFERENCE: continue; default: return false; } return true; } return false; } static bool acpi_properties_format_valid(const union acpi_object *properties) { int i; for (i = 0; i < properties->package.count; i++) { const union acpi_object *property; property = &properties->package.elements[i]; /* * Only two elements allowed, the first one must be a string and * the second one has to satisfy certain conditions. */ if (property->package.count != 2 || property->package.elements[0].type != ACPI_TYPE_STRING || !acpi_property_value_ok(&property->package.elements[1])) return false; } return true; } static void acpi_init_of_compatible(struct acpi_device *adev) { const union acpi_object *of_compatible; int ret; ret = acpi_data_get_property_array(&adev->data, "compatible", ACPI_TYPE_STRING, &of_compatible); if (ret) { ret = acpi_dev_get_property(adev, "compatible", ACPI_TYPE_STRING, &of_compatible); if (ret) { struct acpi_device *parent; parent = acpi_dev_parent(adev); if (parent && parent->flags.of_compatible_ok) goto out; return; } } adev->data.of_compatible = of_compatible; out: adev->flags.of_compatible_ok = 1; } static bool acpi_is_property_guid(const guid_t *guid) { int i; for (i = 0; i < ARRAY_SIZE(prp_guids); i++) { if (guid_equal(guid, &prp_guids[i])) return true; } return false; } struct acpi_device_properties * acpi_data_add_props(struct acpi_device_data *data, const guid_t *guid, union acpi_object *properties) { struct acpi_device_properties *props; props = kzalloc(sizeof(*props), GFP_KERNEL); if (props) { INIT_LIST_HEAD(&props->list); props->guid = guid; props->properties = properties; list_add_tail(&props->list, &data->properties); } return props; } static void acpi_nondev_subnode_tag(acpi_handle handle, void *context) { } static void acpi_untie_nondev_subnodes(struct acpi_device_data *data) { struct acpi_data_node *dn; list_for_each_entry(dn, &data->subnodes, sibling) { acpi_detach_data(dn->handle, acpi_nondev_subnode_tag); acpi_untie_nondev_subnodes(&dn->data); } } static bool acpi_tie_nondev_subnodes(struct acpi_device_data *data) { struct acpi_data_node *dn; list_for_each_entry(dn, &data->subnodes, sibling) { acpi_status status; bool ret; status = acpi_attach_data(dn->handle, acpi_nondev_subnode_tag, dn); if (ACPI_FAILURE(status) && status != AE_ALREADY_EXISTS) { acpi_handle_err(dn->handle, "Can't tag data node\n"); return false; } ret = acpi_tie_nondev_subnodes(&dn->data); if (!ret) return ret; } return true; } static void acpi_data_add_buffer_props(acpi_handle handle, struct acpi_device_data *data, union acpi_object *properties) { struct acpi_device_properties *props; union acpi_object *package; size_t alloc_size; unsigned int i; u32 *count; if (check_mul_overflow((size_t)properties->package.count, sizeof(*package) + sizeof(void *), &alloc_size) || check_add_overflow(sizeof(*props) + sizeof(*package), alloc_size, &alloc_size)) { acpi_handle_warn(handle, "can't allocate memory for %u buffer props", properties->package.count); return; } props = kvzalloc(alloc_size, GFP_KERNEL); if (!props) return; props->guid = &buffer_prop_guid; props->bufs = (void *)(props + 1); props->properties = (void *)(props->bufs + properties->package.count); /* Outer package */ package = props->properties; package->type = ACPI_TYPE_PACKAGE; package->package.elements = package + 1; count = &package->package.count; *count = 0; /* Inner packages */ package++; for (i = 0; i < properties->package.count; i++) { struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER }; union acpi_object *property = &properties->package.elements[i]; union acpi_object *prop, *obj, *buf_obj; acpi_status status; if (property->type != ACPI_TYPE_PACKAGE || property->package.count != 2) { acpi_handle_warn(handle, "buffer property %u has %u entries\n", i, property->package.count); continue; } prop = &property->package.elements[0]; obj = &property->package.elements[1]; if (prop->type != ACPI_TYPE_STRING || obj->type != ACPI_TYPE_STRING) { acpi_handle_warn(handle, "wrong object types %u and %u\n", prop->type, obj->type); continue; } status = acpi_evaluate_object_typed(handle, obj->string.pointer, NULL, &buf, ACPI_TYPE_BUFFER); if (ACPI_FAILURE(status)) { acpi_handle_warn(handle, "can't evaluate \"%*pE\" as buffer\n", obj->string.length, obj->string.pointer); continue; } package->type = ACPI_TYPE_PACKAGE; package->package.elements = prop; package->package.count = 2; buf_obj = buf.pointer; /* Replace the string object with a buffer object */ obj->type = ACPI_TYPE_BUFFER; obj->buffer.length = buf_obj->buffer.length; obj->buffer.pointer = buf_obj->buffer.pointer; props->bufs[i] = buf.pointer; package++; (*count)++; } if (*count) list_add(&props->list, &data->properties); else kvfree(props); } static bool acpi_extract_properties(acpi_handle scope, union acpi_object *desc, struct acpi_device_data *data) { int i; if (desc->package.count % 2) return false; /* Look for the device properties GUID. */ for (i = 0; i < desc->package.count; i += 2) { const union acpi_object *guid; union acpi_object *properties; guid = &desc->package.elements[i]; properties = &desc->package.elements[i + 1]; /* * The first element must be a GUID and the second one must be * a package. */ if (guid->type != ACPI_TYPE_BUFFER || guid->buffer.length != 16 || properties->type != ACPI_TYPE_PACKAGE) break; if (guid_equal((guid_t *)guid->buffer.pointer, &buffer_prop_guid)) { acpi_data_add_buffer_props(scope, data, properties); continue; } if (!acpi_is_property_guid((guid_t *)guid->buffer.pointer)) continue; /* * We found the matching GUID. Now validate the format of the * package immediately following it. */ if (!acpi_properties_format_valid(properties)) continue; acpi_data_add_props(data, (const guid_t *)guid->buffer.pointer, properties); } return !list_empty(&data->properties); } void acpi_init_properties(struct acpi_device *adev) { struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER }; struct acpi_hardware_id *hwid; acpi_status status; bool acpi_of = false; INIT_LIST_HEAD(&adev->data.properties); INIT_LIST_HEAD(&adev->data.subnodes); if (!adev->handle) return; /* * Check if ACPI_DT_NAMESPACE_HID is present and inthat case we fill in * Device Tree compatible properties for this device. */ list_for_each_entry(hwid, &adev->pnp.ids, list) { if (!strcmp(hwid->id, ACPI_DT_NAMESPACE_HID)) { acpi_of = true; break; } } status = acpi_evaluate_object_typed(adev->handle, "_DSD", NULL, &buf, ACPI_TYPE_PACKAGE); if (ACPI_FAILURE(status)) goto out; if (acpi_extract_properties(adev->handle, buf.pointer, &adev->data)) { adev->data.pointer = buf.pointer; if (acpi_of) acpi_init_of_compatible(adev); } if (acpi_enumerate_nondev_subnodes(adev->handle, buf.pointer, &adev->data, acpi_fwnode_handle(adev))) adev->data.pointer = buf.pointer; if (!adev->data.pointer) { acpi_handle_debug(adev->handle, "Invalid _DSD data, skipping\n"); ACPI_FREE(buf.pointer); } else { if (!acpi_tie_nondev_subnodes(&adev->data)) acpi_untie_nondev_subnodes(&adev->data); } out: if (acpi_of && !adev->flags.of_compatible_ok) acpi_handle_info(adev->handle, ACPI_DT_NAMESPACE_HID " requires 'compatible' property\n"); if (!adev->data.pointer) acpi_extract_apple_properties(adev); } static void acpi_free_device_properties(struct list_head *list) { struct acpi_device_properties *props, *tmp; list_for_each_entry_safe(props, tmp, list, list) { u32 i; list_del(&props->list); /* Buffer data properties were separately allocated */ if (props->bufs) for (i = 0; i < props->properties->package.count; i++) ACPI_FREE(props->bufs[i]); kvfree(props); } } static void acpi_destroy_nondev_subnodes(struct list_head *list) { struct acpi_data_node *dn, *next; if (list_empty(list)) return; list_for_each_entry_safe_reverse(dn, next, list, sibling) { acpi_destroy_nondev_subnodes(&dn->data.subnodes); wait_for_completion(&dn->kobj_done); list_del(&dn->sibling); ACPI_FREE((void *)dn->data.pointer); acpi_free_device_properties(&dn->data.properties); kfree(dn); } } void acpi_free_properties(struct acpi_device *adev) { acpi_untie_nondev_subnodes(&adev->data); acpi_destroy_nondev_subnodes(&adev->data.subnodes); ACPI_FREE((void *)adev->data.pointer); adev->data.of_compatible = NULL; adev->data.pointer = NULL; acpi_free_device_properties(&adev->data.properties); } /** * acpi_data_get_property - return an ACPI property with given name * @data: ACPI device deta object to get the property from * @name: Name of the property * @type: Expected property type * @obj: Location to store the property value (if not %NULL) * * Look up a property with @name and store a pointer to the resulting ACPI * object at the location pointed to by @obj if found. * * Callers must not attempt to free the returned objects. These objects will be * freed by the ACPI core automatically during the removal of @data. * * Return: %0 if property with @name has been found (success), * %-EINVAL if the arguments are invalid, * %-EINVAL if the property doesn't exist, * %-EPROTO if the property value type doesn't match @type. */ static int acpi_data_get_property(const struct acpi_device_data *data, const char *name, acpi_object_type type, const union acpi_object **obj) { const struct acpi_device_properties *props; if (!data || !name) return -EINVAL; if (!data->pointer || list_empty(&data->properties)) return -EINVAL; list_for_each_entry(props, &data->properties, list) { const union acpi_object *properties; unsigned int i; properties = props->properties; for (i = 0; i < properties->package.count; i++) { const union acpi_object *propname, *propvalue; const union acpi_object *property; property = &properties->package.elements[i]; propname = &property->package.elements[0]; propvalue = &property->package.elements[1]; if (!strcmp(name, propname->string.pointer)) { if (type != ACPI_TYPE_ANY && propvalue->type != type) return -EPROTO; if (obj) *obj = propvalue; return 0; } } } return -EINVAL; } /** * acpi_dev_get_property - return an ACPI property with given name. * @adev: ACPI device to get the property from. * @name: Name of the property. * @type: Expected property type. * @obj: Location to store the property value (if not %NULL). */ int acpi_dev_get_property(const struct acpi_device *adev, const char *name, acpi_object_type type, const union acpi_object **obj) { return adev ? acpi_data_get_property(&adev->data, name, type, obj) : -EINVAL; } EXPORT_SYMBOL_GPL(acpi_dev_get_property); static const struct acpi_device_data * acpi_device_data_of_node(const struct fwnode_handle *fwnode) { if (is_acpi_device_node(fwnode)) { const struct acpi_device *adev = to_acpi_device_node(fwnode); return &adev->data; } if (is_acpi_data_node(fwnode)) { const struct acpi_data_node *dn = to_acpi_data_node(fwnode); return &dn->data; } return NULL; } /** * acpi_node_prop_get - return an ACPI property with given name. * @fwnode: Firmware node to get the property from. * @propname: Name of the property. * @valptr: Location to store a pointer to the property value (if not %NULL). */ int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr) { return acpi_data_get_property(acpi_device_data_of_node(fwnode), propname, ACPI_TYPE_ANY, (const union acpi_object **)valptr); } /** * acpi_data_get_property_array - return an ACPI array property with given name * @data: ACPI data object to get the property from * @name: Name of the property * @type: Expected type of array elements * @obj: Location to store a pointer to the property value (if not NULL) * * Look up an array property with @name and store a pointer to the resulting * ACPI object at the location pointed to by @obj if found. * * Callers must not attempt to free the returned objects. Those objects will be * freed by the ACPI core automatically during the removal of @data. * * Return: %0 if array property (package) with @name has been found (success), * %-EINVAL if the arguments are invalid, * %-EINVAL if the property doesn't exist, * %-EPROTO if the property is not a package or the type of its elements * doesn't match @type. */ static int acpi_data_get_property_array(const struct acpi_device_data *data, const char *name, acpi_object_type type, const union acpi_object **obj) { const union acpi_object *prop; int ret, i; ret = acpi_data_get_property(data, name, ACPI_TYPE_PACKAGE, &prop); if (ret) return ret; if (type != ACPI_TYPE_ANY) { /* Check that all elements are of correct type. */ for (i = 0; i < prop->package.count; i++) if (prop->package.elements[i].type != type) return -EPROTO; } if (obj) *obj = prop; return 0; } static struct fwnode_handle * acpi_fwnode_get_named_child_node(const struct fwnode_handle *fwnode, const char *childname) { struct fwnode_handle *child; fwnode_for_each_child_node(fwnode, child) { if (is_acpi_data_node(child)) { if (acpi_data_node_match(child, childname)) return child; continue; } if (!strncmp(acpi_device_bid(to_acpi_device_node(child)), childname, ACPI_NAMESEG_SIZE)) return child; } return NULL; } static int acpi_get_ref_args(struct fwnode_reference_args *args, struct fwnode_handle *ref_fwnode, const union acpi_object **element, const union acpi_object *end, size_t num_args) { u32 nargs = 0, i; /* * Assume the following integer elements are all args. Stop counting on * the first reference (possibly represented as a string) or end of the * package arguments. In case of neither reference, nor integer, return * an error, we can't parse it. */ for (i = 0; (*element) + i < end && i < num_args; i++) { acpi_object_type type = (*element)[i].type; if (type == ACPI_TYPE_LOCAL_REFERENCE || type == ACPI_TYPE_STRING) break; if (type == ACPI_TYPE_INTEGER) nargs++; else return -EINVAL; } if (nargs > NR_FWNODE_REFERENCE_ARGS) return -EINVAL; if (args) { args->fwnode = ref_fwnode; args->nargs = nargs; for (i = 0; i < nargs; i++) args->args[i] = (*element)[i].integer.value; } (*element) += nargs; return 0; } static struct fwnode_handle *acpi_parse_string_ref(const struct fwnode_handle *fwnode, const char *refstring) { acpi_handle scope, handle; struct acpi_data_node *dn; struct acpi_device *device; acpi_status status; if (is_acpi_device_node(fwnode)) { scope = to_acpi_device_node(fwnode)->handle; } else if (is_acpi_data_node(fwnode)) { scope = to_acpi_data_node(fwnode)->handle; } else { pr_debug("Bad node type for node %pfw\n", fwnode); return NULL; } status = acpi_get_handle(scope, refstring, &handle); if (ACPI_FAILURE(status)) { acpi_handle_debug(scope, "Unable to get an ACPI handle for %s\n", refstring); return NULL; } device = acpi_fetch_acpi_dev(handle); if (device) return acpi_fwnode_handle(device); status = acpi_get_data_full(handle, acpi_nondev_subnode_tag, (void **)&dn, NULL); if (ACPI_FAILURE(status) || !dn) { acpi_handle_debug(handle, "Subnode not found\n"); return NULL; } return &dn->fwnode; } /** * __acpi_node_get_property_reference - returns handle to the referenced object * @fwnode: Firmware node to get the property from * @propname: Name of the property * @index: Index of the reference to return * @num_args: Maximum number of arguments after each reference * @args: Location to store the returned reference with optional arguments * (may be NULL) * * Find property with @name, verifify that it is a package containing at least * one object reference and if so, store the ACPI device object pointer to the * target object in @args->adev. If the reference includes arguments, store * them in the @args->args[] array. * * If there's more than one reference in the property value package, @index is * used to select the one to return. * * It is possible to leave holes in the property value set like in the * example below: * * Package () { * "cs-gpios", * Package () { * ^GPIO, 19, 0, 0, * ^GPIO, 20, 0, 0, * 0, * ^GPIO, 21, 0, 0, * } * } * * Calling this function with index %2 or index %3 return %-ENOENT. If the * property does not contain any more values %-ENOENT is returned. The NULL * entry must be single integer and preferably contain value %0. * * Return: %0 on success, negative error code on failure. */ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *propname, size_t index, size_t num_args, struct fwnode_reference_args *args) { const union acpi_object *element, *end; const union acpi_object *obj; const struct acpi_device_data *data; struct fwnode_handle *ref_fwnode; struct acpi_device *device; int ret, idx = 0; data = acpi_device_data_of_node(fwnode); if (!data) return -ENOENT; ret = acpi_data_get_property(data, propname, ACPI_TYPE_ANY, &obj); if (ret) return ret == -EINVAL ? -ENOENT : -EINVAL; switch (obj->type) { case ACPI_TYPE_LOCAL_REFERENCE: /* Plain single reference without arguments. */ if (index) return -ENOENT; device = acpi_fetch_acpi_dev(obj->reference.handle); if (!device) return -EINVAL; if (!args) return 0; args->fwnode = acpi_fwnode_handle(device); args->nargs = 0; return 0; case ACPI_TYPE_STRING: if (index) return -ENOENT; ref_fwnode = acpi_parse_string_ref(fwnode, obj->string.pointer); if (!ref_fwnode) return -EINVAL; args->fwnode = ref_fwnode; args->nargs = 0; return 0; case ACPI_TYPE_PACKAGE: /* * If it is not a single reference, then it is a package of * references, followed by number of ints as follows: * * Package () { REF, INT, REF, INT, INT } * * Here, REF may be either a local reference or a string. The * index argument is then used to determine which reference the * caller wants (along with the arguments). */ break; default: return -EINVAL; } if (index >= obj->package.count) return -ENOENT; element = obj->package.elements; end = element + obj->package.count; while (element < end) { switch (element->type) { case ACPI_TYPE_LOCAL_REFERENCE: device = acpi_fetch_acpi_dev(element->reference.handle); if (!device) return -EINVAL; element++; ret = acpi_get_ref_args(idx == index ? args : NULL, acpi_fwnode_handle(device), &element, end, num_args); if (ret < 0) return ret; if (idx == index) return 0; break; case ACPI_TYPE_STRING: ref_fwnode = acpi_parse_string_ref(fwnode, element->string.pointer); if (!ref_fwnode) return -EINVAL; element++; ret = acpi_get_ref_args(idx == index ? args : NULL, ref_fwnode, &element, end, num_args); if (ret < 0) return ret; if (idx == index) return 0; break; case ACPI_TYPE_INTEGER: if (idx == index) return -ENOENT; element++; break; default: return -EINVAL; } idx++; } return -ENOENT; } EXPORT_SYMBOL_GPL(__acpi_node_get_property_reference); static int acpi_data_prop_read_single(const struct acpi_device_data *data, const char *propname, enum dev_prop_type proptype, void *val) { const union acpi_object *obj; int ret = 0; if (proptype >= DEV_PROP_U8 && proptype <= DEV_PROP_U64) ret = acpi_data_get_property(data, propname, ACPI_TYPE_INTEGER, &obj); else if (proptype == DEV_PROP_STRING) ret = acpi_data_get_property(data, propname, ACPI_TYPE_STRING, &obj); if (ret) return ret; switch (proptype) { case DEV_PROP_U8: if (obj->integer.value > U8_MAX) return -EOVERFLOW; if (val) *(u8 *)val = obj->integer.value; break; case DEV_PROP_U16: if (obj->integer.value > U16_MAX) return -EOVERFLOW; if (val) *(u16 *)val = obj->integer.value; break; case DEV_PROP_U32: if (obj->integer.value > U32_MAX) return -EOVERFLOW; if (val) *(u32 *)val = obj->integer.value; break; case DEV_PROP_U64: if (val) *(u64 *)val = obj->integer.value; break; case DEV_PROP_STRING: if (val) *(char **)val = obj->string.pointer; return 1; default: return -EINVAL; } /* When no storage provided return number of available values */ return val ? 0 : 1; } #define acpi_copy_property_array_uint(items, val, nval) \ ({ \ typeof(items) __items = items; \ typeof(val) __val = val; \ typeof(nval) __nval = nval; \ size_t i; \ int ret = 0; \ \ for (i = 0; i < __nval; i++) { \ if (__items->type == ACPI_TYPE_BUFFER) { \ __val[i] = __items->buffer.pointer[i]; \ continue; \ } \ if (__items[i].type != ACPI_TYPE_INTEGER) { \ ret = -EPROTO; \ break; \ } \ if (__items[i].integer.value > _Generic(__val, \ u8 *: U8_MAX, \ u16 *: U16_MAX, \ u32 *: U32_MAX, \ u64 *: U64_MAX)) { \ ret = -EOVERFLOW; \ break; \ } \ \ __val[i] = __items[i].integer.value; \ } \ ret; \ }) static int acpi_copy_property_array_string(const union acpi_object *items, char **val, size_t nval) { int i; for (i = 0; i < nval; i++) { if (items[i].type != ACPI_TYPE_STRING) return -EPROTO; val[i] = items[i].string.pointer; } return nval; } static int acpi_data_prop_read(const struct acpi_device_data *data, const char *propname, enum dev_prop_type proptype, void *val, size_t nval) { const union acpi_object *obj; const union acpi_object *items; int ret; if (nval == 1 || !val) { ret = acpi_data_prop_read_single(data, propname, proptype, val); /* * The overflow error means that the property is there and it is * single-value, but its type does not match, so return. */ if (ret >= 0 || ret == -EOVERFLOW) return ret; /* * Reading this property as a single-value one failed, but its * value may still be represented as one-element array, so * continue. */ } ret = acpi_data_get_property_array(data, propname, ACPI_TYPE_ANY, &obj); if (ret && proptype >= DEV_PROP_U8 && proptype <= DEV_PROP_U64) ret = acpi_data_get_property(data, propname, ACPI_TYPE_BUFFER, &obj); if (ret) return ret; if (!val) { if (obj->type == ACPI_TYPE_BUFFER) return obj->buffer.length; return obj->package.count; } switch (proptype) { case DEV_PROP_STRING: break; default: if (obj->type == ACPI_TYPE_BUFFER) { if (nval > obj->buffer.length) return -EOVERFLOW; } else { if (nval > obj->package.count) return -EOVERFLOW; } break; } if (obj->type == ACPI_TYPE_BUFFER) { if (proptype != DEV_PROP_U8) return -EPROTO; items = obj; } else { items = obj->package.elements; } switch (proptype) { case DEV_PROP_U8: ret = acpi_copy_property_array_uint(items, (u8 *)val, nval); break; case DEV_PROP_U16: ret = acpi_copy_property_array_uint(items, (u16 *)val, nval); break; case DEV_PROP_U32: ret = acpi_copy_property_array_uint(items, (u32 *)val, nval); break; case DEV_PROP_U64: ret = acpi_copy_property_array_uint(items, (u64 *)val, nval); break; case DEV_PROP_STRING: nval = min_t(u32, nval, obj->package.count); if (nval == 0) return -ENODATA; ret = acpi_copy_property_array_string(items, (char **)val, nval); break; default: ret = -EINVAL; break; } return ret; } /** * acpi_node_prop_read - retrieve the value of an ACPI property with given name. * @fwnode: Firmware node to get the property from. * @propname: Name of the property. * @proptype: Expected property type. * @val: Location to store the property value (if not %NULL). * @nval: Size of the array pointed to by @val. * * If @val is %NULL, return the number of array elements comprising the value * of the property. Otherwise, read at most @nval values to the array at the * location pointed to by @val. */ static int acpi_node_prop_read(const struct fwnode_handle *fwnode, const char *propname, enum dev_prop_type proptype, void *val, size_t nval) { return acpi_data_prop_read(acpi_device_data_of_node(fwnode), propname, proptype, val, nval); } static int stop_on_next(struct acpi_device *adev, void *data) { struct acpi_device **ret_p = data; if (!*ret_p) { *ret_p = adev; return 1; } /* Skip until the "previous" object is found. */ if (*ret_p == adev) *ret_p = NULL; return 0; } /** * acpi_get_next_subnode - Return the next child node handle for a fwnode * @fwnode: Firmware node to find the next child node for. * @child: Handle to one of the device's child nodes or a null handle. */ struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode, struct fwnode_handle *child) { struct acpi_device *adev = to_acpi_device_node(fwnode); if ((!child || is_acpi_device_node(child)) && adev) { struct acpi_device *child_adev = to_acpi_device_node(child); acpi_dev_for_each_child(adev, stop_on_next, &child_adev); if (child_adev) return acpi_fwnode_handle(child_adev); child = NULL; } if (!child || is_acpi_data_node(child)) { const struct acpi_data_node *data = to_acpi_data_node(fwnode); const struct list_head *head; struct list_head *next; struct acpi_data_node *dn; /* * We can have a combination of device and data nodes, e.g. with * hierarchical _DSD properties. Make sure the adev pointer is * restored before going through data nodes, otherwise we will * be looking for data_nodes below the last device found instead * of the common fwnode shared by device_nodes and data_nodes. */ adev = to_acpi_device_node(fwnode); if (adev) head = &adev->data.subnodes; else if (data) head = &data->data.subnodes; else return NULL; if (list_empty(head)) return NULL; if (child) { dn = to_acpi_data_node(child); next = dn->sibling.next; if (next == head) return NULL; dn = list_entry(next, struct acpi_data_node, sibling); } else { dn = list_first_entry(head, struct acpi_data_node, sibling); } return &dn->fwnode; } return NULL; } /** * acpi_node_get_parent - Return parent fwnode of this fwnode * @fwnode: Firmware node whose parent to get * * Returns parent node of an ACPI device or data firmware node or %NULL if * not available. */ static struct fwnode_handle * acpi_node_get_parent(const struct fwnode_handle *fwnode) { if (is_acpi_data_node(fwnode)) { /* All data nodes have parent pointer so just return that */ return to_acpi_data_node(fwnode)->parent; } if (is_acpi_device_node(fwnode)) { struct acpi_device *parent; parent = acpi_dev_parent(to_acpi_device_node(fwnode)); if (parent) return acpi_fwnode_handle(parent); } return NULL; } /* * Return true if the node is an ACPI graph node. Called on either ports * or endpoints. */ static bool is_acpi_graph_node(struct fwnode_handle *fwnode, const char *str) { unsigned int len = strlen(str); const char *name; if (!len || !is_acpi_data_node(fwnode)) return false; name = to_acpi_data_node(fwnode)->name; return (fwnode_property_present(fwnode, "reg") && !strncmp(name, str, len) && name[len] == '@') || fwnode_property_present(fwnode, str); } /** * acpi_graph_get_next_endpoint - Get next endpoint ACPI firmware node * @fwnode: Pointer to the parent firmware node * @prev: Previous endpoint node or %NULL to get the first * * Looks up next endpoint ACPI firmware node below a given @fwnode. Returns * %NULL if there is no next endpoint or in case of error. In case of success * the next endpoint is returned. */ static struct fwnode_handle *acpi_graph_get_next_endpoint( const struct fwnode_handle *fwnode, struct fwnode_handle *prev) { struct fwnode_handle *port = NULL; struct fwnode_handle *endpoint; if (!prev) { do { port = fwnode_get_next_child_node(fwnode, port); /* * The names of the port nodes begin with "port@" * followed by the number of the port node and they also * have a "reg" property that also has the number of the * port node. For compatibility reasons a node is also * recognised as a port node from the "port" property. */ if (is_acpi_graph_node(port, "port")) break; } while (port); } else { port = fwnode_get_parent(prev); } if (!port) return NULL; endpoint = fwnode_get_next_child_node(port, prev); while (!endpoint) { port = fwnode_get_next_child_node(fwnode, port); if (!port) break; if (is_acpi_graph_node(port, "port")) endpoint = fwnode_get_next_child_node(port, NULL); } /* * The names of the endpoint nodes begin with "endpoint@" followed by * the number of the endpoint node and they also have a "reg" property * that also has the number of the endpoint node. For compatibility * reasons a node is also recognised as an endpoint node from the * "endpoint" property. */ if (!is_acpi_graph_node(endpoint, "endpoint")) return NULL; return endpoint; } /** * acpi_graph_get_child_prop_value - Return a child with a given property value * @fwnode: device fwnode * @prop_name: The name of the property to look for * @val: the desired property value * * Return the port node corresponding to a given port number. Returns * the child node on success, NULL otherwise. */ static struct fwnode_handle *acpi_graph_get_child_prop_value( const struct fwnode_handle *fwnode, const char *prop_name, unsigned int val) { struct fwnode_handle *child; fwnode_for_each_child_node(fwnode, child) { u32 nr; if (fwnode_property_read_u32(child, prop_name, &nr)) continue; if (val == nr) return child; } return NULL; } /** * acpi_graph_get_remote_endpoint - Parses and returns remote end of an endpoint * @__fwnode: Endpoint firmware node pointing to a remote device * * Returns the remote endpoint corresponding to @__fwnode. NULL on error. */ static struct fwnode_handle * acpi_graph_get_remote_endpoint(const struct fwnode_handle *__fwnode) { struct fwnode_handle *fwnode; unsigned int port_nr, endpoint_nr; struct fwnode_reference_args args; int ret; memset(&args, 0, sizeof(args)); ret = acpi_node_get_property_reference(__fwnode, "remote-endpoint", 0, &args); if (ret) return NULL; /* Direct endpoint reference? */ if (!is_acpi_device_node(args.fwnode)) return args.nargs ? NULL : args.fwnode; /* * Always require two arguments with the reference: port and * endpoint indices. */ if (args.nargs != 2) return NULL; fwnode = args.fwnode; port_nr = args.args[0]; endpoint_nr = args.args[1]; fwnode = acpi_graph_get_child_prop_value(fwnode, "port", port_nr); return acpi_graph_get_child_prop_value(fwnode, "endpoint", endpoint_nr); } static bool acpi_fwnode_device_is_available(const struct fwnode_handle *fwnode) { if (!is_acpi_device_node(fwnode)) return true; return acpi_device_is_present(to_acpi_device_node(fwnode)); } static const void * acpi_fwnode_device_get_match_data(const struct fwnode_handle *fwnode, const struct device *dev) { return acpi_device_get_match_data(dev); } static bool acpi_fwnode_device_dma_supported(const struct fwnode_handle *fwnode) { return acpi_dma_supported(to_acpi_device_node(fwnode)); } static enum dev_dma_attr acpi_fwnode_device_get_dma_attr(const struct fwnode_handle *fwnode) { return acpi_get_dma_attr(to_acpi_device_node(fwnode)); } static bool acpi_fwnode_property_present(const struct fwnode_handle *fwnode, const char *propname) { return !acpi_node_prop_get(fwnode, propname, NULL); } static int acpi_fwnode_property_read_int_array(const struct fwnode_handle *fwnode, const char *propname, unsigned int elem_size, void *val, size_t nval) { enum dev_prop_type type; switch (elem_size) { case sizeof(u8): type = DEV_PROP_U8; break; case sizeof(u16): type = DEV_PROP_U16; break; case sizeof(u32): type = DEV_PROP_U32; break; case sizeof(u64): type = DEV_PROP_U64; break; default: return -ENXIO; } return acpi_node_prop_read(fwnode, propname, type, val, nval); } static int acpi_fwnode_property_read_string_array(const struct fwnode_handle *fwnode, const char *propname, const char **val, size_t nval) { return acpi_node_prop_read(fwnode, propname, DEV_PROP_STRING, val, nval); } static int acpi_fwnode_get_reference_args(const struct fwnode_handle *fwnode, const char *prop, const char *nargs_prop, unsigned int args_count, unsigned int index, struct fwnode_reference_args *args) { return __acpi_node_get_property_reference(fwnode, prop, index, args_count, args); } static const char *acpi_fwnode_get_name(const struct fwnode_handle *fwnode) { const struct acpi_device *adev; struct fwnode_handle *parent; /* Is this the root node? */ parent = fwnode_get_parent(fwnode); if (!parent) return "\\"; fwnode_handle_put(parent); if (is_acpi_data_node(fwnode)) { const struct acpi_data_node *dn = to_acpi_data_node(fwnode); return dn->name; } adev = to_acpi_device_node(fwnode); if (WARN_ON(!adev)) return NULL; return acpi_device_bid(adev); } static const char * acpi_fwnode_get_name_prefix(const struct fwnode_handle *fwnode) { struct fwnode_handle *parent; /* Is this the root node? */ parent = fwnode_get_parent(fwnode); if (!parent) return ""; /* Is this 2nd node from the root? */ parent = fwnode_get_next_parent(parent); if (!parent) return ""; fwnode_handle_put(parent); /* ACPI device or data node. */ return "."; } static struct fwnode_handle * acpi_fwnode_get_parent(struct fwnode_handle *fwnode) { return acpi_node_get_parent(fwnode); } static int acpi_fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode, struct fwnode_endpoint *endpoint) { struct fwnode_handle *port_fwnode = fwnode_get_parent(fwnode); endpoint->local_fwnode = fwnode; if (fwnode_property_read_u32(port_fwnode, "reg", &endpoint->port)) fwnode_property_read_u32(port_fwnode, "port", &endpoint->port); if (fwnode_property_read_u32(fwnode, "reg", &endpoint->id)) fwnode_property_read_u32(fwnode, "endpoint", &endpoint->id); return 0; } static int acpi_fwnode_irq_get(const struct fwnode_handle *fwnode, unsigned int index) { struct resource res; int ret; ret = acpi_irq_get(ACPI_HANDLE_FWNODE(fwnode), index, &res); if (ret) return ret; return res.start; } #define DECLARE_ACPI_FWNODE_OPS(ops) \ const struct fwnode_operations ops = { \ .device_is_available = acpi_fwnode_device_is_available, \ .device_get_match_data = acpi_fwnode_device_get_match_data, \ .device_dma_supported = \ acpi_fwnode_device_dma_supported, \ .device_get_dma_attr = acpi_fwnode_device_get_dma_attr, \ .property_present = acpi_fwnode_property_present, \ .property_read_bool = acpi_fwnode_property_present, \ .property_read_int_array = \ acpi_fwnode_property_read_int_array, \ .property_read_string_array = \ acpi_fwnode_property_read_string_array, \ .get_parent = acpi_node_get_parent, \ .get_next_child_node = acpi_get_next_subnode, \ .get_named_child_node = acpi_fwnode_get_named_child_node, \ .get_name = acpi_fwnode_get_name, \ .get_name_prefix = acpi_fwnode_get_name_prefix, \ .get_reference_args = acpi_fwnode_get_reference_args, \ .graph_get_next_endpoint = \ acpi_graph_get_next_endpoint, \ .graph_get_remote_endpoint = \ acpi_graph_get_remote_endpoint, \ .graph_get_port_parent = acpi_fwnode_get_parent, \ .graph_parse_endpoint = acpi_fwnode_graph_parse_endpoint, \ .irq_get = acpi_fwnode_irq_get, \ }; \ EXPORT_SYMBOL_GPL(ops) DECLARE_ACPI_FWNODE_OPS(acpi_device_fwnode_ops); DECLARE_ACPI_FWNODE_OPS(acpi_data_fwnode_ops); const struct fwnode_operations acpi_static_fwnode_ops; bool is_acpi_device_node(const struct fwnode_handle *fwnode) { return !IS_ERR_OR_NULL(fwnode) && fwnode->ops == &acpi_device_fwnode_ops; } EXPORT_SYMBOL(is_acpi_device_node); bool is_acpi_data_node(const struct fwnode_handle *fwnode) { return !IS_ERR_OR_NULL(fwnode) && fwnode->ops == &acpi_data_fwnode_ops; } EXPORT_SYMBOL(is_acpi_data_node); |
| 56 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_BYTEORDER_GENERIC_H #define _LINUX_BYTEORDER_GENERIC_H /* * linux/byteorder/generic.h * Generic Byte-reordering support * * The "... p" macros, like le64_to_cpup, can be used with pointers * to unaligned data, but there will be a performance penalty on * some architectures. Use get_unaligned for unaligned data. * * Francois-Rene Rideau <fare@tunes.org> 19970707 * gathered all the good ideas from all asm-foo/byteorder.h into one file, * cleaned them up. * I hope it is compliant with non-GCC compilers. * I decided to put __BYTEORDER_HAS_U64__ in byteorder.h, * because I wasn't sure it would be ok to put it in types.h * Upgraded it to 2.1.43 * Francois-Rene Rideau <fare@tunes.org> 19971012 * Upgraded it to 2.1.57 * to please Linus T., replaced huge #ifdef's between little/big endian * by nestedly #include'd files. * Francois-Rene Rideau <fare@tunes.org> 19971205 * Made it to 2.1.71; now a facelift: * Put files under include/linux/byteorder/ * Split swab from generic support. * * TODO: * = Regular kernel maintainers could also replace all these manual * byteswap macros that remain, disseminated among drivers, * after some grep or the sources... * = Linus might want to rename all these macros and files to fit his taste, * to fit his personal naming scheme. * = it seems that a few drivers would also appreciate * nybble swapping support... * = every architecture could add their byteswap macro in asm/byteorder.h * see how some architectures already do (i386, alpha, ppc, etc) * = cpu_to_beXX and beXX_to_cpu might some day need to be well * distinguished throughout the kernel. This is not the case currently, * since little endian, big endian, and pdp endian machines needn't it. * But this might be the case for, say, a port of Linux to 20/21 bit * architectures (and F21 Linux addict around?). */ /* * The following macros are to be defined by <asm/byteorder.h>: * * Conversion of long and short int between network and host format * ntohl(__u32 x) * ntohs(__u16 x) * htonl(__u32 x) * htons(__u16 x) * It seems that some programs (which? where? or perhaps a standard? POSIX?) * might like the above to be functions, not macros (why?). * if that's true, then detect them, and take measures. * Anyway, the measure is: define only ___ntohl as a macro instead, * and in a separate file, have * unsigned long inline ntohl(x){return ___ntohl(x);} * * The same for constant arguments * __constant_ntohl(__u32 x) * __constant_ntohs(__u16 x) * __constant_htonl(__u32 x) * __constant_htons(__u16 x) * * Conversion of XX-bit integers (16- 32- or 64-) * between native CPU format and little/big endian format * 64-bit stuff only defined for proper architectures * cpu_to_[bl]eXX(__uXX x) * [bl]eXX_to_cpu(__uXX x) * * The same, but takes a pointer to the value to convert * cpu_to_[bl]eXXp(__uXX x) * [bl]eXX_to_cpup(__uXX x) * * The same, but change in situ * cpu_to_[bl]eXXs(__uXX x) * [bl]eXX_to_cpus(__uXX x) * * See asm-foo/byteorder.h for examples of how to provide * architecture-optimized versions * */ #define cpu_to_le64 __cpu_to_le64 #define le64_to_cpu __le64_to_cpu #define cpu_to_le32 __cpu_to_le32 #define le32_to_cpu __le32_to_cpu #define cpu_to_le16 __cpu_to_le16 #define le16_to_cpu __le16_to_cpu #define cpu_to_be64 __cpu_to_be64 #define be64_to_cpu __be64_to_cpu #define cpu_to_be32 __cpu_to_be32 #define be32_to_cpu __be32_to_cpu #define cpu_to_be16 __cpu_to_be16 #define be16_to_cpu __be16_to_cpu #define cpu_to_le64p __cpu_to_le64p #define le64_to_cpup __le64_to_cpup #define cpu_to_le32p __cpu_to_le32p #define le32_to_cpup __le32_to_cpup #define cpu_to_le16p __cpu_to_le16p #define le16_to_cpup __le16_to_cpup #define cpu_to_be64p __cpu_to_be64p #define be64_to_cpup __be64_to_cpup #define cpu_to_be32p __cpu_to_be32p #define be32_to_cpup __be32_to_cpup #define cpu_to_be16p __cpu_to_be16p #define be16_to_cpup __be16_to_cpup #define cpu_to_le64s __cpu_to_le64s #define le64_to_cpus __le64_to_cpus #define cpu_to_le32s __cpu_to_le32s #define le32_to_cpus __le32_to_cpus #define cpu_to_le16s __cpu_to_le16s #define le16_to_cpus __le16_to_cpus #define cpu_to_be64s __cpu_to_be64s #define be64_to_cpus __be64_to_cpus #define cpu_to_be32s __cpu_to_be32s #define be32_to_cpus __be32_to_cpus #define cpu_to_be16s __cpu_to_be16s #define be16_to_cpus __be16_to_cpus /* * They have to be macros in order to do the constant folding * correctly - if the argument passed into a inline function * it is no longer constant according to gcc.. */ #undef ntohl #undef ntohs #undef htonl #undef htons #define ___htonl(x) __cpu_to_be32(x) #define ___htons(x) __cpu_to_be16(x) #define ___ntohl(x) __be32_to_cpu(x) #define ___ntohs(x) __be16_to_cpu(x) #define htonl(x) ___htonl(x) #define ntohl(x) ___ntohl(x) #define htons(x) ___htons(x) #define ntohs(x) ___ntohs(x) static inline void le16_add_cpu(__le16 *var, u16 val) { *var = cpu_to_le16(le16_to_cpu(*var) + val); } static inline void le32_add_cpu(__le32 *var, u32 val) { *var = cpu_to_le32(le32_to_cpu(*var) + val); } static inline void le64_add_cpu(__le64 *var, u64 val) { *var = cpu_to_le64(le64_to_cpu(*var) + val); } /* XXX: this stuff can be optimized */ static inline void le32_to_cpu_array(u32 *buf, unsigned int words) { while (words--) { __le32_to_cpus(buf); buf++; } } static inline void cpu_to_le32_array(u32 *buf, unsigned int words) { while (words--) { __cpu_to_le32s(buf); buf++; } } static inline void be16_add_cpu(__be16 *var, u16 val) { *var = cpu_to_be16(be16_to_cpu(*var) + val); } static inline void be32_add_cpu(__be32 *var, u32 val) { *var = cpu_to_be32(be32_to_cpu(*var) + val); } static inline void be64_add_cpu(__be64 *var, u64 val) { *var = cpu_to_be64(be64_to_cpu(*var) + val); } static inline void cpu_to_be32_array(__be32 *dst, const u32 *src, size_t len) { size_t i; for (i = 0; i < len; i++) dst[i] = cpu_to_be32(src[i]); } static inline void be32_to_cpu_array(u32 *dst, const __be32 *src, size_t len) { size_t i; for (i = 0; i < len; i++) dst[i] = be32_to_cpu(src[i]); } #endif /* _LINUX_BYTEORDER_GENERIC_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 | /* SPDX-License-Identifier: GPL-1.0+ */ /* * Bond several ethernet interfaces into a Cisco, running 'Etherchannel'. * * Portions are (c) Copyright 1995 Simon "Guru Aleph-Null" Janes * NCM: Network and Communications Management, Inc. * * BUT, I'm the one who modified it for ethernet, so: * (c) Copyright 1999, Thomas Davis, tadavis@lbl.gov * */ #ifndef _NET_BONDING_H #define _NET_BONDING_H #include <linux/timer.h> #include <linux/proc_fs.h> #include <linux/if_bonding.h> #include <linux/cpumask.h> #include <linux/in6.h> #include <linux/netpoll.h> #include <linux/inetdevice.h> #include <linux/etherdevice.h> #include <linux/reciprocal_div.h> #include <linux/if_link.h> #include <net/bond_3ad.h> #include <net/bond_alb.h> #include <net/bond_options.h> #include <net/ipv6.h> #include <net/addrconf.h> #define BOND_MAX_ARP_TARGETS 16 #define BOND_MAX_NS_TARGETS BOND_MAX_ARP_TARGETS #define BOND_DEFAULT_MIIMON 100 #ifndef __long_aligned #define __long_aligned __attribute__((aligned((sizeof(long))))) #endif #define slave_info(bond_dev, slave_dev, fmt, ...) \ netdev_info(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) #define slave_warn(bond_dev, slave_dev, fmt, ...) \ netdev_warn(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) #define slave_dbg(bond_dev, slave_dev, fmt, ...) \ netdev_dbg(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) #define slave_err(bond_dev, slave_dev, fmt, ...) \ netdev_err(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) #define BOND_MODE(bond) ((bond)->params.mode) /* slave list primitives */ #define bond_slave_list(bond) (&(bond)->dev->adj_list.lower) #define bond_has_slaves(bond) !list_empty(bond_slave_list(bond)) /* IMPORTANT: bond_first/last_slave can return NULL in case of an empty list */ #define bond_first_slave(bond) \ (bond_has_slaves(bond) ? \ netdev_adjacent_get_private(bond_slave_list(bond)->next) : \ NULL) #define bond_last_slave(bond) \ (bond_has_slaves(bond) ? \ netdev_adjacent_get_private(bond_slave_list(bond)->prev) : \ NULL) /* Caller must have rcu_read_lock */ #define bond_first_slave_rcu(bond) \ netdev_lower_get_first_private_rcu(bond->dev) #define bond_is_first_slave(bond, pos) (pos == bond_first_slave(bond)) #define bond_is_last_slave(bond, pos) (pos == bond_last_slave(bond)) /** * bond_for_each_slave - iterate over all slaves * @bond: the bond holding this list * @pos: current slave * @iter: list_head * iterator * * Caller must hold RTNL */ #define bond_for_each_slave(bond, pos, iter) \ netdev_for_each_lower_private((bond)->dev, pos, iter) /* Caller must have rcu_read_lock */ #define bond_for_each_slave_rcu(bond, pos, iter) \ netdev_for_each_lower_private_rcu((bond)->dev, pos, iter) #define BOND_XFRM_FEATURES (NETIF_F_HW_ESP | NETIF_F_HW_ESP_TX_CSUM | \ NETIF_F_GSO_ESP) #ifdef CONFIG_NET_POLL_CONTROLLER extern atomic_t netpoll_block_tx; static inline void block_netpoll_tx(void) { atomic_inc(&netpoll_block_tx); } static inline void unblock_netpoll_tx(void) { atomic_dec(&netpoll_block_tx); } static inline int is_netpoll_tx_blocked(struct net_device *dev) { if (unlikely(netpoll_tx_running(dev))) return atomic_read(&netpoll_block_tx); return 0; } #else #define block_netpoll_tx() #define unblock_netpoll_tx() #define is_netpoll_tx_blocked(dev) (0) #endif struct bond_params { int mode; int xmit_policy; int miimon; u8 num_peer_notif; u8 missed_max; int arp_interval; int arp_validate; int arp_all_targets; int use_carrier; int fail_over_mac; int updelay; int downdelay; int peer_notif_delay; int lacp_active; int lacp_fast; unsigned int min_links; int ad_select; char primary[IFNAMSIZ]; int primary_reselect; __be32 arp_targets[BOND_MAX_ARP_TARGETS]; int tx_queues; int all_slaves_active; int resend_igmp; int lp_interval; int packets_per_slave; int tlb_dynamic_lb; struct reciprocal_value reciprocal_packets_per_slave; u16 ad_actor_sys_prio; u16 ad_user_port_key; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr ns_targets[BOND_MAX_NS_TARGETS]; #endif int coupled_control; /* 2 bytes of padding : see ether_addr_equal_64bits() */ u8 ad_actor_system[ETH_ALEN + 2]; }; struct slave { struct net_device *dev; /* first - useful for panic debug */ struct bonding *bond; /* our master */ int delay; /* all 4 in jiffies */ unsigned long last_link_up; unsigned long last_tx; unsigned long last_rx; unsigned long target_last_arp_rx[BOND_MAX_ARP_TARGETS]; s8 link; /* one of BOND_LINK_XXXX */ s8 link_new_state; /* one of BOND_LINK_XXXX */ u8 backup:1, /* indicates backup slave. Value corresponds with BOND_STATE_ACTIVE and BOND_STATE_BACKUP */ inactive:1, /* indicates inactive slave */ rx_disabled:1, /* indicates whether slave's Rx is disabled */ should_notify:1, /* indicates whether the state changed */ should_notify_link:1; /* indicates whether the link changed */ u8 duplex; u32 original_mtu; u32 link_failure_count; u32 speed; u16 queue_id; u8 perm_hwaddr[MAX_ADDR_LEN]; int prio; struct ad_slave_info *ad_info; struct tlb_slave_info tlb_info; #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *np; #endif struct delayed_work notify_work; struct kobject kobj; struct rtnl_link_stats64 slave_stats; }; static inline struct slave *to_slave(struct kobject *kobj) { return container_of(kobj, struct slave, kobj); } struct bond_up_slave { unsigned int count; struct rcu_head rcu; struct slave *arr[]; }; /* * Link pseudo-state only used internally by monitors */ #define BOND_LINK_NOCHANGE -1 struct bond_ipsec { struct list_head list; struct xfrm_state *xs; }; /* * Here are the locking policies for the two bonding locks: * Get rcu_read_lock when reading or RTNL when writing slave list. */ struct bonding { struct net_device *dev; /* first - useful for panic debug */ struct slave __rcu *curr_active_slave; struct slave __rcu *current_arp_slave; struct slave __rcu *primary_slave; struct bond_up_slave __rcu *usable_slaves; struct bond_up_slave __rcu *all_slaves; bool force_primary; bool notifier_ctx; s32 slave_cnt; /* never change this value outside the attach/detach wrappers */ int (*recv_probe)(const struct sk_buff *, struct bonding *, struct slave *); /* mode_lock is used for mode-specific locking needs, currently used by: * 3ad mode (4) - protect against running bond_3ad_unbind_slave() and * bond_3ad_state_machine_handler() concurrently and also * the access to the state machine shared variables. * TLB mode (5) - to sync the use and modifications of its hash table * ALB mode (6) - to sync the use and modifications of its hash table */ spinlock_t mode_lock; spinlock_t stats_lock; u32 send_peer_notif; u8 igmp_retrans; #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_entry; char proc_file_name[IFNAMSIZ]; #endif /* CONFIG_PROC_FS */ struct list_head bond_list; u32 __percpu *rr_tx_counter; struct ad_bond_info ad_info; struct alb_bond_info alb_info; struct bond_params params; struct workqueue_struct *wq; struct delayed_work mii_work; struct delayed_work arp_work; struct delayed_work alb_work; struct delayed_work ad_work; struct delayed_work mcast_work; struct delayed_work slave_arr_work; #ifdef CONFIG_DEBUG_FS /* debugging support via debugfs */ struct dentry *debug_dir; #endif /* CONFIG_DEBUG_FS */ struct rtnl_link_stats64 bond_stats; #ifdef CONFIG_XFRM_OFFLOAD struct list_head ipsec_list; /* protecting ipsec_list */ struct mutex ipsec_lock; #endif /* CONFIG_XFRM_OFFLOAD */ struct bpf_prog *xdp_prog; }; #define bond_slave_get_rcu(dev) \ ((struct slave *) rcu_dereference(dev->rx_handler_data)) #define bond_slave_get_rtnl(dev) \ ((struct slave *) rtnl_dereference(dev->rx_handler_data)) void bond_queue_slave_event(struct slave *slave); void bond_lower_state_changed(struct slave *slave); struct bond_vlan_tag { __be16 vlan_proto; unsigned short vlan_id; }; /* * Returns NULL if the net_device does not belong to any of the bond's slaves * * Caller must hold bond lock for read */ static inline struct slave *bond_get_slave_by_dev(struct bonding *bond, struct net_device *slave_dev) { return netdev_lower_dev_get_private(bond->dev, slave_dev); } static inline struct bonding *bond_get_bond_by_slave(struct slave *slave) { return slave->bond; } static inline bool bond_should_override_tx_queue(struct bonding *bond) { return BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP || BOND_MODE(bond) == BOND_MODE_ROUNDROBIN; } static inline bool bond_is_lb(const struct bonding *bond) { return BOND_MODE(bond) == BOND_MODE_TLB || BOND_MODE(bond) == BOND_MODE_ALB; } static inline bool bond_needs_speed_duplex(const struct bonding *bond) { return BOND_MODE(bond) == BOND_MODE_8023AD || bond_is_lb(bond); } static inline bool bond_is_nondyn_tlb(const struct bonding *bond) { return (bond_is_lb(bond) && bond->params.tlb_dynamic_lb == 0); } static inline bool bond_mode_can_use_xmit_hash(const struct bonding *bond) { return (BOND_MODE(bond) == BOND_MODE_8023AD || BOND_MODE(bond) == BOND_MODE_XOR || BOND_MODE(bond) == BOND_MODE_TLB || BOND_MODE(bond) == BOND_MODE_ALB); } static inline bool bond_mode_uses_xmit_hash(const struct bonding *bond) { return (BOND_MODE(bond) == BOND_MODE_8023AD || BOND_MODE(bond) == BOND_MODE_XOR || bond_is_nondyn_tlb(bond)); } static inline bool bond_mode_uses_arp(int mode) { return mode != BOND_MODE_8023AD && mode != BOND_MODE_TLB && mode != BOND_MODE_ALB; } static inline bool bond_mode_uses_primary(int mode) { return mode == BOND_MODE_ACTIVEBACKUP || mode == BOND_MODE_TLB || mode == BOND_MODE_ALB; } static inline bool bond_uses_primary(struct bonding *bond) { return bond_mode_uses_primary(BOND_MODE(bond)); } static inline struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond) { struct slave *slave = rcu_dereference_rtnl(bond->curr_active_slave); return bond_uses_primary(bond) && slave ? slave->dev : NULL; } static inline bool bond_slave_is_up(struct slave *slave) { return netif_running(slave->dev) && netif_carrier_ok(slave->dev); } static inline void bond_set_active_slave(struct slave *slave) { if (slave->backup) { slave->backup = 0; bond_queue_slave_event(slave); bond_lower_state_changed(slave); } } static inline void bond_set_backup_slave(struct slave *slave) { if (!slave->backup) { slave->backup = 1; bond_queue_slave_event(slave); bond_lower_state_changed(slave); } } static inline void bond_set_slave_state(struct slave *slave, int slave_state, bool notify) { if (slave->backup == slave_state) return; slave->backup = slave_state; if (notify) { bond_lower_state_changed(slave); bond_queue_slave_event(slave); slave->should_notify = 0; } else { if (slave->should_notify) slave->should_notify = 0; else slave->should_notify = 1; } } static inline void bond_slave_state_change(struct bonding *bond) { struct list_head *iter; struct slave *tmp; bond_for_each_slave(bond, tmp, iter) { if (tmp->link == BOND_LINK_UP) bond_set_active_slave(tmp); else if (tmp->link == BOND_LINK_DOWN) bond_set_backup_slave(tmp); } } static inline void bond_slave_state_notify(struct bonding *bond) { struct list_head *iter; struct slave *tmp; bond_for_each_slave(bond, tmp, iter) { if (tmp->should_notify) { bond_lower_state_changed(tmp); tmp->should_notify = 0; } } } static inline int bond_slave_state(struct slave *slave) { return slave->backup; } static inline bool bond_is_active_slave(struct slave *slave) { return !bond_slave_state(slave); } static inline bool bond_slave_can_tx(struct slave *slave) { return bond_slave_is_up(slave) && slave->link == BOND_LINK_UP && bond_is_active_slave(slave); } static inline bool bond_is_active_slave_dev(const struct net_device *slave_dev) { struct slave *slave; bool active; rcu_read_lock(); slave = bond_slave_get_rcu(slave_dev); active = bond_is_active_slave(slave); rcu_read_unlock(); return active; } static inline void bond_hw_addr_copy(u8 *dst, const u8 *src, unsigned int len) { if (len == ETH_ALEN) { ether_addr_copy(dst, src); return; } memcpy(dst, src, len); } #define BOND_PRI_RESELECT_ALWAYS 0 #define BOND_PRI_RESELECT_BETTER 1 #define BOND_PRI_RESELECT_FAILURE 2 #define BOND_FOM_NONE 0 #define BOND_FOM_ACTIVE 1 #define BOND_FOM_FOLLOW 2 #define BOND_ARP_TARGETS_ANY 0 #define BOND_ARP_TARGETS_ALL 1 #define BOND_ARP_VALIDATE_NONE 0 #define BOND_ARP_VALIDATE_ACTIVE (1 << BOND_STATE_ACTIVE) #define BOND_ARP_VALIDATE_BACKUP (1 << BOND_STATE_BACKUP) #define BOND_ARP_VALIDATE_ALL (BOND_ARP_VALIDATE_ACTIVE | \ BOND_ARP_VALIDATE_BACKUP) #define BOND_ARP_FILTER (BOND_ARP_VALIDATE_ALL + 1) #define BOND_ARP_FILTER_ACTIVE (BOND_ARP_VALIDATE_ACTIVE | \ BOND_ARP_FILTER) #define BOND_ARP_FILTER_BACKUP (BOND_ARP_VALIDATE_BACKUP | \ BOND_ARP_FILTER) #define BOND_SLAVE_NOTIFY_NOW true #define BOND_SLAVE_NOTIFY_LATER false static inline int slave_do_arp_validate(struct bonding *bond, struct slave *slave) { return bond->params.arp_validate & (1 << bond_slave_state(slave)); } static inline int slave_do_arp_validate_only(struct bonding *bond) { return bond->params.arp_validate & BOND_ARP_FILTER; } static inline int bond_is_ip_target_ok(__be32 addr) { return !ipv4_is_lbcast(addr) && !ipv4_is_zeronet(addr); } #if IS_ENABLED(CONFIG_IPV6) static inline int bond_is_ip6_target_ok(struct in6_addr *addr) { return !ipv6_addr_any(addr) && !ipv6_addr_loopback(addr) && !ipv6_addr_is_multicast(addr); } #endif /* Get the oldest arp which we've received on this slave for bond's * arp_targets. */ static inline unsigned long slave_oldest_target_arp_rx(struct bonding *bond, struct slave *slave) { int i = 1; unsigned long ret = slave->target_last_arp_rx[0]; for (; (i < BOND_MAX_ARP_TARGETS) && bond->params.arp_targets[i]; i++) if (time_before(slave->target_last_arp_rx[i], ret)) ret = slave->target_last_arp_rx[i]; return ret; } static inline unsigned long slave_last_rx(struct bonding *bond, struct slave *slave) { if (bond->params.arp_all_targets == BOND_ARP_TARGETS_ALL) return slave_oldest_target_arp_rx(bond, slave); return slave->last_rx; } static inline void slave_update_last_tx(struct slave *slave) { WRITE_ONCE(slave->last_tx, jiffies); } static inline unsigned long slave_last_tx(struct slave *slave) { return READ_ONCE(slave->last_tx); } #ifdef CONFIG_NET_POLL_CONTROLLER static inline netdev_tx_t bond_netpoll_send_skb(const struct slave *slave, struct sk_buff *skb) { return netpoll_send_skb(slave->np, skb); } #else static inline netdev_tx_t bond_netpoll_send_skb(const struct slave *slave, struct sk_buff *skb) { BUG(); return NETDEV_TX_OK; } #endif static inline void bond_set_slave_inactive_flags(struct slave *slave, bool notify) { if (!bond_is_lb(slave->bond)) bond_set_slave_state(slave, BOND_STATE_BACKUP, notify); if (!slave->bond->params.all_slaves_active) slave->inactive = 1; if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) slave->rx_disabled = 1; } static inline void bond_set_slave_tx_disabled_flags(struct slave *slave, bool notify) { bond_set_slave_state(slave, BOND_STATE_BACKUP, notify); } static inline void bond_set_slave_active_flags(struct slave *slave, bool notify) { bond_set_slave_state(slave, BOND_STATE_ACTIVE, notify); slave->inactive = 0; if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) slave->rx_disabled = 0; } static inline void bond_set_slave_rx_enabled_flags(struct slave *slave, bool notify) { slave->rx_disabled = 0; } static inline bool bond_is_slave_inactive(struct slave *slave) { return slave->inactive; } static inline bool bond_is_slave_rx_disabled(struct slave *slave) { return slave->rx_disabled; } static inline void bond_propose_link_state(struct slave *slave, int state) { slave->link_new_state = state; } static inline void bond_commit_link_state(struct slave *slave, bool notify) { if (slave->link_new_state == BOND_LINK_NOCHANGE) return; slave->link = slave->link_new_state; if (notify) { bond_queue_slave_event(slave); bond_lower_state_changed(slave); slave->should_notify_link = 0; } else { if (slave->should_notify_link) slave->should_notify_link = 0; else slave->should_notify_link = 1; } } static inline void bond_set_slave_link_state(struct slave *slave, int state, bool notify) { bond_propose_link_state(slave, state); bond_commit_link_state(slave, notify); } static inline void bond_slave_link_notify(struct bonding *bond) { struct list_head *iter; struct slave *tmp; bond_for_each_slave(bond, tmp, iter) { if (tmp->should_notify_link) { bond_queue_slave_event(tmp); bond_lower_state_changed(tmp); tmp->should_notify_link = 0; } } } static inline __be32 bond_confirm_addr(struct net_device *dev, __be32 dst, __be32 local) { struct in_device *in_dev; __be32 addr = 0; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (in_dev) addr = inet_confirm_addr(dev_net(dev), in_dev, dst, local, RT_SCOPE_HOST); rcu_read_unlock(); return addr; } struct bond_net { struct net *net; /* Associated network namespace */ struct list_head dev_list; #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_dir; #endif struct class_attribute class_attr_bonding_masters; }; int bond_rcv_validate(const struct sk_buff *skb, struct bonding *bond, struct slave *slave); netdev_tx_t bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev); int bond_create(struct net *net, const char *name); int bond_create_sysfs(struct bond_net *net); void bond_destroy_sysfs(struct bond_net *net); void bond_prepare_sysfs_group(struct bonding *bond); int bond_sysfs_slave_add(struct slave *slave); void bond_sysfs_slave_del(struct slave *slave); void bond_xdp_set_features(struct net_device *bond_dev); int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, struct netlink_ext_ack *extack); int bond_release(struct net_device *bond_dev, struct net_device *slave_dev); u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb); int bond_set_carrier(struct bonding *bond); void bond_select_active_slave(struct bonding *bond); void bond_change_active_slave(struct bonding *bond, struct slave *new_active); void bond_create_debugfs(void); void bond_destroy_debugfs(void); void bond_debug_register(struct bonding *bond); void bond_debug_unregister(struct bonding *bond); void bond_debug_reregister(struct bonding *bond); const char *bond_mode_name(int mode); bool bond_xdp_check(struct bonding *bond, int mode); void bond_setup(struct net_device *bond_dev); unsigned int bond_get_num_tx_queues(void); int bond_netlink_init(void); void bond_netlink_fini(void); struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond); const char *bond_slave_link_status(s8 link); struct bond_vlan_tag *bond_verify_device_path(struct net_device *start_dev, struct net_device *end_dev, int level); int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave); void bond_slave_arr_work_rearm(struct bonding *bond, unsigned long delay); void bond_work_init_all(struct bonding *bond); #ifdef CONFIG_PROC_FS void bond_create_proc_entry(struct bonding *bond); void bond_remove_proc_entry(struct bonding *bond); void bond_create_proc_dir(struct bond_net *bn); void bond_destroy_proc_dir(struct bond_net *bn); #else static inline void bond_create_proc_entry(struct bonding *bond) { } static inline void bond_remove_proc_entry(struct bonding *bond) { } static inline void bond_create_proc_dir(struct bond_net *bn) { } static inline void bond_destroy_proc_dir(struct bond_net *bn) { } #endif static inline struct slave *bond_slave_has_mac(struct bonding *bond, const u8 *mac) { struct list_head *iter; struct slave *tmp; bond_for_each_slave(bond, tmp, iter) if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) return tmp; return NULL; } /* Caller must hold rcu_read_lock() for read */ static inline bool bond_slave_has_mac_rcu(struct bonding *bond, const u8 *mac) { struct list_head *iter; struct slave *tmp; bond_for_each_slave_rcu(bond, tmp, iter) if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) return true; return false; } /* Check if the ip is present in arp ip list, or first free slot if ip == 0 * Returns -1 if not found, index if found */ static inline int bond_get_targets_ip(__be32 *targets, __be32 ip) { int i; for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) if (targets[i] == ip) return i; else if (targets[i] == 0) break; return -1; } #if IS_ENABLED(CONFIG_IPV6) static inline int bond_get_targets_ip6(struct in6_addr *targets, struct in6_addr *ip) { struct in6_addr mcaddr; int i; for (i = 0; i < BOND_MAX_NS_TARGETS; i++) { addrconf_addr_solict_mult(&targets[i], &mcaddr); if ((ipv6_addr_equal(&targets[i], ip)) || (ipv6_addr_equal(&mcaddr, ip))) return i; else if (ipv6_addr_any(&targets[i])) break; } return -1; } #endif /* exported from bond_main.c */ extern unsigned int bond_net_id; /* exported from bond_netlink.c */ extern struct rtnl_link_ops bond_link_ops; /* exported from bond_sysfs_slave.c */ extern const struct sysfs_ops slave_sysfs_ops; /* exported from bond_3ad.c */ extern const u8 lacpdu_mcast_addr[]; static inline netdev_tx_t bond_tx_drop(struct net_device *dev, struct sk_buff *skb) { dev_core_stats_tx_dropped_inc(dev); dev_kfree_skb_any(skb); return NET_XMIT_DROP; } #endif /* _NET_BONDING_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/linkage.h> #include <linux/errno.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/ioport.h> #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/timex.h> #include <linux/random.h> #include <linux/init.h> #include <linux/kernel_stat.h> #include <linux/syscore_ops.h> #include <linux/bitops.h> #include <linux/acpi.h> #include <linux/io.h> #include <linux/delay.h> #include <linux/pgtable.h> #include <linux/atomic.h> #include <asm/timer.h> #include <asm/hw_irq.h> #include <asm/desc.h> #include <asm/apic.h> #include <asm/i8259.h> #include <asm/io_apic.h> /* * This is the 'legacy' 8259A Programmable Interrupt Controller, * present in the majority of PC/AT boxes. * plus some generic x86 specific things if generic specifics makes * any sense at all. */ static void init_8259A(int auto_eoi); static bool pcat_compat __ro_after_init; static int i8259A_auto_eoi; DEFINE_RAW_SPINLOCK(i8259A_lock); /* * 8259A PIC functions to handle ISA devices: */ /* * This contains the irq mask for both 8259A irq controllers, */ unsigned int cached_irq_mask = 0xffff; /* * Not all IRQs can be routed through the IO-APIC, eg. on certain (older) * boards the timer interrupt is not really connected to any IO-APIC pin, * it's fed to the master 8259A's IR0 line only. * * Any '1' bit in this mask means the IRQ is routed through the IO-APIC. * this 'mixed mode' IRQ handling costs nothing because it's only used * at IRQ setup time. */ unsigned long io_apic_irqs; static void mask_8259A_irq(unsigned int irq) { unsigned int mask = 1 << irq; unsigned long flags; raw_spin_lock_irqsave(&i8259A_lock, flags); cached_irq_mask |= mask; if (irq & 8) outb(cached_slave_mask, PIC_SLAVE_IMR); else outb(cached_master_mask, PIC_MASTER_IMR); raw_spin_unlock_irqrestore(&i8259A_lock, flags); } static void disable_8259A_irq(struct irq_data *data) { mask_8259A_irq(data->irq); } static void unmask_8259A_irq(unsigned int irq) { unsigned int mask = ~(1 << irq); unsigned long flags; raw_spin_lock_irqsave(&i8259A_lock, flags); cached_irq_mask &= mask; if (irq & 8) outb(cached_slave_mask, PIC_SLAVE_IMR); else outb(cached_master_mask, PIC_MASTER_IMR); raw_spin_unlock_irqrestore(&i8259A_lock, flags); } static void enable_8259A_irq(struct irq_data *data) { unmask_8259A_irq(data->irq); } static int i8259A_irq_pending(unsigned int irq) { unsigned int mask = 1<<irq; unsigned long flags; int ret; raw_spin_lock_irqsave(&i8259A_lock, flags); if (irq < 8) ret = inb(PIC_MASTER_CMD) & mask; else ret = inb(PIC_SLAVE_CMD) & (mask >> 8); raw_spin_unlock_irqrestore(&i8259A_lock, flags); return ret; } static void make_8259A_irq(unsigned int irq) { disable_irq_nosync(irq); io_apic_irqs &= ~(1<<irq); irq_set_chip_and_handler(irq, &i8259A_chip, handle_level_irq); irq_set_status_flags(irq, IRQ_LEVEL); enable_irq(irq); lapic_assign_legacy_vector(irq, true); } /* * This function assumes to be called rarely. Switching between * 8259A registers is slow. * This has to be protected by the irq controller spinlock * before being called. */ static inline int i8259A_irq_real(unsigned int irq) { int value; int irqmask = 1<<irq; if (irq < 8) { outb(0x0B, PIC_MASTER_CMD); /* ISR register */ value = inb(PIC_MASTER_CMD) & irqmask; outb(0x0A, PIC_MASTER_CMD); /* back to the IRR register */ return value; } outb(0x0B, PIC_SLAVE_CMD); /* ISR register */ value = inb(PIC_SLAVE_CMD) & (irqmask >> 8); outb(0x0A, PIC_SLAVE_CMD); /* back to the IRR register */ return value; } /* * Careful! The 8259A is a fragile beast, it pretty * much _has_ to be done exactly like this (mask it * first, _then_ send the EOI, and the order of EOI * to the two 8259s is important! */ static void mask_and_ack_8259A(struct irq_data *data) { unsigned int irq = data->irq; unsigned int irqmask = 1 << irq; unsigned long flags; raw_spin_lock_irqsave(&i8259A_lock, flags); /* * Lightweight spurious IRQ detection. We do not want * to overdo spurious IRQ handling - it's usually a sign * of hardware problems, so we only do the checks we can * do without slowing down good hardware unnecessarily. * * Note that IRQ7 and IRQ15 (the two spurious IRQs * usually resulting from the 8259A-1|2 PICs) occur * even if the IRQ is masked in the 8259A. Thus we * can check spurious 8259A IRQs without doing the * quite slow i8259A_irq_real() call for every IRQ. * This does not cover 100% of spurious interrupts, * but should be enough to warn the user that there * is something bad going on ... */ if (cached_irq_mask & irqmask) goto spurious_8259A_irq; cached_irq_mask |= irqmask; handle_real_irq: if (irq & 8) { inb(PIC_SLAVE_IMR); /* DUMMY - (do we need this?) */ outb(cached_slave_mask, PIC_SLAVE_IMR); /* 'Specific EOI' to slave */ outb(0x60+(irq&7), PIC_SLAVE_CMD); /* 'Specific EOI' to master-IRQ2 */ outb(0x60+PIC_CASCADE_IR, PIC_MASTER_CMD); } else { inb(PIC_MASTER_IMR); /* DUMMY - (do we need this?) */ outb(cached_master_mask, PIC_MASTER_IMR); outb(0x60+irq, PIC_MASTER_CMD); /* 'Specific EOI to master */ } raw_spin_unlock_irqrestore(&i8259A_lock, flags); return; spurious_8259A_irq: /* * this is the slow path - should happen rarely. */ if (i8259A_irq_real(irq)) /* * oops, the IRQ _is_ in service according to the * 8259A - not spurious, go handle it. */ goto handle_real_irq; { static int spurious_irq_mask; /* * At this point we can be sure the IRQ is spurious, * lets ACK and report it. [once per IRQ] */ if (!(spurious_irq_mask & irqmask)) { printk_deferred(KERN_DEBUG "spurious 8259A interrupt: IRQ%d.\n", irq); spurious_irq_mask |= irqmask; } atomic_inc(&irq_err_count); /* * Theoretically we do not have to handle this IRQ, * but in Linux this does not cause problems and is * simpler for us. */ goto handle_real_irq; } } struct irq_chip i8259A_chip = { .name = "XT-PIC", .irq_mask = disable_8259A_irq, .irq_disable = disable_8259A_irq, .irq_unmask = enable_8259A_irq, .irq_mask_ack = mask_and_ack_8259A, }; static char irq_trigger[2]; /* ELCR registers (0x4d0, 0x4d1) control edge/level of IRQ */ static void restore_ELCR(char *trigger) { outb(trigger[0], PIC_ELCR1); outb(trigger[1], PIC_ELCR2); } static void save_ELCR(char *trigger) { /* IRQ 0,1,2,8,13 are marked as reserved */ trigger[0] = inb(PIC_ELCR1) & 0xF8; trigger[1] = inb(PIC_ELCR2) & 0xDE; } static void i8259A_resume(void) { init_8259A(i8259A_auto_eoi); restore_ELCR(irq_trigger); } static int i8259A_suspend(void) { save_ELCR(irq_trigger); return 0; } static void i8259A_shutdown(void) { /* Put the i8259A into a quiescent state that * the kernel initialization code can get it * out of. */ outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */ outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-2 */ } static struct syscore_ops i8259_syscore_ops = { .suspend = i8259A_suspend, .resume = i8259A_resume, .shutdown = i8259A_shutdown, }; static void mask_8259A(void) { unsigned long flags; raw_spin_lock_irqsave(&i8259A_lock, flags); outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */ outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-2 */ raw_spin_unlock_irqrestore(&i8259A_lock, flags); } static void unmask_8259A(void) { unsigned long flags; raw_spin_lock_irqsave(&i8259A_lock, flags); outb(cached_master_mask, PIC_MASTER_IMR); /* restore master IRQ mask */ outb(cached_slave_mask, PIC_SLAVE_IMR); /* restore slave IRQ mask */ raw_spin_unlock_irqrestore(&i8259A_lock, flags); } static int probe_8259A(void) { unsigned char new_val, probe_val = ~(1 << PIC_CASCADE_IR); unsigned long flags; /* * If MADT has the PCAT_COMPAT flag set, then do not bother probing * for the PIC. Some BIOSes leave the PIC uninitialized and probing * fails. * * Right now this causes problems as quite some code depends on * nr_legacy_irqs() > 0 or has_legacy_pic() == true. This is silly * when the system has an IO/APIC because then PIC is not required * at all, except for really old machines where the timer interrupt * must be routed through the PIC. So just pretend that the PIC is * there and let legacy_pic->init() initialize it for nothing. * * Alternatively this could just try to initialize the PIC and * repeat the probe, but for cases where there is no PIC that's * just pointless. */ if (pcat_compat) return nr_legacy_irqs(); /* * Check to see if we have a PIC. Mask all except the cascade and * read back the value we just wrote. If we don't have a PIC, we * will read 0xff as opposed to the value we wrote. */ raw_spin_lock_irqsave(&i8259A_lock, flags); outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-2 */ outb(probe_val, PIC_MASTER_IMR); new_val = inb(PIC_MASTER_IMR); if (new_val != probe_val) { printk(KERN_INFO "Using NULL legacy PIC\n"); legacy_pic = &null_legacy_pic; } raw_spin_unlock_irqrestore(&i8259A_lock, flags); return nr_legacy_irqs(); } static void init_8259A(int auto_eoi) { unsigned long flags; i8259A_auto_eoi = auto_eoi; raw_spin_lock_irqsave(&i8259A_lock, flags); outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */ /* * outb_pic - this has to work on a wide range of PC hardware. */ outb_pic(0x11, PIC_MASTER_CMD); /* ICW1: select 8259A-1 init */ /* ICW2: 8259A-1 IR0-7 mapped to ISA_IRQ_VECTOR(0) */ outb_pic(ISA_IRQ_VECTOR(0), PIC_MASTER_IMR); /* 8259A-1 (the master) has a slave on IR2 */ outb_pic(1U << PIC_CASCADE_IR, PIC_MASTER_IMR); if (auto_eoi) /* master does Auto EOI */ outb_pic(MASTER_ICW4_DEFAULT | PIC_ICW4_AEOI, PIC_MASTER_IMR); else /* master expects normal EOI */ outb_pic(MASTER_ICW4_DEFAULT, PIC_MASTER_IMR); outb_pic(0x11, PIC_SLAVE_CMD); /* ICW1: select 8259A-2 init */ /* ICW2: 8259A-2 IR0-7 mapped to ISA_IRQ_VECTOR(8) */ outb_pic(ISA_IRQ_VECTOR(8), PIC_SLAVE_IMR); /* 8259A-2 is a slave on master's IR2 */ outb_pic(PIC_CASCADE_IR, PIC_SLAVE_IMR); /* (slave's support for AEOI in flat mode is to be investigated) */ outb_pic(SLAVE_ICW4_DEFAULT, PIC_SLAVE_IMR); if (auto_eoi) /* * In AEOI mode we just have to mask the interrupt * when acking. */ i8259A_chip.irq_mask_ack = disable_8259A_irq; else i8259A_chip.irq_mask_ack = mask_and_ack_8259A; udelay(100); /* wait for 8259A to initialize */ outb(cached_master_mask, PIC_MASTER_IMR); /* restore master IRQ mask */ outb(cached_slave_mask, PIC_SLAVE_IMR); /* restore slave IRQ mask */ raw_spin_unlock_irqrestore(&i8259A_lock, flags); } /* * make i8259 a driver so that we can select pic functions at run time. the goal * is to make x86 binary compatible among pc compatible and non-pc compatible * platforms, such as x86 MID. */ static void legacy_pic_noop(void) { }; static void legacy_pic_uint_noop(unsigned int unused) { }; static void legacy_pic_int_noop(int unused) { }; static int legacy_pic_irq_pending_noop(unsigned int irq) { return 0; } static int legacy_pic_probe(void) { return 0; } struct legacy_pic null_legacy_pic = { .nr_legacy_irqs = 0, .chip = &dummy_irq_chip, .mask = legacy_pic_uint_noop, .unmask = legacy_pic_uint_noop, .mask_all = legacy_pic_noop, .restore_mask = legacy_pic_noop, .init = legacy_pic_int_noop, .probe = legacy_pic_probe, .irq_pending = legacy_pic_irq_pending_noop, .make_irq = legacy_pic_uint_noop, }; static struct legacy_pic default_legacy_pic = { .nr_legacy_irqs = NR_IRQS_LEGACY, .chip = &i8259A_chip, .mask = mask_8259A_irq, .unmask = unmask_8259A_irq, .mask_all = mask_8259A, .restore_mask = unmask_8259A, .init = init_8259A, .probe = probe_8259A, .irq_pending = i8259A_irq_pending, .make_irq = make_8259A_irq, }; struct legacy_pic *legacy_pic = &default_legacy_pic; EXPORT_SYMBOL(legacy_pic); static int __init i8259A_init_ops(void) { if (legacy_pic == &default_legacy_pic) register_syscore_ops(&i8259_syscore_ops); return 0; } device_initcall(i8259A_init_ops); void __init legacy_pic_pcat_compat(void) { pcat_compat = true; } |
| 7 7 3 3 1 1 1 7 7 6 7 7 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 | // SPDX-License-Identifier: GPL-2.0 /* * HugeTLB Vmemmap Optimization (HVO) * * Copyright (c) 2020, ByteDance. All rights reserved. * * Author: Muchun Song <songmuchun@bytedance.com> * * See Documentation/mm/vmemmap_dedup.rst */ #define pr_fmt(fmt) "HugeTLB: " fmt #include <linux/pgtable.h> #include <linux/moduleparam.h> #include <linux/bootmem_info.h> #include <linux/mmdebug.h> #include <linux/pagewalk.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> #include "hugetlb_vmemmap.h" /** * struct vmemmap_remap_walk - walk vmemmap page table * * @remap_pte: called for each lowest-level entry (PTE). * @nr_walked: the number of walked pte. * @reuse_page: the page which is reused for the tail vmemmap pages. * @reuse_addr: the virtual address of the @reuse_page page. * @vmemmap_pages: the list head of the vmemmap pages that can be freed * or is mapped from. * @flags: used to modify behavior in vmemmap page table walking * operations. */ struct vmemmap_remap_walk { void (*remap_pte)(pte_t *pte, unsigned long addr, struct vmemmap_remap_walk *walk); unsigned long nr_walked; struct page *reuse_page; unsigned long reuse_addr; struct list_head *vmemmap_pages; /* Skip the TLB flush when we split the PMD */ #define VMEMMAP_SPLIT_NO_TLB_FLUSH BIT(0) /* Skip the TLB flush when we remap the PTE */ #define VMEMMAP_REMAP_NO_TLB_FLUSH BIT(1) /* synchronize_rcu() to avoid writes from page_ref_add_unless() */ #define VMEMMAP_SYNCHRONIZE_RCU BIT(2) unsigned long flags; }; static int vmemmap_split_pmd(pmd_t *pmd, struct page *head, unsigned long start, struct vmemmap_remap_walk *walk) { pmd_t __pmd; int i; unsigned long addr = start; pte_t *pgtable; pgtable = pte_alloc_one_kernel(&init_mm); if (!pgtable) return -ENOMEM; pmd_populate_kernel(&init_mm, &__pmd, pgtable); for (i = 0; i < PTRS_PER_PTE; i++, addr += PAGE_SIZE) { pte_t entry, *pte; pgprot_t pgprot = PAGE_KERNEL; entry = mk_pte(head + i, pgprot); pte = pte_offset_kernel(&__pmd, addr); set_pte_at(&init_mm, addr, pte, entry); } spin_lock(&init_mm.page_table_lock); if (likely(pmd_leaf(*pmd))) { /* * Higher order allocations from buddy allocator must be able to * be treated as indepdenent small pages (as they can be freed * individually). */ if (!PageReserved(head)) split_page(head, get_order(PMD_SIZE)); /* Make pte visible before pmd. See comment in pmd_install(). */ smp_wmb(); pmd_populate_kernel(&init_mm, pmd, pgtable); if (!(walk->flags & VMEMMAP_SPLIT_NO_TLB_FLUSH)) flush_tlb_kernel_range(start, start + PMD_SIZE); } else { pte_free_kernel(&init_mm, pgtable); } spin_unlock(&init_mm.page_table_lock); return 0; } static int vmemmap_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long next, struct mm_walk *walk) { int ret = 0; struct page *head; struct vmemmap_remap_walk *vmemmap_walk = walk->private; /* Only splitting, not remapping the vmemmap pages. */ if (!vmemmap_walk->remap_pte) walk->action = ACTION_CONTINUE; spin_lock(&init_mm.page_table_lock); head = pmd_leaf(*pmd) ? pmd_page(*pmd) : NULL; /* * Due to HugeTLB alignment requirements and the vmemmap * pages being at the start of the hotplugged memory * region in memory_hotplug.memmap_on_memory case. Checking * the vmemmap page associated with the first vmemmap page * if it is self-hosted is sufficient. * * [ hotplugged memory ] * [ section ][...][ section ] * [ vmemmap ][ usable memory ] * ^ | ^ | * +--+ | | * +------------------------+ */ if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG) && unlikely(!vmemmap_walk->nr_walked)) { struct page *page = head ? head + pte_index(addr) : pte_page(ptep_get(pte_offset_kernel(pmd, addr))); if (PageVmemmapSelfHosted(page)) ret = -ENOTSUPP; } spin_unlock(&init_mm.page_table_lock); if (!head || ret) return ret; return vmemmap_split_pmd(pmd, head, addr & PMD_MASK, vmemmap_walk); } static int vmemmap_pte_entry(pte_t *pte, unsigned long addr, unsigned long next, struct mm_walk *walk) { struct vmemmap_remap_walk *vmemmap_walk = walk->private; /* * The reuse_page is found 'first' in page table walking before * starting remapping. */ if (!vmemmap_walk->reuse_page) vmemmap_walk->reuse_page = pte_page(ptep_get(pte)); else vmemmap_walk->remap_pte(pte, addr, vmemmap_walk); vmemmap_walk->nr_walked++; return 0; } static const struct mm_walk_ops vmemmap_remap_ops = { .pmd_entry = vmemmap_pmd_entry, .pte_entry = vmemmap_pte_entry, }; static int vmemmap_remap_range(unsigned long start, unsigned long end, struct vmemmap_remap_walk *walk) { int ret; VM_BUG_ON(!PAGE_ALIGNED(start | end)); mmap_read_lock(&init_mm); ret = walk_page_range_novma(&init_mm, start, end, &vmemmap_remap_ops, NULL, walk); mmap_read_unlock(&init_mm); if (ret) return ret; if (walk->remap_pte && !(walk->flags & VMEMMAP_REMAP_NO_TLB_FLUSH)) flush_tlb_kernel_range(start, end); return 0; } /* * Free a vmemmap page. A vmemmap page can be allocated from the memblock * allocator or buddy allocator. If the PG_reserved flag is set, it means * that it allocated from the memblock allocator, just free it via the * free_bootmem_page(). Otherwise, use __free_page(). */ static inline void free_vmemmap_page(struct page *page) { if (PageReserved(page)) { memmap_boot_pages_add(-1); free_bootmem_page(page); } else { memmap_pages_add(-1); __free_page(page); } } /* Free a list of the vmemmap pages */ static void free_vmemmap_page_list(struct list_head *list) { struct page *page, *next; list_for_each_entry_safe(page, next, list, lru) free_vmemmap_page(page); } static void vmemmap_remap_pte(pte_t *pte, unsigned long addr, struct vmemmap_remap_walk *walk) { /* * Remap the tail pages as read-only to catch illegal write operation * to the tail pages. */ pgprot_t pgprot = PAGE_KERNEL_RO; struct page *page = pte_page(ptep_get(pte)); pte_t entry; /* Remapping the head page requires r/w */ if (unlikely(addr == walk->reuse_addr)) { pgprot = PAGE_KERNEL; list_del(&walk->reuse_page->lru); /* * Makes sure that preceding stores to the page contents from * vmemmap_remap_free() become visible before the set_pte_at() * write. */ smp_wmb(); } entry = mk_pte(walk->reuse_page, pgprot); list_add(&page->lru, walk->vmemmap_pages); set_pte_at(&init_mm, addr, pte, entry); } /* * How many struct page structs need to be reset. When we reuse the head * struct page, the special metadata (e.g. page->flags or page->mapping) * cannot copy to the tail struct page structs. The invalid value will be * checked in the free_tail_page_prepare(). In order to avoid the message * of "corrupted mapping in tail page". We need to reset at least 4 (one * head struct page struct and three tail struct page structs) struct page * structs. */ #define NR_RESET_STRUCT_PAGE 4 static inline void reset_struct_pages(struct page *start) { struct page *from = start + NR_RESET_STRUCT_PAGE; BUILD_BUG_ON(NR_RESET_STRUCT_PAGE * 2 > PAGE_SIZE / sizeof(struct page)); memcpy(start, from, sizeof(*from) * NR_RESET_STRUCT_PAGE); } static void vmemmap_restore_pte(pte_t *pte, unsigned long addr, struct vmemmap_remap_walk *walk) { pgprot_t pgprot = PAGE_KERNEL; struct page *page; void *to; BUG_ON(pte_page(ptep_get(pte)) != walk->reuse_page); page = list_first_entry(walk->vmemmap_pages, struct page, lru); list_del(&page->lru); to = page_to_virt(page); copy_page(to, (void *)walk->reuse_addr); reset_struct_pages(to); /* * Makes sure that preceding stores to the page contents become visible * before the set_pte_at() write. */ smp_wmb(); set_pte_at(&init_mm, addr, pte, mk_pte(page, pgprot)); } /** * vmemmap_remap_split - split the vmemmap virtual address range [@start, @end) * backing PMDs of the directmap into PTEs * @start: start address of the vmemmap virtual address range that we want * to remap. * @end: end address of the vmemmap virtual address range that we want to * remap. * @reuse: reuse address. * * Return: %0 on success, negative error code otherwise. */ static int vmemmap_remap_split(unsigned long start, unsigned long end, unsigned long reuse) { struct vmemmap_remap_walk walk = { .remap_pte = NULL, .flags = VMEMMAP_SPLIT_NO_TLB_FLUSH, }; /* See the comment in the vmemmap_remap_free(). */ BUG_ON(start - reuse != PAGE_SIZE); return vmemmap_remap_range(reuse, end, &walk); } /** * vmemmap_remap_free - remap the vmemmap virtual address range [@start, @end) * to the page which @reuse is mapped to, then free vmemmap * which the range are mapped to. * @start: start address of the vmemmap virtual address range that we want * to remap. * @end: end address of the vmemmap virtual address range that we want to * remap. * @reuse: reuse address. * @vmemmap_pages: list to deposit vmemmap pages to be freed. It is callers * responsibility to free pages. * @flags: modifications to vmemmap_remap_walk flags * * Return: %0 on success, negative error code otherwise. */ static int vmemmap_remap_free(unsigned long start, unsigned long end, unsigned long reuse, struct list_head *vmemmap_pages, unsigned long flags) { int ret; struct vmemmap_remap_walk walk = { .remap_pte = vmemmap_remap_pte, .reuse_addr = reuse, .vmemmap_pages = vmemmap_pages, .flags = flags, }; int nid = page_to_nid((struct page *)reuse); gfp_t gfp_mask = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; /* * Allocate a new head vmemmap page to avoid breaking a contiguous * block of struct page memory when freeing it back to page allocator * in free_vmemmap_page_list(). This will allow the likely contiguous * struct page backing memory to be kept contiguous and allowing for * more allocations of hugepages. Fallback to the currently * mapped head page in case should it fail to allocate. */ walk.reuse_page = alloc_pages_node(nid, gfp_mask, 0); if (walk.reuse_page) { copy_page(page_to_virt(walk.reuse_page), (void *)walk.reuse_addr); list_add(&walk.reuse_page->lru, vmemmap_pages); memmap_pages_add(1); } /* * In order to make remapping routine most efficient for the huge pages, * the routine of vmemmap page table walking has the following rules * (see more details from the vmemmap_pte_range()): * * - The range [@start, @end) and the range [@reuse, @reuse + PAGE_SIZE) * should be continuous. * - The @reuse address is part of the range [@reuse, @end) that we are * walking which is passed to vmemmap_remap_range(). * - The @reuse address is the first in the complete range. * * So we need to make sure that @start and @reuse meet the above rules. */ BUG_ON(start - reuse != PAGE_SIZE); ret = vmemmap_remap_range(reuse, end, &walk); if (ret && walk.nr_walked) { end = reuse + walk.nr_walked * PAGE_SIZE; /* * vmemmap_pages contains pages from the previous * vmemmap_remap_range call which failed. These * are pages which were removed from the vmemmap. * They will be restored in the following call. */ walk = (struct vmemmap_remap_walk) { .remap_pte = vmemmap_restore_pte, .reuse_addr = reuse, .vmemmap_pages = vmemmap_pages, .flags = 0, }; vmemmap_remap_range(reuse, end, &walk); } return ret; } static int alloc_vmemmap_page_list(unsigned long start, unsigned long end, struct list_head *list) { gfp_t gfp_mask = GFP_KERNEL | __GFP_RETRY_MAYFAIL; unsigned long nr_pages = (end - start) >> PAGE_SHIFT; int nid = page_to_nid((struct page *)start); struct page *page, *next; int i; for (i = 0; i < nr_pages; i++) { page = alloc_pages_node(nid, gfp_mask, 0); if (!page) goto out; list_add(&page->lru, list); } memmap_pages_add(nr_pages); return 0; out: list_for_each_entry_safe(page, next, list, lru) __free_page(page); return -ENOMEM; } /** * vmemmap_remap_alloc - remap the vmemmap virtual address range [@start, end) * to the page which is from the @vmemmap_pages * respectively. * @start: start address of the vmemmap virtual address range that we want * to remap. * @end: end address of the vmemmap virtual address range that we want to * remap. * @reuse: reuse address. * @flags: modifications to vmemmap_remap_walk flags * * Return: %0 on success, negative error code otherwise. */ static int vmemmap_remap_alloc(unsigned long start, unsigned long end, unsigned long reuse, unsigned long flags) { LIST_HEAD(vmemmap_pages); struct vmemmap_remap_walk walk = { .remap_pte = vmemmap_restore_pte, .reuse_addr = reuse, .vmemmap_pages = &vmemmap_pages, .flags = flags, }; /* See the comment in the vmemmap_remap_free(). */ BUG_ON(start - reuse != PAGE_SIZE); if (alloc_vmemmap_page_list(start, end, &vmemmap_pages)) return -ENOMEM; return vmemmap_remap_range(reuse, end, &walk); } DEFINE_STATIC_KEY_FALSE(hugetlb_optimize_vmemmap_key); EXPORT_SYMBOL(hugetlb_optimize_vmemmap_key); static bool vmemmap_optimize_enabled = IS_ENABLED(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON); static int __init hugetlb_vmemmap_optimize_param(char *buf) { return kstrtobool(buf, &vmemmap_optimize_enabled); } early_param("hugetlb_free_vmemmap", hugetlb_vmemmap_optimize_param); static int __hugetlb_vmemmap_restore_folio(const struct hstate *h, struct folio *folio, unsigned long flags) { int ret; unsigned long vmemmap_start = (unsigned long)&folio->page, vmemmap_end; unsigned long vmemmap_reuse; VM_WARN_ON_ONCE_FOLIO(!folio_test_hugetlb(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_ref_count(folio), folio); if (!folio_test_hugetlb_vmemmap_optimized(folio)) return 0; if (flags & VMEMMAP_SYNCHRONIZE_RCU) synchronize_rcu(); vmemmap_end = vmemmap_start + hugetlb_vmemmap_size(h); vmemmap_reuse = vmemmap_start; vmemmap_start += HUGETLB_VMEMMAP_RESERVE_SIZE; /* * The pages which the vmemmap virtual address range [@vmemmap_start, * @vmemmap_end) are mapped to are freed to the buddy allocator, and * the range is mapped to the page which @vmemmap_reuse is mapped to. * When a HugeTLB page is freed to the buddy allocator, previously * discarded vmemmap pages must be allocated and remapping. */ ret = vmemmap_remap_alloc(vmemmap_start, vmemmap_end, vmemmap_reuse, flags); if (!ret) { folio_clear_hugetlb_vmemmap_optimized(folio); static_branch_dec(&hugetlb_optimize_vmemmap_key); } return ret; } /** * hugetlb_vmemmap_restore_folio - restore previously optimized (by * hugetlb_vmemmap_optimize_folio()) vmemmap pages which * will be reallocated and remapped. * @h: struct hstate. * @folio: the folio whose vmemmap pages will be restored. * * Return: %0 if @folio's vmemmap pages have been reallocated and remapped, * negative error code otherwise. */ int hugetlb_vmemmap_restore_folio(const struct hstate *h, struct folio *folio) { return __hugetlb_vmemmap_restore_folio(h, folio, VMEMMAP_SYNCHRONIZE_RCU); } /** * hugetlb_vmemmap_restore_folios - restore vmemmap for every folio on the list. * @h: hstate. * @folio_list: list of folios. * @non_hvo_folios: Output list of folios for which vmemmap exists. * * Return: number of folios for which vmemmap was restored, or an error code * if an error was encountered restoring vmemmap for a folio. * Folios that have vmemmap are moved to the non_hvo_folios * list. Processing of entries stops when the first error is * encountered. The folio that experienced the error and all * non-processed folios will remain on folio_list. */ long hugetlb_vmemmap_restore_folios(const struct hstate *h, struct list_head *folio_list, struct list_head *non_hvo_folios) { struct folio *folio, *t_folio; long restored = 0; long ret = 0; unsigned long flags = VMEMMAP_REMAP_NO_TLB_FLUSH | VMEMMAP_SYNCHRONIZE_RCU; list_for_each_entry_safe(folio, t_folio, folio_list, lru) { if (folio_test_hugetlb_vmemmap_optimized(folio)) { ret = __hugetlb_vmemmap_restore_folio(h, folio, flags); /* only need to synchronize_rcu() once for each batch */ flags &= ~VMEMMAP_SYNCHRONIZE_RCU; if (ret) break; restored++; } /* Add non-optimized folios to output list */ list_move(&folio->lru, non_hvo_folios); } if (restored) flush_tlb_all(); if (!ret) ret = restored; return ret; } /* Return true iff a HugeTLB whose vmemmap should and can be optimized. */ static bool vmemmap_should_optimize_folio(const struct hstate *h, struct folio *folio) { if (folio_test_hugetlb_vmemmap_optimized(folio)) return false; if (!READ_ONCE(vmemmap_optimize_enabled)) return false; if (!hugetlb_vmemmap_optimizable(h)) return false; return true; } static int __hugetlb_vmemmap_optimize_folio(const struct hstate *h, struct folio *folio, struct list_head *vmemmap_pages, unsigned long flags) { int ret = 0; unsigned long vmemmap_start = (unsigned long)&folio->page, vmemmap_end; unsigned long vmemmap_reuse; VM_WARN_ON_ONCE_FOLIO(!folio_test_hugetlb(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_ref_count(folio), folio); if (!vmemmap_should_optimize_folio(h, folio)) return ret; static_branch_inc(&hugetlb_optimize_vmemmap_key); if (flags & VMEMMAP_SYNCHRONIZE_RCU) synchronize_rcu(); /* * Very Subtle * If VMEMMAP_REMAP_NO_TLB_FLUSH is set, TLB flushing is not performed * immediately after remapping. As a result, subsequent accesses * and modifications to struct pages associated with the hugetlb * page could be to the OLD struct pages. Set the vmemmap optimized * flag here so that it is copied to the new head page. This keeps * the old and new struct pages in sync. * If there is an error during optimization, we will immediately FLUSH * the TLB and clear the flag below. */ folio_set_hugetlb_vmemmap_optimized(folio); vmemmap_end = vmemmap_start + hugetlb_vmemmap_size(h); vmemmap_reuse = vmemmap_start; vmemmap_start += HUGETLB_VMEMMAP_RESERVE_SIZE; /* * Remap the vmemmap virtual address range [@vmemmap_start, @vmemmap_end) * to the page which @vmemmap_reuse is mapped to. Add pages previously * mapping the range to vmemmap_pages list so that they can be freed by * the caller. */ ret = vmemmap_remap_free(vmemmap_start, vmemmap_end, vmemmap_reuse, vmemmap_pages, flags); if (ret) { static_branch_dec(&hugetlb_optimize_vmemmap_key); folio_clear_hugetlb_vmemmap_optimized(folio); } return ret; } /** * hugetlb_vmemmap_optimize_folio - optimize @folio's vmemmap pages. * @h: struct hstate. * @folio: the folio whose vmemmap pages will be optimized. * * This function only tries to optimize @folio's vmemmap pages and does not * guarantee that the optimization will succeed after it returns. The caller * can use folio_test_hugetlb_vmemmap_optimized(@folio) to detect if @folio's * vmemmap pages have been optimized. */ void hugetlb_vmemmap_optimize_folio(const struct hstate *h, struct folio *folio) { LIST_HEAD(vmemmap_pages); __hugetlb_vmemmap_optimize_folio(h, folio, &vmemmap_pages, VMEMMAP_SYNCHRONIZE_RCU); free_vmemmap_page_list(&vmemmap_pages); } static int hugetlb_vmemmap_split_folio(const struct hstate *h, struct folio *folio) { unsigned long vmemmap_start = (unsigned long)&folio->page, vmemmap_end; unsigned long vmemmap_reuse; if (!vmemmap_should_optimize_folio(h, folio)) return 0; vmemmap_end = vmemmap_start + hugetlb_vmemmap_size(h); vmemmap_reuse = vmemmap_start; vmemmap_start += HUGETLB_VMEMMAP_RESERVE_SIZE; /* * Split PMDs on the vmemmap virtual address range [@vmemmap_start, * @vmemmap_end] */ return vmemmap_remap_split(vmemmap_start, vmemmap_end, vmemmap_reuse); } static void __hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_list, bool boot) { struct folio *folio; int nr_to_optimize; LIST_HEAD(vmemmap_pages); unsigned long flags = VMEMMAP_REMAP_NO_TLB_FLUSH | VMEMMAP_SYNCHRONIZE_RCU; nr_to_optimize = 0; list_for_each_entry(folio, folio_list, lru) { int ret; unsigned long spfn, epfn; if (boot && folio_test_hugetlb_vmemmap_optimized(folio)) { /* * Already optimized by pre-HVO, just map the * mirrored tail page structs RO. */ spfn = (unsigned long)&folio->page; epfn = spfn + pages_per_huge_page(h); vmemmap_wrprotect_hvo(spfn, epfn, folio_nid(folio), HUGETLB_VMEMMAP_RESERVE_SIZE); register_page_bootmem_memmap(pfn_to_section_nr(spfn), &folio->page, HUGETLB_VMEMMAP_RESERVE_SIZE); static_branch_inc(&hugetlb_optimize_vmemmap_key); continue; } nr_to_optimize++; ret = hugetlb_vmemmap_split_folio(h, folio); /* * Spliting the PMD requires allocating a page, thus lets fail * early once we encounter the first OOM. No point in retrying * as it can be dynamically done on remap with the memory * we get back from the vmemmap deduplication. */ if (ret == -ENOMEM) break; } if (!nr_to_optimize) /* * All pre-HVO folios, nothing left to do. It's ok if * there is a mix of pre-HVO and not yet HVO-ed folios * here, as __hugetlb_vmemmap_optimize_folio() will * skip any folios that already have the optimized flag * set, see vmemmap_should_optimize_folio(). */ goto out; flush_tlb_all(); list_for_each_entry(folio, folio_list, lru) { int ret; ret = __hugetlb_vmemmap_optimize_folio(h, folio, &vmemmap_pages, flags); /* only need to synchronize_rcu() once for each batch */ flags &= ~VMEMMAP_SYNCHRONIZE_RCU; /* * Pages to be freed may have been accumulated. If we * encounter an ENOMEM, free what we have and try again. * This can occur in the case that both spliting fails * halfway and head page allocation also failed. In this * case __hugetlb_vmemmap_optimize_folio() would free memory * allowing more vmemmap remaps to occur. */ if (ret == -ENOMEM && !list_empty(&vmemmap_pages)) { flush_tlb_all(); free_vmemmap_page_list(&vmemmap_pages); INIT_LIST_HEAD(&vmemmap_pages); __hugetlb_vmemmap_optimize_folio(h, folio, &vmemmap_pages, flags); } } out: flush_tlb_all(); free_vmemmap_page_list(&vmemmap_pages); } void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_list) { __hugetlb_vmemmap_optimize_folios(h, folio_list, false); } void hugetlb_vmemmap_optimize_bootmem_folios(struct hstate *h, struct list_head *folio_list) { __hugetlb_vmemmap_optimize_folios(h, folio_list, true); } #ifdef CONFIG_SPARSEMEM_VMEMMAP_PREINIT /* Return true of a bootmem allocated HugeTLB page should be pre-HVO-ed */ static bool vmemmap_should_optimize_bootmem_page(struct huge_bootmem_page *m) { unsigned long section_size, psize, pmd_vmemmap_size; phys_addr_t paddr; if (!READ_ONCE(vmemmap_optimize_enabled)) return false; if (!hugetlb_vmemmap_optimizable(m->hstate)) return false; psize = huge_page_size(m->hstate); paddr = virt_to_phys(m); /* * Pre-HVO only works if the bootmem huge page * is aligned to the section size. */ section_size = (1UL << PA_SECTION_SHIFT); if (!IS_ALIGNED(paddr, section_size) || !IS_ALIGNED(psize, section_size)) return false; /* * The pre-HVO code does not deal with splitting PMDS, * so the bootmem page must be aligned to the number * of base pages that can be mapped with one vmemmap PMD. */ pmd_vmemmap_size = (PMD_SIZE / (sizeof(struct page))) << PAGE_SHIFT; if (!IS_ALIGNED(paddr, pmd_vmemmap_size) || !IS_ALIGNED(psize, pmd_vmemmap_size)) return false; return true; } /* * Initialize memmap section for a gigantic page, HVO-style. */ void __init hugetlb_vmemmap_init_early(int nid) { unsigned long psize, paddr, section_size; unsigned long ns, i, pnum, pfn, nr_pages; unsigned long start, end; struct huge_bootmem_page *m = NULL; void *map; /* * Noting to do if bootmem pages were not allocated * early in boot, or if HVO wasn't enabled in the * first place. */ if (!hugetlb_bootmem_allocated()) return; if (!READ_ONCE(vmemmap_optimize_enabled)) return; section_size = (1UL << PA_SECTION_SHIFT); list_for_each_entry(m, &huge_boot_pages[nid], list) { if (!vmemmap_should_optimize_bootmem_page(m)) continue; nr_pages = pages_per_huge_page(m->hstate); psize = nr_pages << PAGE_SHIFT; paddr = virt_to_phys(m); pfn = PHYS_PFN(paddr); map = pfn_to_page(pfn); start = (unsigned long)map; end = start + nr_pages * sizeof(struct page); if (vmemmap_populate_hvo(start, end, nid, HUGETLB_VMEMMAP_RESERVE_SIZE) < 0) continue; memmap_boot_pages_add(HUGETLB_VMEMMAP_RESERVE_SIZE / PAGE_SIZE); pnum = pfn_to_section_nr(pfn); ns = psize / section_size; for (i = 0; i < ns; i++) { sparse_init_early_section(nid, map, pnum, SECTION_IS_VMEMMAP_PREINIT); map += section_map_size(); pnum++; } m->flags |= HUGE_BOOTMEM_HVO; } } void __init hugetlb_vmemmap_init_late(int nid) { struct huge_bootmem_page *m, *tm; unsigned long phys, nr_pages, start, end; unsigned long pfn, nr_mmap; struct hstate *h; void *map; if (!hugetlb_bootmem_allocated()) return; if (!READ_ONCE(vmemmap_optimize_enabled)) return; list_for_each_entry_safe(m, tm, &huge_boot_pages[nid], list) { if (!(m->flags & HUGE_BOOTMEM_HVO)) continue; phys = virt_to_phys(m); h = m->hstate; pfn = PHYS_PFN(phys); nr_pages = pages_per_huge_page(h); if (!hugetlb_bootmem_page_zones_valid(nid, m)) { /* * Oops, the hugetlb page spans multiple zones. * Remove it from the list, and undo HVO. */ list_del(&m->list); map = pfn_to_page(pfn); start = (unsigned long)map; end = start + nr_pages * sizeof(struct page); vmemmap_undo_hvo(start, end, nid, HUGETLB_VMEMMAP_RESERVE_SIZE); nr_mmap = end - start - HUGETLB_VMEMMAP_RESERVE_SIZE; memmap_boot_pages_add(DIV_ROUND_UP(nr_mmap, PAGE_SIZE)); memblock_phys_free(phys, huge_page_size(h)); continue; } else m->flags |= HUGE_BOOTMEM_ZONES_VALID; } } #endif static const struct ctl_table hugetlb_vmemmap_sysctls[] = { { .procname = "hugetlb_optimize_vmemmap", .data = &vmemmap_optimize_enabled, .maxlen = sizeof(vmemmap_optimize_enabled), .mode = 0644, .proc_handler = proc_dobool, }, }; static int __init hugetlb_vmemmap_init(void) { const struct hstate *h; /* HUGETLB_VMEMMAP_RESERVE_SIZE should cover all used struct pages */ BUILD_BUG_ON(__NR_USED_SUBPAGE > HUGETLB_VMEMMAP_RESERVE_PAGES); for_each_hstate(h) { if (hugetlb_vmemmap_optimizable(h)) { register_sysctl_init("vm", hugetlb_vmemmap_sysctls); break; } } return 0; } late_initcall(hugetlb_vmemmap_init); |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NetLabel Network Address Lists * * This file contains network address list functions used to manage ordered * lists of network addresses for use by the NetLabel subsystem. The NetLabel * system manages static and dynamic label mappings for network protocols such * as CIPSO and RIPSO. * * Author: Paul Moore <paul@paul-moore.com> */ /* * (c) Copyright Hewlett-Packard Development Company, L.P., 2008 */ #include <linux/types.h> #include <linux/rcupdate.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <net/ip.h> #include <net/ipv6.h> #include <linux/audit.h> #include "netlabel_addrlist.h" /* * Address List Functions */ /** * netlbl_af4list_search - Search for a matching IPv4 address entry * @addr: IPv4 address * @head: the list head * * Description: * Searches the IPv4 address list given by @head. If a matching address entry * is found it is returned, otherwise NULL is returned. The caller is * responsible for calling the rcu_read_[un]lock() functions. * */ struct netlbl_af4list *netlbl_af4list_search(__be32 addr, struct list_head *head) { struct netlbl_af4list *iter; list_for_each_entry_rcu(iter, head, list) if (iter->valid && (addr & iter->mask) == iter->addr) return iter; return NULL; } /** * netlbl_af4list_search_exact - Search for an exact IPv4 address entry * @addr: IPv4 address * @mask: IPv4 address mask * @head: the list head * * Description: * Searches the IPv4 address list given by @head. If an exact match if found * it is returned, otherwise NULL is returned. The caller is responsible for * calling the rcu_read_[un]lock() functions. * */ struct netlbl_af4list *netlbl_af4list_search_exact(__be32 addr, __be32 mask, struct list_head *head) { struct netlbl_af4list *iter; list_for_each_entry_rcu(iter, head, list) if (iter->valid && iter->addr == addr && iter->mask == mask) return iter; return NULL; } #if IS_ENABLED(CONFIG_IPV6) /** * netlbl_af6list_search - Search for a matching IPv6 address entry * @addr: IPv6 address * @head: the list head * * Description: * Searches the IPv6 address list given by @head. If a matching address entry * is found it is returned, otherwise NULL is returned. The caller is * responsible for calling the rcu_read_[un]lock() functions. * */ struct netlbl_af6list *netlbl_af6list_search(const struct in6_addr *addr, struct list_head *head) { struct netlbl_af6list *iter; list_for_each_entry_rcu(iter, head, list) if (iter->valid && ipv6_masked_addr_cmp(&iter->addr, &iter->mask, addr) == 0) return iter; return NULL; } /** * netlbl_af6list_search_exact - Search for an exact IPv6 address entry * @addr: IPv6 address * @mask: IPv6 address mask * @head: the list head * * Description: * Searches the IPv6 address list given by @head. If an exact match if found * it is returned, otherwise NULL is returned. The caller is responsible for * calling the rcu_read_[un]lock() functions. * */ struct netlbl_af6list *netlbl_af6list_search_exact(const struct in6_addr *addr, const struct in6_addr *mask, struct list_head *head) { struct netlbl_af6list *iter; list_for_each_entry_rcu(iter, head, list) if (iter->valid && ipv6_addr_equal(&iter->addr, addr) && ipv6_addr_equal(&iter->mask, mask)) return iter; return NULL; } #endif /* IPv6 */ /** * netlbl_af4list_add - Add a new IPv4 address entry to a list * @entry: address entry * @head: the list head * * Description: * Add a new address entry to the list pointed to by @head. On success zero is * returned, otherwise a negative value is returned. The caller is responsible * for calling the necessary locking functions. * */ int netlbl_af4list_add(struct netlbl_af4list *entry, struct list_head *head) { struct netlbl_af4list *iter; iter = netlbl_af4list_search(entry->addr, head); if (iter != NULL && iter->addr == entry->addr && iter->mask == entry->mask) return -EEXIST; /* in order to speed up address searches through the list (the common * case) we need to keep the list in order based on the size of the * address mask such that the entry with the widest mask (smallest * numerical value) appears first in the list */ list_for_each_entry_rcu(iter, head, list) if (iter->valid && ntohl(entry->mask) > ntohl(iter->mask)) { __list_add_rcu(&entry->list, iter->list.prev, &iter->list); return 0; } list_add_tail_rcu(&entry->list, head); return 0; } #if IS_ENABLED(CONFIG_IPV6) /** * netlbl_af6list_add - Add a new IPv6 address entry to a list * @entry: address entry * @head: the list head * * Description: * Add a new address entry to the list pointed to by @head. On success zero is * returned, otherwise a negative value is returned. The caller is responsible * for calling the necessary locking functions. * */ int netlbl_af6list_add(struct netlbl_af6list *entry, struct list_head *head) { struct netlbl_af6list *iter; iter = netlbl_af6list_search(&entry->addr, head); if (iter != NULL && ipv6_addr_equal(&iter->addr, &entry->addr) && ipv6_addr_equal(&iter->mask, &entry->mask)) return -EEXIST; /* in order to speed up address searches through the list (the common * case) we need to keep the list in order based on the size of the * address mask such that the entry with the widest mask (smallest * numerical value) appears first in the list */ list_for_each_entry_rcu(iter, head, list) if (iter->valid && ipv6_addr_cmp(&entry->mask, &iter->mask) > 0) { __list_add_rcu(&entry->list, iter->list.prev, &iter->list); return 0; } list_add_tail_rcu(&entry->list, head); return 0; } #endif /* IPv6 */ /** * netlbl_af4list_remove_entry - Remove an IPv4 address entry * @entry: address entry * * Description: * Remove the specified IP address entry. The caller is responsible for * calling the necessary locking functions. * */ void netlbl_af4list_remove_entry(struct netlbl_af4list *entry) { entry->valid = 0; list_del_rcu(&entry->list); } /** * netlbl_af4list_remove - Remove an IPv4 address entry * @addr: IP address * @mask: IP address mask * @head: the list head * * Description: * Remove an IP address entry from the list pointed to by @head. Returns the * entry on success, NULL on failure. The caller is responsible for calling * the necessary locking functions. * */ struct netlbl_af4list *netlbl_af4list_remove(__be32 addr, __be32 mask, struct list_head *head) { struct netlbl_af4list *entry; entry = netlbl_af4list_search_exact(addr, mask, head); if (entry == NULL) return NULL; netlbl_af4list_remove_entry(entry); return entry; } #if IS_ENABLED(CONFIG_IPV6) /** * netlbl_af6list_remove_entry - Remove an IPv6 address entry * @entry: address entry * * Description: * Remove the specified IP address entry. The caller is responsible for * calling the necessary locking functions. * */ void netlbl_af6list_remove_entry(struct netlbl_af6list *entry) { entry->valid = 0; list_del_rcu(&entry->list); } /** * netlbl_af6list_remove - Remove an IPv6 address entry * @addr: IP address * @mask: IP address mask * @head: the list head * * Description: * Remove an IP address entry from the list pointed to by @head. Returns the * entry on success, NULL on failure. The caller is responsible for calling * the necessary locking functions. * */ struct netlbl_af6list *netlbl_af6list_remove(const struct in6_addr *addr, const struct in6_addr *mask, struct list_head *head) { struct netlbl_af6list *entry; entry = netlbl_af6list_search_exact(addr, mask, head); if (entry == NULL) return NULL; netlbl_af6list_remove_entry(entry); return entry; } #endif /* IPv6 */ /* * Audit Helper Functions */ #ifdef CONFIG_AUDIT /** * netlbl_af4list_audit_addr - Audit an IPv4 address * @audit_buf: audit buffer * @src: true if source address, false if destination * @dev: network interface * @addr: IP address * @mask: IP address mask * * Description: * Write the IPv4 address and address mask, if necessary, to @audit_buf. * */ void netlbl_af4list_audit_addr(struct audit_buffer *audit_buf, int src, const char *dev, __be32 addr, __be32 mask) { u32 mask_val = ntohl(mask); char *dir = (src ? "src" : "dst"); if (dev != NULL) audit_log_format(audit_buf, " netif=%s", dev); audit_log_format(audit_buf, " %s=%pI4", dir, &addr); if (mask_val != 0xffffffff) { u32 mask_len = 0; while (mask_val > 0) { mask_val <<= 1; mask_len++; } audit_log_format(audit_buf, " %s_prefixlen=%d", dir, mask_len); } } #if IS_ENABLED(CONFIG_IPV6) /** * netlbl_af6list_audit_addr - Audit an IPv6 address * @audit_buf: audit buffer * @src: true if source address, false if destination * @dev: network interface * @addr: IP address * @mask: IP address mask * * Description: * Write the IPv6 address and address mask, if necessary, to @audit_buf. * */ void netlbl_af6list_audit_addr(struct audit_buffer *audit_buf, int src, const char *dev, const struct in6_addr *addr, const struct in6_addr *mask) { char *dir = (src ? "src" : "dst"); if (dev != NULL) audit_log_format(audit_buf, " netif=%s", dev); audit_log_format(audit_buf, " %s=%pI6", dir, addr); if (ntohl(mask->s6_addr32[3]) != 0xffffffff) { u32 mask_len = 0; u32 mask_val; int iter = -1; while (ntohl(mask->s6_addr32[++iter]) == 0xffffffff) mask_len += 32; mask_val = ntohl(mask->s6_addr32[iter]); while (mask_val > 0) { mask_val <<= 1; mask_len++; } audit_log_format(audit_buf, " %s_prefixlen=%d", dir, mask_len); } } #endif /* IPv6 */ #endif /* CONFIG_AUDIT */ |
| 203 76 1 113 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CLOSURE_H #define _LINUX_CLOSURE_H #include <linux/llist.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> #include <linux/workqueue.h> /* * Closure is perhaps the most overused and abused term in computer science, but * since I've been unable to come up with anything better you're stuck with it * again. * * What are closures? * * They embed a refcount. The basic idea is they count "things that are in * progress" - in flight bios, some other thread that's doing something else - * anything you might want to wait on. * * The refcount may be manipulated with closure_get() and closure_put(). * closure_put() is where many of the interesting things happen, when it causes * the refcount to go to 0. * * Closures can be used to wait on things both synchronously and asynchronously, * and synchronous and asynchronous use can be mixed without restriction. To * wait synchronously, use closure_sync() - you will sleep until your closure's * refcount hits 1. * * To wait asynchronously, use * continue_at(cl, next_function, workqueue); * * passing it, as you might expect, the function to run when nothing is pending * and the workqueue to run that function out of. * * continue_at() also, critically, requires a 'return' immediately following the * location where this macro is referenced, to return to the calling function. * There's good reason for this. * * To use safely closures asynchronously, they must always have a refcount while * they are running owned by the thread that is running them. Otherwise, suppose * you submit some bios and wish to have a function run when they all complete: * * foo_endio(struct bio *bio) * { * closure_put(cl); * } * * closure_init(cl); * * do_stuff(); * closure_get(cl); * bio1->bi_endio = foo_endio; * bio_submit(bio1); * * do_more_stuff(); * closure_get(cl); * bio2->bi_endio = foo_endio; * bio_submit(bio2); * * continue_at(cl, complete_some_read, system_wq); * * If closure's refcount started at 0, complete_some_read() could run before the * second bio was submitted - which is almost always not what you want! More * importantly, it wouldn't be possible to say whether the original thread or * complete_some_read()'s thread owned the closure - and whatever state it was * associated with! * * So, closure_init() initializes a closure's refcount to 1 - and when a * closure_fn is run, the refcount will be reset to 1 first. * * Then, the rule is - if you got the refcount with closure_get(), release it * with closure_put() (i.e, in a bio->bi_endio function). If you have a refcount * on a closure because you called closure_init() or you were run out of a * closure - _always_ use continue_at(). Doing so consistently will help * eliminate an entire class of particularly pernicious races. * * Lastly, you might have a wait list dedicated to a specific event, and have no * need for specifying the condition - you just want to wait until someone runs * closure_wake_up() on the appropriate wait list. In that case, just use * closure_wait(). It will return either true or false, depending on whether the * closure was already on a wait list or not - a closure can only be on one wait * list at a time. * * Parents: * * closure_init() takes two arguments - it takes the closure to initialize, and * a (possibly null) parent. * * If parent is non null, the new closure will have a refcount for its lifetime; * a closure is considered to be "finished" when its refcount hits 0 and the * function to run is null. Hence * * continue_at(cl, NULL, NULL); * * returns up the (spaghetti) stack of closures, precisely like normal return * returns up the C stack. continue_at() with non null fn is better thought of * as doing a tail call. * * All this implies that a closure should typically be embedded in a particular * struct (which its refcount will normally control the lifetime of), and that * struct can very much be thought of as a stack frame. */ struct closure; struct closure_syncer; typedef void (closure_fn) (struct work_struct *); extern struct dentry *bcache_debug; struct closure_waitlist { struct llist_head list; }; enum closure_state { /* * CLOSURE_WAITING: Set iff the closure is on a waitlist. Must be set by * the thread that owns the closure, and cleared by the thread that's * waking up the closure. * * The rest are for debugging and don't affect behaviour: * * CLOSURE_RUNNING: Set when a closure is running (i.e. by * closure_init() and when closure_put() runs then next function), and * must be cleared before remaining hits 0. Primarily to help guard * against incorrect usage and accidentally transferring references. * continue_at() and closure_return() clear it for you, if you're doing * something unusual you can use closure_set_dead() which also helps * annotate where references are being transferred. */ CLOSURE_BITS_START = (1U << 26), CLOSURE_DESTRUCTOR = (1U << 26), CLOSURE_WAITING = (1U << 28), CLOSURE_RUNNING = (1U << 30), }; #define CLOSURE_GUARD_MASK \ ((CLOSURE_DESTRUCTOR|CLOSURE_WAITING|CLOSURE_RUNNING) << 1) #define CLOSURE_REMAINING_MASK (CLOSURE_BITS_START - 1) #define CLOSURE_REMAINING_INITIALIZER (1|CLOSURE_RUNNING) struct closure { union { struct { struct workqueue_struct *wq; struct closure_syncer *s; struct llist_node list; closure_fn *fn; }; struct work_struct work; }; struct closure *parent; atomic_t remaining; bool closure_get_happened; #ifdef CONFIG_DEBUG_CLOSURES #define CLOSURE_MAGIC_DEAD 0xc054dead #define CLOSURE_MAGIC_ALIVE 0xc054a11e #define CLOSURE_MAGIC_STACK 0xc05451cc unsigned int magic; struct list_head all; unsigned long ip; unsigned long waiting_on; #endif }; void closure_sub(struct closure *cl, int v); void closure_put(struct closure *cl); void __closure_wake_up(struct closure_waitlist *list); bool closure_wait(struct closure_waitlist *list, struct closure *cl); void __closure_sync(struct closure *cl); static inline unsigned closure_nr_remaining(struct closure *cl) { return atomic_read(&cl->remaining) & CLOSURE_REMAINING_MASK; } /** * closure_sync - sleep until a closure a closure has nothing left to wait on * * Sleeps until the refcount hits 1 - the thread that's running the closure owns * the last refcount. */ static inline void closure_sync(struct closure *cl) { #ifdef CONFIG_DEBUG_CLOSURES BUG_ON(closure_nr_remaining(cl) != 1 && !cl->closure_get_happened); #endif if (cl->closure_get_happened) __closure_sync(cl); } int __closure_sync_timeout(struct closure *cl, unsigned long timeout); static inline int closure_sync_timeout(struct closure *cl, unsigned long timeout) { #ifdef CONFIG_DEBUG_CLOSURES BUG_ON(closure_nr_remaining(cl) != 1 && !cl->closure_get_happened); #endif return cl->closure_get_happened ? __closure_sync_timeout(cl, timeout) : 0; } #ifdef CONFIG_DEBUG_CLOSURES void closure_debug_create(struct closure *cl); void closure_debug_destroy(struct closure *cl); #else static inline void closure_debug_create(struct closure *cl) {} static inline void closure_debug_destroy(struct closure *cl) {} #endif static inline void closure_set_ip(struct closure *cl) { #ifdef CONFIG_DEBUG_CLOSURES cl->ip = _THIS_IP_; #endif } static inline void closure_set_ret_ip(struct closure *cl) { #ifdef CONFIG_DEBUG_CLOSURES cl->ip = _RET_IP_; #endif } static inline void closure_set_waiting(struct closure *cl, unsigned long f) { #ifdef CONFIG_DEBUG_CLOSURES cl->waiting_on = f; #endif } static inline void closure_set_stopped(struct closure *cl) { atomic_sub(CLOSURE_RUNNING, &cl->remaining); } static inline void set_closure_fn(struct closure *cl, closure_fn *fn, struct workqueue_struct *wq) { closure_set_ip(cl); cl->fn = fn; cl->wq = wq; } static inline void closure_queue(struct closure *cl) { struct workqueue_struct *wq = cl->wq; /** * Changes made to closure, work_struct, or a couple of other structs * may cause work.func not pointing to the right location. */ BUILD_BUG_ON(offsetof(struct closure, fn) != offsetof(struct work_struct, func)); if (wq) { INIT_WORK(&cl->work, cl->work.func); BUG_ON(!queue_work(wq, &cl->work)); } else cl->fn(&cl->work); } /** * closure_get - increment a closure's refcount */ static inline void closure_get(struct closure *cl) { cl->closure_get_happened = true; #ifdef CONFIG_DEBUG_CLOSURES BUG_ON((atomic_inc_return(&cl->remaining) & CLOSURE_REMAINING_MASK) <= 1); #else atomic_inc(&cl->remaining); #endif } /** * closure_get_not_zero */ static inline bool closure_get_not_zero(struct closure *cl) { unsigned old = atomic_read(&cl->remaining); do { if (!(old & CLOSURE_REMAINING_MASK)) return false; } while (!atomic_try_cmpxchg_acquire(&cl->remaining, &old, old + 1)); return true; } /** * closure_init - Initialize a closure, setting the refcount to 1 * @cl: closure to initialize * @parent: parent of the new closure. cl will take a refcount on it for its * lifetime; may be NULL. */ static inline void closure_init(struct closure *cl, struct closure *parent) { cl->fn = NULL; cl->parent = parent; if (parent) closure_get(parent); atomic_set(&cl->remaining, CLOSURE_REMAINING_INITIALIZER); cl->closure_get_happened = false; closure_debug_create(cl); closure_set_ip(cl); } static inline void closure_init_stack(struct closure *cl) { memset(cl, 0, sizeof(struct closure)); atomic_set(&cl->remaining, CLOSURE_REMAINING_INITIALIZER); #ifdef CONFIG_DEBUG_CLOSURES cl->magic = CLOSURE_MAGIC_STACK; #endif } static inline void closure_init_stack_release(struct closure *cl) { memset(cl, 0, sizeof(struct closure)); atomic_set_release(&cl->remaining, CLOSURE_REMAINING_INITIALIZER); #ifdef CONFIG_DEBUG_CLOSURES cl->magic = CLOSURE_MAGIC_STACK; #endif } /** * closure_wake_up - wake up all closures on a wait list, * with memory barrier */ static inline void closure_wake_up(struct closure_waitlist *list) { /* Memory barrier for the wait list */ smp_mb(); __closure_wake_up(list); } #define CLOSURE_CALLBACK(name) void name(struct work_struct *ws) #define closure_type(name, type, member) \ struct closure *cl = container_of(ws, struct closure, work); \ type *name = container_of(cl, type, member) /** * continue_at - jump to another function with barrier * * After @cl is no longer waiting on anything (i.e. all outstanding refs have * been dropped with closure_put()), it will resume execution at @fn running out * of @wq (or, if @wq is NULL, @fn will be called by closure_put() directly). * * This is because after calling continue_at() you no longer have a ref on @cl, * and whatever @cl owns may be freed out from under you - a running closure fn * has a ref on its own closure which continue_at() drops. * * Note you are expected to immediately return after using this macro. */ #define continue_at(_cl, _fn, _wq) \ do { \ set_closure_fn(_cl, _fn, _wq); \ closure_sub(_cl, CLOSURE_RUNNING + 1); \ } while (0) /** * closure_return - finish execution of a closure * * This is used to indicate that @cl is finished: when all outstanding refs on * @cl have been dropped @cl's ref on its parent closure (as passed to * closure_init()) will be dropped, if one was specified - thus this can be * thought of as returning to the parent closure. */ #define closure_return(_cl) continue_at((_cl), NULL, NULL) void closure_return_sync(struct closure *cl); /** * continue_at_nobarrier - jump to another function without barrier * * Causes @fn to be executed out of @cl, in @wq context (or called directly if * @wq is NULL). * * The ref the caller of continue_at_nobarrier() had on @cl is now owned by @fn, * thus it's not safe to touch anything protected by @cl after a * continue_at_nobarrier(). */ #define continue_at_nobarrier(_cl, _fn, _wq) \ do { \ set_closure_fn(_cl, _fn, _wq); \ closure_queue(_cl); \ } while (0) /** * closure_return_with_destructor - finish execution of a closure, * with destructor * * Works like closure_return(), except @destructor will be called when all * outstanding refs on @cl have been dropped; @destructor may be used to safely * free the memory occupied by @cl, and it is called with the ref on the parent * closure still held - so @destructor could safely return an item to a * freelist protected by @cl's parent. */ #define closure_return_with_destructor(_cl, _destructor) \ do { \ set_closure_fn(_cl, _destructor, NULL); \ closure_sub(_cl, CLOSURE_RUNNING - CLOSURE_DESTRUCTOR + 1); \ } while (0) /** * closure_call - execute @fn out of a new, uninitialized closure * * Typically used when running out of one closure, and we want to run @fn * asynchronously out of a new closure - @parent will then wait for @cl to * finish. */ static inline void closure_call(struct closure *cl, closure_fn fn, struct workqueue_struct *wq, struct closure *parent) { closure_init(cl, parent); continue_at_nobarrier(cl, fn, wq); } #define __closure_wait_event(waitlist, _cond) \ do { \ struct closure cl; \ \ closure_init_stack(&cl); \ \ while (1) { \ closure_wait(waitlist, &cl); \ if (_cond) \ break; \ closure_sync(&cl); \ } \ closure_wake_up(waitlist); \ closure_sync(&cl); \ } while (0) #define closure_wait_event(waitlist, _cond) \ do { \ if (!(_cond)) \ __closure_wait_event(waitlist, _cond); \ } while (0) #define __closure_wait_event_timeout(waitlist, _cond, _until) \ ({ \ struct closure cl; \ long _t; \ \ closure_init_stack(&cl); \ \ while (1) { \ closure_wait(waitlist, &cl); \ if (_cond) { \ _t = max_t(long, 1L, _until - jiffies); \ break; \ } \ _t = max_t(long, 0L, _until - jiffies); \ if (!_t) \ break; \ closure_sync_timeout(&cl, _t); \ } \ closure_wake_up(waitlist); \ closure_sync(&cl); \ _t; \ }) /* * Returns 0 if timeout expired, remaining time in jiffies (at least 1) if * condition became true */ #define closure_wait_event_timeout(waitlist, _cond, _timeout) \ ({ \ unsigned long _until = jiffies + _timeout; \ (_cond) \ ? max_t(long, 1L, _until - jiffies) \ : __closure_wait_event_timeout(waitlist, _cond, _until);\ }) #endif /* _LINUX_CLOSURE_H */ |
| 1 457 12 14 3843 3778 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_USER_NAMESPACE_H #define _LINUX_USER_NAMESPACE_H #include <linux/kref.h> #include <linux/nsproxy.h> #include <linux/ns_common.h> #include <linux/rculist_nulls.h> #include <linux/sched.h> #include <linux/workqueue.h> #include <linux/rcuref.h> #include <linux/rwsem.h> #include <linux/sysctl.h> #include <linux/err.h> #define UID_GID_MAP_MAX_BASE_EXTENTS 5 #define UID_GID_MAP_MAX_EXTENTS 340 struct uid_gid_extent { u32 first; u32 lower_first; u32 count; }; struct uid_gid_map { /* 64 bytes -- 1 cache line */ union { struct { struct uid_gid_extent extent[UID_GID_MAP_MAX_BASE_EXTENTS]; u32 nr_extents; }; struct { struct uid_gid_extent *forward; struct uid_gid_extent *reverse; }; }; }; #define USERNS_SETGROUPS_ALLOWED 1UL #define USERNS_INIT_FLAGS USERNS_SETGROUPS_ALLOWED struct ucounts; enum ucount_type { UCOUNT_USER_NAMESPACES, UCOUNT_PID_NAMESPACES, UCOUNT_UTS_NAMESPACES, UCOUNT_IPC_NAMESPACES, UCOUNT_NET_NAMESPACES, UCOUNT_MNT_NAMESPACES, UCOUNT_CGROUP_NAMESPACES, UCOUNT_TIME_NAMESPACES, #ifdef CONFIG_INOTIFY_USER UCOUNT_INOTIFY_INSTANCES, UCOUNT_INOTIFY_WATCHES, #endif #ifdef CONFIG_FANOTIFY UCOUNT_FANOTIFY_GROUPS, UCOUNT_FANOTIFY_MARKS, #endif UCOUNT_COUNTS, }; enum rlimit_type { UCOUNT_RLIMIT_NPROC, UCOUNT_RLIMIT_MSGQUEUE, UCOUNT_RLIMIT_SIGPENDING, UCOUNT_RLIMIT_MEMLOCK, UCOUNT_RLIMIT_COUNTS, }; #if IS_ENABLED(CONFIG_BINFMT_MISC) struct binfmt_misc; #endif struct user_namespace { struct uid_gid_map uid_map; struct uid_gid_map gid_map; struct uid_gid_map projid_map; struct user_namespace *parent; int level; kuid_t owner; kgid_t group; struct ns_common ns; unsigned long flags; /* parent_could_setfcap: true if the creator if this ns had CAP_SETFCAP * in its effective capability set at the child ns creation time. */ bool parent_could_setfcap; #ifdef CONFIG_KEYS /* List of joinable keyrings in this namespace. Modification access of * these pointers is controlled by keyring_sem. Once * user_keyring_register is set, it won't be changed, so it can be * accessed directly with READ_ONCE(). */ struct list_head keyring_name_list; struct key *user_keyring_register; struct rw_semaphore keyring_sem; #endif /* Register of per-UID persistent keyrings for this namespace */ #ifdef CONFIG_PERSISTENT_KEYRINGS struct key *persistent_keyring_register; #endif struct work_struct work; #ifdef CONFIG_SYSCTL struct ctl_table_set set; struct ctl_table_header *sysctls; #endif struct ucounts *ucounts; long ucount_max[UCOUNT_COUNTS]; long rlimit_max[UCOUNT_RLIMIT_COUNTS]; #if IS_ENABLED(CONFIG_BINFMT_MISC) struct binfmt_misc *binfmt_misc; #endif } __randomize_layout; struct ucounts { struct hlist_nulls_node node; struct user_namespace *ns; kuid_t uid; struct rcu_head rcu; rcuref_t count; atomic_long_t ucount[UCOUNT_COUNTS]; atomic_long_t rlimit[UCOUNT_RLIMIT_COUNTS]; }; extern struct user_namespace init_user_ns; extern struct ucounts init_ucounts; bool setup_userns_sysctls(struct user_namespace *ns); void retire_userns_sysctls(struct user_namespace *ns); struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid, enum ucount_type type); void dec_ucount(struct ucounts *ucounts, enum ucount_type type); struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid); void put_ucounts(struct ucounts *ucounts); static inline struct ucounts * __must_check get_ucounts(struct ucounts *ucounts) { if (rcuref_get(&ucounts->count)) return ucounts; return NULL; } static inline long get_rlimit_value(struct ucounts *ucounts, enum rlimit_type type) { return atomic_long_read(&ucounts->rlimit[type]); } long inc_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v); bool dec_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v); long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type, bool override_rlimit); void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type); bool is_rlimit_overlimit(struct ucounts *ucounts, enum rlimit_type type, unsigned long max); static inline long get_userns_rlimit_max(struct user_namespace *ns, enum rlimit_type type) { return READ_ONCE(ns->rlimit_max[type]); } static inline void set_userns_rlimit_max(struct user_namespace *ns, enum rlimit_type type, unsigned long max) { ns->rlimit_max[type] = max <= LONG_MAX ? max : LONG_MAX; } #ifdef CONFIG_USER_NS static inline struct user_namespace *get_user_ns(struct user_namespace *ns) { if (ns) refcount_inc(&ns->ns.count); return ns; } extern int create_user_ns(struct cred *new); extern int unshare_userns(unsigned long unshare_flags, struct cred **new_cred); extern void __put_user_ns(struct user_namespace *ns); static inline void put_user_ns(struct user_namespace *ns) { if (ns && refcount_dec_and_test(&ns->ns.count)) __put_user_ns(ns); } struct seq_operations; extern const struct seq_operations proc_uid_seq_operations; extern const struct seq_operations proc_gid_seq_operations; extern const struct seq_operations proc_projid_seq_operations; extern ssize_t proc_uid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_gid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_projid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_setgroups_write(struct file *, const char __user *, size_t, loff_t *); extern int proc_setgroups_show(struct seq_file *m, void *v); extern bool userns_may_setgroups(const struct user_namespace *ns); extern bool in_userns(const struct user_namespace *ancestor, const struct user_namespace *child); extern bool current_in_userns(const struct user_namespace *target_ns); struct ns_common *ns_get_owner(struct ns_common *ns); #else static inline struct user_namespace *get_user_ns(struct user_namespace *ns) { return &init_user_ns; } static inline int create_user_ns(struct cred *new) { return -EINVAL; } static inline int unshare_userns(unsigned long unshare_flags, struct cred **new_cred) { if (unshare_flags & CLONE_NEWUSER) return -EINVAL; return 0; } static inline void put_user_ns(struct user_namespace *ns) { } static inline bool userns_may_setgroups(const struct user_namespace *ns) { return true; } static inline bool in_userns(const struct user_namespace *ancestor, const struct user_namespace *child) { return true; } static inline bool current_in_userns(const struct user_namespace *target_ns) { return true; } static inline struct ns_common *ns_get_owner(struct ns_common *ns) { return ERR_PTR(-EPERM); } #endif #endif /* _LINUX_USER_H */ |
| 338 332 4 330 7 41 192 3 2 192 192 192 54 87 87 2 2 87 294 262 67 26 4 26 257 447 442 437 442 447 447 536 412 178 22 11 22 24 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 | /* * linux/fs/nls/nls_base.c * * Native language support--charsets and unicode translations. * By Gordon Chaffee 1996, 1997 * * Unicode based case conversion 1999 by Wolfram Pienkoss * */ #include <linux/module.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/kmod.h> #include <linux/spinlock.h> #include <asm/byteorder.h> static struct nls_table default_table; static struct nls_table *tables = &default_table; static DEFINE_SPINLOCK(nls_lock); /* * Sample implementation from Unicode home page. * http://www.stonehand.com/unicode/standard/fss-utf.html */ struct utf8_table { int cmask; int cval; int shift; long lmask; long lval; }; static const struct utf8_table utf8_table[] = { {0x80, 0x00, 0*6, 0x7F, 0, /* 1 byte sequence */}, {0xE0, 0xC0, 1*6, 0x7FF, 0x80, /* 2 byte sequence */}, {0xF0, 0xE0, 2*6, 0xFFFF, 0x800, /* 3 byte sequence */}, {0xF8, 0xF0, 3*6, 0x1FFFFF, 0x10000, /* 4 byte sequence */}, {0xFC, 0xF8, 4*6, 0x3FFFFFF, 0x200000, /* 5 byte sequence */}, {0xFE, 0xFC, 5*6, 0x7FFFFFFF, 0x4000000, /* 6 byte sequence */}, {0, /* end of table */} }; #define UNICODE_MAX 0x0010ffff #define PLANE_SIZE 0x00010000 #define SURROGATE_MASK 0xfffff800 #define SURROGATE_PAIR 0x0000d800 #define SURROGATE_LOW 0x00000400 #define SURROGATE_BITS 0x000003ff int utf8_to_utf32(const u8 *s, int inlen, unicode_t *pu) { unsigned long l; int c0, c, nc; const struct utf8_table *t; nc = 0; c0 = *s; l = c0; for (t = utf8_table; t->cmask; t++) { nc++; if ((c0 & t->cmask) == t->cval) { l &= t->lmask; if (l < t->lval || l > UNICODE_MAX || (l & SURROGATE_MASK) == SURROGATE_PAIR) return -1; *pu = (unicode_t) l; return nc; } if (inlen <= nc) return -1; s++; c = (*s ^ 0x80) & 0xFF; if (c & 0xC0) return -1; l = (l << 6) | c; } return -1; } EXPORT_SYMBOL(utf8_to_utf32); int utf32_to_utf8(unicode_t u, u8 *s, int maxout) { unsigned long l; int c, nc; const struct utf8_table *t; if (!s) return 0; l = u; if (l > UNICODE_MAX || (l & SURROGATE_MASK) == SURROGATE_PAIR) return -1; nc = 0; for (t = utf8_table; t->cmask && maxout; t++, maxout--) { nc++; if (l <= t->lmask) { c = t->shift; *s = (u8) (t->cval | (l >> c)); while (c > 0) { c -= 6; s++; *s = (u8) (0x80 | ((l >> c) & 0x3F)); } return nc; } } return -1; } EXPORT_SYMBOL(utf32_to_utf8); static inline void put_utf16(wchar_t *s, unsigned c, enum utf16_endian endian) { switch (endian) { default: *s = (wchar_t) c; break; case UTF16_LITTLE_ENDIAN: *s = __cpu_to_le16(c); break; case UTF16_BIG_ENDIAN: *s = __cpu_to_be16(c); break; } } int utf8s_to_utf16s(const u8 *s, int inlen, enum utf16_endian endian, wchar_t *pwcs, int maxout) { u16 *op; int size; unicode_t u; op = pwcs; while (inlen > 0 && maxout > 0 && *s) { if (*s & 0x80) { size = utf8_to_utf32(s, inlen, &u); if (size < 0) return -EINVAL; s += size; inlen -= size; if (u >= PLANE_SIZE) { if (maxout < 2) break; u -= PLANE_SIZE; put_utf16(op++, SURROGATE_PAIR | ((u >> 10) & SURROGATE_BITS), endian); put_utf16(op++, SURROGATE_PAIR | SURROGATE_LOW | (u & SURROGATE_BITS), endian); maxout -= 2; } else { put_utf16(op++, u, endian); maxout--; } } else { put_utf16(op++, *s++, endian); inlen--; maxout--; } } return op - pwcs; } EXPORT_SYMBOL(utf8s_to_utf16s); static inline unsigned long get_utf16(unsigned c, enum utf16_endian endian) { switch (endian) { default: return c; case UTF16_LITTLE_ENDIAN: return __le16_to_cpu(c); case UTF16_BIG_ENDIAN: return __be16_to_cpu(c); } } int utf16s_to_utf8s(const wchar_t *pwcs, int inlen, enum utf16_endian endian, u8 *s, int maxout) { u8 *op; int size; unsigned long u, v; op = s; while (inlen > 0 && maxout > 0) { u = get_utf16(*pwcs, endian); if (!u) break; pwcs++; inlen--; if (u > 0x7f) { if ((u & SURROGATE_MASK) == SURROGATE_PAIR) { if (u & SURROGATE_LOW) { /* Ignore character and move on */ continue; } if (inlen <= 0) break; v = get_utf16(*pwcs, endian); if ((v & SURROGATE_MASK) != SURROGATE_PAIR || !(v & SURROGATE_LOW)) { /* Ignore character and move on */ continue; } u = PLANE_SIZE + ((u & SURROGATE_BITS) << 10) + (v & SURROGATE_BITS); pwcs++; inlen--; } size = utf32_to_utf8(u, op, maxout); if (size == -1) { /* Ignore character and move on */ } else { op += size; maxout -= size; } } else { *op++ = (u8) u; maxout--; } } return op - s; } EXPORT_SYMBOL(utf16s_to_utf8s); int __register_nls(struct nls_table *nls, struct module *owner) { struct nls_table ** tmp = &tables; if (nls->next) return -EBUSY; nls->owner = owner; spin_lock(&nls_lock); while (*tmp) { if (nls == *tmp) { spin_unlock(&nls_lock); return -EBUSY; } tmp = &(*tmp)->next; } nls->next = tables; tables = nls; spin_unlock(&nls_lock); return 0; } EXPORT_SYMBOL(__register_nls); int unregister_nls(struct nls_table * nls) { struct nls_table ** tmp = &tables; spin_lock(&nls_lock); while (*tmp) { if (nls == *tmp) { *tmp = nls->next; spin_unlock(&nls_lock); return 0; } tmp = &(*tmp)->next; } spin_unlock(&nls_lock); return -EINVAL; } static struct nls_table *find_nls(const char *charset) { struct nls_table *nls; spin_lock(&nls_lock); for (nls = tables; nls; nls = nls->next) { if (!strcmp(nls->charset, charset)) break; if (nls->alias && !strcmp(nls->alias, charset)) break; } if (nls && !try_module_get(nls->owner)) nls = NULL; spin_unlock(&nls_lock); return nls; } struct nls_table *load_nls(const char *charset) { return try_then_request_module(find_nls(charset), "nls_%s", charset); } void unload_nls(struct nls_table *nls) { if (nls) module_put(nls->owner); } static const wchar_t charset2uni[256] = { /* 0x00*/ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10*/ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20*/ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30*/ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40*/ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50*/ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60*/ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70*/ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80*/ 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, /* 0x90*/ 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f, /* 0xa0*/ 0x00a0, 0x00a1, 0x00a2, 0x00a3, 0x00a4, 0x00a5, 0x00a6, 0x00a7, 0x00a8, 0x00a9, 0x00aa, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00af, /* 0xb0*/ 0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7, 0x00b8, 0x00b9, 0x00ba, 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x00bf, /* 0xc0*/ 0x00c0, 0x00c1, 0x00c2, 0x00c3, 0x00c4, 0x00c5, 0x00c6, 0x00c7, 0x00c8, 0x00c9, 0x00ca, 0x00cb, 0x00cc, 0x00cd, 0x00ce, 0x00cf, /* 0xd0*/ 0x00d0, 0x00d1, 0x00d2, 0x00d3, 0x00d4, 0x00d5, 0x00d6, 0x00d7, 0x00d8, 0x00d9, 0x00da, 0x00db, 0x00dc, 0x00dd, 0x00de, 0x00df, /* 0xe0*/ 0x00e0, 0x00e1, 0x00e2, 0x00e3, 0x00e4, 0x00e5, 0x00e6, 0x00e7, 0x00e8, 0x00e9, 0x00ea, 0x00eb, 0x00ec, 0x00ed, 0x00ee, 0x00ef, /* 0xf0*/ 0x00f0, 0x00f1, 0x00f2, 0x00f3, 0x00f4, 0x00f5, 0x00f6, 0x00f7, 0x00f8, 0x00f9, 0x00fa, 0x00fb, 0x00fc, 0x00fd, 0x00fe, 0x00ff, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static const unsigned char *const page_uni2charset[256] = { page00 }; static const unsigned char charset2lower[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */ 0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table default_table = { .charset = "default", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; /* Returns a simple default translation table */ struct nls_table *load_nls_default(void) { struct nls_table *default_nls; default_nls = load_nls(CONFIG_NLS_DEFAULT); if (default_nls != NULL) return default_nls; else return &default_table; } EXPORT_SYMBOL(unregister_nls); EXPORT_SYMBOL(unload_nls); EXPORT_SYMBOL(load_nls); EXPORT_SYMBOL(load_nls_default); MODULE_DESCRIPTION("Base file system native language support"); MODULE_LICENSE("Dual BSD/GPL"); |
| 44 45 44 45 43 43 45 45 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * jump label x86 support * * Copyright (C) 2009 Jason Baron <jbaron@redhat.com> * */ #include <linux/jump_label.h> #include <linux/memory.h> #include <linux/uaccess.h> #include <linux/module.h> #include <linux/list.h> #include <linux/jhash.h> #include <linux/cpu.h> #include <asm/kprobes.h> #include <asm/alternative.h> #include <asm/text-patching.h> #include <asm/insn.h> int arch_jump_entry_size(struct jump_entry *entry) { struct insn insn = {}; insn_decode_kernel(&insn, (void *)jump_entry_code(entry)); BUG_ON(insn.length != 2 && insn.length != 5); return insn.length; } struct jump_label_patch { const void *code; int size; }; static struct jump_label_patch __jump_label_patch(struct jump_entry *entry, enum jump_label_type type) { const void *expect, *code, *nop; const void *addr, *dest; int size; addr = (void *)jump_entry_code(entry); dest = (void *)jump_entry_target(entry); size = arch_jump_entry_size(entry); switch (size) { case JMP8_INSN_SIZE: code = text_gen_insn(JMP8_INSN_OPCODE, addr, dest); nop = x86_nops[size]; break; case JMP32_INSN_SIZE: code = text_gen_insn(JMP32_INSN_OPCODE, addr, dest); nop = x86_nops[size]; break; default: BUG(); } if (type == JUMP_LABEL_JMP) expect = nop; else expect = code; if (memcmp(addr, expect, size)) { /* * The location is not an op that we were expecting. * Something went wrong. Crash the box, as something could be * corrupting the kernel. */ pr_crit("jump_label: Fatal kernel bug, unexpected op at %pS [%p] (%5ph != %5ph)) size:%d type:%d\n", addr, addr, addr, expect, size, type); BUG(); } if (type == JUMP_LABEL_NOP) code = nop; return (struct jump_label_patch){.code = code, .size = size}; } static __always_inline void __jump_label_transform(struct jump_entry *entry, enum jump_label_type type, int init) { const struct jump_label_patch jlp = __jump_label_patch(entry, type); /* * As long as only a single processor is running and the code is still * not marked as RO, text_poke_early() can be used; Checking that * system_state is SYSTEM_BOOTING guarantees it. It will be set to * SYSTEM_SCHEDULING before other cores are awaken and before the * code is write-protected. * * At the time the change is being done, just ignore whether we * are doing nop -> jump or jump -> nop transition, and assume * always nop being the 'currently valid' instruction */ if (init || system_state == SYSTEM_BOOTING) { text_poke_early((void *)jump_entry_code(entry), jlp.code, jlp.size); return; } text_poke_bp((void *)jump_entry_code(entry), jlp.code, jlp.size, NULL); } static void __ref jump_label_transform(struct jump_entry *entry, enum jump_label_type type, int init) { mutex_lock(&text_mutex); __jump_label_transform(entry, type, init); mutex_unlock(&text_mutex); } void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type) { jump_label_transform(entry, type, 0); } bool arch_jump_label_transform_queue(struct jump_entry *entry, enum jump_label_type type) { struct jump_label_patch jlp; if (system_state == SYSTEM_BOOTING) { /* * Fallback to the non-batching mode. */ arch_jump_label_transform(entry, type); return true; } mutex_lock(&text_mutex); jlp = __jump_label_patch(entry, type); text_poke_queue((void *)jump_entry_code(entry), jlp.code, jlp.size, NULL); mutex_unlock(&text_mutex); return true; } void arch_jump_label_transform_apply(void) { mutex_lock(&text_mutex); text_poke_finish(); mutex_unlock(&text_mutex); } |
| 13 13 1 12 13 1 1 1 1 1 1 3 2 3 6 6 1 13 11 12 1 13 1 8 13 1 5 7 8 4 4 11 11 2 2 14 13 2 11 9 1 26 1 11 15 10 1 27 13 14 27 13 13 13 14 16 11 11 22 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/blkdev.h> #include <linux/iversion.h> #include "ctree.h" #include "fs.h" #include "messages.h" #include "compression.h" #include "delalloc-space.h" #include "disk-io.h" #include "reflink.h" #include "transaction.h" #include "subpage.h" #include "accessors.h" #include "file-item.h" #include "file.h" #include "super.h" #define BTRFS_MAX_DEDUPE_LEN SZ_16M static int clone_finish_inode_update(struct btrfs_trans_handle *trans, struct inode *inode, u64 endoff, const u64 destoff, const u64 olen, int no_time_update) { int ret; inode_inc_iversion(inode); if (!no_time_update) { inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); } /* * We round up to the block size at eof when determining which * extents to clone above, but shouldn't round up the file size. */ if (endoff > destoff + olen) endoff = destoff + olen; if (endoff > inode->i_size) { i_size_write(inode, endoff); btrfs_inode_safe_disk_i_size_write(BTRFS_I(inode), 0); } ret = btrfs_update_inode(trans, BTRFS_I(inode)); if (ret) { btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); goto out; } ret = btrfs_end_transaction(trans); out: return ret; } static int copy_inline_to_page(struct btrfs_inode *inode, const u64 file_offset, char *inline_data, const u64 size, const u64 datal, const u8 comp_type) { struct btrfs_fs_info *fs_info = inode->root->fs_info; const u32 block_size = fs_info->sectorsize; const u64 range_end = file_offset + block_size - 1; const size_t inline_size = size - btrfs_file_extent_calc_inline_size(0); char *data_start = inline_data + btrfs_file_extent_calc_inline_size(0); struct extent_changeset *data_reserved = NULL; struct folio *folio = NULL; struct address_space *mapping = inode->vfs_inode.i_mapping; int ret; ASSERT(IS_ALIGNED(file_offset, block_size)); /* * We have flushed and locked the ranges of the source and destination * inodes, we also have locked the inodes, so we are safe to do a * reservation here. Also we must not do the reservation while holding * a transaction open, otherwise we would deadlock. */ ret = btrfs_delalloc_reserve_space(inode, &data_reserved, file_offset, block_size); if (ret) goto out; folio = __filemap_get_folio(mapping, file_offset >> PAGE_SHIFT, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, btrfs_alloc_write_mask(mapping)); if (IS_ERR(folio)) { ret = -ENOMEM; goto out_unlock; } ret = set_folio_extent_mapped(folio); if (ret < 0) goto out_unlock; clear_extent_bit(&inode->io_tree, file_offset, range_end, EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, NULL); ret = btrfs_set_extent_delalloc(inode, file_offset, range_end, 0, NULL); if (ret) goto out_unlock; /* * After dirtying the page our caller will need to start a transaction, * and if we are low on metadata free space, that can cause flushing of * delalloc for all inodes in order to get metadata space released. * However we are holding the range locked for the whole duration of * the clone/dedupe operation, so we may deadlock if that happens and no * other task releases enough space. So mark this inode as not being * possible to flush to avoid such deadlock. We will clear that flag * when we finish cloning all extents, since a transaction is started * after finding each extent to clone. */ set_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &inode->runtime_flags); if (comp_type == BTRFS_COMPRESS_NONE) { memcpy_to_folio(folio, offset_in_folio(folio, file_offset), data_start, datal); } else { ret = btrfs_decompress(comp_type, data_start, folio, offset_in_folio(folio, file_offset), inline_size, datal); if (ret) goto out_unlock; flush_dcache_folio(folio); } /* * If our inline data is smaller then the block/page size, then the * remaining of the block/page is equivalent to zeroes. We had something * like the following done: * * $ xfs_io -f -c "pwrite -S 0xab 0 500" file * $ sync # (or fsync) * $ xfs_io -c "falloc 0 4K" file * $ xfs_io -c "pwrite -S 0xcd 4K 4K" * * So what's in the range [500, 4095] corresponds to zeroes. */ if (datal < block_size) folio_zero_range(folio, datal, block_size - datal); btrfs_folio_set_uptodate(fs_info, folio, file_offset, block_size); btrfs_folio_clear_checked(fs_info, folio, file_offset, block_size); btrfs_folio_set_dirty(fs_info, folio, file_offset, block_size); out_unlock: if (!IS_ERR(folio)) { folio_unlock(folio); folio_put(folio); } if (ret) btrfs_delalloc_release_space(inode, data_reserved, file_offset, block_size, true); btrfs_delalloc_release_extents(inode, block_size); out: extent_changeset_free(data_reserved); return ret; } /* * Deal with cloning of inline extents. We try to copy the inline extent from * the source inode to destination inode when possible. When not possible we * copy the inline extent's data into the respective page of the inode. */ static int clone_copy_inline_extent(struct btrfs_inode *inode, struct btrfs_path *path, struct btrfs_key *new_key, const u64 drop_start, const u64 datal, const u64 size, const u8 comp_type, char *inline_data, struct btrfs_trans_handle **trans_out) { struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; const u64 aligned_end = ALIGN(new_key->offset + datal, fs_info->sectorsize); struct btrfs_trans_handle *trans = NULL; struct btrfs_drop_extents_args drop_args = { 0 }; int ret; struct btrfs_key key; if (new_key->offset > 0) { ret = copy_inline_to_page(inode, new_key->offset, inline_data, size, datal, comp_type); goto out; } key.objectid = btrfs_ino(inode); key.type = BTRFS_EXTENT_DATA_KEY; key.offset = 0; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) { return ret; } else if (ret > 0) { if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) { ret = btrfs_next_leaf(root, path); if (ret < 0) return ret; else if (ret > 0) goto copy_inline_extent; } btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.objectid == btrfs_ino(inode) && key.type == BTRFS_EXTENT_DATA_KEY) { /* * There's an implicit hole at file offset 0, copy the * inline extent's data to the page. */ ASSERT(key.offset > 0); goto copy_to_page; } } else if (i_size_read(&inode->vfs_inode) <= datal) { struct btrfs_file_extent_item *ei; ei = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_file_extent_item); /* * If it's an inline extent replace it with the source inline * extent, otherwise copy the source inline extent data into * the respective page at the destination inode. */ if (btrfs_file_extent_type(path->nodes[0], ei) == BTRFS_FILE_EXTENT_INLINE) goto copy_inline_extent; goto copy_to_page; } copy_inline_extent: /* * We have no extent items, or we have an extent at offset 0 which may * or may not be inlined. All these cases are dealt the same way. */ if (i_size_read(&inode->vfs_inode) > datal) { /* * At the destination offset 0 we have either a hole, a regular * extent or an inline extent larger then the one we want to * clone. Deal with all these cases by copying the inline extent * data into the respective page at the destination inode. */ goto copy_to_page; } /* * Release path before starting a new transaction so we don't hold locks * that would confuse lockdep. */ btrfs_release_path(path); /* * If we end up here it means were copy the inline extent into a leaf * of the destination inode. We know we will drop or adjust at most one * extent item in the destination root. * * 1 unit - adjusting old extent (we may have to split it) * 1 unit - add new extent * 1 unit - inode update */ trans = btrfs_start_transaction(root, 3); if (IS_ERR(trans)) { ret = PTR_ERR(trans); trans = NULL; goto out; } drop_args.path = path; drop_args.start = drop_start; drop_args.end = aligned_end; drop_args.drop_cache = true; ret = btrfs_drop_extents(trans, root, inode, &drop_args); if (ret) goto out; ret = btrfs_insert_empty_item(trans, root, path, new_key, size); if (ret) goto out; write_extent_buffer(path->nodes[0], inline_data, btrfs_item_ptr_offset(path->nodes[0], path->slots[0]), size); btrfs_update_inode_bytes(inode, datal, drop_args.bytes_found); btrfs_set_inode_full_sync(inode); ret = btrfs_inode_set_file_extent_range(inode, 0, aligned_end); out: if (!ret && !trans) { /* * No transaction here means we copied the inline extent into a * page of the destination inode. * * 1 unit to update inode item */ trans = btrfs_start_transaction(root, 1); if (IS_ERR(trans)) { ret = PTR_ERR(trans); trans = NULL; } } if (ret && trans) { btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); } if (!ret) *trans_out = trans; return ret; copy_to_page: /* * Release our path because we don't need it anymore and also because * copy_inline_to_page() needs to reserve data and metadata, which may * need to flush delalloc when we are low on available space and * therefore cause a deadlock if writeback of an inline extent needs to * write to the same leaf or an ordered extent completion needs to write * to the same leaf. */ btrfs_release_path(path); ret = copy_inline_to_page(inode, new_key->offset, inline_data, size, datal, comp_type); goto out; } /* * Clone a range from inode file to another. * * @src: Inode to clone from * @inode: Inode to clone to * @off: Offset within source to start clone from * @olen: Original length, passed by user, of range to clone * @olen_aligned: Block-aligned value of olen * @destoff: Offset within @inode to start clone * @no_time_update: Whether to update mtime/ctime on the target inode */ static int btrfs_clone(struct inode *src, struct inode *inode, const u64 off, const u64 olen, const u64 olen_aligned, const u64 destoff, int no_time_update) { struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_path *path = NULL; struct extent_buffer *leaf; struct btrfs_trans_handle *trans; char *buf = NULL; struct btrfs_key key; u32 nritems; int slot; int ret; const u64 len = olen_aligned; u64 last_dest_end = destoff; u64 prev_extent_end = off; ret = -ENOMEM; buf = kvmalloc(fs_info->nodesize, GFP_KERNEL); if (!buf) return ret; path = btrfs_alloc_path(); if (!path) { kvfree(buf); return ret; } path->reada = READA_FORWARD; /* Clone data */ key.objectid = btrfs_ino(BTRFS_I(src)); key.type = BTRFS_EXTENT_DATA_KEY; key.offset = off; while (1) { struct btrfs_file_extent_item *extent; u64 extent_gen; int type; u32 size; struct btrfs_key new_key; u64 disko = 0, diskl = 0; u64 datao = 0, datal = 0; u8 comp; u64 drop_start; /* Note the key will change type as we walk through the tree */ ret = btrfs_search_slot(NULL, BTRFS_I(src)->root, &key, path, 0, 0); if (ret < 0) goto out; /* * First search, if no extent item that starts at offset off was * found but the previous item is an extent item, it's possible * it might overlap our target range, therefore process it. */ if (key.offset == off && ret > 0 && path->slots[0] > 0) { btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0] - 1); if (key.type == BTRFS_EXTENT_DATA_KEY) path->slots[0]--; } nritems = btrfs_header_nritems(path->nodes[0]); process_slot: if (path->slots[0] >= nritems) { ret = btrfs_next_leaf(BTRFS_I(src)->root, path); if (ret < 0) goto out; if (ret > 0) break; nritems = btrfs_header_nritems(path->nodes[0]); } leaf = path->nodes[0]; slot = path->slots[0]; btrfs_item_key_to_cpu(leaf, &key, slot); if (key.type > BTRFS_EXTENT_DATA_KEY || key.objectid != btrfs_ino(BTRFS_I(src))) break; ASSERT(key.type == BTRFS_EXTENT_DATA_KEY); extent = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); extent_gen = btrfs_file_extent_generation(leaf, extent); comp = btrfs_file_extent_compression(leaf, extent); type = btrfs_file_extent_type(leaf, extent); if (type == BTRFS_FILE_EXTENT_REG || type == BTRFS_FILE_EXTENT_PREALLOC) { disko = btrfs_file_extent_disk_bytenr(leaf, extent); diskl = btrfs_file_extent_disk_num_bytes(leaf, extent); datao = btrfs_file_extent_offset(leaf, extent); datal = btrfs_file_extent_num_bytes(leaf, extent); } else if (type == BTRFS_FILE_EXTENT_INLINE) { /* Take upper bound, may be compressed */ datal = btrfs_file_extent_ram_bytes(leaf, extent); } /* * The first search might have left us at an extent item that * ends before our target range's start, can happen if we have * holes and NO_HOLES feature enabled. * * Subsequent searches may leave us on a file range we have * processed before - this happens due to a race with ordered * extent completion for a file range that is outside our source * range, but that range was part of a file extent item that * also covered a leading part of our source range. */ if (key.offset + datal <= prev_extent_end) { path->slots[0]++; goto process_slot; } else if (key.offset >= off + len) { break; } prev_extent_end = key.offset + datal; size = btrfs_item_size(leaf, slot); read_extent_buffer(leaf, buf, btrfs_item_ptr_offset(leaf, slot), size); btrfs_release_path(path); memcpy(&new_key, &key, sizeof(new_key)); new_key.objectid = btrfs_ino(BTRFS_I(inode)); if (off <= key.offset) new_key.offset = key.offset + destoff - off; else new_key.offset = destoff; /* * Deal with a hole that doesn't have an extent item that * represents it (NO_HOLES feature enabled). * This hole is either in the middle of the cloning range or at * the beginning (fully overlaps it or partially overlaps it). */ if (new_key.offset != last_dest_end) drop_start = last_dest_end; else drop_start = new_key.offset; if (type == BTRFS_FILE_EXTENT_REG || type == BTRFS_FILE_EXTENT_PREALLOC) { struct btrfs_replace_extent_info clone_info; /* * a | --- range to clone ---| b * | ------------- extent ------------- | */ /* Subtract range b */ if (key.offset + datal > off + len) datal = off + len - key.offset; /* Subtract range a */ if (off > key.offset) { datao += off - key.offset; datal -= off - key.offset; } clone_info.disk_offset = disko; clone_info.disk_len = diskl; clone_info.data_offset = datao; clone_info.data_len = datal; clone_info.file_offset = new_key.offset; clone_info.extent_buf = buf; clone_info.is_new_extent = false; clone_info.update_times = !no_time_update; ret = btrfs_replace_file_extents(BTRFS_I(inode), path, drop_start, new_key.offset + datal - 1, &clone_info, &trans); if (ret) goto out; } else { ASSERT(type == BTRFS_FILE_EXTENT_INLINE); /* * Inline extents always have to start at file offset 0 * and can never be bigger then the sector size. We can * never clone only parts of an inline extent, since all * reflink operations must start at a sector size aligned * offset, and the length must be aligned too or end at * the i_size (which implies the whole inlined data). */ ASSERT(key.offset == 0); ASSERT(datal <= fs_info->sectorsize); if (WARN_ON(type != BTRFS_FILE_EXTENT_INLINE) || WARN_ON(key.offset != 0) || WARN_ON(datal > fs_info->sectorsize)) { ret = -EUCLEAN; goto out; } ret = clone_copy_inline_extent(BTRFS_I(inode), path, &new_key, drop_start, datal, size, comp, buf, &trans); if (ret) goto out; } btrfs_release_path(path); /* * Whenever we share an extent we update the last_reflink_trans * of each inode to the current transaction. This is needed to * make sure fsync does not log multiple checksum items with * overlapping ranges (because some extent items might refer * only to sections of the original extent). For the destination * inode we do this regardless of the generation of the extents * or even if they are inline extents or explicit holes, to make * sure a full fsync does not skip them. For the source inode, * we only need to update last_reflink_trans in case it's a new * extent that is not a hole or an inline extent, to deal with * the checksums problem on fsync. */ if (extent_gen == trans->transid && disko > 0) BTRFS_I(src)->last_reflink_trans = trans->transid; BTRFS_I(inode)->last_reflink_trans = trans->transid; last_dest_end = ALIGN(new_key.offset + datal, fs_info->sectorsize); ret = clone_finish_inode_update(trans, inode, last_dest_end, destoff, olen, no_time_update); if (ret) goto out; if (new_key.offset + datal >= destoff + len) break; btrfs_release_path(path); key.offset = prev_extent_end; if (fatal_signal_pending(current)) { ret = -EINTR; goto out; } cond_resched(); } ret = 0; if (last_dest_end < destoff + len) { /* * We have an implicit hole that fully or partially overlaps our * cloning range at its end. This means that we either have the * NO_HOLES feature enabled or the implicit hole happened due to * mixing buffered and direct IO writes against this file. */ btrfs_release_path(path); /* * When using NO_HOLES and we are cloning a range that covers * only a hole (no extents) into a range beyond the current * i_size, punching a hole in the target range will not create * an extent map defining a hole, because the range starts at or * beyond current i_size. If the file previously had an i_size * greater than the new i_size set by this clone operation, we * need to make sure the next fsync is a full fsync, so that it * detects and logs a hole covering a range from the current * i_size to the new i_size. If the clone range covers extents, * besides a hole, then we know the full sync flag was already * set by previous calls to btrfs_replace_file_extents() that * replaced file extent items. */ if (last_dest_end >= i_size_read(inode)) btrfs_set_inode_full_sync(BTRFS_I(inode)); ret = btrfs_replace_file_extents(BTRFS_I(inode), path, last_dest_end, destoff + len - 1, NULL, &trans); if (ret) goto out; ret = clone_finish_inode_update(trans, inode, destoff + len, destoff, olen, no_time_update); } out: btrfs_free_path(path); kvfree(buf); clear_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &BTRFS_I(inode)->runtime_flags); return ret; } static void btrfs_double_mmap_lock(struct btrfs_inode *inode1, struct btrfs_inode *inode2) { if (inode1 < inode2) swap(inode1, inode2); down_write(&inode1->i_mmap_lock); down_write_nested(&inode2->i_mmap_lock, SINGLE_DEPTH_NESTING); } static void btrfs_double_mmap_unlock(struct btrfs_inode *inode1, struct btrfs_inode *inode2) { up_write(&inode1->i_mmap_lock); up_write(&inode2->i_mmap_lock); } static int btrfs_extent_same_range(struct btrfs_inode *src, u64 loff, u64 len, struct btrfs_inode *dst, u64 dst_loff) { const u64 end = dst_loff + len - 1; struct extent_state *cached_state = NULL; struct btrfs_fs_info *fs_info = src->root->fs_info; const u64 bs = fs_info->sectorsize; int ret; /* * Lock destination range to serialize with concurrent readahead(), and * we are safe from concurrency with relocation of source extents * because we have already locked the inode's i_mmap_lock in exclusive * mode. */ lock_extent(&dst->io_tree, dst_loff, end, &cached_state); ret = btrfs_clone(&src->vfs_inode, &dst->vfs_inode, loff, len, ALIGN(len, bs), dst_loff, 1); unlock_extent(&dst->io_tree, dst_loff, end, &cached_state); btrfs_btree_balance_dirty(fs_info); return ret; } static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen, struct inode *dst, u64 dst_loff) { int ret = 0; u64 i, tail_len, chunk_count; struct btrfs_root *root_dst = BTRFS_I(dst)->root; spin_lock(&root_dst->root_item_lock); if (root_dst->send_in_progress) { btrfs_warn_rl(root_dst->fs_info, "cannot deduplicate to root %llu while send operations are using it (%d in progress)", btrfs_root_id(root_dst), root_dst->send_in_progress); spin_unlock(&root_dst->root_item_lock); return -EAGAIN; } root_dst->dedupe_in_progress++; spin_unlock(&root_dst->root_item_lock); tail_len = olen % BTRFS_MAX_DEDUPE_LEN; chunk_count = div_u64(olen, BTRFS_MAX_DEDUPE_LEN); for (i = 0; i < chunk_count; i++) { ret = btrfs_extent_same_range(BTRFS_I(src), loff, BTRFS_MAX_DEDUPE_LEN, BTRFS_I(dst), dst_loff); if (ret) goto out; loff += BTRFS_MAX_DEDUPE_LEN; dst_loff += BTRFS_MAX_DEDUPE_LEN; } if (tail_len > 0) ret = btrfs_extent_same_range(BTRFS_I(src), loff, tail_len, BTRFS_I(dst), dst_loff); out: spin_lock(&root_dst->root_item_lock); root_dst->dedupe_in_progress--; spin_unlock(&root_dst->root_item_lock); return ret; } static noinline int btrfs_clone_files(struct file *file, struct file *file_src, u64 off, u64 olen, u64 destoff) { struct extent_state *cached_state = NULL; struct inode *inode = file_inode(file); struct inode *src = file_inode(file_src); struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); int ret; int wb_ret; u64 len = olen; u64 bs = fs_info->sectorsize; u64 end; /* * VFS's generic_remap_file_range_prep() protects us from cloning the * eof block into the middle of a file, which would result in corruption * if the file size is not blocksize aligned. So we don't need to check * for that case here. */ if (off + len == src->i_size) len = ALIGN(src->i_size, bs) - off; if (destoff > inode->i_size) { const u64 wb_start = ALIGN_DOWN(inode->i_size, bs); ret = btrfs_cont_expand(BTRFS_I(inode), inode->i_size, destoff); if (ret) return ret; /* * We may have truncated the last block if the inode's size is * not sector size aligned, so we need to wait for writeback to * complete before proceeding further, otherwise we can race * with cloning and attempt to increment a reference to an * extent that no longer exists (writeback completed right after * we found the previous extent covering eof and before we * attempted to increment its reference count). */ ret = btrfs_wait_ordered_range(BTRFS_I(inode), wb_start, destoff - wb_start); if (ret) return ret; } /* * Lock destination range to serialize with concurrent readahead(), and * we are safe from concurrency with relocation of source extents * because we have already locked the inode's i_mmap_lock in exclusive * mode. */ end = destoff + len - 1; lock_extent(&BTRFS_I(inode)->io_tree, destoff, end, &cached_state); ret = btrfs_clone(src, inode, off, olen, len, destoff, 0); unlock_extent(&BTRFS_I(inode)->io_tree, destoff, end, &cached_state); /* * We may have copied an inline extent into a page of the destination * range, so wait for writeback to complete before truncating pages * from the page cache. This is a rare case. */ wb_ret = btrfs_wait_ordered_range(BTRFS_I(inode), destoff, len); ret = ret ? ret : wb_ret; /* * Truncate page cache pages so that future reads will see the cloned * data immediately and not the previous data. */ truncate_inode_pages_range(&inode->i_data, round_down(destoff, PAGE_SIZE), round_up(destoff + len, PAGE_SIZE) - 1); btrfs_btree_balance_dirty(fs_info); return ret; } static int btrfs_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) { struct btrfs_inode *inode_in = BTRFS_I(file_inode(file_in)); struct btrfs_inode *inode_out = BTRFS_I(file_inode(file_out)); u64 bs = inode_out->root->fs_info->sectorsize; u64 wb_len; int ret; if (!(remap_flags & REMAP_FILE_DEDUP)) { struct btrfs_root *root_out = inode_out->root; if (btrfs_root_readonly(root_out)) return -EROFS; ASSERT(inode_in->vfs_inode.i_sb == inode_out->vfs_inode.i_sb); } /* Don't make the dst file partly checksummed */ if ((inode_in->flags & BTRFS_INODE_NODATASUM) != (inode_out->flags & BTRFS_INODE_NODATASUM)) { return -EINVAL; } /* * Now that the inodes are locked, we need to start writeback ourselves * and can not rely on the writeback from the VFS's generic helper * generic_remap_file_range_prep() because: * * 1) For compression we must call filemap_fdatawrite_range() range * twice (btrfs_fdatawrite_range() does it for us), and the generic * helper only calls it once; * * 2) filemap_fdatawrite_range(), called by the generic helper only * waits for the writeback to complete, i.e. for IO to be done, and * not for the ordered extents to complete. We need to wait for them * to complete so that new file extent items are in the fs tree. */ if (*len == 0 && !(remap_flags & REMAP_FILE_DEDUP)) wb_len = ALIGN(inode_in->vfs_inode.i_size, bs) - ALIGN_DOWN(pos_in, bs); else wb_len = ALIGN(*len, bs); /* * Workaround to make sure NOCOW buffered write reach disk as NOCOW. * * Btrfs' back references do not have a block level granularity, they * work at the whole extent level. * NOCOW buffered write without data space reserved may not be able * to fall back to CoW due to lack of data space, thus could cause * data loss. * * Here we take a shortcut by flushing the whole inode, so that all * nocow write should reach disk as nocow before we increase the * reference of the extent. We could do better by only flushing NOCOW * data, but that needs extra accounting. * * Also we don't need to check ASYNC_EXTENT, as async extent will be * CoWed anyway, not affecting nocow part. */ ret = filemap_flush(inode_in->vfs_inode.i_mapping); if (ret < 0) return ret; ret = btrfs_wait_ordered_range(inode_in, ALIGN_DOWN(pos_in, bs), wb_len); if (ret < 0) return ret; ret = btrfs_wait_ordered_range(inode_out, ALIGN_DOWN(pos_out, bs), wb_len); if (ret < 0) return ret; return generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out, len, remap_flags); } static bool file_sync_write(const struct file *file) { if (file->f_flags & (__O_SYNC | O_DSYNC)) return true; if (IS_SYNC(file_inode(file))) return true; return false; } loff_t btrfs_remap_file_range(struct file *src_file, loff_t off, struct file *dst_file, loff_t destoff, loff_t len, unsigned int remap_flags) { struct btrfs_inode *src_inode = BTRFS_I(file_inode(src_file)); struct btrfs_inode *dst_inode = BTRFS_I(file_inode(dst_file)); bool same_inode = dst_inode == src_inode; int ret; if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY)) return -EINVAL; if (same_inode) { btrfs_inode_lock(src_inode, BTRFS_ILOCK_MMAP); } else { lock_two_nondirectories(&src_inode->vfs_inode, &dst_inode->vfs_inode); btrfs_double_mmap_lock(src_inode, dst_inode); } ret = btrfs_remap_file_range_prep(src_file, off, dst_file, destoff, &len, remap_flags); if (ret < 0 || len == 0) goto out_unlock; if (remap_flags & REMAP_FILE_DEDUP) ret = btrfs_extent_same(&src_inode->vfs_inode, off, len, &dst_inode->vfs_inode, destoff); else ret = btrfs_clone_files(dst_file, src_file, off, len, destoff); out_unlock: if (same_inode) { btrfs_inode_unlock(src_inode, BTRFS_ILOCK_MMAP); } else { btrfs_double_mmap_unlock(src_inode, dst_inode); unlock_two_nondirectories(&src_inode->vfs_inode, &dst_inode->vfs_inode); } /* * If either the source or the destination file was opened with O_SYNC, * O_DSYNC or has the S_SYNC attribute, fsync both the destination and * source files/ranges, so that after a successful return (0) followed * by a power failure results in the reflinked data to be readable from * both files/ranges. */ if (ret == 0 && len > 0 && (file_sync_write(src_file) || file_sync_write(dst_file))) { ret = btrfs_sync_file(src_file, off, off + len - 1, 0); if (ret == 0) ret = btrfs_sync_file(dst_file, destoff, destoff + len - 1, 0); } return ret < 0 ? ret : len; } |
| 1 2 4 1715 1707 19 1721 5 5 1829 1660 2403 2406 5 43 43 98 101 100 41 12 1763 11 4 7 3 28 28 28 28 27 9 5 6 42 29 25 2 6 4 50 6 10 13 6 89 8 6 3 4 1 11 32 32 32 10 10 11 2 2 13 13 13 13 21 21 8 3 5 48 48 6 1 18 3 6 18 16 2 15 8 32 31 32 11 11 11 11 11 12 8 3 19 13 2 2 2 6 2 2 17 16 10 12 3 2 5 3 2 1667 1 1659 9 1662 1662 2 5 7 1662 6 4 6 6 1662 6 1668 1670 36 2 1 29 7 34 34 8 24 18 6 6 1 5 9 14 2 4 2 2 2 3 1 4 5 4 2 1 1 1 1 5 9 5 20 20 24 2 3 5 24 5 35 21 15 4 31 35 37 3 4 7 7 6 3 4 4 53 57 56 57 53 53 53 42 42 2 30 10 42 42 39 33 41 42 9 9 1 2 5 2 4 8 2 4 6 9 9 6 6 2 4 6 36 6 6 1 4 4 4 7 2 6 13 13 13 3 4 2 1 3 4 6 13 13 10 4 1 2 1 1 3 17 12 4 13 4 13 17 18 19 2 17 1 4 11 4 11 20 5 15 8 3 3 10 8 16 2 12 4 9 2 2 9 2 8 10 17 17 11 3 10 9 3 34 1 34 8 3 9 17 14 3 36 37 36 2 1 1 10 24 19 59 59 47 20 2 9 3 12 36 21 14 56 2100 2104 1 1 1 819 1 1661 1656 1823 4 2 4 2445 2273 1826 1827 1823 1829 1824 4 1 4 4 1 1 2 1 2 1 4 1 1 3 3 1 8 7 1 1 3 3 3 1 3 2 1 17 14 3 3 3 8 8 8 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/locks.c * * We implement four types of file locks: BSD locks, posix locks, open * file description locks, and leases. For details about BSD locks, * see the flock(2) man page; for details about the other three, see * fcntl(2). * * * Locking conflicts and dependencies: * If multiple threads attempt to lock the same byte (or flock the same file) * only one can be granted the lock, and other must wait their turn. * The first lock has been "applied" or "granted", the others are "waiting" * and are "blocked" by the "applied" lock.. * * Waiting and applied locks are all kept in trees whose properties are: * * - the root of a tree may be an applied or waiting lock. * - every other node in the tree is a waiting lock that * conflicts with every ancestor of that node. * * Every such tree begins life as a waiting singleton which obviously * satisfies the above properties. * * The only ways we modify trees preserve these properties: * * 1. We may add a new leaf node, but only after first verifying that it * conflicts with all of its ancestors. * 2. We may remove the root of a tree, creating a new singleton * tree from the root and N new trees rooted in the immediate * children. * 3. If the root of a tree is not currently an applied lock, we may * apply it (if possible). * 4. We may upgrade the root of the tree (either extend its range, * or upgrade its entire range from read to write). * * When an applied lock is modified in a way that reduces or downgrades any * part of its range, we remove all its children (2 above). This particularly * happens when a lock is unlocked. * * For each of those child trees we "wake up" the thread which is * waiting for the lock so it can continue handling as follows: if the * root of the tree applies, we do so (3). If it doesn't, it must * conflict with some applied lock. We remove (wake up) all of its children * (2), and add it is a new leaf to the tree rooted in the applied * lock (1). We then repeat the process recursively with those * children. * */ #include <linux/capability.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/filelock.h> #include <linux/fs.h> #include <linux/init.h> #include <linux/security.h> #include <linux/slab.h> #include <linux/syscalls.h> #include <linux/time.h> #include <linux/rcupdate.h> #include <linux/pid_namespace.h> #include <linux/hashtable.h> #include <linux/percpu.h> #include <linux/sysctl.h> #define CREATE_TRACE_POINTS #include <trace/events/filelock.h> #include <linux/uaccess.h> static struct file_lock *file_lock(struct file_lock_core *flc) { return container_of(flc, struct file_lock, c); } static struct file_lease *file_lease(struct file_lock_core *flc) { return container_of(flc, struct file_lease, c); } static bool lease_breaking(struct file_lease *fl) { return fl->c.flc_flags & (FL_UNLOCK_PENDING | FL_DOWNGRADE_PENDING); } static int target_leasetype(struct file_lease *fl) { if (fl->c.flc_flags & FL_UNLOCK_PENDING) return F_UNLCK; if (fl->c.flc_flags & FL_DOWNGRADE_PENDING) return F_RDLCK; return fl->c.flc_type; } static int leases_enable = 1; static int lease_break_time = 45; #ifdef CONFIG_SYSCTL static const struct ctl_table locks_sysctls[] = { { .procname = "leases-enable", .data = &leases_enable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #ifdef CONFIG_MMU { .procname = "lease-break-time", .data = &lease_break_time, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #endif /* CONFIG_MMU */ }; static int __init init_fs_locks_sysctls(void) { register_sysctl_init("fs", locks_sysctls); return 0; } early_initcall(init_fs_locks_sysctls); #endif /* CONFIG_SYSCTL */ /* * The global file_lock_list is only used for displaying /proc/locks, so we * keep a list on each CPU, with each list protected by its own spinlock. * Global serialization is done using file_rwsem. * * Note that alterations to the list also require that the relevant flc_lock is * held. */ struct file_lock_list_struct { spinlock_t lock; struct hlist_head hlist; }; static DEFINE_PER_CPU(struct file_lock_list_struct, file_lock_list); DEFINE_STATIC_PERCPU_RWSEM(file_rwsem); /* * The blocked_hash is used to find POSIX lock loops for deadlock detection. * It is protected by blocked_lock_lock. * * We hash locks by lockowner in order to optimize searching for the lock a * particular lockowner is waiting on. * * FIXME: make this value scale via some heuristic? We generally will want more * buckets when we have more lockowners holding locks, but that's a little * difficult to determine without knowing what the workload will look like. */ #define BLOCKED_HASH_BITS 7 static DEFINE_HASHTABLE(blocked_hash, BLOCKED_HASH_BITS); /* * This lock protects the blocked_hash. Generally, if you're accessing it, you * want to be holding this lock. * * In addition, it also protects the fl->fl_blocked_requests list, and the * fl->fl_blocker pointer for file_lock structures that are acting as lock * requests (in contrast to those that are acting as records of acquired locks). * * Note that when we acquire this lock in order to change the above fields, * we often hold the flc_lock as well. In certain cases, when reading the fields * protected by this lock, we can skip acquiring it iff we already hold the * flc_lock. */ static DEFINE_SPINLOCK(blocked_lock_lock); static struct kmem_cache *flctx_cache __ro_after_init; static struct kmem_cache *filelock_cache __ro_after_init; static struct kmem_cache *filelease_cache __ro_after_init; static struct file_lock_context * locks_get_lock_context(struct inode *inode, int type) { struct file_lock_context *ctx; /* paired with cmpxchg() below */ ctx = locks_inode_context(inode); if (likely(ctx) || type == F_UNLCK) goto out; ctx = kmem_cache_alloc(flctx_cache, GFP_KERNEL); if (!ctx) goto out; spin_lock_init(&ctx->flc_lock); INIT_LIST_HEAD(&ctx->flc_flock); INIT_LIST_HEAD(&ctx->flc_posix); INIT_LIST_HEAD(&ctx->flc_lease); /* * Assign the pointer if it's not already assigned. If it is, then * free the context we just allocated. */ if (cmpxchg(&inode->i_flctx, NULL, ctx)) { kmem_cache_free(flctx_cache, ctx); ctx = locks_inode_context(inode); } out: trace_locks_get_lock_context(inode, type, ctx); return ctx; } static void locks_dump_ctx_list(struct list_head *list, char *list_type) { struct file_lock_core *flc; list_for_each_entry(flc, list, flc_list) pr_warn("%s: fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n", list_type, flc->flc_owner, flc->flc_flags, flc->flc_type, flc->flc_pid); } static void locks_check_ctx_lists(struct inode *inode) { struct file_lock_context *ctx = inode->i_flctx; if (unlikely(!list_empty(&ctx->flc_flock) || !list_empty(&ctx->flc_posix) || !list_empty(&ctx->flc_lease))) { pr_warn("Leaked locks on dev=0x%x:0x%x ino=0x%lx:\n", MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino); locks_dump_ctx_list(&ctx->flc_flock, "FLOCK"); locks_dump_ctx_list(&ctx->flc_posix, "POSIX"); locks_dump_ctx_list(&ctx->flc_lease, "LEASE"); } } static void locks_check_ctx_file_list(struct file *filp, struct list_head *list, char *list_type) { struct file_lock_core *flc; struct inode *inode = file_inode(filp); list_for_each_entry(flc, list, flc_list) if (flc->flc_file == filp) pr_warn("Leaked %s lock on dev=0x%x:0x%x ino=0x%lx " " fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n", list_type, MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino, flc->flc_owner, flc->flc_flags, flc->flc_type, flc->flc_pid); } void locks_free_lock_context(struct inode *inode) { struct file_lock_context *ctx = locks_inode_context(inode); if (unlikely(ctx)) { locks_check_ctx_lists(inode); kmem_cache_free(flctx_cache, ctx); } } static void locks_init_lock_heads(struct file_lock_core *flc) { INIT_HLIST_NODE(&flc->flc_link); INIT_LIST_HEAD(&flc->flc_list); INIT_LIST_HEAD(&flc->flc_blocked_requests); INIT_LIST_HEAD(&flc->flc_blocked_member); init_waitqueue_head(&flc->flc_wait); } /* Allocate an empty lock structure. */ struct file_lock *locks_alloc_lock(void) { struct file_lock *fl = kmem_cache_zalloc(filelock_cache, GFP_KERNEL); if (fl) locks_init_lock_heads(&fl->c); return fl; } EXPORT_SYMBOL_GPL(locks_alloc_lock); /* Allocate an empty lock structure. */ struct file_lease *locks_alloc_lease(void) { struct file_lease *fl = kmem_cache_zalloc(filelease_cache, GFP_KERNEL); if (fl) locks_init_lock_heads(&fl->c); return fl; } EXPORT_SYMBOL_GPL(locks_alloc_lease); void locks_release_private(struct file_lock *fl) { struct file_lock_core *flc = &fl->c; BUG_ON(waitqueue_active(&flc->flc_wait)); BUG_ON(!list_empty(&flc->flc_list)); BUG_ON(!list_empty(&flc->flc_blocked_requests)); BUG_ON(!list_empty(&flc->flc_blocked_member)); BUG_ON(!hlist_unhashed(&flc->flc_link)); if (fl->fl_ops) { if (fl->fl_ops->fl_release_private) fl->fl_ops->fl_release_private(fl); fl->fl_ops = NULL; } if (fl->fl_lmops) { if (fl->fl_lmops->lm_put_owner) { fl->fl_lmops->lm_put_owner(flc->flc_owner); flc->flc_owner = NULL; } fl->fl_lmops = NULL; } } EXPORT_SYMBOL_GPL(locks_release_private); /** * locks_owner_has_blockers - Check for blocking lock requests * @flctx: file lock context * @owner: lock owner * * Return values: * %true: @owner has at least one blocker * %false: @owner has no blockers */ bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner) { struct file_lock_core *flc; spin_lock(&flctx->flc_lock); list_for_each_entry(flc, &flctx->flc_posix, flc_list) { if (flc->flc_owner != owner) continue; if (!list_empty(&flc->flc_blocked_requests)) { spin_unlock(&flctx->flc_lock); return true; } } spin_unlock(&flctx->flc_lock); return false; } EXPORT_SYMBOL_GPL(locks_owner_has_blockers); /* Free a lock which is not in use. */ void locks_free_lock(struct file_lock *fl) { locks_release_private(fl); kmem_cache_free(filelock_cache, fl); } EXPORT_SYMBOL(locks_free_lock); /* Free a lease which is not in use. */ void locks_free_lease(struct file_lease *fl) { kmem_cache_free(filelease_cache, fl); } EXPORT_SYMBOL(locks_free_lease); static void locks_dispose_list(struct list_head *dispose) { struct file_lock_core *flc; while (!list_empty(dispose)) { flc = list_first_entry(dispose, struct file_lock_core, flc_list); list_del_init(&flc->flc_list); if (flc->flc_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT)) locks_free_lease(file_lease(flc)); else locks_free_lock(file_lock(flc)); } } void locks_init_lock(struct file_lock *fl) { memset(fl, 0, sizeof(struct file_lock)); locks_init_lock_heads(&fl->c); } EXPORT_SYMBOL(locks_init_lock); void locks_init_lease(struct file_lease *fl) { memset(fl, 0, sizeof(*fl)); locks_init_lock_heads(&fl->c); } EXPORT_SYMBOL(locks_init_lease); /* * Initialize a new lock from an existing file_lock structure. */ void locks_copy_conflock(struct file_lock *new, struct file_lock *fl) { new->c.flc_owner = fl->c.flc_owner; new->c.flc_pid = fl->c.flc_pid; new->c.flc_file = NULL; new->c.flc_flags = fl->c.flc_flags; new->c.flc_type = fl->c.flc_type; new->fl_start = fl->fl_start; new->fl_end = fl->fl_end; new->fl_lmops = fl->fl_lmops; new->fl_ops = NULL; if (fl->fl_lmops) { if (fl->fl_lmops->lm_get_owner) fl->fl_lmops->lm_get_owner(fl->c.flc_owner); } } EXPORT_SYMBOL(locks_copy_conflock); void locks_copy_lock(struct file_lock *new, struct file_lock *fl) { /* "new" must be a freshly-initialized lock */ WARN_ON_ONCE(new->fl_ops); locks_copy_conflock(new, fl); new->c.flc_file = fl->c.flc_file; new->fl_ops = fl->fl_ops; if (fl->fl_ops) { if (fl->fl_ops->fl_copy_lock) fl->fl_ops->fl_copy_lock(new, fl); } } EXPORT_SYMBOL(locks_copy_lock); static void locks_move_blocks(struct file_lock *new, struct file_lock *fl) { struct file_lock *f; /* * As ctx->flc_lock is held, new requests cannot be added to * ->flc_blocked_requests, so we don't need a lock to check if it * is empty. */ if (list_empty(&fl->c.flc_blocked_requests)) return; spin_lock(&blocked_lock_lock); list_splice_init(&fl->c.flc_blocked_requests, &new->c.flc_blocked_requests); list_for_each_entry(f, &new->c.flc_blocked_requests, c.flc_blocked_member) f->c.flc_blocker = &new->c; spin_unlock(&blocked_lock_lock); } static inline int flock_translate_cmd(int cmd) { switch (cmd) { case LOCK_SH: return F_RDLCK; case LOCK_EX: return F_WRLCK; case LOCK_UN: return F_UNLCK; } return -EINVAL; } /* Fill in a file_lock structure with an appropriate FLOCK lock. */ static void flock_make_lock(struct file *filp, struct file_lock *fl, int type) { locks_init_lock(fl); fl->c.flc_file = filp; fl->c.flc_owner = filp; fl->c.flc_pid = current->tgid; fl->c.flc_flags = FL_FLOCK; fl->c.flc_type = type; fl->fl_end = OFFSET_MAX; } static int assign_type(struct file_lock_core *flc, int type) { switch (type) { case F_RDLCK: case F_WRLCK: case F_UNLCK: flc->flc_type = type; break; default: return -EINVAL; } return 0; } static int flock64_to_posix_lock(struct file *filp, struct file_lock *fl, struct flock64 *l) { switch (l->l_whence) { case SEEK_SET: fl->fl_start = 0; break; case SEEK_CUR: fl->fl_start = filp->f_pos; break; case SEEK_END: fl->fl_start = i_size_read(file_inode(filp)); break; default: return -EINVAL; } if (l->l_start > OFFSET_MAX - fl->fl_start) return -EOVERFLOW; fl->fl_start += l->l_start; if (fl->fl_start < 0) return -EINVAL; /* POSIX-1996 leaves the case l->l_len < 0 undefined; POSIX-2001 defines it. */ if (l->l_len > 0) { if (l->l_len - 1 > OFFSET_MAX - fl->fl_start) return -EOVERFLOW; fl->fl_end = fl->fl_start + (l->l_len - 1); } else if (l->l_len < 0) { if (fl->fl_start + l->l_len < 0) return -EINVAL; fl->fl_end = fl->fl_start - 1; fl->fl_start += l->l_len; } else fl->fl_end = OFFSET_MAX; fl->c.flc_owner = current->files; fl->c.flc_pid = current->tgid; fl->c.flc_file = filp; fl->c.flc_flags = FL_POSIX; fl->fl_ops = NULL; fl->fl_lmops = NULL; return assign_type(&fl->c, l->l_type); } /* Verify a "struct flock" and copy it to a "struct file_lock" as a POSIX * style lock. */ static int flock_to_posix_lock(struct file *filp, struct file_lock *fl, struct flock *l) { struct flock64 ll = { .l_type = l->l_type, .l_whence = l->l_whence, .l_start = l->l_start, .l_len = l->l_len, }; return flock64_to_posix_lock(filp, fl, &ll); } /* default lease lock manager operations */ static bool lease_break_callback(struct file_lease *fl) { kill_fasync(&fl->fl_fasync, SIGIO, POLL_MSG); return false; } static void lease_setup(struct file_lease *fl, void **priv) { struct file *filp = fl->c.flc_file; struct fasync_struct *fa = *priv; /* * fasync_insert_entry() returns the old entry if any. If there was no * old entry, then it used "priv" and inserted it into the fasync list. * Clear the pointer to indicate that it shouldn't be freed. */ if (!fasync_insert_entry(fa->fa_fd, filp, &fl->fl_fasync, fa)) *priv = NULL; __f_setown(filp, task_pid(current), PIDTYPE_TGID, 0); } static const struct lease_manager_operations lease_manager_ops = { .lm_break = lease_break_callback, .lm_change = lease_modify, .lm_setup = lease_setup, }; /* * Initialize a lease, use the default lock manager operations */ static int lease_init(struct file *filp, int type, struct file_lease *fl) { if (assign_type(&fl->c, type) != 0) return -EINVAL; fl->c.flc_owner = filp; fl->c.flc_pid = current->tgid; fl->c.flc_file = filp; fl->c.flc_flags = FL_LEASE; fl->fl_lmops = &lease_manager_ops; return 0; } /* Allocate a file_lock initialised to this type of lease */ static struct file_lease *lease_alloc(struct file *filp, int type) { struct file_lease *fl = locks_alloc_lease(); int error = -ENOMEM; if (fl == NULL) return ERR_PTR(error); error = lease_init(filp, type, fl); if (error) { locks_free_lease(fl); return ERR_PTR(error); } return fl; } /* Check if two locks overlap each other. */ static inline int locks_overlap(struct file_lock *fl1, struct file_lock *fl2) { return ((fl1->fl_end >= fl2->fl_start) && (fl2->fl_end >= fl1->fl_start)); } /* * Check whether two locks have the same owner. */ static int posix_same_owner(struct file_lock_core *fl1, struct file_lock_core *fl2) { return fl1->flc_owner == fl2->flc_owner; } /* Must be called with the flc_lock held! */ static void locks_insert_global_locks(struct file_lock_core *flc) { struct file_lock_list_struct *fll = this_cpu_ptr(&file_lock_list); percpu_rwsem_assert_held(&file_rwsem); spin_lock(&fll->lock); flc->flc_link_cpu = smp_processor_id(); hlist_add_head(&flc->flc_link, &fll->hlist); spin_unlock(&fll->lock); } /* Must be called with the flc_lock held! */ static void locks_delete_global_locks(struct file_lock_core *flc) { struct file_lock_list_struct *fll; percpu_rwsem_assert_held(&file_rwsem); /* * Avoid taking lock if already unhashed. This is safe since this check * is done while holding the flc_lock, and new insertions into the list * also require that it be held. */ if (hlist_unhashed(&flc->flc_link)) return; fll = per_cpu_ptr(&file_lock_list, flc->flc_link_cpu); spin_lock(&fll->lock); hlist_del_init(&flc->flc_link); spin_unlock(&fll->lock); } static unsigned long posix_owner_key(struct file_lock_core *flc) { return (unsigned long) flc->flc_owner; } static void locks_insert_global_blocked(struct file_lock_core *waiter) { lockdep_assert_held(&blocked_lock_lock); hash_add(blocked_hash, &waiter->flc_link, posix_owner_key(waiter)); } static void locks_delete_global_blocked(struct file_lock_core *waiter) { lockdep_assert_held(&blocked_lock_lock); hash_del(&waiter->flc_link); } /* Remove waiter from blocker's block list. * When blocker ends up pointing to itself then the list is empty. * * Must be called with blocked_lock_lock held. */ static void __locks_unlink_block(struct file_lock_core *waiter) { locks_delete_global_blocked(waiter); list_del_init(&waiter->flc_blocked_member); } static void __locks_wake_up_blocks(struct file_lock_core *blocker) { while (!list_empty(&blocker->flc_blocked_requests)) { struct file_lock_core *waiter; struct file_lock *fl; waiter = list_first_entry(&blocker->flc_blocked_requests, struct file_lock_core, flc_blocked_member); fl = file_lock(waiter); __locks_unlink_block(waiter); if ((waiter->flc_flags & (FL_POSIX | FL_FLOCK)) && fl->fl_lmops && fl->fl_lmops->lm_notify) fl->fl_lmops->lm_notify(fl); else locks_wake_up(fl); /* * The setting of flc_blocker to NULL marks the "done" * point in deleting a block. Paired with acquire at the top * of locks_delete_block(). */ smp_store_release(&waiter->flc_blocker, NULL); } } static int __locks_delete_block(struct file_lock_core *waiter) { int status = -ENOENT; /* * If fl_blocker is NULL, it won't be set again as this thread "owns" * the lock and is the only one that might try to claim the lock. * * We use acquire/release to manage fl_blocker so that we can * optimize away taking the blocked_lock_lock in many cases. * * The smp_load_acquire guarantees two things: * * 1/ that fl_blocked_requests can be tested locklessly. If something * was recently added to that list it must have been in a locked region * *before* the locked region when fl_blocker was set to NULL. * * 2/ that no other thread is accessing 'waiter', so it is safe to free * it. __locks_wake_up_blocks is careful not to touch waiter after * fl_blocker is released. * * If a lockless check of fl_blocker shows it to be NULL, we know that * no new locks can be inserted into its fl_blocked_requests list, and * can avoid doing anything further if the list is empty. */ if (!smp_load_acquire(&waiter->flc_blocker) && list_empty(&waiter->flc_blocked_requests)) return status; spin_lock(&blocked_lock_lock); if (waiter->flc_blocker) status = 0; __locks_wake_up_blocks(waiter); __locks_unlink_block(waiter); /* * The setting of fl_blocker to NULL marks the "done" point in deleting * a block. Paired with acquire at the top of this function. */ smp_store_release(&waiter->flc_blocker, NULL); spin_unlock(&blocked_lock_lock); return status; } /** * locks_delete_block - stop waiting for a file lock * @waiter: the lock which was waiting * * lockd/nfsd need to disconnect the lock while working on it. */ int locks_delete_block(struct file_lock *waiter) { return __locks_delete_block(&waiter->c); } EXPORT_SYMBOL(locks_delete_block); /* Insert waiter into blocker's block list. * We use a circular list so that processes can be easily woken up in * the order they blocked. The documentation doesn't require this but * it seems like the reasonable thing to do. * * Must be called with both the flc_lock and blocked_lock_lock held. The * fl_blocked_requests list itself is protected by the blocked_lock_lock, * but by ensuring that the flc_lock is also held on insertions we can avoid * taking the blocked_lock_lock in some cases when we see that the * fl_blocked_requests list is empty. * * Rather than just adding to the list, we check for conflicts with any existing * waiters, and add beneath any waiter that blocks the new waiter. * Thus wakeups don't happen until needed. */ static void __locks_insert_block(struct file_lock_core *blocker, struct file_lock_core *waiter, bool conflict(struct file_lock_core *, struct file_lock_core *)) { struct file_lock_core *flc; BUG_ON(!list_empty(&waiter->flc_blocked_member)); new_blocker: list_for_each_entry(flc, &blocker->flc_blocked_requests, flc_blocked_member) if (conflict(flc, waiter)) { blocker = flc; goto new_blocker; } waiter->flc_blocker = blocker; list_add_tail(&waiter->flc_blocked_member, &blocker->flc_blocked_requests); if ((blocker->flc_flags & (FL_POSIX|FL_OFDLCK)) == FL_POSIX) locks_insert_global_blocked(waiter); /* The requests in waiter->flc_blocked are known to conflict with * waiter, but might not conflict with blocker, or the requests * and lock which block it. So they all need to be woken. */ __locks_wake_up_blocks(waiter); } /* Must be called with flc_lock held. */ static void locks_insert_block(struct file_lock_core *blocker, struct file_lock_core *waiter, bool conflict(struct file_lock_core *, struct file_lock_core *)) { spin_lock(&blocked_lock_lock); __locks_insert_block(blocker, waiter, conflict); spin_unlock(&blocked_lock_lock); } /* * Wake up processes blocked waiting for blocker. * * Must be called with the inode->flc_lock held! */ static void locks_wake_up_blocks(struct file_lock_core *blocker) { /* * Avoid taking global lock if list is empty. This is safe since new * blocked requests are only added to the list under the flc_lock, and * the flc_lock is always held here. Note that removal from the * fl_blocked_requests list does not require the flc_lock, so we must * recheck list_empty() after acquiring the blocked_lock_lock. */ if (list_empty(&blocker->flc_blocked_requests)) return; spin_lock(&blocked_lock_lock); __locks_wake_up_blocks(blocker); spin_unlock(&blocked_lock_lock); } static void locks_insert_lock_ctx(struct file_lock_core *fl, struct list_head *before) { list_add_tail(&fl->flc_list, before); locks_insert_global_locks(fl); } static void locks_unlink_lock_ctx(struct file_lock_core *fl) { locks_delete_global_locks(fl); list_del_init(&fl->flc_list); locks_wake_up_blocks(fl); } static void locks_delete_lock_ctx(struct file_lock_core *fl, struct list_head *dispose) { locks_unlink_lock_ctx(fl); if (dispose) list_add(&fl->flc_list, dispose); else locks_free_lock(file_lock(fl)); } /* Determine if lock sys_fl blocks lock caller_fl. Common functionality * checks for shared/exclusive status of overlapping locks. */ static bool locks_conflict(struct file_lock_core *caller_flc, struct file_lock_core *sys_flc) { if (sys_flc->flc_type == F_WRLCK) return true; if (caller_flc->flc_type == F_WRLCK) return true; return false; } /* Determine if lock sys_fl blocks lock caller_fl. POSIX specific * checking before calling the locks_conflict(). */ static bool posix_locks_conflict(struct file_lock_core *caller_flc, struct file_lock_core *sys_flc) { struct file_lock *caller_fl = file_lock(caller_flc); struct file_lock *sys_fl = file_lock(sys_flc); /* POSIX locks owned by the same process do not conflict with * each other. */ if (posix_same_owner(caller_flc, sys_flc)) return false; /* Check whether they overlap */ if (!locks_overlap(caller_fl, sys_fl)) return false; return locks_conflict(caller_flc, sys_flc); } /* Determine if lock sys_fl blocks lock caller_fl. Used on xx_GETLK * path so checks for additional GETLK-specific things like F_UNLCK. */ static bool posix_test_locks_conflict(struct file_lock *caller_fl, struct file_lock *sys_fl) { struct file_lock_core *caller = &caller_fl->c; struct file_lock_core *sys = &sys_fl->c; /* F_UNLCK checks any locks on the same fd. */ if (lock_is_unlock(caller_fl)) { if (!posix_same_owner(caller, sys)) return false; return locks_overlap(caller_fl, sys_fl); } return posix_locks_conflict(caller, sys); } /* Determine if lock sys_fl blocks lock caller_fl. FLOCK specific * checking before calling the locks_conflict(). */ static bool flock_locks_conflict(struct file_lock_core *caller_flc, struct file_lock_core *sys_flc) { /* FLOCK locks referring to the same filp do not conflict with * each other. */ if (caller_flc->flc_file == sys_flc->flc_file) return false; return locks_conflict(caller_flc, sys_flc); } void posix_test_lock(struct file *filp, struct file_lock *fl) { struct file_lock *cfl; struct file_lock_context *ctx; struct inode *inode = file_inode(filp); void *owner; void (*func)(void); ctx = locks_inode_context(inode); if (!ctx || list_empty_careful(&ctx->flc_posix)) { fl->c.flc_type = F_UNLCK; return; } retry: spin_lock(&ctx->flc_lock); list_for_each_entry(cfl, &ctx->flc_posix, c.flc_list) { if (!posix_test_locks_conflict(fl, cfl)) continue; if (cfl->fl_lmops && cfl->fl_lmops->lm_lock_expirable && (*cfl->fl_lmops->lm_lock_expirable)(cfl)) { owner = cfl->fl_lmops->lm_mod_owner; func = cfl->fl_lmops->lm_expire_lock; __module_get(owner); spin_unlock(&ctx->flc_lock); (*func)(); module_put(owner); goto retry; } locks_copy_conflock(fl, cfl); goto out; } fl->c.flc_type = F_UNLCK; out: spin_unlock(&ctx->flc_lock); return; } EXPORT_SYMBOL(posix_test_lock); /* * Deadlock detection: * * We attempt to detect deadlocks that are due purely to posix file * locks. * * We assume that a task can be waiting for at most one lock at a time. * So for any acquired lock, the process holding that lock may be * waiting on at most one other lock. That lock in turns may be held by * someone waiting for at most one other lock. Given a requested lock * caller_fl which is about to wait for a conflicting lock block_fl, we * follow this chain of waiters to ensure we are not about to create a * cycle. * * Since we do this before we ever put a process to sleep on a lock, we * are ensured that there is never a cycle; that is what guarantees that * the while() loop in posix_locks_deadlock() eventually completes. * * Note: the above assumption may not be true when handling lock * requests from a broken NFS client. It may also fail in the presence * of tasks (such as posix threads) sharing the same open file table. * To handle those cases, we just bail out after a few iterations. * * For FL_OFDLCK locks, the owner is the filp, not the files_struct. * Because the owner is not even nominally tied to a thread of * execution, the deadlock detection below can't reasonably work well. Just * skip it for those. * * In principle, we could do a more limited deadlock detection on FL_OFDLCK * locks that just checks for the case where two tasks are attempting to * upgrade from read to write locks on the same inode. */ #define MAX_DEADLK_ITERATIONS 10 /* Find a lock that the owner of the given @blocker is blocking on. */ static struct file_lock_core *what_owner_is_waiting_for(struct file_lock_core *blocker) { struct file_lock_core *flc; hash_for_each_possible(blocked_hash, flc, flc_link, posix_owner_key(blocker)) { if (posix_same_owner(flc, blocker)) { while (flc->flc_blocker) flc = flc->flc_blocker; return flc; } } return NULL; } /* Must be called with the blocked_lock_lock held! */ static bool posix_locks_deadlock(struct file_lock *caller_fl, struct file_lock *block_fl) { struct file_lock_core *caller = &caller_fl->c; struct file_lock_core *blocker = &block_fl->c; int i = 0; lockdep_assert_held(&blocked_lock_lock); /* * This deadlock detector can't reasonably detect deadlocks with * FL_OFDLCK locks, since they aren't owned by a process, per-se. */ if (caller->flc_flags & FL_OFDLCK) return false; while ((blocker = what_owner_is_waiting_for(blocker))) { if (i++ > MAX_DEADLK_ITERATIONS) return false; if (posix_same_owner(caller, blocker)) return true; } return false; } /* Try to create a FLOCK lock on filp. We always insert new FLOCK locks * after any leases, but before any posix locks. * * Note that if called with an FL_EXISTS argument, the caller may determine * whether or not a lock was successfully freed by testing the return * value for -ENOENT. */ static int flock_lock_inode(struct inode *inode, struct file_lock *request) { struct file_lock *new_fl = NULL; struct file_lock *fl; struct file_lock_context *ctx; int error = 0; bool found = false; LIST_HEAD(dispose); ctx = locks_get_lock_context(inode, request->c.flc_type); if (!ctx) { if (request->c.flc_type != F_UNLCK) return -ENOMEM; return (request->c.flc_flags & FL_EXISTS) ? -ENOENT : 0; } if (!(request->c.flc_flags & FL_ACCESS) && (request->c.flc_type != F_UNLCK)) { new_fl = locks_alloc_lock(); if (!new_fl) return -ENOMEM; } percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); if (request->c.flc_flags & FL_ACCESS) goto find_conflict; list_for_each_entry(fl, &ctx->flc_flock, c.flc_list) { if (request->c.flc_file != fl->c.flc_file) continue; if (request->c.flc_type == fl->c.flc_type) goto out; found = true; locks_delete_lock_ctx(&fl->c, &dispose); break; } if (lock_is_unlock(request)) { if ((request->c.flc_flags & FL_EXISTS) && !found) error = -ENOENT; goto out; } find_conflict: list_for_each_entry(fl, &ctx->flc_flock, c.flc_list) { if (!flock_locks_conflict(&request->c, &fl->c)) continue; error = -EAGAIN; if (!(request->c.flc_flags & FL_SLEEP)) goto out; error = FILE_LOCK_DEFERRED; locks_insert_block(&fl->c, &request->c, flock_locks_conflict); goto out; } if (request->c.flc_flags & FL_ACCESS) goto out; locks_copy_lock(new_fl, request); locks_move_blocks(new_fl, request); locks_insert_lock_ctx(&new_fl->c, &ctx->flc_flock); new_fl = NULL; error = 0; out: spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); if (new_fl) locks_free_lock(new_fl); locks_dispose_list(&dispose); trace_flock_lock_inode(inode, request, error); return error; } static int posix_lock_inode(struct inode *inode, struct file_lock *request, struct file_lock *conflock) { struct file_lock *fl, *tmp; struct file_lock *new_fl = NULL; struct file_lock *new_fl2 = NULL; struct file_lock *left = NULL; struct file_lock *right = NULL; struct file_lock_context *ctx; int error; bool added = false; LIST_HEAD(dispose); void *owner; void (*func)(void); ctx = locks_get_lock_context(inode, request->c.flc_type); if (!ctx) return lock_is_unlock(request) ? 0 : -ENOMEM; /* * We may need two file_lock structures for this operation, * so we get them in advance to avoid races. * * In some cases we can be sure, that no new locks will be needed */ if (!(request->c.flc_flags & FL_ACCESS) && (request->c.flc_type != F_UNLCK || request->fl_start != 0 || request->fl_end != OFFSET_MAX)) { new_fl = locks_alloc_lock(); new_fl2 = locks_alloc_lock(); } retry: percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); /* * New lock request. Walk all POSIX locks and look for conflicts. If * there are any, either return error or put the request on the * blocker's list of waiters and the global blocked_hash. */ if (request->c.flc_type != F_UNLCK) { list_for_each_entry(fl, &ctx->flc_posix, c.flc_list) { if (!posix_locks_conflict(&request->c, &fl->c)) continue; if (fl->fl_lmops && fl->fl_lmops->lm_lock_expirable && (*fl->fl_lmops->lm_lock_expirable)(fl)) { owner = fl->fl_lmops->lm_mod_owner; func = fl->fl_lmops->lm_expire_lock; __module_get(owner); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); (*func)(); module_put(owner); goto retry; } if (conflock) locks_copy_conflock(conflock, fl); error = -EAGAIN; if (!(request->c.flc_flags & FL_SLEEP)) goto out; /* * Deadlock detection and insertion into the blocked * locks list must be done while holding the same lock! */ error = -EDEADLK; spin_lock(&blocked_lock_lock); /* * Ensure that we don't find any locks blocked on this * request during deadlock detection. */ __locks_wake_up_blocks(&request->c); if (likely(!posix_locks_deadlock(request, fl))) { error = FILE_LOCK_DEFERRED; __locks_insert_block(&fl->c, &request->c, posix_locks_conflict); } spin_unlock(&blocked_lock_lock); goto out; } } /* If we're just looking for a conflict, we're done. */ error = 0; if (request->c.flc_flags & FL_ACCESS) goto out; /* Find the first old lock with the same owner as the new lock */ list_for_each_entry(fl, &ctx->flc_posix, c.flc_list) { if (posix_same_owner(&request->c, &fl->c)) break; } /* Process locks with this owner. */ list_for_each_entry_safe_from(fl, tmp, &ctx->flc_posix, c.flc_list) { if (!posix_same_owner(&request->c, &fl->c)) break; /* Detect adjacent or overlapping regions (if same lock type) */ if (request->c.flc_type == fl->c.flc_type) { /* In all comparisons of start vs end, use * "start - 1" rather than "end + 1". If end * is OFFSET_MAX, end + 1 will become negative. */ if (fl->fl_end < request->fl_start - 1) continue; /* If the next lock in the list has entirely bigger * addresses than the new one, insert the lock here. */ if (fl->fl_start - 1 > request->fl_end) break; /* If we come here, the new and old lock are of the * same type and adjacent or overlapping. Make one * lock yielding from the lower start address of both * locks to the higher end address. */ if (fl->fl_start > request->fl_start) fl->fl_start = request->fl_start; else request->fl_start = fl->fl_start; if (fl->fl_end < request->fl_end) fl->fl_end = request->fl_end; else request->fl_end = fl->fl_end; if (added) { locks_delete_lock_ctx(&fl->c, &dispose); continue; } request = fl; added = true; } else { /* Processing for different lock types is a bit * more complex. */ if (fl->fl_end < request->fl_start) continue; if (fl->fl_start > request->fl_end) break; if (lock_is_unlock(request)) added = true; if (fl->fl_start < request->fl_start) left = fl; /* If the next lock in the list has a higher end * address than the new one, insert the new one here. */ if (fl->fl_end > request->fl_end) { right = fl; break; } if (fl->fl_start >= request->fl_start) { /* The new lock completely replaces an old * one (This may happen several times). */ if (added) { locks_delete_lock_ctx(&fl->c, &dispose); continue; } /* * Replace the old lock with new_fl, and * remove the old one. It's safe to do the * insert here since we know that we won't be * using new_fl later, and that the lock is * just replacing an existing lock. */ error = -ENOLCK; if (!new_fl) goto out; locks_copy_lock(new_fl, request); locks_move_blocks(new_fl, request); request = new_fl; new_fl = NULL; locks_insert_lock_ctx(&request->c, &fl->c.flc_list); locks_delete_lock_ctx(&fl->c, &dispose); added = true; } } } /* * The above code only modifies existing locks in case of merging or * replacing. If new lock(s) need to be inserted all modifications are * done below this, so it's safe yet to bail out. */ error = -ENOLCK; /* "no luck" */ if (right && left == right && !new_fl2) goto out; error = 0; if (!added) { if (lock_is_unlock(request)) { if (request->c.flc_flags & FL_EXISTS) error = -ENOENT; goto out; } if (!new_fl) { error = -ENOLCK; goto out; } locks_copy_lock(new_fl, request); locks_move_blocks(new_fl, request); locks_insert_lock_ctx(&new_fl->c, &fl->c.flc_list); fl = new_fl; new_fl = NULL; } if (right) { if (left == right) { /* The new lock breaks the old one in two pieces, * so we have to use the second new lock. */ left = new_fl2; new_fl2 = NULL; locks_copy_lock(left, right); locks_insert_lock_ctx(&left->c, &fl->c.flc_list); } right->fl_start = request->fl_end + 1; locks_wake_up_blocks(&right->c); } if (left) { left->fl_end = request->fl_start - 1; locks_wake_up_blocks(&left->c); } out: trace_posix_lock_inode(inode, request, error); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); /* * Free any unused locks. */ if (new_fl) locks_free_lock(new_fl); if (new_fl2) locks_free_lock(new_fl2); locks_dispose_list(&dispose); return error; } /** * posix_lock_file - Apply a POSIX-style lock to a file * @filp: The file to apply the lock to * @fl: The lock to be applied * @conflock: Place to return a copy of the conflicting lock, if found. * * Add a POSIX style lock to a file. * We merge adjacent & overlapping locks whenever possible. * POSIX locks are sorted by owner task, then by starting address * * Note that if called with an FL_EXISTS argument, the caller may determine * whether or not a lock was successfully freed by testing the return * value for -ENOENT. */ int posix_lock_file(struct file *filp, struct file_lock *fl, struct file_lock *conflock) { return posix_lock_inode(file_inode(filp), fl, conflock); } EXPORT_SYMBOL(posix_lock_file); /** * posix_lock_inode_wait - Apply a POSIX-style lock to a file * @inode: inode of file to which lock request should be applied * @fl: The lock to be applied * * Apply a POSIX style lock request to an inode. */ static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl) { int error; might_sleep (); for (;;) { error = posix_lock_inode(inode, fl, NULL); if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl->c.flc_wait, list_empty(&fl->c.flc_blocked_member)); if (error) break; } locks_delete_block(fl); return error; } static void lease_clear_pending(struct file_lease *fl, int arg) { switch (arg) { case F_UNLCK: fl->c.flc_flags &= ~FL_UNLOCK_PENDING; fallthrough; case F_RDLCK: fl->c.flc_flags &= ~FL_DOWNGRADE_PENDING; } } /* We already had a lease on this file; just change its type */ int lease_modify(struct file_lease *fl, int arg, struct list_head *dispose) { int error = assign_type(&fl->c, arg); if (error) return error; lease_clear_pending(fl, arg); locks_wake_up_blocks(&fl->c); if (arg == F_UNLCK) { struct file *filp = fl->c.flc_file; f_delown(filp); file_f_owner(filp)->signum = 0; fasync_helper(0, fl->c.flc_file, 0, &fl->fl_fasync); if (fl->fl_fasync != NULL) { printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync); fl->fl_fasync = NULL; } locks_delete_lock_ctx(&fl->c, dispose); } return 0; } EXPORT_SYMBOL(lease_modify); static bool past_time(unsigned long then) { if (!then) /* 0 is a special value meaning "this never expires": */ return false; return time_after(jiffies, then); } static void time_out_leases(struct inode *inode, struct list_head *dispose) { struct file_lock_context *ctx = inode->i_flctx; struct file_lease *fl, *tmp; lockdep_assert_held(&ctx->flc_lock); list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, c.flc_list) { trace_time_out_leases(inode, fl); if (past_time(fl->fl_downgrade_time)) lease_modify(fl, F_RDLCK, dispose); if (past_time(fl->fl_break_time)) lease_modify(fl, F_UNLCK, dispose); } } static bool leases_conflict(struct file_lock_core *lc, struct file_lock_core *bc) { bool rc; struct file_lease *lease = file_lease(lc); struct file_lease *breaker = file_lease(bc); if (lease->fl_lmops->lm_breaker_owns_lease && lease->fl_lmops->lm_breaker_owns_lease(lease)) return false; if ((bc->flc_flags & FL_LAYOUT) != (lc->flc_flags & FL_LAYOUT)) { rc = false; goto trace; } if ((bc->flc_flags & FL_DELEG) && (lc->flc_flags & FL_LEASE)) { rc = false; goto trace; } rc = locks_conflict(bc, lc); trace: trace_leases_conflict(rc, lease, breaker); return rc; } static bool any_leases_conflict(struct inode *inode, struct file_lease *breaker) { struct file_lock_context *ctx = inode->i_flctx; struct file_lock_core *flc; lockdep_assert_held(&ctx->flc_lock); list_for_each_entry(flc, &ctx->flc_lease, flc_list) { if (leases_conflict(flc, &breaker->c)) return true; } return false; } /** * __break_lease - revoke all outstanding leases on file * @inode: the inode of the file to return * @mode: O_RDONLY: break only write leases; O_WRONLY or O_RDWR: * break all leases * @type: FL_LEASE: break leases and delegations; FL_DELEG: break * only delegations * * break_lease (inlined for speed) has checked there already is at least * some kind of lock (maybe a lease) on this file. Leases are broken on * a call to open() or truncate(). This function can sleep unless you * specified %O_NONBLOCK to your open(). */ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) { int error = 0; struct file_lock_context *ctx; struct file_lease *new_fl, *fl, *tmp; unsigned long break_time; int want_write = (mode & O_ACCMODE) != O_RDONLY; LIST_HEAD(dispose); new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK); if (IS_ERR(new_fl)) return PTR_ERR(new_fl); new_fl->c.flc_flags = type; /* typically we will check that ctx is non-NULL before calling */ ctx = locks_inode_context(inode); if (!ctx) { WARN_ON_ONCE(1); goto free_lock; } percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); if (!any_leases_conflict(inode, new_fl)) goto out; break_time = 0; if (lease_break_time > 0) { break_time = jiffies + lease_break_time * HZ; if (break_time == 0) break_time++; /* so that 0 means no break time */ } list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, c.flc_list) { if (!leases_conflict(&fl->c, &new_fl->c)) continue; if (want_write) { if (fl->c.flc_flags & FL_UNLOCK_PENDING) continue; fl->c.flc_flags |= FL_UNLOCK_PENDING; fl->fl_break_time = break_time; } else { if (lease_breaking(fl)) continue; fl->c.flc_flags |= FL_DOWNGRADE_PENDING; fl->fl_downgrade_time = break_time; } if (fl->fl_lmops->lm_break(fl)) locks_delete_lock_ctx(&fl->c, &dispose); } if (list_empty(&ctx->flc_lease)) goto out; if (mode & O_NONBLOCK) { trace_break_lease_noblock(inode, new_fl); error = -EWOULDBLOCK; goto out; } restart: fl = list_first_entry(&ctx->flc_lease, struct file_lease, c.flc_list); break_time = fl->fl_break_time; if (break_time != 0) break_time -= jiffies; if (break_time == 0) break_time++; locks_insert_block(&fl->c, &new_fl->c, leases_conflict); trace_break_lease_block(inode, new_fl); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); error = wait_event_interruptible_timeout(new_fl->c.flc_wait, list_empty(&new_fl->c.flc_blocked_member), break_time); percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); trace_break_lease_unblock(inode, new_fl); __locks_delete_block(&new_fl->c); if (error >= 0) { /* * Wait for the next conflicting lease that has not been * broken yet */ if (error == 0) time_out_leases(inode, &dispose); if (any_leases_conflict(inode, new_fl)) goto restart; error = 0; } out: spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); free_lock: locks_free_lease(new_fl); return error; } EXPORT_SYMBOL(__break_lease); /** * lease_get_mtime - update modified time of an inode with exclusive lease * @inode: the inode * @time: pointer to a timespec which contains the last modified time * * This is to force NFS clients to flush their caches for files with * exclusive leases. The justification is that if someone has an * exclusive lease, then they could be modifying it. */ void lease_get_mtime(struct inode *inode, struct timespec64 *time) { bool has_lease = false; struct file_lock_context *ctx; struct file_lock_core *flc; ctx = locks_inode_context(inode); if (ctx && !list_empty_careful(&ctx->flc_lease)) { spin_lock(&ctx->flc_lock); flc = list_first_entry_or_null(&ctx->flc_lease, struct file_lock_core, flc_list); if (flc && flc->flc_type == F_WRLCK) has_lease = true; spin_unlock(&ctx->flc_lock); } if (has_lease) *time = current_time(inode); } EXPORT_SYMBOL(lease_get_mtime); /** * fcntl_getlease - Enquire what lease is currently active * @filp: the file * * The value returned by this function will be one of * (if no lease break is pending): * * %F_RDLCK to indicate a shared lease is held. * * %F_WRLCK to indicate an exclusive lease is held. * * %F_UNLCK to indicate no lease is held. * * (if a lease break is pending): * * %F_RDLCK to indicate an exclusive lease needs to be * changed to a shared lease (or removed). * * %F_UNLCK to indicate the lease needs to be removed. * * XXX: sfr & willy disagree over whether F_INPROGRESS * should be returned to userspace. */ int fcntl_getlease(struct file *filp) { struct file_lease *fl; struct inode *inode = file_inode(filp); struct file_lock_context *ctx; int type = F_UNLCK; LIST_HEAD(dispose); ctx = locks_inode_context(inode); if (ctx && !list_empty_careful(&ctx->flc_lease)) { percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); list_for_each_entry(fl, &ctx->flc_lease, c.flc_list) { if (fl->c.flc_file != filp) continue; type = target_leasetype(fl); break; } spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); } return type; } /** * check_conflicting_open - see if the given file points to an inode that has * an existing open that would conflict with the * desired lease. * @filp: file to check * @arg: type of lease that we're trying to acquire * @flags: current lock flags * * Check to see if there's an existing open fd on this file that would * conflict with the lease we're trying to set. */ static int check_conflicting_open(struct file *filp, const int arg, int flags) { struct inode *inode = file_inode(filp); int self_wcount = 0, self_rcount = 0; if (flags & FL_LAYOUT) return 0; if (flags & FL_DELEG) /* We leave these checks to the caller */ return 0; if (arg == F_RDLCK) return inode_is_open_for_write(inode) ? -EAGAIN : 0; else if (arg != F_WRLCK) return 0; /* * Make sure that only read/write count is from lease requestor. * Note that this will result in denying write leases when i_writecount * is negative, which is what we want. (We shouldn't grant write leases * on files open for execution.) */ if (filp->f_mode & FMODE_WRITE) self_wcount = 1; else if (filp->f_mode & FMODE_READ) self_rcount = 1; if (atomic_read(&inode->i_writecount) != self_wcount || atomic_read(&inode->i_readcount) != self_rcount) return -EAGAIN; return 0; } static int generic_add_lease(struct file *filp, int arg, struct file_lease **flp, void **priv) { struct file_lease *fl, *my_fl = NULL, *lease; struct inode *inode = file_inode(filp); struct file_lock_context *ctx; bool is_deleg = (*flp)->c.flc_flags & FL_DELEG; int error; LIST_HEAD(dispose); lease = *flp; trace_generic_add_lease(inode, lease); error = file_f_owner_allocate(filp); if (error) return error; /* Note that arg is never F_UNLCK here */ ctx = locks_get_lock_context(inode, arg); if (!ctx) return -ENOMEM; /* * In the delegation case we need mutual exclusion with * a number of operations that take the i_mutex. We trylock * because delegations are an optional optimization, and if * there's some chance of a conflict--we'd rather not * bother, maybe that's a sign this just isn't a good file to * hand out a delegation on. */ if (is_deleg && !inode_trylock(inode)) return -EAGAIN; percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); error = check_conflicting_open(filp, arg, lease->c.flc_flags); if (error) goto out; /* * At this point, we know that if there is an exclusive * lease on this file, then we hold it on this filp * (otherwise our open of this file would have blocked). * And if we are trying to acquire an exclusive lease, * then the file is not open by anyone (including us) * except for this filp. */ error = -EAGAIN; list_for_each_entry(fl, &ctx->flc_lease, c.flc_list) { if (fl->c.flc_file == filp && fl->c.flc_owner == lease->c.flc_owner) { my_fl = fl; continue; } /* * No exclusive leases if someone else has a lease on * this file: */ if (arg == F_WRLCK) goto out; /* * Modifying our existing lease is OK, but no getting a * new lease if someone else is opening for write: */ if (fl->c.flc_flags & FL_UNLOCK_PENDING) goto out; } if (my_fl != NULL) { lease = my_fl; error = lease->fl_lmops->lm_change(lease, arg, &dispose); if (error) goto out; goto out_setup; } error = -EINVAL; if (!leases_enable) goto out; locks_insert_lock_ctx(&lease->c, &ctx->flc_lease); /* * The check in break_lease() is lockless. It's possible for another * open to race in after we did the earlier check for a conflicting * open but before the lease was inserted. Check again for a * conflicting open and cancel the lease if there is one. * * We also add a barrier here to ensure that the insertion of the lock * precedes these checks. */ smp_mb(); error = check_conflicting_open(filp, arg, lease->c.flc_flags); if (error) { locks_unlink_lock_ctx(&lease->c); goto out; } out_setup: if (lease->fl_lmops->lm_setup) lease->fl_lmops->lm_setup(lease, priv); out: spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); if (is_deleg) inode_unlock(inode); if (!error && !my_fl) *flp = NULL; return error; } static int generic_delete_lease(struct file *filp, void *owner) { int error = -EAGAIN; struct file_lease *fl, *victim = NULL; struct inode *inode = file_inode(filp); struct file_lock_context *ctx; LIST_HEAD(dispose); ctx = locks_inode_context(inode); if (!ctx) { trace_generic_delete_lease(inode, NULL); return error; } percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); list_for_each_entry(fl, &ctx->flc_lease, c.flc_list) { if (fl->c.flc_file == filp && fl->c.flc_owner == owner) { victim = fl; break; } } trace_generic_delete_lease(inode, victim); if (victim) error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); return error; } /** * generic_setlease - sets a lease on an open file * @filp: file pointer * @arg: type of lease to obtain * @flp: input - file_lock to use, output - file_lock inserted * @priv: private data for lm_setup (may be NULL if lm_setup * doesn't require it) * * The (input) flp->fl_lmops->lm_break function is required * by break_lease(). */ int generic_setlease(struct file *filp, int arg, struct file_lease **flp, void **priv) { switch (arg) { case F_UNLCK: return generic_delete_lease(filp, *priv); case F_RDLCK: case F_WRLCK: if (!(*flp)->fl_lmops->lm_break) { WARN_ON_ONCE(1); return -ENOLCK; } return generic_add_lease(filp, arg, flp, priv); default: return -EINVAL; } } EXPORT_SYMBOL(generic_setlease); /* * Kernel subsystems can register to be notified on any attempt to set * a new lease with the lease_notifier_chain. This is used by (e.g.) nfsd * to close files that it may have cached when there is an attempt to set a * conflicting lease. */ static struct srcu_notifier_head lease_notifier_chain; static inline void lease_notifier_chain_init(void) { srcu_init_notifier_head(&lease_notifier_chain); } static inline void setlease_notifier(int arg, struct file_lease *lease) { if (arg != F_UNLCK) srcu_notifier_call_chain(&lease_notifier_chain, arg, lease); } int lease_register_notifier(struct notifier_block *nb) { return srcu_notifier_chain_register(&lease_notifier_chain, nb); } EXPORT_SYMBOL_GPL(lease_register_notifier); void lease_unregister_notifier(struct notifier_block *nb) { srcu_notifier_chain_unregister(&lease_notifier_chain, nb); } EXPORT_SYMBOL_GPL(lease_unregister_notifier); int kernel_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) { if (lease) setlease_notifier(arg, *lease); if (filp->f_op->setlease) return filp->f_op->setlease(filp, arg, lease, priv); else return generic_setlease(filp, arg, lease, priv); } EXPORT_SYMBOL_GPL(kernel_setlease); /** * vfs_setlease - sets a lease on an open file * @filp: file pointer * @arg: type of lease to obtain * @lease: file_lock to use when adding a lease * @priv: private info for lm_setup when adding a lease (may be * NULL if lm_setup doesn't require it) * * Call this to establish a lease on the file. The "lease" argument is not * used for F_UNLCK requests and may be NULL. For commands that set or alter * an existing lease, the ``(*lease)->fl_lmops->lm_break`` operation must be * set; if not, this function will return -ENOLCK (and generate a scary-looking * stack trace). * * The "priv" pointer is passed directly to the lm_setup function as-is. It * may be NULL if the lm_setup operation doesn't require it. */ int vfs_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) { struct inode *inode = file_inode(filp); vfsuid_t vfsuid = i_uid_into_vfsuid(file_mnt_idmap(filp), inode); int error; if ((!vfsuid_eq_kuid(vfsuid, current_fsuid())) && !capable(CAP_LEASE)) return -EACCES; if (!S_ISREG(inode->i_mode)) return -EINVAL; error = security_file_lock(filp, arg); if (error) return error; return kernel_setlease(filp, arg, lease, priv); } EXPORT_SYMBOL_GPL(vfs_setlease); static int do_fcntl_add_lease(unsigned int fd, struct file *filp, int arg) { struct file_lease *fl; struct fasync_struct *new; int error; fl = lease_alloc(filp, arg); if (IS_ERR(fl)) return PTR_ERR(fl); new = fasync_alloc(); if (!new) { locks_free_lease(fl); return -ENOMEM; } new->fa_fd = fd; error = vfs_setlease(filp, arg, &fl, (void **)&new); if (fl) locks_free_lease(fl); if (new) fasync_free(new); return error; } /** * fcntl_setlease - sets a lease on an open file * @fd: open file descriptor * @filp: file pointer * @arg: type of lease to obtain * * Call this fcntl to establish a lease on the file. * Note that you also need to call %F_SETSIG to * receive a signal when the lease is broken. */ int fcntl_setlease(unsigned int fd, struct file *filp, int arg) { if (arg == F_UNLCK) return vfs_setlease(filp, F_UNLCK, NULL, (void **)&filp); return do_fcntl_add_lease(fd, filp, arg); } /** * flock_lock_inode_wait - Apply a FLOCK-style lock to a file * @inode: inode of the file to apply to * @fl: The lock to be applied * * Apply a FLOCK style lock request to an inode. */ static int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl) { int error; might_sleep(); for (;;) { error = flock_lock_inode(inode, fl); if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl->c.flc_wait, list_empty(&fl->c.flc_blocked_member)); if (error) break; } locks_delete_block(fl); return error; } /** * locks_lock_inode_wait - Apply a lock to an inode * @inode: inode of the file to apply to * @fl: The lock to be applied * * Apply a POSIX or FLOCK style lock request to an inode. */ int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) { int res = 0; switch (fl->c.flc_flags & (FL_POSIX|FL_FLOCK)) { case FL_POSIX: res = posix_lock_inode_wait(inode, fl); break; case FL_FLOCK: res = flock_lock_inode_wait(inode, fl); break; default: BUG(); } return res; } EXPORT_SYMBOL(locks_lock_inode_wait); /** * sys_flock: - flock() system call. * @fd: the file descriptor to lock. * @cmd: the type of lock to apply. * * Apply a %FL_FLOCK style lock to an open file descriptor. * The @cmd can be one of: * * - %LOCK_SH -- a shared lock. * - %LOCK_EX -- an exclusive lock. * - %LOCK_UN -- remove an existing lock. * - %LOCK_MAND -- a 'mandatory' flock. (DEPRECATED) * * %LOCK_MAND support has been removed from the kernel. */ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) { int can_sleep, error, type; struct file_lock fl; /* * LOCK_MAND locks were broken for a long time in that they never * conflicted with one another and didn't prevent any sort of open, * read or write activity. * * Just ignore these requests now, to preserve legacy behavior, but * throw a warning to let people know that they don't actually work. */ if (cmd & LOCK_MAND) { pr_warn_once("%s(%d): Attempt to set a LOCK_MAND lock via flock(2). This support has been removed and the request ignored.\n", current->comm, current->pid); return 0; } type = flock_translate_cmd(cmd & ~LOCK_NB); if (type < 0) return type; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; if (type != F_UNLCK && !(fd_file(f)->f_mode & (FMODE_READ | FMODE_WRITE))) return -EBADF; flock_make_lock(fd_file(f), &fl, type); error = security_file_lock(fd_file(f), fl.c.flc_type); if (error) return error; can_sleep = !(cmd & LOCK_NB); if (can_sleep) fl.c.flc_flags |= FL_SLEEP; if (fd_file(f)->f_op->flock) error = fd_file(f)->f_op->flock(fd_file(f), (can_sleep) ? F_SETLKW : F_SETLK, &fl); else error = locks_lock_file_wait(fd_file(f), &fl); locks_release_private(&fl); return error; } /** * vfs_test_lock - test file byte range lock * @filp: The file to test lock for * @fl: The lock to test; also used to hold result * * Returns -ERRNO on failure. Indicates presence of conflicting lock by * setting conf->fl_type to something other than F_UNLCK. */ int vfs_test_lock(struct file *filp, struct file_lock *fl) { WARN_ON_ONCE(filp != fl->c.flc_file); if (filp->f_op->lock) return filp->f_op->lock(filp, F_GETLK, fl); posix_test_lock(filp, fl); return 0; } EXPORT_SYMBOL_GPL(vfs_test_lock); /** * locks_translate_pid - translate a file_lock's fl_pid number into a namespace * @fl: The file_lock who's fl_pid should be translated * @ns: The namespace into which the pid should be translated * * Used to translate a fl_pid into a namespace virtual pid number */ static pid_t locks_translate_pid(struct file_lock_core *fl, struct pid_namespace *ns) { pid_t vnr; struct pid *pid; if (fl->flc_flags & FL_OFDLCK) return -1; /* Remote locks report a negative pid value */ if (fl->flc_pid <= 0) return fl->flc_pid; /* * If the flock owner process is dead and its pid has been already * freed, the translation below won't work, but we still want to show * flock owner pid number in init pidns. */ if (ns == &init_pid_ns) return (pid_t) fl->flc_pid; rcu_read_lock(); pid = find_pid_ns(fl->flc_pid, &init_pid_ns); vnr = pid_nr_ns(pid, ns); rcu_read_unlock(); return vnr; } static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl) { flock->l_pid = locks_translate_pid(&fl->c, task_active_pid_ns(current)); #if BITS_PER_LONG == 32 /* * Make sure we can represent the posix lock via * legacy 32bit flock. */ if (fl->fl_start > OFFT_OFFSET_MAX) return -EOVERFLOW; if (fl->fl_end != OFFSET_MAX && fl->fl_end > OFFT_OFFSET_MAX) return -EOVERFLOW; #endif flock->l_start = fl->fl_start; flock->l_len = fl->fl_end == OFFSET_MAX ? 0 : fl->fl_end - fl->fl_start + 1; flock->l_whence = 0; flock->l_type = fl->c.flc_type; return 0; } #if BITS_PER_LONG == 32 static void posix_lock_to_flock64(struct flock64 *flock, struct file_lock *fl) { flock->l_pid = locks_translate_pid(&fl->c, task_active_pid_ns(current)); flock->l_start = fl->fl_start; flock->l_len = fl->fl_end == OFFSET_MAX ? 0 : fl->fl_end - fl->fl_start + 1; flock->l_whence = 0; flock->l_type = fl->c.flc_type; } #endif /* Report the first existing lock that would conflict with l. * This implements the F_GETLK command of fcntl(). */ int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock *flock) { struct file_lock *fl; int error; fl = locks_alloc_lock(); if (fl == NULL) return -ENOMEM; error = -EINVAL; if (cmd != F_OFD_GETLK && flock->l_type != F_RDLCK && flock->l_type != F_WRLCK) goto out; error = flock_to_posix_lock(filp, fl, flock); if (error) goto out; if (cmd == F_OFD_GETLK) { error = -EINVAL; if (flock->l_pid != 0) goto out; fl->c.flc_flags |= FL_OFDLCK; fl->c.flc_owner = filp; } error = vfs_test_lock(filp, fl); if (error) goto out; flock->l_type = fl->c.flc_type; if (fl->c.flc_type != F_UNLCK) { error = posix_lock_to_flock(flock, fl); if (error) goto out; } out: locks_free_lock(fl); return error; } /** * vfs_lock_file - file byte range lock * @filp: The file to apply the lock to * @cmd: type of locking operation (F_SETLK, F_GETLK, etc.) * @fl: The lock to be applied * @conf: Place to return a copy of the conflicting lock, if found. * * A caller that doesn't care about the conflicting lock may pass NULL * as the final argument. * * If the filesystem defines a private ->lock() method, then @conf will * be left unchanged; so a caller that cares should initialize it to * some acceptable default. * * To avoid blocking kernel daemons, such as lockd, that need to acquire POSIX * locks, the ->lock() interface may return asynchronously, before the lock has * been granted or denied by the underlying filesystem, if (and only if) * lm_grant is set. Additionally EXPORT_OP_ASYNC_LOCK in export_operations * flags need to be set. * * Callers expecting ->lock() to return asynchronously will only use F_SETLK, * not F_SETLKW; they will set FL_SLEEP if (and only if) the request is for a * blocking lock. When ->lock() does return asynchronously, it must return * FILE_LOCK_DEFERRED, and call ->lm_grant() when the lock request completes. * If the request is for non-blocking lock the file system should return * FILE_LOCK_DEFERRED then try to get the lock and call the callback routine * with the result. If the request timed out the callback routine will return a * nonzero return code and the file system should release the lock. The file * system is also responsible to keep a corresponding posix lock when it * grants a lock so the VFS can find out which locks are locally held and do * the correct lock cleanup when required. * The underlying filesystem must not drop the kernel lock or call * ->lm_grant() before returning to the caller with a FILE_LOCK_DEFERRED * return code. */ int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf) { WARN_ON_ONCE(filp != fl->c.flc_file); if (filp->f_op->lock) return filp->f_op->lock(filp, cmd, fl); else return posix_lock_file(filp, fl, conf); } EXPORT_SYMBOL_GPL(vfs_lock_file); static int do_lock_file_wait(struct file *filp, unsigned int cmd, struct file_lock *fl) { int error; error = security_file_lock(filp, fl->c.flc_type); if (error) return error; for (;;) { error = vfs_lock_file(filp, cmd, fl, NULL); if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl->c.flc_wait, list_empty(&fl->c.flc_blocked_member)); if (error) break; } locks_delete_block(fl); return error; } /* Ensure that fl->fl_file has compatible f_mode for F_SETLK calls */ static int check_fmode_for_setlk(struct file_lock *fl) { switch (fl->c.flc_type) { case F_RDLCK: if (!(fl->c.flc_file->f_mode & FMODE_READ)) return -EBADF; break; case F_WRLCK: if (!(fl->c.flc_file->f_mode & FMODE_WRITE)) return -EBADF; } return 0; } /* Apply the lock described by l to an open file descriptor. * This implements both the F_SETLK and F_SETLKW commands of fcntl(). */ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, struct flock *flock) { struct file_lock *file_lock = locks_alloc_lock(); struct inode *inode = file_inode(filp); struct file *f; int error; if (file_lock == NULL) return -ENOLCK; error = flock_to_posix_lock(filp, file_lock, flock); if (error) goto out; error = check_fmode_for_setlk(file_lock); if (error) goto out; /* * If the cmd is requesting file-private locks, then set the * FL_OFDLCK flag and override the owner. */ switch (cmd) { case F_OFD_SETLK: error = -EINVAL; if (flock->l_pid != 0) goto out; cmd = F_SETLK; file_lock->c.flc_flags |= FL_OFDLCK; file_lock->c.flc_owner = filp; break; case F_OFD_SETLKW: error = -EINVAL; if (flock->l_pid != 0) goto out; cmd = F_SETLKW; file_lock->c.flc_flags |= FL_OFDLCK; file_lock->c.flc_owner = filp; fallthrough; case F_SETLKW: file_lock->c.flc_flags |= FL_SLEEP; } error = do_lock_file_wait(filp, cmd, file_lock); /* * Detect close/fcntl races and recover by zapping all POSIX locks * associated with this file and our files_struct, just like on * filp_flush(). There is no need to do that when we're * unlocking though, or for OFD locks. */ if (!error && file_lock->c.flc_type != F_UNLCK && !(file_lock->c.flc_flags & FL_OFDLCK)) { struct files_struct *files = current->files; /* * We need that spin_lock here - it prevents reordering between * update of i_flctx->flc_posix and check for it done in * close(). rcu_read_lock() wouldn't do. */ spin_lock(&files->file_lock); f = files_lookup_fd_locked(files, fd); spin_unlock(&files->file_lock); if (f != filp) { locks_remove_posix(filp, files); error = -EBADF; } } out: trace_fcntl_setlk(inode, file_lock, error); locks_free_lock(file_lock); return error; } #if BITS_PER_LONG == 32 /* Report the first existing lock that would conflict with l. * This implements the F_GETLK command of fcntl(). */ int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 *flock) { struct file_lock *fl; int error; fl = locks_alloc_lock(); if (fl == NULL) return -ENOMEM; error = -EINVAL; if (cmd != F_OFD_GETLK && flock->l_type != F_RDLCK && flock->l_type != F_WRLCK) goto out; error = flock64_to_posix_lock(filp, fl, flock); if (error) goto out; if (cmd == F_OFD_GETLK) { error = -EINVAL; if (flock->l_pid != 0) goto out; fl->c.flc_flags |= FL_OFDLCK; fl->c.flc_owner = filp; } error = vfs_test_lock(filp, fl); if (error) goto out; flock->l_type = fl->c.flc_type; if (fl->c.flc_type != F_UNLCK) posix_lock_to_flock64(flock, fl); out: locks_free_lock(fl); return error; } /* Apply the lock described by l to an open file descriptor. * This implements both the F_SETLK and F_SETLKW commands of fcntl(). */ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, struct flock64 *flock) { struct file_lock *file_lock = locks_alloc_lock(); struct file *f; int error; if (file_lock == NULL) return -ENOLCK; error = flock64_to_posix_lock(filp, file_lock, flock); if (error) goto out; error = check_fmode_for_setlk(file_lock); if (error) goto out; /* * If the cmd is requesting file-private locks, then set the * FL_OFDLCK flag and override the owner. */ switch (cmd) { case F_OFD_SETLK: error = -EINVAL; if (flock->l_pid != 0) goto out; cmd = F_SETLK64; file_lock->c.flc_flags |= FL_OFDLCK; file_lock->c.flc_owner = filp; break; case F_OFD_SETLKW: error = -EINVAL; if (flock->l_pid != 0) goto out; cmd = F_SETLKW64; file_lock->c.flc_flags |= FL_OFDLCK; file_lock->c.flc_owner = filp; fallthrough; case F_SETLKW64: file_lock->c.flc_flags |= FL_SLEEP; } error = do_lock_file_wait(filp, cmd, file_lock); /* * Detect close/fcntl races and recover by zapping all POSIX locks * associated with this file and our files_struct, just like on * filp_flush(). There is no need to do that when we're * unlocking though, or for OFD locks. */ if (!error && file_lock->c.flc_type != F_UNLCK && !(file_lock->c.flc_flags & FL_OFDLCK)) { struct files_struct *files = current->files; /* * We need that spin_lock here - it prevents reordering between * update of i_flctx->flc_posix and check for it done in * close(). rcu_read_lock() wouldn't do. */ spin_lock(&files->file_lock); f = files_lookup_fd_locked(files, fd); spin_unlock(&files->file_lock); if (f != filp) { locks_remove_posix(filp, files); error = -EBADF; } } out: locks_free_lock(file_lock); return error; } #endif /* BITS_PER_LONG == 32 */ /* * This function is called when the file is being removed * from the task's fd array. POSIX locks belonging to this task * are deleted at this time. */ void locks_remove_posix(struct file *filp, fl_owner_t owner) { int error; struct inode *inode = file_inode(filp); struct file_lock lock; struct file_lock_context *ctx; /* * If there are no locks held on this file, we don't need to call * posix_lock_file(). Another process could be setting a lock on this * file at the same time, but we wouldn't remove that lock anyway. */ ctx = locks_inode_context(inode); if (!ctx || list_empty(&ctx->flc_posix)) return; locks_init_lock(&lock); lock.c.flc_type = F_UNLCK; lock.c.flc_flags = FL_POSIX | FL_CLOSE; lock.fl_start = 0; lock.fl_end = OFFSET_MAX; lock.c.flc_owner = owner; lock.c.flc_pid = current->tgid; lock.c.flc_file = filp; lock.fl_ops = NULL; lock.fl_lmops = NULL; error = vfs_lock_file(filp, F_SETLK, &lock, NULL); if (lock.fl_ops && lock.fl_ops->fl_release_private) lock.fl_ops->fl_release_private(&lock); trace_locks_remove_posix(inode, &lock, error); } EXPORT_SYMBOL(locks_remove_posix); /* The i_flctx must be valid when calling into here */ static void locks_remove_flock(struct file *filp, struct file_lock_context *flctx) { struct file_lock fl; struct inode *inode = file_inode(filp); if (list_empty(&flctx->flc_flock)) return; flock_make_lock(filp, &fl, F_UNLCK); fl.c.flc_flags |= FL_CLOSE; if (filp->f_op->flock) filp->f_op->flock(filp, F_SETLKW, &fl); else flock_lock_inode(inode, &fl); if (fl.fl_ops && fl.fl_ops->fl_release_private) fl.fl_ops->fl_release_private(&fl); } /* The i_flctx must be valid when calling into here */ static void locks_remove_lease(struct file *filp, struct file_lock_context *ctx) { struct file_lease *fl, *tmp; LIST_HEAD(dispose); if (list_empty(&ctx->flc_lease)) return; percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, c.flc_list) if (filp == fl->c.flc_file) lease_modify(fl, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); } /* * This function is called on the last close of an open file. */ void locks_remove_file(struct file *filp) { struct file_lock_context *ctx; ctx = locks_inode_context(file_inode(filp)); if (!ctx) return; /* remove any OFD locks */ locks_remove_posix(filp, filp); /* remove flock locks */ locks_remove_flock(filp, ctx); /* remove any leases */ locks_remove_lease(filp, ctx); spin_lock(&ctx->flc_lock); locks_check_ctx_file_list(filp, &ctx->flc_posix, "POSIX"); locks_check_ctx_file_list(filp, &ctx->flc_flock, "FLOCK"); locks_check_ctx_file_list(filp, &ctx->flc_lease, "LEASE"); spin_unlock(&ctx->flc_lock); } /** * vfs_cancel_lock - file byte range unblock lock * @filp: The file to apply the unblock to * @fl: The lock to be unblocked * * Used by lock managers to cancel blocked requests */ int vfs_cancel_lock(struct file *filp, struct file_lock *fl) { WARN_ON_ONCE(filp != fl->c.flc_file); if (filp->f_op->lock) return filp->f_op->lock(filp, F_CANCELLK, fl); return 0; } EXPORT_SYMBOL_GPL(vfs_cancel_lock); /** * vfs_inode_has_locks - are any file locks held on @inode? * @inode: inode to check for locks * * Return true if there are any FL_POSIX or FL_FLOCK locks currently * set on @inode. */ bool vfs_inode_has_locks(struct inode *inode) { struct file_lock_context *ctx; bool ret; ctx = locks_inode_context(inode); if (!ctx) return false; spin_lock(&ctx->flc_lock); ret = !list_empty(&ctx->flc_posix) || !list_empty(&ctx->flc_flock); spin_unlock(&ctx->flc_lock); return ret; } EXPORT_SYMBOL_GPL(vfs_inode_has_locks); #ifdef CONFIG_PROC_FS #include <linux/proc_fs.h> #include <linux/seq_file.h> struct locks_iterator { int li_cpu; loff_t li_pos; }; static void lock_get_status(struct seq_file *f, struct file_lock_core *flc, loff_t id, char *pfx, int repeat) { struct inode *inode = NULL; unsigned int pid; struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb); int type = flc->flc_type; struct file_lock *fl = file_lock(flc); pid = locks_translate_pid(flc, proc_pidns); /* * If lock owner is dead (and pid is freed) or not visible in current * pidns, zero is shown as a pid value. Check lock info from * init_pid_ns to get saved lock pid value. */ if (flc->flc_file != NULL) inode = file_inode(flc->flc_file); seq_printf(f, "%lld: ", id); if (repeat) seq_printf(f, "%*s", repeat - 1 + (int)strlen(pfx), pfx); if (flc->flc_flags & FL_POSIX) { if (flc->flc_flags & FL_ACCESS) seq_puts(f, "ACCESS"); else if (flc->flc_flags & FL_OFDLCK) seq_puts(f, "OFDLCK"); else seq_puts(f, "POSIX "); seq_printf(f, " %s ", (inode == NULL) ? "*NOINODE*" : "ADVISORY "); } else if (flc->flc_flags & FL_FLOCK) { seq_puts(f, "FLOCK ADVISORY "); } else if (flc->flc_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT)) { struct file_lease *lease = file_lease(flc); type = target_leasetype(lease); if (flc->flc_flags & FL_DELEG) seq_puts(f, "DELEG "); else seq_puts(f, "LEASE "); if (lease_breaking(lease)) seq_puts(f, "BREAKING "); else if (flc->flc_file) seq_puts(f, "ACTIVE "); else seq_puts(f, "BREAKER "); } else { seq_puts(f, "UNKNOWN UNKNOWN "); } seq_printf(f, "%s ", (type == F_WRLCK) ? "WRITE" : (type == F_RDLCK) ? "READ" : "UNLCK"); if (inode) { /* userspace relies on this representation of dev_t */ seq_printf(f, "%d %02x:%02x:%lu ", pid, MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino); } else { seq_printf(f, "%d <none>:0 ", pid); } if (flc->flc_flags & FL_POSIX) { if (fl->fl_end == OFFSET_MAX) seq_printf(f, "%Ld EOF\n", fl->fl_start); else seq_printf(f, "%Ld %Ld\n", fl->fl_start, fl->fl_end); } else { seq_puts(f, "0 EOF\n"); } } static struct file_lock_core *get_next_blocked_member(struct file_lock_core *node) { struct file_lock_core *tmp; /* NULL node or root node */ if (node == NULL || node->flc_blocker == NULL) return NULL; /* Next member in the linked list could be itself */ tmp = list_next_entry(node, flc_blocked_member); if (list_entry_is_head(tmp, &node->flc_blocker->flc_blocked_requests, flc_blocked_member) || tmp == node) { return NULL; } return tmp; } static int locks_show(struct seq_file *f, void *v) { struct locks_iterator *iter = f->private; struct file_lock_core *cur, *tmp; struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb); int level = 0; cur = hlist_entry(v, struct file_lock_core, flc_link); if (locks_translate_pid(cur, proc_pidns) == 0) return 0; /* View this crossed linked list as a binary tree, the first member of flc_blocked_requests * is the left child of current node, the next silibing in flc_blocked_member is the * right child, we can alse get the parent of current node from flc_blocker, so this * question becomes traversal of a binary tree */ while (cur != NULL) { if (level) lock_get_status(f, cur, iter->li_pos, "-> ", level); else lock_get_status(f, cur, iter->li_pos, "", level); if (!list_empty(&cur->flc_blocked_requests)) { /* Turn left */ cur = list_first_entry_or_null(&cur->flc_blocked_requests, struct file_lock_core, flc_blocked_member); level++; } else { /* Turn right */ tmp = get_next_blocked_member(cur); /* Fall back to parent node */ while (tmp == NULL && cur->flc_blocker != NULL) { cur = cur->flc_blocker; level--; tmp = get_next_blocked_member(cur); } cur = tmp; } } return 0; } static void __show_fd_locks(struct seq_file *f, struct list_head *head, int *id, struct file *filp, struct files_struct *files) { struct file_lock_core *fl; list_for_each_entry(fl, head, flc_list) { if (filp != fl->flc_file) continue; if (fl->flc_owner != files && fl->flc_owner != filp) continue; (*id)++; seq_puts(f, "lock:\t"); lock_get_status(f, fl, *id, "", 0); } } void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) { struct inode *inode = file_inode(filp); struct file_lock_context *ctx; int id = 0; ctx = locks_inode_context(inode); if (!ctx) return; spin_lock(&ctx->flc_lock); __show_fd_locks(f, &ctx->flc_flock, &id, filp, files); __show_fd_locks(f, &ctx->flc_posix, &id, filp, files); __show_fd_locks(f, &ctx->flc_lease, &id, filp, files); spin_unlock(&ctx->flc_lock); } static void *locks_start(struct seq_file *f, loff_t *pos) __acquires(&blocked_lock_lock) { struct locks_iterator *iter = f->private; iter->li_pos = *pos + 1; percpu_down_write(&file_rwsem); spin_lock(&blocked_lock_lock); return seq_hlist_start_percpu(&file_lock_list.hlist, &iter->li_cpu, *pos); } static void *locks_next(struct seq_file *f, void *v, loff_t *pos) { struct locks_iterator *iter = f->private; ++iter->li_pos; return seq_hlist_next_percpu(v, &file_lock_list.hlist, &iter->li_cpu, pos); } static void locks_stop(struct seq_file *f, void *v) __releases(&blocked_lock_lock) { spin_unlock(&blocked_lock_lock); percpu_up_write(&file_rwsem); } static const struct seq_operations locks_seq_operations = { .start = locks_start, .next = locks_next, .stop = locks_stop, .show = locks_show, }; static int __init proc_locks_init(void) { proc_create_seq_private("locks", 0, NULL, &locks_seq_operations, sizeof(struct locks_iterator), NULL); return 0; } fs_initcall(proc_locks_init); #endif static int __init filelock_init(void) { int i; flctx_cache = kmem_cache_create("file_lock_ctx", sizeof(struct file_lock_context), 0, SLAB_PANIC, NULL); filelock_cache = kmem_cache_create("file_lock_cache", sizeof(struct file_lock), 0, SLAB_PANIC, NULL); filelease_cache = kmem_cache_create("file_lease_cache", sizeof(struct file_lease), 0, SLAB_PANIC, NULL); for_each_possible_cpu(i) { struct file_lock_list_struct *fll = per_cpu_ptr(&file_lock_list, i); spin_lock_init(&fll->lock); INIT_HLIST_HEAD(&fll->hlist); } lease_notifier_chain_init(); return 0; } core_initcall(filelock_init); |
| 8 8 8 95 95 3 92 95 13 7 7 220 2 2 1 1 127 96 7 96 130 103 222 3 127 25 25 25 9 25 104 1 1 103 23 1 5 1 1 2 2 104 104 27 96 96 4 27 103 104 25 91 90 23 1 23 4 4 1 1 126 126 2 5 5 2 220 3 222 27 1 27 | 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 | // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" #include "alloc_background.h" #include "alloc_foreground.h" #include "btree_io.h" #include "btree_update_interior.h" #include "btree_write_buffer.h" #include "buckets.h" #include "checksum.h" #include "disk_groups.h" #include "error.h" #include "journal.h" #include "journal_io.h" #include "journal_reclaim.h" #include "journal_seq_blacklist.h" #include "replicas.h" #include "sb-clean.h" #include "trace.h" #include <linux/ioprio.h> #include <linux/string_choices.h> #include <linux/sched/sysctl.h> void bch2_journal_pos_from_member_info_set(struct bch_fs *c) { lockdep_assert_held(&c->sb_lock); for_each_member_device(c, ca) { struct bch_member *m = bch2_members_v2_get_mut(c->disk_sb.sb, ca->dev_idx); m->last_journal_bucket = cpu_to_le32(ca->journal.cur_idx); m->last_journal_bucket_offset = cpu_to_le32(ca->mi.bucket_size - ca->journal.sectors_free); } } void bch2_journal_pos_from_member_info_resume(struct bch_fs *c) { mutex_lock(&c->sb_lock); for_each_member_device(c, ca) { struct bch_member m = bch2_sb_member_get(c->disk_sb.sb, ca->dev_idx); unsigned idx = le32_to_cpu(m.last_journal_bucket); if (idx < ca->journal.nr) ca->journal.cur_idx = idx; unsigned offset = le32_to_cpu(m.last_journal_bucket_offset); if (offset <= ca->mi.bucket_size) ca->journal.sectors_free = ca->mi.bucket_size - offset; } mutex_unlock(&c->sb_lock); } void bch2_journal_ptrs_to_text(struct printbuf *out, struct bch_fs *c, struct journal_replay *j) { darray_for_each(j->ptrs, i) { if (i != j->ptrs.data) prt_printf(out, " "); prt_printf(out, "%u:%u:%u (sector %llu)", i->dev, i->bucket, i->bucket_offset, i->sector); } } static void bch2_journal_replay_to_text(struct printbuf *out, struct bch_fs *c, struct journal_replay *j) { prt_printf(out, "seq %llu ", le64_to_cpu(j->j.seq)); bch2_journal_ptrs_to_text(out, c, j); for_each_jset_entry_type(entry, &j->j, BCH_JSET_ENTRY_datetime) { struct jset_entry_datetime *datetime = container_of(entry, struct jset_entry_datetime, entry); bch2_prt_datetime(out, le64_to_cpu(datetime->seconds)); break; } } static struct nonce journal_nonce(const struct jset *jset) { return (struct nonce) {{ [0] = 0, [1] = ((__le32 *) &jset->seq)[0], [2] = ((__le32 *) &jset->seq)[1], [3] = BCH_NONCE_JOURNAL, }}; } static bool jset_csum_good(struct bch_fs *c, struct jset *j, struct bch_csum *csum) { if (!bch2_checksum_type_valid(c, JSET_CSUM_TYPE(j))) { *csum = (struct bch_csum) {}; return false; } *csum = csum_vstruct(c, JSET_CSUM_TYPE(j), journal_nonce(j), j); return !bch2_crc_cmp(j->csum, *csum); } static inline u32 journal_entry_radix_idx(struct bch_fs *c, u64 seq) { return (seq - c->journal_entries_base_seq) & (~0U >> 1); } static void __journal_replay_free(struct bch_fs *c, struct journal_replay *i) { struct journal_replay **p = genradix_ptr(&c->journal_entries, journal_entry_radix_idx(c, le64_to_cpu(i->j.seq))); BUG_ON(*p != i); *p = NULL; kvfree(i); } static void journal_replay_free(struct bch_fs *c, struct journal_replay *i, bool blacklisted) { if (blacklisted) i->ignore_blacklisted = true; else i->ignore_not_dirty = true; if (!c->opts.read_entire_journal) __journal_replay_free(c, i); } struct journal_list { struct closure cl; u64 last_seq; struct mutex lock; int ret; }; #define JOURNAL_ENTRY_ADD_OK 0 #define JOURNAL_ENTRY_ADD_OUT_OF_RANGE 5 /* * Given a journal entry we just read, add it to the list of journal entries to * be replayed: */ static int journal_entry_add(struct bch_fs *c, struct bch_dev *ca, struct journal_ptr entry_ptr, struct journal_list *jlist, struct jset *j) { struct genradix_iter iter; struct journal_replay **_i, *i, *dup; size_t bytes = vstruct_bytes(j); u64 last_seq = !JSET_NO_FLUSH(j) ? le64_to_cpu(j->last_seq) : 0; struct printbuf buf = PRINTBUF; int ret = JOURNAL_ENTRY_ADD_OK; if (!c->journal.oldest_seq_found_ondisk || le64_to_cpu(j->seq) < c->journal.oldest_seq_found_ondisk) c->journal.oldest_seq_found_ondisk = le64_to_cpu(j->seq); /* Is this entry older than the range we need? */ if (!c->opts.read_entire_journal && le64_to_cpu(j->seq) < jlist->last_seq) return JOURNAL_ENTRY_ADD_OUT_OF_RANGE; /* * genradixes are indexed by a ulong, not a u64, so we can't index them * by sequence number directly: Assume instead that they will all fall * within the range of +-2billion of the filrst one we find. */ if (!c->journal_entries_base_seq) c->journal_entries_base_seq = max_t(s64, 1, le64_to_cpu(j->seq) - S32_MAX); /* Drop entries we don't need anymore */ if (last_seq > jlist->last_seq && !c->opts.read_entire_journal) { genradix_for_each_from(&c->journal_entries, iter, _i, journal_entry_radix_idx(c, jlist->last_seq)) { i = *_i; if (journal_replay_ignore(i)) continue; if (le64_to_cpu(i->j.seq) >= last_seq) break; journal_replay_free(c, i, false); } } jlist->last_seq = max(jlist->last_seq, last_seq); _i = genradix_ptr_alloc(&c->journal_entries, journal_entry_radix_idx(c, le64_to_cpu(j->seq)), GFP_KERNEL); if (!_i) return -BCH_ERR_ENOMEM_journal_entry_add; /* * Duplicate journal entries? If so we want the one that didn't have a * checksum error: */ dup = *_i; if (dup) { bool identical = bytes == vstruct_bytes(&dup->j) && !memcmp(j, &dup->j, bytes); bool not_identical = !identical && entry_ptr.csum_good && dup->csum_good; bool same_device = false; darray_for_each(dup->ptrs, ptr) if (ptr->dev == ca->dev_idx) same_device = true; ret = darray_push(&dup->ptrs, entry_ptr); if (ret) goto out; bch2_journal_replay_to_text(&buf, c, dup); fsck_err_on(same_device, c, journal_entry_dup_same_device, "duplicate journal entry on same device\n%s", buf.buf); fsck_err_on(not_identical, c, journal_entry_replicas_data_mismatch, "found duplicate but non identical journal entries\n%s", buf.buf); if (entry_ptr.csum_good && !identical) goto replace; goto out; } replace: i = kvmalloc(offsetof(struct journal_replay, j) + bytes, GFP_KERNEL); if (!i) return -BCH_ERR_ENOMEM_journal_entry_add; darray_init(&i->ptrs); i->csum_good = entry_ptr.csum_good; i->ignore_blacklisted = false; i->ignore_not_dirty = false; unsafe_memcpy(&i->j, j, bytes, "embedded variable length struct"); if (dup) { /* The first ptr should represent the jset we kept: */ darray_for_each(dup->ptrs, ptr) darray_push(&i->ptrs, *ptr); __journal_replay_free(c, dup); } else { darray_push(&i->ptrs, entry_ptr); } *_i = i; out: fsck_err: printbuf_exit(&buf); return ret; } /* this fills in a range with empty jset_entries: */ static void journal_entry_null_range(void *start, void *end) { struct jset_entry *entry; for (entry = start; entry != end; entry = vstruct_next(entry)) memset(entry, 0, sizeof(*entry)); } #define JOURNAL_ENTRY_REREAD 5 #define JOURNAL_ENTRY_NONE 6 #define JOURNAL_ENTRY_BAD 7 static void journal_entry_err_msg(struct printbuf *out, u32 version, struct jset *jset, struct jset_entry *entry) { prt_str(out, "invalid journal entry, version="); bch2_version_to_text(out, version); if (entry) { prt_str(out, " type="); bch2_prt_jset_entry_type(out, entry->type); } if (!jset) { prt_printf(out, " in superblock"); } else { prt_printf(out, " seq=%llu", le64_to_cpu(jset->seq)); if (entry) prt_printf(out, " offset=%zi/%u", (u64 *) entry - jset->_data, le32_to_cpu(jset->u64s)); } prt_str(out, ": "); } #define journal_entry_err(c, version, jset, entry, _err, msg, ...) \ ({ \ struct printbuf _buf = PRINTBUF; \ \ journal_entry_err_msg(&_buf, version, jset, entry); \ prt_printf(&_buf, msg, ##__VA_ARGS__); \ \ switch (from.flags & BCH_VALIDATE_write) { \ case READ: \ mustfix_fsck_err(c, _err, "%s", _buf.buf); \ break; \ case WRITE: \ bch2_sb_error_count(c, BCH_FSCK_ERR_##_err); \ if (bch2_fs_inconsistent(c, \ "corrupt metadata before write: %s\n", _buf.buf)) {\ ret = -BCH_ERR_fsck_errors_not_fixed; \ goto fsck_err; \ } \ break; \ } \ \ printbuf_exit(&_buf); \ true; \ }) #define journal_entry_err_on(cond, ...) \ ((cond) ? journal_entry_err(__VA_ARGS__) : false) #define FSCK_DELETED_KEY 5 static int journal_validate_key(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, struct bkey_i *k, struct bkey_validate_context from, unsigned version, int big_endian) { enum bch_validate_flags flags = from.flags; int write = flags & BCH_VALIDATE_write; void *next = vstruct_next(entry); int ret = 0; if (journal_entry_err_on(!k->k.u64s, c, version, jset, entry, journal_entry_bkey_u64s_0, "k->u64s 0")) { entry->u64s = cpu_to_le16((u64 *) k - entry->_data); journal_entry_null_range(vstruct_next(entry), next); return FSCK_DELETED_KEY; } if (journal_entry_err_on((void *) bkey_next(k) > (void *) vstruct_next(entry), c, version, jset, entry, journal_entry_bkey_past_end, "extends past end of journal entry")) { entry->u64s = cpu_to_le16((u64 *) k - entry->_data); journal_entry_null_range(vstruct_next(entry), next); return FSCK_DELETED_KEY; } if (journal_entry_err_on(k->k.format != KEY_FORMAT_CURRENT, c, version, jset, entry, journal_entry_bkey_bad_format, "bad format %u", k->k.format)) { le16_add_cpu(&entry->u64s, -((u16) k->k.u64s)); memmove(k, bkey_next(k), next - (void *) bkey_next(k)); journal_entry_null_range(vstruct_next(entry), next); return FSCK_DELETED_KEY; } if (!write) bch2_bkey_compat(from.level, from.btree, version, big_endian, write, NULL, bkey_to_packed(k)); ret = bch2_bkey_validate(c, bkey_i_to_s_c(k), from); if (ret == -BCH_ERR_fsck_delete_bkey) { le16_add_cpu(&entry->u64s, -((u16) k->k.u64s)); memmove(k, bkey_next(k), next - (void *) bkey_next(k)); journal_entry_null_range(vstruct_next(entry), next); return FSCK_DELETED_KEY; } if (ret) goto fsck_err; if (write) bch2_bkey_compat(from.level, from.btree, version, big_endian, write, NULL, bkey_to_packed(k)); fsck_err: return ret; } static int journal_entry_btree_keys_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, struct bkey_validate_context from) { struct bkey_i *k = entry->start; from.level = entry->level; from.btree = entry->btree_id; while (k != vstruct_last(entry)) { int ret = journal_validate_key(c, jset, entry, k, from, version, big_endian); if (ret == FSCK_DELETED_KEY) continue; else if (ret) return ret; k = bkey_next(k); } return 0; } static void journal_entry_btree_keys_to_text(struct printbuf *out, struct bch_fs *c, struct jset_entry *entry) { bool first = true; jset_entry_for_each_key(entry, k) { if (!first) { prt_newline(out); bch2_prt_jset_entry_type(out, entry->type); prt_str(out, ": "); } bch2_btree_id_level_to_text(out, entry->btree_id, entry->level); prt_char(out, ' '); bch2_bkey_val_to_text(out, c, bkey_i_to_s_c(k)); first = false; } } static int journal_entry_btree_root_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, struct bkey_validate_context from) { struct bkey_i *k = entry->start; int ret = 0; from.root = true; from.level = entry->level + 1; from.btree = entry->btree_id; if (journal_entry_err_on(!entry->u64s || le16_to_cpu(entry->u64s) != k->k.u64s, c, version, jset, entry, journal_entry_btree_root_bad_size, "invalid btree root journal entry: wrong number of keys")) { void *next = vstruct_next(entry); /* * we don't want to null out this jset_entry, * just the contents, so that later we can tell * we were _supposed_ to have a btree root */ entry->u64s = 0; journal_entry_null_range(vstruct_next(entry), next); return 0; } ret = journal_validate_key(c, jset, entry, k, from, version, big_endian); if (ret == FSCK_DELETED_KEY) ret = 0; fsck_err: return ret; } static void journal_entry_btree_root_to_text(struct printbuf *out, struct bch_fs *c, struct jset_entry *entry) { journal_entry_btree_keys_to_text(out, c, entry); } static int journal_entry_prio_ptrs_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, struct bkey_validate_context from) { /* obsolete, don't care: */ return 0; } static void journal_entry_prio_ptrs_to_text(struct printbuf *out, struct bch_fs *c, struct jset_entry *entry) { } static int journal_entry_blacklist_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, struct bkey_validate_context from) { int ret = 0; if (journal_entry_err_on(le16_to_cpu(entry->u64s) != 1, c, version, jset, entry, journal_entry_blacklist_bad_size, "invalid journal seq blacklist entry: bad size")) { journal_entry_null_range(entry, vstruct_next(entry)); } fsck_err: return ret; } static void journal_entry_blacklist_to_text(struct printbuf *out, struct bch_fs *c, struct jset_entry *entry) { struct jset_entry_blacklist *bl = container_of(entry, struct jset_entry_blacklist, entry); prt_printf(out, "seq=%llu", le64_to_cpu(bl->seq)); } static int journal_entry_blacklist_v2_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, struct bkey_validate_context from) { struct jset_entry_blacklist_v2 *bl_entry; int ret = 0; if (journal_entry_err_on(le16_to_cpu(entry->u64s) != 2, c, version, jset, entry, journal_entry_blacklist_v2_bad_size, "invalid journal seq blacklist entry: bad size")) { journal_entry_null_range(entry, vstruct_next(entry)); goto out; } bl_entry = container_of(entry, struct jset_entry_blacklist_v2, entry); if (journal_entry_err_on(le64_to_cpu(bl_entry->start) > le64_to_cpu(bl_entry->end), c, version, jset, entry, journal_entry_blacklist_v2_start_past_end, "invalid journal seq blacklist entry: start > end")) { journal_entry_null_range(entry, vstruct_next(entry)); } out: fsck_err: return ret; } static void journal_entry_blacklist_v2_to_text(struct printbuf *out, struct bch_fs *c, struct jset_entry *entry) { struct jset_entry_blacklist_v2 *bl = container_of(entry, struct jset_entry_blacklist_v2, entry); prt_printf(out, "start=%llu end=%llu", le64_to_cpu(bl->start), le64_to_cpu(bl->end)); } static int journal_entry_usage_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, struct bkey_validate_context from) { struct jset_entry_usage *u = container_of(entry, struct jset_entry_usage, entry); unsigned bytes = jset_u64s(le16_to_cpu(entry->u64s)) * sizeof(u64); int ret = 0; if (journal_entry_err_on(bytes < sizeof(*u), c, version, jset, entry, journal_entry_usage_bad_size, "invalid journal entry usage: bad size")) { journal_entry_null_range(entry, vstruct_next(entry)); return ret; } fsck_err: return ret; } static void journal_entry_usage_to_text(struct printbuf *out, struct bch_fs *c, struct jset_entry *entry) { struct jset_entry_usage *u = container_of(entry, struct jset_entry_usage, entry); prt_str(out, "type="); bch2_prt_fs_usage_type(out, u->entry.btree_id); prt_printf(out, " v=%llu", le64_to_cpu(u->v)); } static int journal_entry_data_usage_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, struct bkey_validate_context from) { struct jset_entry_data_usage *u = container_of(entry, struct jset_entry_data_usage, entry); unsigned bytes = jset_u64s(le16_to_cpu(entry->u64s)) * sizeof(u64); struct printbuf err = PRINTBUF; int ret = 0; if (journal_entry_err_on(bytes < sizeof(*u) || bytes < sizeof(*u) + u->r.nr_devs, c, version, jset, entry, journal_entry_data_usage_bad_size, "invalid journal entry usage: bad size")) { journal_entry_null_range(entry, vstruct_next(entry)); goto out; } if (journal_entry_err_on(bch2_replicas_entry_validate(&u->r, c, &err), c, version, jset, entry, journal_entry_data_usage_bad_size, "invalid journal entry usage: %s", err.buf)) { journal_entry_null_range(entry, vstruct_next(entry)); goto out; } out: fsck_err: printbuf_exit(&err); return ret; } static void journal_entry_data_usage_to_text(struct printbuf *out, struct bch_fs *c, struct jset_entry *entry) { struct jset_entry_data_usage *u = container_of(entry, struct jset_entry_data_usage, entry); bch2_replicas_entry_to_text(out, &u->r); prt_printf(out, "=%llu", le64_to_cpu(u->v)); } static int journal_entry_clock_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, struct bkey_validate_context from) { struct jset_entry_clock *clock = container_of(entry, struct jset_entry_clock, entry); unsigned bytes = jset_u64s(le16_to_cpu(entry->u64s)) * sizeof(u64); int ret = 0; if (journal_entry_err_on(bytes != sizeof(*clock), c, version, jset, entry, journal_entry_clock_bad_size, "bad size")) { journal_entry_null_range(entry, vstruct_next(entry)); return ret; } if (journal_entry_err_on(clock->rw > 1, c, version, jset, entry, journal_entry_clock_bad_rw, "bad rw")) { journal_entry_null_range(entry, vstruct_next(entry)); return ret; } fsck_err: return ret; } static void journal_entry_clock_to_text(struct printbuf *out, struct bch_fs *c, struct jset_entry *entry) { struct jset_entry_clock *clock = container_of(entry, struct jset_entry_clock, entry); prt_printf(out, "%s=%llu", str_write_read(clock->rw), le64_to_cpu(clock->time)); } static int journal_entry_dev_usage_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, struct bkey_validate_context from) { struct jset_entry_dev_usage *u = container_of(entry, struct jset_entry_dev_usage, entry); unsigned bytes = jset_u64s(le16_to_cpu(entry->u64s)) * sizeof(u64); unsigned expected = sizeof(*u); int ret = 0; if (journal_entry_err_on(bytes < expected, c, version, jset, entry, journal_entry_dev_usage_bad_size, "bad size (%u < %u)", bytes, expected)) { journal_entry_null_range(entry, vstruct_next(entry)); return ret; } if (journal_entry_err_on(u->pad, c, version, jset, entry, journal_entry_dev_usage_bad_pad, "bad pad")) { journal_entry_null_range(entry, vstruct_next(entry)); return ret; } fsck_err: return ret; } static void journal_entry_dev_usage_to_text(struct printbuf *out, struct bch_fs *c, struct jset_entry *entry) { struct jset_entry_dev_usage *u = container_of(entry, struct jset_entry_dev_usage, entry); unsigned i, nr_types = jset_entry_dev_usage_nr_types(u); if (vstruct_bytes(entry) < sizeof(*u)) return; prt_printf(out, "dev=%u", le32_to_cpu(u->dev)); printbuf_indent_add(out, 2); for (i = 0; i < nr_types; i++) { prt_newline(out); bch2_prt_data_type(out, i); prt_printf(out, ": buckets=%llu sectors=%llu fragmented=%llu", le64_to_cpu(u->d[i].buckets), le64_to_cpu(u->d[i].sectors), le64_to_cpu(u->d[i].fragmented)); } printbuf_indent_sub(out, 2); } static int journal_entry_log_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, struct bkey_validate_context from) { return 0; } static void journal_entry_log_to_text(struct printbuf *out, struct bch_fs *c, struct jset_entry *entry) { struct jset_entry_log *l = container_of(entry, struct jset_entry_log, entry); prt_printf(out, "%.*s", jset_entry_log_msg_bytes(l), l->d); } static int journal_entry_overwrite_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, struct bkey_validate_context from) { from.flags = 0; return journal_entry_btree_keys_validate(c, jset, entry, version, big_endian, from); } static void journal_entry_overwrite_to_text(struct printbuf *out, struct bch_fs *c, struct jset_entry *entry) { journal_entry_btree_keys_to_text(out, c, entry); } static int journal_entry_log_bkey_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, struct bkey_validate_context from) { from.flags = 0; return journal_entry_btree_keys_validate(c, jset, entry, version, big_endian, from); } static void journal_entry_log_bkey_to_text(struct printbuf *out, struct bch_fs *c, struct jset_entry *entry) { journal_entry_btree_keys_to_text(out, c, entry); } static int journal_entry_write_buffer_keys_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, struct bkey_validate_context from) { return journal_entry_btree_keys_validate(c, jset, entry, version, big_endian, from); } static void journal_entry_write_buffer_keys_to_text(struct printbuf *out, struct bch_fs *c, struct jset_entry *entry) { journal_entry_btree_keys_to_text(out, c, entry); } static int journal_entry_datetime_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, struct bkey_validate_context from) { unsigned bytes = vstruct_bytes(entry); unsigned expected = 16; int ret = 0; if (journal_entry_err_on(vstruct_bytes(entry) < expected, c, version, jset, entry, journal_entry_dev_usage_bad_size, "bad size (%u < %u)", bytes, expected)) { journal_entry_null_range(entry, vstruct_next(entry)); return ret; } fsck_err: return ret; } static void journal_entry_datetime_to_text(struct printbuf *out, struct bch_fs *c, struct jset_entry *entry) { struct jset_entry_datetime *datetime = container_of(entry, struct jset_entry_datetime, entry); bch2_prt_datetime(out, le64_to_cpu(datetime->seconds)); } struct jset_entry_ops { int (*validate)(struct bch_fs *, struct jset *, struct jset_entry *, unsigned, int, struct bkey_validate_context); void (*to_text)(struct printbuf *, struct bch_fs *, struct jset_entry *); }; static const struct jset_entry_ops bch2_jset_entry_ops[] = { #define x(f, nr) \ [BCH_JSET_ENTRY_##f] = (struct jset_entry_ops) { \ .validate = journal_entry_##f##_validate, \ .to_text = journal_entry_##f##_to_text, \ }, BCH_JSET_ENTRY_TYPES() #undef x }; int bch2_journal_entry_validate(struct bch_fs *c, struct jset *jset, struct jset_entry *entry, unsigned version, int big_endian, struct bkey_validate_context from) { return entry->type < BCH_JSET_ENTRY_NR ? bch2_jset_entry_ops[entry->type].validate(c, jset, entry, version, big_endian, from) : 0; } void bch2_journal_entry_to_text(struct printbuf *out, struct bch_fs *c, struct jset_entry *entry) { bch2_prt_jset_entry_type(out, entry->type); if (entry->type < BCH_JSET_ENTRY_NR) { prt_str(out, ": "); bch2_jset_entry_ops[entry->type].to_text(out, c, entry); } } static int jset_validate_entries(struct bch_fs *c, struct jset *jset, enum bch_validate_flags flags) { struct bkey_validate_context from = { .flags = flags, .from = BKEY_VALIDATE_journal, .journal_seq = le64_to_cpu(jset->seq), }; unsigned version = le32_to_cpu(jset->version); int ret = 0; vstruct_for_each(jset, entry) { from.journal_offset = (u64 *) entry - jset->_data; if (journal_entry_err_on(vstruct_next(entry) > vstruct_last(jset), c, version, jset, entry, journal_entry_past_jset_end, "journal entry extends past end of jset")) { jset->u64s = cpu_to_le32((u64 *) entry - jset->_data); break; } ret = bch2_journal_entry_validate(c, jset, entry, version, JSET_BIG_ENDIAN(jset), from); if (ret) break; } fsck_err: return ret; } static int jset_validate(struct bch_fs *c, struct bch_dev *ca, struct jset *jset, u64 sector, enum bch_validate_flags flags) { struct bkey_validate_context from = { .flags = flags, .from = BKEY_VALIDATE_journal, .journal_seq = le64_to_cpu(jset->seq), }; int ret = 0; if (le64_to_cpu(jset->magic) != jset_magic(c)) return JOURNAL_ENTRY_NONE; unsigned version = le32_to_cpu(jset->version); if (journal_entry_err_on(!bch2_version_compatible(version), c, version, jset, NULL, jset_unsupported_version, "%s sector %llu seq %llu: incompatible journal entry version %u.%u", ca ? ca->name : c->name, sector, le64_to_cpu(jset->seq), BCH_VERSION_MAJOR(version), BCH_VERSION_MINOR(version))) { /* don't try to continue: */ return -EINVAL; } if (journal_entry_err_on(!bch2_checksum_type_valid(c, JSET_CSUM_TYPE(jset)), c, version, jset, NULL, jset_unknown_csum, "%s sector %llu seq %llu: journal entry with unknown csum type %llu", ca ? ca->name : c->name, sector, le64_to_cpu(jset->seq), JSET_CSUM_TYPE(jset))) ret = JOURNAL_ENTRY_BAD; /* last_seq is ignored when JSET_NO_FLUSH is true */ if (journal_entry_err_on(!JSET_NO_FLUSH(jset) && le64_to_cpu(jset->last_seq) > le64_to_cpu(jset->seq), c, version, jset, NULL, jset_last_seq_newer_than_seq, "invalid journal entry: last_seq > seq (%llu > %llu)", le64_to_cpu(jset->last_seq), le64_to_cpu(jset->seq))) { jset->last_seq = jset->seq; return JOURNAL_ENTRY_BAD; } ret = jset_validate_entries(c, jset, flags); fsck_err: return ret; } static int jset_validate_early(struct bch_fs *c, struct bch_dev *ca, struct jset *jset, u64 sector, unsigned bucket_sectors_left, unsigned sectors_read) { struct bkey_validate_context from = { .from = BKEY_VALIDATE_journal, .journal_seq = le64_to_cpu(jset->seq), }; int ret = 0; if (le64_to_cpu(jset->magic) != jset_magic(c)) return JOURNAL_ENTRY_NONE; unsigned version = le32_to_cpu(jset->version); if (journal_entry_err_on(!bch2_version_compatible(version), c, version, jset, NULL, jset_unsupported_version, "%s sector %llu seq %llu: unknown journal entry version %u.%u", ca ? ca->name : c->name, sector, le64_to_cpu(jset->seq), BCH_VERSION_MAJOR(version), BCH_VERSION_MINOR(version))) { /* don't try to continue: */ return -EINVAL; } size_t bytes = vstruct_bytes(jset); if (bytes > (sectors_read << 9) && sectors_read < bucket_sectors_left) return JOURNAL_ENTRY_REREAD; if (journal_entry_err_on(bytes > bucket_sectors_left << 9, c, version, jset, NULL, jset_past_bucket_end, "%s sector %llu seq %llu: journal entry too big (%zu bytes)", ca ? ca->name : c->name, sector, le64_to_cpu(jset->seq), bytes)) le32_add_cpu(&jset->u64s, -((bytes - (bucket_sectors_left << 9)) / 8)); fsck_err: return ret; } struct journal_read_buf { void *data; size_t size; }; static int journal_read_buf_realloc(struct journal_read_buf *b, size_t new_size) { void *n; /* the bios are sized for this many pages, max: */ if (new_size > JOURNAL_ENTRY_SIZE_MAX) return -BCH_ERR_ENOMEM_journal_read_buf_realloc; new_size = roundup_pow_of_two(new_size); n = kvmalloc(new_size, GFP_KERNEL); if (!n) return -BCH_ERR_ENOMEM_journal_read_buf_realloc; kvfree(b->data); b->data = n; b->size = new_size; return 0; } static int journal_read_bucket(struct bch_dev *ca, struct journal_read_buf *buf, struct journal_list *jlist, unsigned bucket) { struct bch_fs *c = ca->fs; struct journal_device *ja = &ca->journal; struct jset *j = NULL; unsigned sectors, sectors_read = 0; u64 offset = bucket_to_sector(ca, ja->buckets[bucket]), end = offset + ca->mi.bucket_size; bool saw_bad = false, csum_good; struct printbuf err = PRINTBUF; int ret = 0; pr_debug("reading %u", bucket); while (offset < end) { if (!sectors_read) { struct bio *bio; unsigned nr_bvecs; reread: sectors_read = min_t(unsigned, end - offset, buf->size >> 9); nr_bvecs = buf_pages(buf->data, sectors_read << 9); bio = bio_kmalloc(nr_bvecs, GFP_KERNEL); if (!bio) return -BCH_ERR_ENOMEM_journal_read_bucket; bio_init(bio, ca->disk_sb.bdev, bio->bi_inline_vecs, nr_bvecs, REQ_OP_READ); bio->bi_iter.bi_sector = offset; bch2_bio_map(bio, buf->data, sectors_read << 9); u64 submit_time = local_clock(); ret = submit_bio_wait(bio); kfree(bio); if (!ret && bch2_meta_read_fault("journal")) ret = -BCH_ERR_EIO_fault_injected; bch2_account_io_completion(ca, BCH_MEMBER_ERROR_read, submit_time, !ret); if (ret) { bch_err_dev_ratelimited(ca, "journal read error: sector %llu", offset); /* * We don't error out of the recovery process * here, since the relevant journal entry may be * found on a different device, and missing or * no journal entries will be handled later */ goto out; } j = buf->data; } ret = jset_validate_early(c, ca, j, offset, end - offset, sectors_read); switch (ret) { case 0: sectors = vstruct_sectors(j, c->block_bits); break; case JOURNAL_ENTRY_REREAD: if (vstruct_bytes(j) > buf->size) { ret = journal_read_buf_realloc(buf, vstruct_bytes(j)); if (ret) goto err; } goto reread; case JOURNAL_ENTRY_NONE: if (!saw_bad) goto out; /* * On checksum error we don't really trust the size * field of the journal entry we read, so try reading * again at next block boundary: */ sectors = block_sectors(c); goto next_block; default: goto err; } if (le64_to_cpu(j->seq) > ja->highest_seq_found) { ja->highest_seq_found = le64_to_cpu(j->seq); ja->cur_idx = bucket; ja->sectors_free = ca->mi.bucket_size - bucket_remainder(ca, offset) - sectors; } /* * This happens sometimes if we don't have discards on - * when we've partially overwritten a bucket with new * journal entries. We don't need the rest of the * bucket: */ if (le64_to_cpu(j->seq) < ja->bucket_seq[bucket]) goto out; ja->bucket_seq[bucket] = le64_to_cpu(j->seq); enum bch_csum_type csum_type = JSET_CSUM_TYPE(j); struct bch_csum csum; csum_good = jset_csum_good(c, j, &csum); bch2_account_io_completion(ca, BCH_MEMBER_ERROR_checksum, 0, csum_good); if (!csum_good) { bch_err_dev_ratelimited(ca, "%s", (printbuf_reset(&err), prt_str(&err, "journal "), bch2_csum_err_msg(&err, csum_type, j->csum, csum), err.buf)); saw_bad = true; } ret = bch2_encrypt(c, JSET_CSUM_TYPE(j), journal_nonce(j), j->encrypted_start, vstruct_end(j) - (void *) j->encrypted_start); bch2_fs_fatal_err_on(ret, c, "decrypting journal entry: %s", bch2_err_str(ret)); mutex_lock(&jlist->lock); ret = journal_entry_add(c, ca, (struct journal_ptr) { .csum_good = csum_good, .dev = ca->dev_idx, .bucket = bucket, .bucket_offset = offset - bucket_to_sector(ca, ja->buckets[bucket]), .sector = offset, }, jlist, j); mutex_unlock(&jlist->lock); switch (ret) { case JOURNAL_ENTRY_ADD_OK: break; case JOURNAL_ENTRY_ADD_OUT_OF_RANGE: break; default: goto err; } next_block: pr_debug("next"); offset += sectors; sectors_read -= sectors; j = ((void *) j) + (sectors << 9); } out: ret = 0; err: printbuf_exit(&err); return ret; } static CLOSURE_CALLBACK(bch2_journal_read_device) { closure_type(ja, struct journal_device, read); struct bch_dev *ca = container_of(ja, struct bch_dev, journal); struct bch_fs *c = ca->fs; struct journal_list *jlist = container_of(cl->parent, struct journal_list, cl); struct journal_read_buf buf = { NULL, 0 }; unsigned i; int ret = 0; if (!ja->nr) goto out; ret = journal_read_buf_realloc(&buf, PAGE_SIZE); if (ret) goto err; pr_debug("%u journal buckets", ja->nr); for (i = 0; i < ja->nr; i++) { ret = journal_read_bucket(ca, &buf, jlist, i); if (ret) goto err; } /* * Set dirty_idx to indicate the entire journal is full and needs to be * reclaimed - journal reclaim will immediately reclaim whatever isn't * pinned when it first runs: */ ja->discard_idx = ja->dirty_idx_ondisk = ja->dirty_idx = (ja->cur_idx + 1) % ja->nr; out: bch_verbose(c, "journal read done on device %s, ret %i", ca->name, ret); kvfree(buf.data); percpu_ref_put(&ca->io_ref[READ]); closure_return(cl); return; err: mutex_lock(&jlist->lock); jlist->ret = ret; mutex_unlock(&jlist->lock); goto out; } int bch2_journal_read(struct bch_fs *c, u64 *last_seq, u64 *blacklist_seq, u64 *start_seq) { struct journal_list jlist; struct journal_replay *i, **_i, *prev = NULL; struct genradix_iter radix_iter; struct printbuf buf = PRINTBUF; bool degraded = false, last_write_torn = false; u64 seq; int ret = 0; closure_init_stack(&jlist.cl); mutex_init(&jlist.lock); jlist.last_seq = 0; jlist.ret = 0; for_each_member_device(c, ca) { if (!c->opts.fsck && !(bch2_dev_has_data(c, ca) & (1 << BCH_DATA_journal))) continue; if ((ca->mi.state == BCH_MEMBER_STATE_rw || ca->mi.state == BCH_MEMBER_STATE_ro) && percpu_ref_tryget(&ca->io_ref[READ])) closure_call(&ca->journal.read, bch2_journal_read_device, system_unbound_wq, &jlist.cl); else degraded = true; } while (closure_sync_timeout(&jlist.cl, sysctl_hung_task_timeout_secs * HZ / 2)) ; if (jlist.ret) return jlist.ret; *last_seq = 0; *start_seq = 0; *blacklist_seq = 0; /* * Find most recent flush entry, and ignore newer non flush entries - * those entries will be blacklisted: */ genradix_for_each_reverse(&c->journal_entries, radix_iter, _i) { i = *_i; if (journal_replay_ignore(i)) continue; if (!*start_seq) *blacklist_seq = *start_seq = le64_to_cpu(i->j.seq) + 1; if (JSET_NO_FLUSH(&i->j)) { i->ignore_blacklisted = true; continue; } if (!last_write_torn && !i->csum_good) { last_write_torn = true; i->ignore_blacklisted = true; continue; } struct bkey_validate_context from = { .from = BKEY_VALIDATE_journal, .journal_seq = le64_to_cpu(i->j.seq), }; if (journal_entry_err_on(le64_to_cpu(i->j.last_seq) > le64_to_cpu(i->j.seq), c, le32_to_cpu(i->j.version), &i->j, NULL, jset_last_seq_newer_than_seq, "invalid journal entry: last_seq > seq (%llu > %llu)", le64_to_cpu(i->j.last_seq), le64_to_cpu(i->j.seq))) i->j.last_seq = i->j.seq; *last_seq = le64_to_cpu(i->j.last_seq); *blacklist_seq = le64_to_cpu(i->j.seq) + 1; break; } if (!*start_seq) { bch_info(c, "journal read done, but no entries found"); return 0; } if (!*last_seq) { fsck_err(c, dirty_but_no_journal_entries_post_drop_nonflushes, "journal read done, but no entries found after dropping non-flushes"); return 0; } bch_info(c, "journal read done, replaying entries %llu-%llu", *last_seq, *blacklist_seq - 1); if (*start_seq != *blacklist_seq) bch_info(c, "dropped unflushed entries %llu-%llu", *blacklist_seq, *start_seq - 1); /* Drop blacklisted entries and entries older than last_seq: */ genradix_for_each(&c->journal_entries, radix_iter, _i) { i = *_i; if (journal_replay_ignore(i)) continue; seq = le64_to_cpu(i->j.seq); if (seq < *last_seq) { journal_replay_free(c, i, false); continue; } if (bch2_journal_seq_is_blacklisted(c, seq, true)) { fsck_err_on(!JSET_NO_FLUSH(&i->j), c, jset_seq_blacklisted, "found blacklisted journal entry %llu", seq); i->ignore_blacklisted = true; } } /* Check for missing entries: */ seq = *last_seq; genradix_for_each(&c->journal_entries, radix_iter, _i) { i = *_i; if (journal_replay_ignore(i)) continue; BUG_ON(seq > le64_to_cpu(i->j.seq)); while (seq < le64_to_cpu(i->j.seq)) { u64 missing_start, missing_end; struct printbuf buf1 = PRINTBUF, buf2 = PRINTBUF; while (seq < le64_to_cpu(i->j.seq) && bch2_journal_seq_is_blacklisted(c, seq, false)) seq++; if (seq == le64_to_cpu(i->j.seq)) break; missing_start = seq; while (seq < le64_to_cpu(i->j.seq) && !bch2_journal_seq_is_blacklisted(c, seq, false)) seq++; if (prev) { bch2_journal_ptrs_to_text(&buf1, c, prev); prt_printf(&buf1, " size %zu", vstruct_sectors(&prev->j, c->block_bits)); } else prt_printf(&buf1, "(none)"); bch2_journal_ptrs_to_text(&buf2, c, i); missing_end = seq - 1; fsck_err(c, journal_entries_missing, "journal entries %llu-%llu missing! (replaying %llu-%llu)\n" "prev at %s\n" "next at %s, continue?", missing_start, missing_end, *last_seq, *blacklist_seq - 1, buf1.buf, buf2.buf); printbuf_exit(&buf1); printbuf_exit(&buf2); } prev = i; seq++; } genradix_for_each(&c->journal_entries, radix_iter, _i) { struct bch_replicas_padded replicas = { .e.data_type = BCH_DATA_journal, .e.nr_devs = 0, .e.nr_required = 1, }; i = *_i; if (journal_replay_ignore(i)) continue; darray_for_each(i->ptrs, ptr) { struct bch_dev *ca = bch2_dev_have_ref(c, ptr->dev); if (!ptr->csum_good) bch_err_dev_offset(ca, ptr->sector, "invalid journal checksum, seq %llu%s", le64_to_cpu(i->j.seq), i->csum_good ? " (had good copy on another device)" : ""); } ret = jset_validate(c, bch2_dev_have_ref(c, i->ptrs.data[0].dev), &i->j, i->ptrs.data[0].sector, READ); if (ret) goto err; darray_for_each(i->ptrs, ptr) replicas_entry_add_dev(&replicas.e, ptr->dev); bch2_replicas_entry_sort(&replicas.e); printbuf_reset(&buf); bch2_replicas_entry_to_text(&buf, &replicas.e); if (!degraded && !bch2_replicas_marked(c, &replicas.e) && (le64_to_cpu(i->j.seq) == *last_seq || fsck_err(c, journal_entry_replicas_not_marked, "superblock not marked as containing replicas for journal entry %llu\n%s", le64_to_cpu(i->j.seq), buf.buf))) { ret = bch2_mark_replicas(c, &replicas.e); if (ret) goto err; } } err: fsck_err: printbuf_exit(&buf); return ret; } /* journal write: */ static void journal_advance_devs_to_next_bucket(struct journal *j, struct dev_alloc_list *devs, unsigned sectors, __le64 seq) { struct bch_fs *c = container_of(j, struct bch_fs, journal); darray_for_each(*devs, i) { struct bch_dev *ca = rcu_dereference(c->devs[*i]); if (!ca) continue; struct journal_device *ja = &ca->journal; if (sectors > ja->sectors_free && sectors <= ca->mi.bucket_size && bch2_journal_dev_buckets_available(j, ja, journal_space_discarded)) { ja->cur_idx = (ja->cur_idx + 1) % ja->nr; ja->sectors_free = ca->mi.bucket_size; /* * ja->bucket_seq[ja->cur_idx] must always have * something sensible: */ ja->bucket_seq[ja->cur_idx] = le64_to_cpu(seq); } } } static void __journal_write_alloc(struct journal *j, struct journal_buf *w, struct dev_alloc_list *devs, unsigned sectors, unsigned *replicas, unsigned replicas_want) { struct bch_fs *c = container_of(j, struct bch_fs, journal); darray_for_each(*devs, i) { struct bch_dev *ca = rcu_dereference(c->devs[*i]); if (!ca) continue; struct journal_device *ja = &ca->journal; /* * Check that we can use this device, and aren't already using * it: */ if (!ca->mi.durability || ca->mi.state != BCH_MEMBER_STATE_rw || !ja->nr || bch2_bkey_has_device_c(bkey_i_to_s_c(&w->key), ca->dev_idx) || sectors > ja->sectors_free) continue; bch2_dev_stripe_increment(ca, &j->wp.stripe); bch2_bkey_append_ptr(&w->key, (struct bch_extent_ptr) { .offset = bucket_to_sector(ca, ja->buckets[ja->cur_idx]) + ca->mi.bucket_size - ja->sectors_free, .dev = ca->dev_idx, }); ja->sectors_free -= sectors; ja->bucket_seq[ja->cur_idx] = le64_to_cpu(w->data->seq); *replicas += ca->mi.durability; if (*replicas >= replicas_want) break; } } /** * journal_write_alloc - decide where to write next journal entry * * @j: journal object * @w: journal buf (entry to be written) * * Returns: 0 on success, or -BCH_ERR_insufficient_devices on failure */ static int journal_write_alloc(struct journal *j, struct journal_buf *w) { struct bch_fs *c = container_of(j, struct bch_fs, journal); struct bch_devs_mask devs; struct dev_alloc_list devs_sorted; unsigned sectors = vstruct_sectors(w->data, c->block_bits); unsigned target = c->opts.metadata_target ?: c->opts.foreground_target; unsigned replicas = 0, replicas_want = READ_ONCE(c->opts.metadata_replicas); unsigned replicas_need = min_t(unsigned, replicas_want, READ_ONCE(c->opts.metadata_replicas_required)); bool advance_done = false; rcu_read_lock(); /* We might run more than once if we have to stop and do discards: */ struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(bkey_i_to_s_c(&w->key)); bkey_for_each_ptr(ptrs, p) { struct bch_dev *ca = bch2_dev_rcu_noerror(c, p->dev); if (ca) replicas += ca->mi.durability; } retry_target: devs = target_rw_devs(c, BCH_DATA_journal, target); devs_sorted = bch2_dev_alloc_list(c, &j->wp.stripe, &devs); retry_alloc: __journal_write_alloc(j, w, &devs_sorted, sectors, &replicas, replicas_want); if (likely(replicas >= replicas_want)) goto done; if (!advance_done) { journal_advance_devs_to_next_bucket(j, &devs_sorted, sectors, w->data->seq); advance_done = true; goto retry_alloc; } if (replicas < replicas_want && target) { /* Retry from all devices: */ target = 0; advance_done = false; goto retry_target; } done: rcu_read_unlock(); BUG_ON(bkey_val_u64s(&w->key.k) > BCH_REPLICAS_MAX); return replicas >= replicas_need ? 0 : -BCH_ERR_insufficient_journal_devices; } static void journal_buf_realloc(struct journal *j, struct journal_buf *buf) { struct bch_fs *c = container_of(j, struct bch_fs, journal); /* we aren't holding j->lock: */ unsigned new_size = READ_ONCE(j->buf_size_want); void *new_buf; if (buf->buf_size >= new_size) return; size_t btree_write_buffer_size = new_size / 64; if (bch2_btree_write_buffer_resize(c, btree_write_buffer_size)) return; new_buf = kvmalloc(new_size, GFP_NOFS|__GFP_NOWARN); if (!new_buf) return; memcpy(new_buf, buf->data, buf->buf_size); spin_lock(&j->lock); swap(buf->data, new_buf); swap(buf->buf_size, new_size); spin_unlock(&j->lock); kvfree(new_buf); } static CLOSURE_CALLBACK(journal_write_done) { closure_type(w, struct journal_buf, io); struct journal *j = container_of(w, struct journal, buf[w->idx]); struct bch_fs *c = container_of(j, struct bch_fs, journal); struct bch_replicas_padded replicas; u64 seq = le64_to_cpu(w->data->seq); int err = 0; bch2_time_stats_update(!JSET_NO_FLUSH(w->data) ? j->flush_write_time : j->noflush_write_time, j->write_start_time); if (!w->devs_written.nr) { if (!bch2_journal_error(j)) bch_err(c, "unable to write journal to sufficient devices"); err = -BCH_ERR_journal_write_err; } else { bch2_devlist_to_replicas(&replicas.e, BCH_DATA_journal, w->devs_written); err = bch2_mark_replicas(c, &replicas.e); } if (err) bch2_fatal_error(c); closure_debug_destroy(cl); spin_lock(&j->lock); if (seq >= j->pin.front) journal_seq_pin(j, seq)->devs = w->devs_written; if (err && (!j->err_seq || seq < j->err_seq)) j->err_seq = seq; w->write_done = true; if (!j->free_buf || j->free_buf_size < w->buf_size) { swap(j->free_buf, w->data); swap(j->free_buf_size, w->buf_size); } if (w->data) { void *buf = w->data; w->data = NULL; w->buf_size = 0; spin_unlock(&j->lock); kvfree(buf); spin_lock(&j->lock); } bool completed = false; bool do_discards = false; for (seq = journal_last_unwritten_seq(j); seq <= journal_cur_seq(j); seq++) { w = j->buf + (seq & JOURNAL_BUF_MASK); if (!w->write_done) break; if (!j->err_seq && !w->noflush) { j->flushed_seq_ondisk = seq; j->last_seq_ondisk = w->last_seq; closure_wake_up(&c->freelist_wait); bch2_reset_alloc_cursors(c); } j->seq_ondisk = seq; /* * Updating last_seq_ondisk may let bch2_journal_reclaim_work() discard * more buckets: * * Must come before signaling write completion, for * bch2_fs_journal_stop(): */ if (j->watermark != BCH_WATERMARK_stripe) journal_reclaim_kick(&c->journal); closure_wake_up(&w->wait); completed = true; } if (completed) { bch2_journal_reclaim_fast(j); bch2_journal_space_available(j); track_event_change(&c->times[BCH_TIME_blocked_journal_max_in_flight], false); journal_wake(j); } if (journal_last_unwritten_seq(j) == journal_cur_seq(j) && j->reservations.cur_entry_offset < JOURNAL_ENTRY_CLOSED_VAL) { struct journal_buf *buf = journal_cur_buf(j); long delta = buf->expires - jiffies; /* * We don't close a journal entry to write it while there's * previous entries still in flight - the current journal entry * might want to be written now: */ mod_delayed_work(j->wq, &j->write_work, max(0L, delta)); } /* * We don't typically trigger journal writes from her - the next journal * write will be triggered immediately after the previous one is * allocated, in bch2_journal_write() - but the journal write error path * is special: */ bch2_journal_do_writes(j); spin_unlock(&j->lock); if (do_discards) bch2_do_discards(c); } static void journal_write_endio(struct bio *bio) { struct journal_bio *jbio = container_of(bio, struct journal_bio, bio); struct bch_dev *ca = jbio->ca; struct journal *j = &ca->fs->journal; struct journal_buf *w = j->buf + jbio->buf_idx; bch2_account_io_completion(ca, BCH_MEMBER_ERROR_write, jbio->submit_time, !bio->bi_status); if (bio->bi_status) { bch_err_dev_ratelimited(ca, "error writing journal entry %llu: %s", le64_to_cpu(w->data->seq), bch2_blk_status_to_str(bio->bi_status)); unsigned long flags; spin_lock_irqsave(&j->err_lock, flags); bch2_dev_list_drop_dev(&w->devs_written, ca->dev_idx); spin_unlock_irqrestore(&j->err_lock, flags); } closure_put(&w->io); percpu_ref_put(&ca->io_ref[WRITE]); } static CLOSURE_CALLBACK(journal_write_submit) { closure_type(w, struct journal_buf, io); struct journal *j = container_of(w, struct journal, buf[w->idx]); struct bch_fs *c = container_of(j, struct bch_fs, journal); unsigned sectors = vstruct_sectors(w->data, c->block_bits); extent_for_each_ptr(bkey_i_to_s_extent(&w->key), ptr) { struct bch_dev *ca = bch2_dev_get_ioref(c, ptr->dev, WRITE); if (!ca) { /* XXX: fix this */ bch_err(c, "missing device %u for journal write", ptr->dev); continue; } this_cpu_add(ca->io_done->sectors[WRITE][BCH_DATA_journal], sectors); struct journal_device *ja = &ca->journal; struct journal_bio *jbio = ja->bio[w->idx]; struct bio *bio = &jbio->bio; jbio->submit_time = local_clock(); bio_reset(bio, ca->disk_sb.bdev, REQ_OP_WRITE|REQ_SYNC|REQ_META); bio->bi_iter.bi_sector = ptr->offset; bio->bi_end_io = journal_write_endio; bio->bi_private = ca; bio->bi_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_RT, 0); BUG_ON(bio->bi_iter.bi_sector == ca->prev_journal_sector); ca->prev_journal_sector = bio->bi_iter.bi_sector; if (!JSET_NO_FLUSH(w->data)) bio->bi_opf |= REQ_FUA; if (!JSET_NO_FLUSH(w->data) && !w->separate_flush) bio->bi_opf |= REQ_PREFLUSH; bch2_bio_map(bio, w->data, sectors << 9); trace_and_count(c, journal_write, bio); closure_bio_submit(bio, cl); ja->bucket_seq[ja->cur_idx] = le64_to_cpu(w->data->seq); } continue_at(cl, journal_write_done, j->wq); } static CLOSURE_CALLBACK(journal_write_preflush) { closure_type(w, struct journal_buf, io); struct journal *j = container_of(w, struct journal, buf[w->idx]); struct bch_fs *c = container_of(j, struct bch_fs, journal); /* * Wait for previous journal writes to comelete; they won't necessarily * be flushed if they're still in flight */ if (j->seq_ondisk + 1 != le64_to_cpu(w->data->seq)) { spin_lock(&j->lock); if (j->seq_ondisk + 1 != le64_to_cpu(w->data->seq)) { closure_wait(&j->async_wait, cl); spin_unlock(&j->lock); continue_at(cl, journal_write_preflush, j->wq); return; } spin_unlock(&j->lock); } if (w->separate_flush) { for_each_rw_member(c, ca) { percpu_ref_get(&ca->io_ref[WRITE]); struct journal_device *ja = &ca->journal; struct bio *bio = &ja->bio[w->idx]->bio; bio_reset(bio, ca->disk_sb.bdev, REQ_OP_WRITE|REQ_SYNC|REQ_META|REQ_PREFLUSH); bio->bi_end_io = journal_write_endio; bio->bi_private = ca; closure_bio_submit(bio, cl); } continue_at(cl, journal_write_submit, j->wq); } else { /* * no need to punt to another work item if we're not waiting on * preflushes */ journal_write_submit(&cl->work); } } static int bch2_journal_write_prep(struct journal *j, struct journal_buf *w) { struct bch_fs *c = container_of(j, struct bch_fs, journal); struct jset_entry *start, *end; struct jset *jset = w->data; struct journal_keys_to_wb wb = { NULL }; unsigned sectors, bytes, u64s; unsigned long btree_roots_have = 0; bool validate_before_checksum = false; u64 seq = le64_to_cpu(jset->seq); int ret; /* * Simple compaction, dropping empty jset_entries (from journal * reservations that weren't fully used) and merging jset_entries that * can be. * * If we wanted to be really fancy here, we could sort all the keys in * the jset and drop keys that were overwritten - probably not worth it: */ vstruct_for_each(jset, i) { unsigned u64s = le16_to_cpu(i->u64s); /* Empty entry: */ if (!u64s) continue; /* * New btree roots are set by journalling them; when the journal * entry gets written we have to propagate them to * c->btree_roots * * But, every journal entry we write has to contain all the * btree roots (at least for now); so after we copy btree roots * to c->btree_roots we have to get any missing btree roots and * add them to this journal entry: */ switch (i->type) { case BCH_JSET_ENTRY_btree_root: bch2_journal_entry_to_btree_root(c, i); __set_bit(i->btree_id, &btree_roots_have); break; case BCH_JSET_ENTRY_write_buffer_keys: EBUG_ON(!w->need_flush_to_write_buffer); if (!wb.wb) bch2_journal_keys_to_write_buffer_start(c, &wb, seq); jset_entry_for_each_key(i, k) { ret = bch2_journal_key_to_wb(c, &wb, i->btree_id, k); if (ret) { bch2_fs_fatal_error(c, "flushing journal keys to btree write buffer: %s", bch2_err_str(ret)); bch2_journal_keys_to_write_buffer_end(c, &wb); return ret; } } i->type = BCH_JSET_ENTRY_btree_keys; break; } } if (wb.wb) { ret = bch2_journal_keys_to_write_buffer_end(c, &wb); if (ret) { bch2_fs_fatal_error(c, "error flushing journal keys to btree write buffer: %s", bch2_err_str(ret)); return ret; } } spin_lock(&c->journal.lock); w->need_flush_to_write_buffer = false; spin_unlock(&c->journal.lock); start = end = vstruct_last(jset); end = bch2_btree_roots_to_journal_entries(c, end, btree_roots_have); struct jset_entry_datetime *d = container_of(jset_entry_init(&end, sizeof(*d)), struct jset_entry_datetime, entry); d->entry.type = BCH_JSET_ENTRY_datetime; d->seconds = cpu_to_le64(ktime_get_real_seconds()); bch2_journal_super_entries_add_common(c, &end, seq); u64s = (u64 *) end - (u64 *) start; WARN_ON(u64s > j->entry_u64s_reserved); le32_add_cpu(&jset->u64s, u64s); sectors = vstruct_sectors(jset, c->block_bits); bytes = vstruct_bytes(jset); if (sectors > w->sectors) { bch2_fs_fatal_error(c, ": journal write overran available space, %zu > %u (extra %u reserved %u/%u)", vstruct_bytes(jset), w->sectors << 9, u64s, w->u64s_reserved, j->entry_u64s_reserved); return -EINVAL; } jset->magic = cpu_to_le64(jset_magic(c)); jset->version = cpu_to_le32(c->sb.version); SET_JSET_BIG_ENDIAN(jset, CPU_BIG_ENDIAN); SET_JSET_CSUM_TYPE(jset, bch2_meta_checksum_type(c)); if (!JSET_NO_FLUSH(jset) && journal_entry_empty(jset)) j->last_empty_seq = seq; if (bch2_csum_type_is_encryption(JSET_CSUM_TYPE(jset))) validate_before_checksum = true; if (le32_to_cpu(jset->version) < bcachefs_metadata_version_current) validate_before_checksum = true; if (validate_before_checksum && (ret = jset_validate(c, NULL, jset, 0, WRITE))) return ret; ret = bch2_encrypt(c, JSET_CSUM_TYPE(jset), journal_nonce(jset), jset->encrypted_start, vstruct_end(jset) - (void *) jset->encrypted_start); if (bch2_fs_fatal_err_on(ret, c, "decrypting journal entry: %s", bch2_err_str(ret))) return ret; jset->csum = csum_vstruct(c, JSET_CSUM_TYPE(jset), journal_nonce(jset), jset); if (!validate_before_checksum && (ret = jset_validate(c, NULL, jset, 0, WRITE))) return ret; memset((void *) jset + bytes, 0, (sectors << 9) - bytes); return 0; } static int bch2_journal_write_pick_flush(struct journal *j, struct journal_buf *w) { struct bch_fs *c = container_of(j, struct bch_fs, journal); int error = bch2_journal_error(j); /* * If the journal is in an error state - we did an emergency shutdown - * we prefer to continue doing journal writes. We just mark them as * noflush so they'll never be used, but they'll still be visible by the * list_journal tool - this helps in debugging. * * There's a caveat: the first journal write after marking the * superblock dirty must always be a flush write, because on startup * from a clean shutdown we didn't necessarily read the journal and the * new journal write might overwrite whatever was in the journal * previously - we can't leave the journal without any flush writes in * it. * * So if we're in an error state, and we're still starting up, we don't * write anything at all. */ if (error && test_bit(JOURNAL_need_flush_write, &j->flags)) return error; if (error || w->noflush || (!w->must_flush && time_before(jiffies, j->last_flush_write + msecs_to_jiffies(c->opts.journal_flush_delay)) && test_bit(JOURNAL_may_skip_flush, &j->flags))) { w->noflush = true; SET_JSET_NO_FLUSH(w->data, true); w->data->last_seq = 0; w->last_seq = 0; j->nr_noflush_writes++; } else { w->must_flush = true; j->last_flush_write = jiffies; j->nr_flush_writes++; clear_bit(JOURNAL_need_flush_write, &j->flags); } return 0; } CLOSURE_CALLBACK(bch2_journal_write) { closure_type(w, struct journal_buf, io); struct journal *j = container_of(w, struct journal, buf[w->idx]); struct bch_fs *c = container_of(j, struct bch_fs, journal); struct bch_replicas_padded replicas; unsigned nr_rw_members = 0; int ret; for_each_rw_member(c, ca) nr_rw_members++; BUG_ON(BCH_SB_CLEAN(c->disk_sb.sb)); BUG_ON(!w->write_started); BUG_ON(w->write_allocated); BUG_ON(w->write_done); j->write_start_time = local_clock(); spin_lock(&j->lock); if (nr_rw_members > 1) w->separate_flush = true; ret = bch2_journal_write_pick_flush(j, w); spin_unlock(&j->lock); if (ret) goto err; mutex_lock(&j->buf_lock); journal_buf_realloc(j, w); ret = bch2_journal_write_prep(j, w); mutex_unlock(&j->buf_lock); if (ret) goto err; j->entry_bytes_written += vstruct_bytes(w->data); while (1) { spin_lock(&j->lock); ret = journal_write_alloc(j, w); if (!ret || !j->can_discard) break; spin_unlock(&j->lock); bch2_journal_do_discards(j); } if (ret && !bch2_journal_error(j)) { struct printbuf buf = PRINTBUF; buf.atomic++; __bch2_journal_debug_to_text(&buf, j); spin_unlock(&j->lock); prt_printf(&buf, bch2_fmt(c, "Unable to allocate journal write at seq %llu for %zu sectors: %s"), le64_to_cpu(w->data->seq), vstruct_sectors(w->data, c->block_bits), bch2_err_str(ret)); bch2_print_string_as_lines(KERN_ERR, buf.buf); printbuf_exit(&buf); } if (ret) goto err; /* * write is allocated, no longer need to account for it in * bch2_journal_space_available(): */ w->sectors = 0; w->write_allocated = true; /* * journal entry has been compacted and allocated, recalculate space * available: */ bch2_journal_space_available(j); bch2_journal_do_writes(j); spin_unlock(&j->lock); w->devs_written = bch2_bkey_devs(bkey_i_to_s_c(&w->key)); if (c->opts.nochanges) goto no_io; /* * Mark journal replicas before we submit the write to guarantee * recovery will find the journal entries after a crash. */ bch2_devlist_to_replicas(&replicas.e, BCH_DATA_journal, w->devs_written); ret = bch2_mark_replicas(c, &replicas.e); if (ret) goto err; if (!JSET_NO_FLUSH(w->data)) continue_at(cl, journal_write_preflush, j->wq); else continue_at(cl, journal_write_submit, j->wq); return; no_io: continue_at(cl, journal_write_done, j->wq); return; err: bch2_fatal_error(c); continue_at(cl, journal_write_done, j->wq); } |
| 439 440 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * This file contains functions which manage high resolution tick * related events. * * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner */ #include <linux/cpu.h> #include <linux/err.h> #include <linux/hrtimer.h> #include <linux/interrupt.h> #include <linux/percpu.h> #include <linux/profile.h> #include <linux/sched.h> #include "tick-internal.h" /** * tick_program_event - program the CPU local timer device for the next event */ int tick_program_event(ktime_t expires, int force) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); if (unlikely(expires == KTIME_MAX)) { /* * We don't need the clock event device any more, stop it. */ clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT_STOPPED); dev->next_event = KTIME_MAX; return 0; } if (unlikely(clockevent_state_oneshot_stopped(dev))) { /* * We need the clock event again, configure it in ONESHOT mode * before using it. */ clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT); } return clockevents_program_event(dev, expires, force); } /** * tick_resume_oneshot - resume oneshot mode */ void tick_resume_oneshot(void) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT); clockevents_program_event(dev, ktime_get(), true); } /** * tick_setup_oneshot - setup the event device for oneshot mode (hres or nohz) */ void tick_setup_oneshot(struct clock_event_device *newdev, void (*handler)(struct clock_event_device *), ktime_t next_event) { newdev->event_handler = handler; clockevents_switch_state(newdev, CLOCK_EVT_STATE_ONESHOT); clockevents_program_event(newdev, next_event, true); } /** * tick_switch_to_oneshot - switch to oneshot mode */ int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *)) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); struct clock_event_device *dev = td->evtdev; if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT) || !tick_device_is_functional(dev)) { pr_info("Clockevents: could not switch to one-shot mode:"); if (!dev) { pr_cont(" no tick device\n"); } else { if (!tick_device_is_functional(dev)) pr_cont(" %s is not functional.\n", dev->name); else pr_cont(" %s does not support one-shot mode.\n", dev->name); } return -EINVAL; } td->mode = TICKDEV_MODE_ONESHOT; dev->event_handler = handler; clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT); tick_broadcast_switch_to_oneshot(); return 0; } /** * tick_oneshot_mode_active - check whether the system is in oneshot mode * * returns 1 when either nohz or highres are enabled. otherwise 0. */ int tick_oneshot_mode_active(void) { unsigned long flags; int ret; local_irq_save(flags); ret = __this_cpu_read(tick_cpu_device.mode) == TICKDEV_MODE_ONESHOT; local_irq_restore(flags); return ret; } #ifdef CONFIG_HIGH_RES_TIMERS /** * tick_init_highres - switch to high resolution mode * * Called with interrupts disabled. */ int tick_init_highres(void) { return tick_switch_to_oneshot(hrtimer_interrupt); } #endif |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 5 |